[{"content":"This thrust focuses on foundational mechanics, computational representations, sensing concepts, and complex dynamical systems that support structural health monitoring, digital twins, and resilient infrastructure systems.\nThe aim is to develop mathematical, mechanical, and computational tools that help represent structural behaviour in ways that are physically meaningful, interpretable, and useful for monitoring, prognosis, and decision support. This thrust also provides space for exploratory work inspired by bio-inspired sensing and active-matter-like collective dynamics where such ideas can inform sensing, modelling, or infrastructure monitoring.\nWhat We Study # Mechanics-Aware Representations Computational approaches for representing structural response, deformation, and behaviour using concepts from mechanics, numerical methods, and approximation theory.\nMechanicsApproximationComputation Computational Tools for SHM Methods that support structural health monitoring by connecting measured response, computational models, and engineering interpretation.\nSHMComputational MechanicsInterpretability Physics-Guided Modelling Modelling approaches that use physical principles and engineering knowledge to improve robustness, reliability, and meaning in data-driven infrastructure monitoring.\nPhysics-Guided MethodsModellingInfrastructure Emerging Sensing and Dynamical Systems Concepts Exploratory ideas inspired by mechanics, structural dynamics, bio-inspired sensing, and collective dynamical systems for future infrastructure monitoring applications.\nSensingStructural DynamicsExploratory Research Methods and Tools # Research in this thrust may involve solid mechanics, structural dynamics, finite element methods, numerical methods, approximation theory, scientific computing, sensing concepts, and machine learning.\nThe emphasis is on foundational ideas that can support more reliable sensing, monitoring, diagnosis, prognosis, and digital twin development for civil infrastructure systems.\nThis thrust also provides space for exploratory work at the interface of mechanics, sensing, computation, and complex dynamical systems, including faint connections to bio-inspired and active-matter-inspired thinking where relevant.\nStudent Background # Students interested in this thrust may benefit from background in solid mechanics, structural dynamics, finite element methods, numerical methods, scientific computing, sensing, or machine learning.\nIt is not necessary to have expertise in all areas. Specific topics are shaped based on the student’s background, interests, and expected time commitment.\nInterested Students # Students interested in mechanics-aware modelling, computational methods, physics-guided sensing, or exploratory sensing concepts for infrastructure monitoring are encouraged to read the broader Research page and contact me through the Join the Group page.\nSpecific project topics are discussed individually after understanding the student’s background, interests, and available research opportunities.\n","externalUrl":null,"permalink":"/research-themes/foundational-mechanics/","section":"Research-Themes","summary":"This thrust focuses on foundational mechanics, computational representations, sensing concepts, and complex dynamical systems that support structural health monitoring, digital twins, and resilient infrastructure systems.\nThe aim is to develop mathematical, mechanical, and computational tools that help represent structural behaviour in ways that are physically meaningful, interpretable, and useful for monitoring, prognosis, and decision support. This thrust also provides space for exploratory work inspired by bio-inspired sensing and active-matter-like collective dynamics where such ideas can inform sensing, modelling, or infrastructure monitoring.\n","title":"Foundational Mechanics, Sensing, and Complex Dynamical Systems","type":"research-themes"},{"content":"This page highlights selected academic activities, invited lectures, workshops, outreach efforts, and professional engagements connected to teaching, research, and the development of RISE Lab.\nWorkshops and Short Courses # Upcoming Workshop Machine Learning for Scientific Computing Role: Coordinator Venue: Indian Institute of Technology Bombay Date: July 23–24, 2026 Status: Upcoming This workshop introduces machine learning methods for scientific computing and engineering applications, with emphasis on traditional numerical methods, physics-informed learning, surrogate modelling, and data-driven solution of differential equations. The workshop will include hands-on training for structural problems, post-processing, visualization, open-source tools, and cloud-based computing workflows. Machine Learning Scientific Computing PINNs Surrogate Models Engineering Simulation Upcoming Workshop Machine Learning for Structural Health Monitoring Role: Coordinator Venue: Indian Institute of Technology Bombay Date: July 22, 2026 Status: Upcoming This workshop focuses on machine learning, computer vision, and physics-informed methods for structural health monitoring and bridge condition assessment. The workshop will discuss how data-driven and physics-guided approaches can support reliable infrastructure monitoring, full-field response interpretation, and rapid condition assessment. Structural Health Monitoring Computer Vision Machine Learning Bridge Monitoring Smart Infrastructure Invited Lectures and Talks # Invited Lecture Data Fusion Using Kalman-Filter Methods for Real-Time Structural Health Monitoring Event: Mechanical Sciences Young Investigators Meet (MSYIM) Venue: Indian Institute of Technology Kanpur Date: March 13, 2026 Status: Completed This invited lecture presented Kalman-filter-based data fusion methods for real-time structural health monitoring, with emphasis on combining acceleration and displacement measurements for improved structural response estimation. The talk discussed online estimation of displacement, velocity, and acceleration-bias effects, along with numerical and experimental validation for structural dynamics applications. Sensor Data Fusion Kalman Filter Real-Time SHM Structural Dynamics Online Estimation Invited Lecture From Equations to Solutions: Physics-Informed Neural Networks for Mechanics Problems Event: Core Meets Code Venue: Online Date: May 22, 2026 Status: Completed This invited lecture introduces physics-informed neural networks for solving and discovering differential-equation-based models in mechanics and scientific computing. The lecture will discuss data-driven solution and discovery of partial differential equations, continuous and discrete-time formulations, and connections between machine learning, numerical methods, and nonlinear dynamical systems. Physics-Informed Neural Networks Scientific Computing Machine Learning Nonlinear Dynamics PDEs Academic and Professional Engagement # Academic Engagement Research, Teaching, and Student Engagement In addition to research and teaching, activities include student mentoring, academic discussions, workshop planning, seminar participation, and engagement with emerging topics in smart and resilient infrastructure systems. Teaching Mentoring Research Engagement RISE Lab ","externalUrl":null,"permalink":"/activities/","section":"","summary":"This page highlights selected academic activities, invited lectures, workshops, outreach efforts, and professional engagements connected to teaching, research, and the development of RISE Lab.\nWorkshops and Short Courses # Upcoming Workshop Machine Learning for Scientific Computing Role: Coordinator Venue: Indian Institute of Technology Bombay Date: July 23–24, 2026 Status: Upcoming This workshop introduces machine learning methods for scientific computing and engineering applications, with emphasis on traditional numerical methods, physics-informed learning, surrogate modelling, and data-driven solution of differential equations. ","title":"Activities","type":"page"},{"content":"RISE Lab is actively looking for motivated PhD students, M.Tech students, and highly motivated B.Tech students interested in smart and resilient infrastructure systems.\nThe group works at the interface of structural engineering, sensing, computer vision, AI/ML, scientific computing, digital twins, structural health monitoring, prognosis, and infrastructure resilience.\nSpecific project topics are discussed individually after understanding the student’s background, interests, expected time commitment, and available research opportunities.\nPhD Students # I am especially interested in recruiting PhD students who want to work on long-term research problems related to smart infrastructure, structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, scientific machine learning, uncertainty-aware prognosis, and resilient infrastructure systems.\nPhD students are expected to develop strong foundations in structural engineering, computational methods, research writing, and independent problem formulation.\nAs the group is growing, early PhD students will have the opportunity to help shape the research culture, computational tools, experimental directions, and long-term identity of RISE Lab.\nM.Tech Students # M.Tech students can work on focused research problems aligned with the broader directions of the group.\nPossible broad areas include structural health monitoring, sensing, computer vision, digital twins, finite element modelling, machine learning for engineering systems, uncertainty-aware monitoring, and infrastructure resilience.\nProjects will be scoped according to the available time, student background, and research goals. Students interested in continuing toward PhD-level research are especially welcome.\nB.Tech Students # Motivated B.Tech students can get involved through B.Tech projects, summer/winter projects, or exploratory research assignments.\nB.Tech projects are usually introductory or exploratory and may involve coding, simulations, literature review, data analysis, computational demonstrations, or small proof-of-concept studies.\nStudents who are curious, consistent, and willing to learn are encouraged to reach out even if they do not yet have advanced research experience.\nResearch Areas # Smart and Resilient Infrastructure # Research on civil infrastructure systems that can be monitored, interpreted, and supported through sensing, computation, and data-driven decision support.\nPhysics-Guided Sensing and Monitoring # Sensing and signal-processing methods that combine measurements with structural mechanics and engineering knowledge.\nStructural Health Monitoring # Methods for damage detection, condition assessment, prognosis, and infrastructure health monitoring.\nComputer Vision and AI # Image, video, and machine-learning methods for infrastructure monitoring, inspection, and response interpretation.\nDigital Twins and System Identification # Data-informed computational models for understanding, updating, and predicting structural behaviour.\nScientific Machine Learning and Uncertainty # Physics-guided learning, interpretable AI, uncertainty quantification, and decision support for engineering systems.\nUseful Background # Useful background areas include:\nstructural engineering applied mechanics structural dynamics finite element methods programming in Python or MATLAB machine learning or deep learning signal processing computer vision numerical methods Prior experience in all these areas is not required. Students can join with strength in one area and develop the remaining skills during the project.\nHow to Apply # Interested students may email with the subject line:\nProspective PhD/M.Tech/B.Tech Student – [Your Area of Interest]\nPlease include:\nCV academic transcript brief statement of research interests relevant project, coding, or research experience publications, if any whether you are applying through IIT Bombay admissions, external fellowship, or a project-based route In the email, briefly explain which broad research area interests you and why.\nNote to Prospective Students # You do not need to have prior experience in artificial intelligence, computer vision, or advanced programming before reaching out.\nA strong interest in research, willingness to learn, consistency, and curiosity about civil infrastructure problems are the most important qualities.\n","externalUrl":null,"permalink":"/join/","section":"","summary":"RISE Lab is actively looking for motivated PhD students, M.Tech students, and highly motivated B.Tech students interested in smart and resilient infrastructure systems.\nThe group works at the interface of structural engineering, sensing, computer vision, AI/ML, scientific computing, digital twins, structural health monitoring, prognosis, and infrastructure resilience.\nSpecific project topics are discussed individually after understanding the student’s background, interests, expected time commitment, and available research opportunities.\nPhD Students # I am especially interested in recruiting PhD students who want to work on long-term research problems related to smart infrastructure, structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, scientific machine learning, uncertainty-aware prognosis, and resilient infrastructure systems.\n","title":"Join","type":"page"},{"content":"This thrust focuses on uncertainty-aware methods for structural health monitoring, damage diagnosis, model updating, prognosis, and decision support.\nThe goal is to move from deterministic monitoring outputs toward confidence-aware interpretation, where engineers can understand not only what a model predicts, but also how reliable that prediction may be.\nWhat We Study # Uncertainty-Aware Monitoring Methods for understanding how measurement noise, modelling assumptions, environmental variability, and limited data affect infrastructure monitoring outcomes.\nUncertaintySHMMonitoring Probabilistic Diagnosis Approaches for interpreting structural condition with confidence estimates, rather than relying only on deterministic damage indicators or classifications.\nProbabilistic MethodsDiagnosisReliability Confidence-Aware Prediction Methods that support infrastructure prognosis and decision-making by accounting for uncertainty in data, models, and future structural behaviour.\nPredictionPrognosisDecision Support Risk-Informed Decision Support Frameworks that connect monitoring outputs with inspection, maintenance, and rehabilitation decisions under uncertainty.\nRiskMaintenanceInfrastructure Methods and Tools # Research in this thrust may involve probability, statistics, Bayesian reasoning, inverse problems, structural reliability, machine learning, digital twins, and structural health monitoring.\nThe emphasis is on developing monitoring and prediction methods that are not only accurate, but also calibrated, interpretable, and useful for engineering decisions.\nStudent Background # Students interested in this thrust may benefit from background in probability, statistics, Bayesian inference, structural reliability, inverse problems, machine learning, or structural health monitoring.\nIt is not necessary to have expertise in all areas. Specific topics are shaped based on the student’s background, interests, and expected time commitment.\nInterested Students # Students interested in uncertainty-aware monitoring, probabilistic diagnosis, infrastructure prognosis, Bayesian methods, or decision support are encouraged to read the broader Research page and contact me through the Join the Group page.\nSpecific project topics are discussed individually after understanding the student’s background, interests, and available research opportunities.\n","externalUrl":null,"permalink":"/research-themes/uncertainty-aware-shm/","section":"Research-Themes","summary":"This thrust focuses on uncertainty-aware methods for structural health monitoring, damage diagnosis, model updating, prognosis, and decision support.\nThe goal is to move from deterministic monitoring outputs toward confidence-aware interpretation, where engineers can understand not only what a model predicts, but also how reliable that prediction may be.\nWhat We Study # Uncertainty-Aware Monitoring Methods for understanding how measurement noise, modelling assumptions, environmental variability, and limited data affect infrastructure monitoring outcomes.\n","title":"Uncertainty-Aware SHM and Bayesian Inference","type":"research-themes"},{"content":"RISE Lab — Resilient Infrastructure and Smart Engineering Lab is a growing research group in the Department of Civil Engineering at IIT Bombay.\nThe group works on smart and resilient infrastructure systems through structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, prognosis, and decision support.\nFaculty Lead # Prof. Ashish Pal # Assistant Professor Department of Civil Engineering\nIndian Institute of Technology Bombay\nResearch interests include structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, scientific machine learning, system identification, uncertainty quantification, and resilient infrastructure systems.\nCurrent Group # Dr. S. S. Jayakrishna # Post-Doctoral Researcher Working with the group on research related to structural health monitoring, sensing, AI/ML, and smart infrastructure systems.\nSaransh Kar # M.Tech Student Working with the group on research related to structural health monitoring, sensing, AI/ML, and smart infrastructure systems.\nFormer Students # Anushka Singh # Undergraduate Student Worked with the group on multiple research projects related to infrastructure monitoring, sensing, AI/ML-assisted response interpretation, and computational tools for structural engineering applications.\nGrowing Research Group # RISE Lab is actively growing and welcomes motivated students who want to contribute to the early development of the group’s research culture, computational tools, experimental directions, and long-term identity.\nThe group is especially interested in recruiting PhD students, M.Tech students, and motivated B.Tech students interested in smart infrastructure, structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, scientific machine learning, and infrastructure resilience.\nProspective Student Profiles # PhD Students # Ideal for students interested in long-term research on smart infrastructure, structural health monitoring, physics-guided sensing, computer vision, digital twins, scientific machine learning, system identification, uncertainty quantification, and resilient infrastructure systems.\nM.Tech Students # Ideal for students interested in focused thesis projects involving structural dynamics, finite element methods, computer vision, sensing, digital twins, physics-informed learning, and AI/ML for civil infrastructure.\nB.Tech Students # Ideal for motivated students seeking early exposure to research through exploratory projects, coding-based assignments, literature reviews, simulations, and computational demonstrations.\nResearch Opportunities # Interested students are encouraged to visit the Join page for current research directions and application instructions.\n","externalUrl":null,"permalink":"/team/","section":"","summary":"RISE Lab — Resilient Infrastructure and Smart Engineering Lab is a growing research group in the Department of Civil Engineering at IIT Bombay.\nThe group works on smart and resilient infrastructure systems through structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, prognosis, and decision support.\nFaculty Lead # Prof. Ashish Pal # Assistant Professor Department of Civil Engineering\nIndian Institute of Technology Bombay\n","title":"Team","type":"page"},{"content":"This thrust focuses on scientific machine learning methods for understanding structural and dynamical systems from data.\nThe emphasis is on combining data-driven learning with mechanics, governing principles, physical constraints, and computational models so that machine learning methods remain meaningful for engineering analysis and infrastructure monitoring.\nWhat We Study # Scientific Machine Learning for Engineering Systems Methods that combine machine learning with physical principles, numerical modelling, and engineering knowledge for structural and infrastructure applications.\nScientific MLEngineering SystemsMechanics Interpretable AI for Dynamical Systems Learning approaches that aim to make predictions and representations more interpretable in terms of structural behaviour, physical variables, and engineering mechanisms.\nInterpretable AIDynamical SystemsStructural Response Physics-Guided Learning Machine learning methods that use physical constraints, structural mechanics, and engineering insight to improve reliability, robustness, and generalization.\nPhysics-Guided AIRobust LearningSHM Computational Modelling and Data Approaches that connect simulation, measurement, and learning to support model interpretation, monitoring, and decision support in civil infrastructure systems.\nComputational ModellingData-Driven MethodsInfrastructure Methods and Tools # Research in this thrust may involve differential equations, structural dynamics, numerical methods, optimization, machine learning, scientific computing, and Python/MATLAB programming.\nThe emphasis is on developing AI/ML tools that are not only accurate, but also interpretable, physically meaningful, and suitable for engineering use.\nStudent Background # Students interested in this thrust may benefit from background in differential equations, structural dynamics, numerical methods, machine learning, optimization, Python/MATLAB programming, or scientific computing.\nIt is not necessary to have expertise in all areas. Specific topics are shaped based on the student’s background, interests, and expected time commitment.\nInterested Students # Students interested in scientific machine learning, interpretable AI, structural dynamics, computational modelling, or AI for engineering systems are encouraged to read the broader Research page and contact me through the Join the Group page.\nSpecific project topics are discussed individually after understanding the student’s background, interests, and available research opportunities.\n","externalUrl":null,"permalink":"/research-themes/scientific-machine-learning/","section":"Research-Themes","summary":"This thrust focuses on scientific machine learning methods for understanding structural and dynamical systems from data.\nThe emphasis is on combining data-driven learning with mechanics, governing principles, physical constraints, and computational models so that machine learning methods remain meaningful for engineering analysis and infrastructure monitoring.\nWhat We Study # Scientific Machine Learning for Engineering Systems Methods that combine machine learning with physical principles, numerical modelling, and engineering knowledge for structural and infrastructure applications.\n","title":"Scientific Machine Learning and Equation Discovery","type":"research-themes"},{"content":"My teaching focuses on building strong foundations in structural engineering, mechanics, numerical methods, and computational thinking. I aim to connect classical civil engineering concepts with modern computational tools, simulations, and research-oriented problem solving.\nCourses Taught # Introduction to Structural Design # Undergraduate course covering the fundamentals of reinforced concrete behaviour and design, including flexure, shear, serviceability, limit state design philosophy, and practical design considerations for structural members.\nIntroduction to Finite Elements # Postgraduate course introducing the finite element method for engineering analysis, including weak forms, interpolation functions, element formulations, numerical integration, isoparametric elements, and applications in structural and continuum mechanics.\nTeaching Philosophy # My teaching approach emphasizes conceptual clarity, physical interpretation, mathematical foundations, and computational implementation.\nIn structural engineering courses, I focus on helping students connect design equations and analysis procedures with the underlying mechanics of structural behaviour. In computational courses, I emphasize how numerical methods can be understood, implemented, verified, and used responsibly for engineering problems.\nStudent Projects and Research Integration # Students interested in course projects, B.Tech projects, M.Tech thesis work, or PhD research are encouraged to explore topics at the interface of:\nstructural health monitoring, finite element methods, structural dynamics, computer vision, scientific machine learning, digital twins, AI/ML for engineering systems, and smart infrastructure monitoring. Students interested in research opportunities may explore the Research page and the Join the Group page.\n","externalUrl":null,"permalink":"/teaching/","section":"","summary":"My teaching focuses on building strong foundations in structural engineering, mechanics, numerical methods, and computational thinking. I aim to connect classical civil engineering concepts with modern computational tools, simulations, and research-oriented problem solving.\nCourses Taught # Introduction to Structural Design # Undergraduate course covering the fundamentals of reinforced concrete behaviour and design, including flexure, shear, serviceability, limit state design philosophy, and practical design considerations for structural members.\n","title":"Teaching","type":"page"},{"content":"Research projects at RISE Lab focus on smart and resilient infrastructure systems through sensing, structural health monitoring, computer vision, AI/ML, digital twins, prognosis, and decision support.\nThe projects listed here represent ongoing sponsored, internal, exploratory, and collaborative research activities.\nSponsored Research Projects # ANRF Early Career Research Grant High-Fidelity Digital Twins via Scientific Discovery Using Physics-Informed Machine Learning and Uncertainty Quantification for Structural Health Monitoring and Performance Assessment Funding Agency: Anusandhan National Research Foundation (ANRF) Scheme: Early Career Research Grant Role: Principal Investigator Status: Ongoing Duration: Three years This project develops high-fidelity digital twin frameworks for structural health monitoring and performance assessment of civil infrastructure systems. The research integrates physics-informed machine learning, scientific discovery, nonlinear dynamics, and uncertainty quantification to improve the reliability of model updating, damage interpretation, and predictive assessment. The project is motivated by the need to monitor structures and seismic protection systems that may exhibit nonlinear behaviour due to base isolation, energy dissipation devices, cracks, yielding, fatigue, or degradation during service life. The broader aim is to support safer, more intelligent, and more resilient infrastructure systems through data-informed and physically meaningful digital twins. ANRF-ECRG Digital Twins Machine Learning Nonlinear Dynamics Damage Detection Scientific Discovery Uncertainty Quantification Seed-Funded and Collaborative Research Projects # Seed / Internal Research Support System Identification of Nonlinear Dynamic Systems Using Interpretable Machine Learning Methods for Applications in Structural Health Monitoring Funding Source: Industrial Research and Consultancy Centre, IIT Bombay Scheme: Seed Funding Role: Principal Investigator Status: Ongoing Duration: Four years This project focuses on interpretable machine learning methods for system identification of nonlinear dynamic systems in structural health monitoring. The research aims to understand structural behaviour from measured vibration response and support reliable detection, interpretation, and assessment of damage in civil infrastructure systems. The broader objective is to develop data-driven yet physically meaningful models that can help identify nonlinear behaviour, improve structural monitoring, and support the development of digital representations of damaged or evolving structures. Seed Funding Nonlinear Dynamics System Identification Machine Learning Damage Detection Structural Health Monitoring Seed Funding / Collaborative Research Computer-Vision and Physics-Informed Machine Learning Based Bridge Structural Health Monitoring Funding Source: Industrial Research and Consultancy Centre, IIT Bombay Scheme: Seed Funding Role: Principal Investigator Collaborator: Prof. Debarshi Sen, Assistant Professor, Southern Illinois University, Carbondale, Illinois, USA Status: Ongoing Duration: 12 months This project develops computer-vision and machine-learning methods for bridge structural health monitoring and condition assessment. The research explores how visual measurements can support full-field monitoring of bridge response and complement traditional sensing approaches. The project also investigates physics-informed learning approaches to improve the reliability, robustness, and physical consistency of bridge condition assessment models, with validation through laboratory-scale experiments. Computer Vision Structural Health Monitoring Bridge Condition Assessment Physics-Informed Machine Learning Collaborative Research Student and Collaborative Opportunities # Students and collaborators interested in these areas are encouraged to explore the Research page and the Join the Group page.\nSpecific project topics are discussed individually based on research needs, student background, time commitment, and available opportunities.\n","externalUrl":null,"permalink":"/projects/","section":"","summary":"Research projects at RISE Lab focus on smart and resilient infrastructure systems through sensing, structural health monitoring, computer vision, AI/ML, digital twins, prognosis, and decision support.\nThe projects listed here represent ongoing sponsored, internal, exploratory, and collaborative research activities.\nSponsored Research Projects # ANRF Early Career Research Grant High-Fidelity Digital Twins via Scientific Discovery Using Physics-Informed Machine Learning and Uncertainty Quantification for Structural Health Monitoring and Performance Assessment Funding Agency: Anusandhan National Research Foundation (ANRF) Scheme: Early Career Research Grant Role: Principal Investigator Status: Ongoing Duration: Three years ","title":"Projects","type":"page"},{"content":"The publications below reflect research in structural health monitoring, nonlinear system identification, scientific machine learning, sensor fusion, uncertainty quantification, digital twins, and smart and resilient infrastructure systems.\nProspective PhD and M.Tech students are encouraged to explore these papers to understand the group’s research style, technical foundations, and broader areas of interest.\nView research opportunities →\nJournal Articles Latching control: Experimental study on pendulum latched mass damper Authors: Wang, Hao and Pal, Ashish and Nagarajaiah, Satish and Ke, Shitang and Zhu, Songye Journal: Engineering Structures (2026) View Publication → Signal-based online acceleration and strain data fusion using B-splines and Kalman filter for full-field dynamic displacement estimation Authors: Das, Aniruddha and Pal, Ashish and Nagarajaiah, Satish and Sajeer, Mohamed M. and Mukhopadhyay, Suparno Journal: Mechanical Systems and Signal Processing (2026) View Publication → Physics-informed AI and ML-based sparse system identification algorithm for discovery of PDE\u0026#39;s representing nonlinear dynamic systems Authors: Pal, Ashish and Bhowmick, Sutanu and Nagarajaiah, Satish Journal: Mechanical Systems and Signal Processing (2025) View Publication → Data fusion based on short-term memory Kalman filtering using intermittent-displacement and acceleration signal with a time-varying bias Authors: Pal, Ashish and Nagarajaiah, Satish Journal: Mechanical Systems and Signal Processing (2024) View Publication → Sparsity promoting algorithm for identification of nonlinear dynamic system based on Unscented Kalman Filter using novel selective thresholding and penalty-based model selection Authors: Pal, Ashish and Nagarajaiah, Satish Journal: Mechanical Systems and Signal Processing (2024) View Publication → Deep Learning-Based Subsurface Damage Localization Using Full-Field Surface Strains Authors: Pal, Ashish and Meng, Wei and Nagarajaiah, Satish Journal: Sensors (2023) View Publication → Subsurface damage detection via noncontact laser based surface level strain sensing smart skin with carbon nanotubes Authors: Pal, Ashish and Meng, Wei and Bachilo, Sergei M. and Weisman, R. Bruce and Nagarajaiah, Satish Journal: Engineering Structures (2023) View Publication → Hybrid method for full-field response estimation using sparse measurement data based on inverse analysis and static condensation Authors: Pal, Ashish and Meng, Wei and Nagarajaiah, Satish Journal: Journal of Infrastructure Intelligence and Resilience (2022) View Publication → Next-generation 2D optical strain mapping with strain-sensing smart skin compared to digital image correlation Authors: Meng, Wei and Pal, Ashish and Bachilo, Sergei M. and Weisman, R. Bruce and Nagarajaiah, Satish Journal: Scientific Reports (2022) View Publication → Peak Factor--Based Modal Combination Rule of Response-Spectrum Method for Peak Floor Accelerations Authors: Pal, Ashish and Gupta, Vinay K Journal: Journal of Structural Engineering (2021) View Publication → A note on spectral velocity approximation at shorter intermediate periods Authors: Pal, Ashish and Gupta, Vinay K Journal: Soil Dynamics and Earthquake Engineering (2021) View Publication → Conference Papers Modal Identification and Damage Detection of Railway Bridges Using Time-Varying Modes Identified from Train Induced Vibrations Authors: Pal, Ashish and Gaur, Astha and Mukhopadhyay, Suparno Conference: Model Validation and Uncertainty Quantification, Volume 3: Proceedings of the 38th IMAC, A Conference and Exposition on Structural Dynamics 2020 (2020) Books / Book Chapters Deep Learning for Image Segmentation and Subsurface Damage Detection Based on Full-Field Surface Strains Authors: Pal, Ashish and Meng, Wei and Nagarajaiah, Satish Book: Proceedings of the Society for Experimental Mechanics Series (2023) Next-Generation Non-contact Strain-Sensing Method Using Strain-Sensing Smart Skin (S4) for Static and Dynamic Measurement Authors: Meng, Wei and Pal, Ashish and Bachilo, Sergei M. and Weisman, R. Bruce and Nagarajaiah, Satish Book: Model Validation and Uncertainty Quantification, Volume 3 (2023) View Publication → arXiv Preprints KAN/MultKAN with Physics-Informed Spline fitting (KAN-PISF) for ordinary/partial differential equation discovery of nonlinear dynamic systems Authors: Pal, Ashish and Nagarajaiah, Satish arXiv: (2024) View Publication → ","externalUrl":null,"permalink":"/publications/","section":"","summary":"The publications below reflect research in structural health monitoring, nonlinear system identification, scientific machine learning, sensor fusion, uncertainty quantification, digital twins, and smart and resilient infrastructure systems.\nProspective PhD and M.Tech students are encouraged to explore these papers to understand the group’s research style, technical foundations, and broader areas of interest.\nView research opportunities →\nJournal Articles Latching control: Experimental study on pendulum latched mass damper Authors: Wang, Hao and Pal, Ashish and Nagarajaiah, Satish and Ke, Shitang and Zhu, Songye Journal: Engineering Structures (2026) View Publication → Signal-based online acceleration and strain data fusion using B-splines and Kalman filter for full-field dynamic displacement estimation Authors: Das, Aniruddha and Pal, Ashish and Nagarajaiah, Satish and Sajeer, Mohamed M. and Mukhopadhyay, Suparno Journal: Mechanical Systems and Signal Processing (2026) View Publication → Physics-informed AI and ML-based sparse system identification algorithm for discovery of PDE's representing nonlinear dynamic systems Authors: Pal, Ashish and Bhowmick, Sutanu and Nagarajaiah, Satish Journal: Mechanical Systems and Signal Processing (2025) View Publication → Data fusion based on short-term memory Kalman filtering using intermittent-displacement and acceleration signal with a time-varying bias Authors: Pal, Ashish and Nagarajaiah, Satish Journal: Mechanical Systems and Signal Processing (2024) View Publication → Sparsity promoting algorithm for identification of nonlinear dynamic system based on Unscented Kalman Filter using novel selective thresholding and penalty-based model selection Authors: Pal, Ashish and Nagarajaiah, Satish Journal: Mechanical Systems and Signal Processing (2024) View Publication → Deep Learning-Based Subsurface Damage Localization Using Full-Field Surface Strains Authors: Pal, Ashish and Meng, Wei and Nagarajaiah, Satish Journal: Sensors (2023) View Publication → Subsurface damage detection via noncontact laser based surface level strain sensing smart skin with carbon nanotubes Authors: Pal, Ashish and Meng, Wei and Bachilo, Sergei M. and Weisman, R. Bruce and Nagarajaiah, Satish Journal: Engineering Structures (2023) View Publication → Hybrid method for full-field response estimation using sparse measurement data based on inverse analysis and static condensation Authors: Pal, Ashish and Meng, Wei and Nagarajaiah, Satish Journal: Journal of Infrastructure Intelligence and Resilience (2022) View Publication → Next-generation 2D optical strain mapping with strain-sensing smart skin compared to digital image correlation Authors: Meng, Wei and Pal, Ashish and Bachilo, Sergei M. and Weisman, R. Bruce and Nagarajaiah, Satish Journal: Scientific Reports (2022) View Publication → Peak Factor--Based Modal Combination Rule of Response-Spectrum Method for Peak Floor Accelerations Authors: Pal, Ashish and Gupta, Vinay K Journal: Journal of Structural Engineering (2021) View Publication → A note on spectral velocity approximation at shorter intermediate periods Authors: Pal, Ashish and Gupta, Vinay K Journal: Soil Dynamics and Earthquake Engineering (2021) View Publication → Conference Papers Modal Identification and Damage Detection of Railway Bridges Using Time-Varying Modes Identified from Train Induced Vibrations Authors: Pal, Ashish and Gaur, Astha and Mukhopadhyay, Suparno Conference: Model Validation and Uncertainty Quantification, Volume 3: Proceedings of the 38th IMAC, A Conference and Exposition on Structural Dynamics 2020 (2020) Books / Book Chapters Deep Learning for Image Segmentation and Subsurface Damage Detection Based on Full-Field Surface Strains Authors: Pal, Ashish and Meng, Wei and Nagarajaiah, Satish Book: Proceedings of the Society for Experimental Mechanics Series (2023) Next-Generation Non-contact Strain-Sensing Method Using Strain-Sensing Smart Skin (S4) for Static and Dynamic Measurement Authors: Meng, Wei and Pal, Ashish and Bachilo, Sergei M. and Weisman, R. Bruce and Nagarajaiah, Satish Book: Model Validation and Uncertainty Quantification, Volume 3 (2023) View Publication → arXiv Preprints KAN/MultKAN with Physics-Informed Spline fitting (KAN-PISF) for ordinary/partial differential equation discovery of nonlinear dynamic systems Authors: Pal, Ashish and Nagarajaiah, Satish arXiv: (2024) View Publication → ","title":"Research Publications","type":"page"},{"content":"This thrust focuses on identifying structural behaviour, estimating hidden response quantities, and updating computational models using monitoring data.\nThe long-term objective is to support digital twins that are not only visual representations, but data-informed and mechanics-aware models that can evolve with measurements from real civil infrastructure systems.\nWhat We Study # Structural State Estimation Methods for estimating important structural response quantities from measured data, especially when measurements are noisy, sparse, indirect, or incomplete.\nState EstimationStructural DynamicsMonitoring System Identification Approaches for understanding structural properties and behaviour from response data using mechanics, computation, and data-driven modelling.\nSystem IdentificationStructural BehaviourInverse Problems Model Updating Methods for improving computational models of structures using sensing data, experimental observations, and engineering constraints.\nModel UpdatingFinite Element ModelsData Assimilation Digital Twins for Infrastructure Data-informed computational models that support monitoring, interpretation, prognosis, and decision support for civil infrastructure systems.\nDigital TwinsInfrastructureDecision Support Methods and Tools # Research in this thrust may involve structural dynamics, finite element modelling, inverse problems, filtering, optimization, machine learning, scientific computing, and sensing data.\nThe emphasis is on connecting measured response with computational models so that digital twins can support reliable interpretation of structural behaviour and infrastructure condition.\nStudent Background # Students interested in this thrust may benefit from background in structural dynamics, finite element analysis, inverse problems, optimization, filtering, scientific computing, or machine learning.\nIt is not necessary to have expertise in all areas. Specific topics are shaped based on the student’s background, interests, and expected time commitment.\nInterested Students # Students interested in system identification, model updating, digital twins, structural dynamics, or infrastructure monitoring are encouraged to read the broader Research page and contact me through the Join the Group page.\nSpecific project topics are discussed individually after understanding the student’s background, interests, and available research opportunities.\n","externalUrl":null,"permalink":"/research-themes/system-identification-digital-twins/","section":"Research-Themes","summary":"This thrust focuses on identifying structural behaviour, estimating hidden response quantities, and updating computational models using monitoring data.\nThe long-term objective is to support digital twins that are not only visual representations, but data-informed and mechanics-aware models that can evolve with measurements from real civil infrastructure systems.\nWhat We Study # Structural State Estimation Methods for estimating important structural response quantities from measured data, especially when measurements are noisy, sparse, indirect, or incomplete.\n","title":"System Identification and Digital Twin Updating","type":"research-themes"},{"content":"This thrust focuses on methods for detecting, localizing, and interpreting damage in civil infrastructure systems. The goal is to develop damage diagnosis approaches that are connected to structural response, deformation patterns, stiffness changes, vibration behaviour, and engineering interpretation.\nRather than relying only on black-box classification, the work emphasizes physically meaningful indicators, interpretable models, and decision-support methods for infrastructure condition assessment.\nWhat We Study # Damage-Sensitive Structural Response Methods for using measured or simulated structural response to identify abnormal behaviour, stiffness changes, local deterioration, and possible damage-sensitive patterns.\nDamage DetectionStructural ResponseSHM Condition Assessment Approaches for interpreting sensing, vibration, visual, and computational data to support assessment of the current condition of civil infrastructure systems.\nCondition AssessmentMonitoringInfrastructure Physics-Guided Diagnosis Damage diagnosis methods that use mechanics, structural dynamics, and engineering knowledge to improve reliability and interpretability.\nMechanicsDiagnosisInterpretability AI-Assisted Damage Interpretation Machine learning methods for identifying structural condition states while maintaining connection to measurable response features and engineering meaning.\nAI/MLClassificationDecision Support Methods and Tools # Research in this thrust may involve structural analysis, structural dynamics, finite element simulations, signal processing, image-based inspection, machine learning, and experimental measurements.\nThe emphasis is on developing methods that can support reliable damage detection, localization, condition assessment, and infrastructure health monitoring under realistic uncertainty and measurement limitations.\nStudent Background # Students interested in this thrust may benefit from background in structural analysis, structural dynamics, finite element modelling, signal processing, machine learning, experimental mechanics, or infrastructure inspection.\nIt is not necessary to have expertise in all areas. Specific topics are shaped based on the student’s background, interests, and expected time commitment.\nInterested Students # Students interested in damage detection, condition assessment, structural health monitoring, or AI-assisted infrastructure diagnosis are encouraged to read the broader Research page and contact me through the Join the Group page.\nSpecific project topics are discussed individually after understanding the student’s background, interests, and available research opportunities.\n","externalUrl":null,"permalink":"/research-themes/damage-detection/","section":"Research-Themes","summary":"This thrust focuses on methods for detecting, localizing, and interpreting damage in civil infrastructure systems. The goal is to develop damage diagnosis approaches that are connected to structural response, deformation patterns, stiffness changes, vibration behaviour, and engineering interpretation.\nRather than relying only on black-box classification, the work emphasizes physically meaningful indicators, interpretable models, and decision-support methods for infrastructure condition assessment.\nWhat We Study # Damage-Sensitive Structural Response Methods for using measured or simulated structural response to identify abnormal behaviour, stiffness changes, local deterioration, and possible damage-sensitive patterns.\n","title":"Damage Detection, Localization, and Condition Assessment","type":"research-themes"},{"content":" Research Vision # My research develops physics-guided intelligent systems for sensing, interpreting, modelling, and decision-making in civil infrastructure.\nThe central idea is to combine structural dynamics, sensing technologies, scientific computing, and artificial intelligence so that structural health monitoring moves beyond data collection toward diagnosis, prediction, uncertainty-aware interpretation, and practical decision support.\nSensing Mechanics Structural Dynamics AI/ML Digital Twins Decision Support Research Thrust Areas # T1\nPhysics-guided Sensing and Signal Processing for SHM # This thrust focuses on converting measurements from cameras, accelerometers, strain sensors, drones, and heterogeneous monitoring systems into physically meaningful structural response quantities.\nThe goal is to develop sensing and signal-processing methods that are not purely data-driven, but are guided by structural dynamics, measurement physics, and mechanics-based constraints.\nRepresentative directions: SRDD-based derivative estimation, physics-informed computer vision, multi-rate sensor fusion, full-field strain prediction, night-time SHM, drone-based and drive-by monitoring.\nView projects in this thrust →\nT2\nDamage Detection, Localization, and Condition Assessment # This thrust develops methods to detect, localize, and interpret structural damage from vibration, strain, wave propagation, and global response data.\nA key goal is to move toward reliable damage diagnosis even when healthy baseline data are unavailable, which is a common challenge for existing civil infrastructure.\nRepresentative directions: spline-based damage indicators, baseline-free localization, wave attenuation through cracks, KAN-based damage classification, PDE-guided response dictionaries.\nView projects in this thrust →\nT3\nSystem Identification and Digital Twin Updating # This thrust focuses on identifying structural parameters, hidden states, changing properties, and full-field response quantities from measured data.\nThe long-term objective is to support digital twins that are continuously updated using monitoring data and can represent the evolving condition of real structures.\nRepresentative directions: SRDD-enhanced state estimation, time-varying stiffness and damping identification, non-stationary response modelling, sparse-to-full-field reconstruction, digital twin updating.\nView projects in this thrust →\nT4\nScientific Machine Learning and Equation Discovery # This thrust explores whether governing equations, reduced-order models, and interpretable dynamical descriptions can be discovered from structural response data.\nThe emphasis is on scientific machine learning methods that preserve interpretability and connect machine learning outputs back to mechanics.\nRepresentative directions: output-only PDE discovery, sparse regression for structural dynamics, response-curve dictionaries, latent-space discovery, KAN-based scientific modelling.\nView projects in this thrust →\nT5\nUncertainty-aware SHM and Bayesian Inference # This thrust addresses uncertainty in measurements, models, damage estimates, reconstructed signals, and digital twin predictions.\nThe objective is to make SHM outputs more useful for engineering decisions by quantifying confidence, ambiguity, and risk.\nRepresentative directions: Bayesian uncertainty quantification, inverse damage analysis, prior modelling, uncertainty-aware signal completion, Monte-Carlo-style machine learning.\nView projects in this thrust →\nT6\nFoundational Mechanics, Approximation Theory, and Bio-inspired Sensing # This thrust develops foundational methods that support the rest of the research program, including continuous-field representations, adaptive splines, meshless approximations, damage-sensitive shape functions, and unconventional sensing concepts.\nThe goal is to create new mechanics-aware representations and sensing ideas that can make damage detection and structural interpretation more robust.\nRepresentative directions: adaptive splines, hybrid polynomial–B-spline fields, learned knot placement, continuous stiffness/damage fields, damage-sensitive finite element functions, bio-inspired mechanical sensing.\nView projects in this thrust →\nHow the Research Program Fits Together # From measurements to structural meaning The first layer of the research program develops sensing, signal-processing, and computer-vision methods that extract reliable structural response from noisy, incomplete, and heterogeneous measurements.\nRelated thrusts: T1, T5\nSensingSignal ProcessingVision From response to diagnosis The second layer uses mechanics-guided features, response fields, wave propagation, splines, and learning algorithms to detect, localize, and interpret structural damage.\nRelated thrusts: T2, T6\nDamage DetectionLocalizationMechanics From diagnosis to digital twins The third layer identifies structural properties, updates computational models, reconstructs full-field response, and builds data-informed digital twins for infrastructure systems.\nRelated thrusts: T3, T4\nSystem IDDigital TwinsScientific ML From prediction to decision support The final layer quantifies uncertainty and connects monitoring outputs to inspection, maintenance, rehabilitation, and risk-informed decision-making.\nRelated thrusts: T5, T6\nUncertaintyBayesian InferenceDecision Support ","externalUrl":null,"permalink":"/research/","section":"","summary":" Research Vision # My research develops physics-guided intelligent systems for sensing, interpreting, modelling, and decision-making in civil infrastructure.\nThe central idea is to combine structural dynamics, sensing technologies, scientific computing, and artificial intelligence so that structural health monitoring moves beyond data collection toward diagnosis, prediction, uncertainty-aware interpretation, and practical decision support.\nSensing Mechanics Structural Dynamics AI/ML Digital Twins Decision Support Research Thrust Areas # T1\n","title":"Research","type":"page"},{"content":" About Prof. Ashish Pal # Prof. Ashish Pal is an Assistant Professor in the Department of Civil Engineering at the Indian Institute of Technology Bombay. He leads RISE Lab — Resilient Infrastructure and Smart Engineering Lab, a research group developing sensing, AI, and digital-twin methods for smart and resilient civil infrastructure systems.\nHis work brings together structural engineering, sensing technologies, computer vision, machine learning, scientific computing, and digital twins. A central theme of his research is to develop intelligent methods that are not only data-driven, but also guided by physical principles and engineering knowledge.\nAcademic Background # Prof. Pal’s academic training is in civil and structural engineering, with research experience across structural dynamics, computational mechanics, system identification, sensing, and artificial intelligence for engineering systems.\nPh.D. Civil Engineering, Rice University, Texas, USA M.Tech Civil Engineering, Indian Institute of Technology Kanpur, India B.Tech Civil Engineering, Indian Institute of Technology Kanpur, India His research journey has involved combining classical structural engineering concepts with modern computational tools such as machine learning, computer vision, full-field sensing, and scientific machine learning.\nResearch Journey # The motivation behind RISE Lab comes from a simple question:\nHow can civil infrastructure systems become more intelligent, reliable, and resilient over their service life?\nTraditional structural engineering provides strong physical models, but real infrastructure systems are affected by noise, uncertainty, incomplete measurements, ageing, environmental variability, and limited inspection data. Modern AI and computer vision offer powerful tools, but they must be made reliable, interpretable, and physically meaningful for engineering use.\nRISE Lab aims to bridge these two worlds by developing methods that combine data, sensing, structural mechanics, and machine intelligence.\nRISE Lab # RISE Lab stands for Resilient Infrastructure and Smart Engineering Lab.\nThe group focuses on developing methods for infrastructure health monitoring, prognosis, sensing, digital twins, and decision support. The goal is to contribute toward infrastructure systems that can sense, interpret, predict, and support maintenance decisions.\nThe lab’s research philosophy is to combine:\nengineering mechanics, sensing and measurement, computer vision, machine learning, scientific computing, uncertainty quantification, and digital twin modelling. For Students and Collaborators # RISE Lab is being built as a research group for students who are interested in solving civil infrastructure problems using modern computational and experimental tools.\nStudents interested in structural health monitoring, smart infrastructure, computer vision, AI/ML, digital twins, physics-guided sensing, and infrastructure resilience are encouraged to explore the Research page and the Join the Group page.\nResearchers, industry partners, and public agencies interested in infrastructure monitoring, sensing, digital twins, or resilient infrastructure systems are welcome to connect through the Contact page.\n","externalUrl":null,"permalink":"/about/","section":"","summary":"About Prof. Ashish Pal # Prof. Ashish Pal is an Assistant Professor in the Department of Civil Engineering at the Indian Institute of Technology Bombay. He leads RISE Lab — Resilient Infrastructure and Smart Engineering Lab, a research group developing sensing, AI, and digital-twin methods for smart and resilient civil infrastructure systems.\nHis work brings together structural engineering, sensing technologies, computer vision, machine learning, scientific computing, and digital twins. A central theme of his research is to develop intelligent methods that are not only data-driven, but also guided by physical principles and engineering knowledge.\n","title":"About","type":"page"},{"content":"This thrust focuses on sensing, signal processing, and computer vision methods for structural health monitoring of civil infrastructure. The goal is to extract reliable structural information from measurements that may be noisy, incomplete, indirect, or collected under field constraints.\nA central idea is to combine measured data with structural dynamics, mechanics, and engineering knowledge so that sensing outputs remain physically meaningful and useful for infrastructure monitoring.\nWhat We Study # Structural Response Measurement Methods for estimating displacement, vibration, strain, modal response, and other structural quantities from sensor and vision-based measurements.\nSensingStructural DynamicsSHM Vision-Based Monitoring Computer vision approaches for extracting structural motion, deformation, and visual indicators of condition from images and videos.\nComputer VisionVibrationInspection Physics-Guided Signal Processing Signal-processing methods that use physical constraints and engineering knowledge to improve the reliability of measured structural response.\nSignal ProcessingMechanicsMeasurement Multi-Sensor Infrastructure Monitoring Approaches for using data from cameras, accelerometers, strain sensors, drones, and other sensing platforms for infrastructure monitoring.\nSensor DataInfrastructureMonitoring Methods and Tools # Research in this thrust may involve structural dynamics, signal processing, image and video analysis, machine learning, experimental measurements, and computational modelling. Depending on the problem, the work may use Python, MATLAB, finite element simulations, laboratory experiments, or field-oriented sensing data.\nStudent Background # Students interested in this thrust may benefit from background in structural dynamics, signal processing, computer vision, machine learning, Python/MATLAB programming, or experimental measurements.\nIt is not necessary to have expertise in all areas. Specific topics are shaped based on the student’s background, interests, and expected time commitment.\nInterested Students # Students interested in physics-guided sensing, computer vision, signal processing, or infrastructure monitoring are encouraged to read the broader Research page and contact me through the Join the Group page.\nSpecific project topics are discussed individually after understanding the student’s background, interests, and available research opportunities.\n","externalUrl":null,"permalink":"/research-themes/physics-guided-sensing/","section":"Research-Themes","summary":"This thrust focuses on sensing, signal processing, and computer vision methods for structural health monitoring of civil infrastructure. The goal is to extract reliable structural information from measurements that may be noisy, incomplete, indirect, or collected under field constraints.\nA central idea is to combine measured data with structural dynamics, mechanics, and engineering knowledge so that sensing outputs remain physically meaningful and useful for infrastructure monitoring.\nWhat We Study # Structural Response Measurement Methods for estimating displacement, vibration, strain, modal response, and other structural quantities from sensor and vision-based measurements.\n","title":"Physics-Guided Sensing and Signal Processing for SHM","type":"research-themes"},{"content":"\nProspective Students: I am looking for motivated PhD, M.Tech, and B.Tech students interested in smart infrastructure, physics-guided sensing, structural health monitoring, computer vision, AI/ML, digital twins, and infrastructure resilience.\nJoin the group →\nRISE Lab # Resilient Infrastructure and Smart Engineering Lab # Physics-guided sensing, health monitoring, prognosis, and digital twins for smart and resilient infrastructure systems. Led by Prof. Ashish Pal\nDepartment of Civil Engineering\nIndian Institute of Technology Bombay\nRISE Lab develops machine learning, computer vision, physics-guided sensing, and digital-twin methods for health monitoring, prognosis, and decision support in civil infrastructure systems. The long-term goal is to enable smart and resilient infrastructure that can sense, interpret, predict, and support maintenance decisions using data, sensing technologies, structural mechanics, and machine intelligence.\nCore Areas # Smart Infrastructure Physics-Guided Sensing Structural Health Monitoring Computer Vision and AI Digital Twins Infrastructure Prognosis and Resilience\nResearch Vision # Sense # Develop sensing and signal-processing methods to extract reliable structural response from cameras, accelerometers, strain sensors, drones, and heterogeneous field measurements.\nInterpret # Use physics-informed AI and scientific machine learning to identify structural behavior, detect damage, and discover governing patterns from measured data.\nPredict # Build digital twins and computational models that can update with data, quantify uncertainty, and forecast infrastructure performance.\nDecide # Support inspection, maintenance, and resilience decisions through interpretable models, uncertainty-aware diagnosis, and engineering judgment.\nFeatured Publications # Mechanical Systems and Signal Processing • 2025 Sparse PDE Discovery for Nonlinear Dynamic Systems # Physics-informed AI and machine learning for discovering governing equations from dynamic response data.\nView publications →\nMechanical Systems and Signal Processing • 2024 Sparse Identification of Nonlinear Dynamic Systems # A sparsity-promoting system identification framework using unscented Kalman filtering, selective thresholding, and model selection.\nView publications →\nMechanical Systems and Signal Processing • 2024 Data Fusion for Structural Response Estimation # Kalman-filter-based fusion of intermittent displacement and acceleration measurements for high-fidelity structural sensing.\nView publications →\nCurrent Research Directions # Physics-Informed AI for SHM # Develop AI/ML models that combine structural dynamics, sensing data, and physical principles for reliable damage detection, health monitoring, and condition assessment.\nExplore research →\nDigital Twins for Civil Infrastructure # Create computational twins of bridges and building frames by integrating finite element models, sensing data, state estimation, and machine learning.\nExplore research →\nVision-Based Infrastructure Monitoring # Use cameras, drones, and computer vision to measure vibration, displacement, cracks, and visible damage in civil infrastructure systems.\nExplore research →\nJoin the Group # Students interested in PhD, M.Tech thesis, or B.Tech research projects in smart infrastructure, physics-guided sensing, structural health monitoring, computer vision, AI/ML, digital twins, prognosis, and infrastructure resilience are encouraged to get in touch.\nView current opportunities →\n","externalUrl":null,"permalink":"/","section":"","summary":"\nProspective Students: I am looking for motivated PhD, M.Tech, and B.Tech students interested in smart infrastructure, physics-guided sensing, structural health monitoring, computer vision, AI/ML, digital twins, and infrastructure resilience.\nJoin the group →\nRISE Lab # Resilient Infrastructure and Smart Engineering Lab # Physics-guided sensing, health monitoring, prognosis, and digital twins for smart and resilient infrastructure systems. Led by Prof. Ashish Pal\nDepartment of Civil Engineering\nIndian Institute of Technology Bombay\n","title":"","type":"page"},{"content":"","externalUrl":null,"permalink":"/categories/","section":"Categories","summary":"","title":"Categories","type":"categories"},{"content":"I welcome research discussions, student enquiries, academic collaborations, invited talks, workshops, and industry-facing conversations related to smart and resilient infrastructure systems, structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, prognosis, and decision support.\nAcademic Affiliation # Prof. Ashish Pal\nAssistant Professor\nDepartment of Civil Engineering\nIndian Institute of Technology Bombay\nPowai, Mumbai, Maharashtra, India, 400076\nEmail # For academic, research, teaching, collaboration, and student-related communication, please contact me through my institutional email.\nEmail: ashish.pal@civil.iitb.ac.in Phone: +91-22-2576-9311\nResearch Interests # Smart and Resilient Infrastructure Structural Health Monitoring Physics-Guided Sensing Digital Twins for Civil Infrastructure Computer Vision and AI for Infrastructure Monitoring Scientific Machine Learning Structural Dynamics and System Identification Uncertainty-Aware Prognosis and Decision Support Student Enquiries # Prospective PhD, M.Tech, and undergraduate students interested in research projects may write with:\nBrief academic background Research interests Relevant coursework or project experience CV or resume Specific reason for interest in the group Please also see the Join page for current research opportunities and expectations.\nCollaboration Enquiries # I am open to academic and industry collaborations in:\nAI/ML for structural health monitoring Physics-guided sensing and infrastructure monitoring Digital twin frameworks for civil infrastructure Vision-based inspection and monitoring Scientific machine learning for engineering systems Infrastructure prognosis and decision support Smart and resilient infrastructure systems For collaboration discussions, please include a short description of the proposed problem, available data or facilities, and the expected research or application outcome.\nProfiles # Google Scholar GitHub LinkedIn IIT Bombay Faculty Profile ","externalUrl":null,"permalink":"/contact/","section":"","summary":"I welcome research discussions, student enquiries, academic collaborations, invited talks, workshops, and industry-facing conversations related to smart and resilient infrastructure systems, structural health monitoring, physics-guided sensing, computer vision, AI/ML, digital twins, prognosis, and decision support.\nAcademic Affiliation # Prof. Ashish Pal\nAssistant Professor\nDepartment of Civil Engineering\nIndian Institute of Technology Bombay\nPowai, Mumbai, Maharashtra, India, 400076\nEmail # For academic, research, teaching, collaboration, and student-related communication, please contact me through my institutional email.\n","title":"Contact","type":"page"},{"content":"","externalUrl":null,"permalink":"/research-themes/","section":"Research-Themes","summary":"","title":"Research-Themes","type":"research-themes"},{"content":"","externalUrl":null,"permalink":"/tags/","section":"Tags","summary":"","title":"Tags","type":"tags"}]