Expensive models and experiments
PIML can reduce repeated simulation or experimental cost while retaining the governing knowledge used in Artificial Intelligence (AI) and Data Science.
Engineering Research Community
Artificial Intelligence (AI) and Data Science & Physics-Informed Machine Learning
Physics-grounded modelling, learning and validation for Artificial Intelligence (AI) and Data Science
Artificial Intelligence and Data Science covers statistical learning, data engineering, machine learning, deep learning, visualization, optimization, databases and responsible deployment. PIML extends this discipline to scientific and engineering data whose generation is constrained by laws, symmetries, units, geometry and causal mechanisms.
The branch contributes rigorous data pipelines, evaluation, uncertainty, scalable learning and reproducibility. Its responsibility is to prevent physical constraints from becoming decorative loss terms and to test whether hybrid models truly improve generalization, identifiability or decision value.
This page presents ten focused research areas, degree-level project pathways, selected publications and direct support through the PIMLS biweekly members meeting.
This Artificial Intelligence (AI) and Data Science guide covers Physics-Informed Neural Networks (PINNs), physics-guided machine learning, scientific machine learning, neural operators, hybrid models and engineering digital twins. Explore the research and project pathways below, then join the Physics-Informed Machine Learning Society to connect with the international PIMLS community.
The central ideaEstablished Artificial Intelligence (AI) and Data Science knowledge + measurements and simulation + machine learning
10focused research areas
3academic project pathways
6selected publications
Biweeklymember research meeting
Why this combination matters
Why Artificial Intelligence (AI) and Data Science Needs Physics-Informed Learning
Use available scientific knowledge to make limited data more useful, transparent and testable.
Incomplete engineering models
Learn uncertain parameters, closures or discrepancies around an inspectable mechanistic foundation.
Transfer across conditions
Test whether structured models generalize across geometries, materials, assets, operating regimes or sites.
Trustworthy evidence
Use physical residuals, independent measurements, uncertainty and conventional engineering baselines before deployment.
Ten focused directions
Major Artificial Intelligence (AI) and Data Science PIML Research Areas
Each card connects a meaningful Artificial Intelligence (AI) and Data Science question with suitable scientific knowledge, modelling choices and evidence needed to test it.
01
Forward PDE Surrogates
Repeated high-fidelity solves are expensive. PIML opportunities: Compare PINNs, neural operators and classical reduced models across parameters and meshes.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
02
Inverse Problems
Parameters or sources must be inferred from sparse noisy observations. PIML opportunities: Use governing residuals with identifiability and uncertainty analysis.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
03
Equation Discovery
Unknown dynamics may be recoverable from data and candidate structure. PIML opportunities: Combine sparse regression or differentiable models with dimensional and conservation constraints.
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
04
Neural Operators
A model should learn mappings between functions, not one fixed solution. PIML opportunities: Evaluate resolution, geometry, parameter and boundary-condition generalization.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
05
Differentiable Simulation
Gradients through models enable calibration, design and control. PIML opportunities: Assess gradient fidelity, stiffness, computational cost and model discrepancy.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
06
Multi-Fidelity Learning
Data range from coarse simulation to scarce experiments. PIML opportunities: Fuse fidelity levels while representing bias and avoiding information leakage.
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
07
Scientific Data Assimilation
Dynamic states require updates from partial observations. PIML opportunities: Compare learned filters with variational and ensemble baselines.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
08
Uncertainty Quantification
Point predictions are insufficient for inverse and safety-critical decisions. PIML opportunities: Separate aleatoric, parameter, model-form and numerical uncertainty.
Model and evidenceMechanistic and data-only baselines, uncertainty and independent validation
09
Geometric and Equivariant Learning
Symmetry and geometry determine valid transformations. PIML opportunities: Encode invariance/equivariance in architectures and test data-efficiency gains.
Model and evidenceGeometry, material or system parameters, sensor data and physical residuals
10
Physics-Guided Generative Models
Generated fields or designs may violate feasibility. PIML opportunities: Impose constraints and verify samples with independent solvers and diversity metrics.
Model and evidenceGoverning equations, calibrated measurements and held-out operating conditions
Choose the right research depth
Projects for Every Academic Stage
Start with a scope that matches your time, mathematical background, experimental access and expected research contribution.
Project pathway 1
B.E./B.Tech
Learn the foundations with a bounded, measurable system.
- PINN versus finite-difference benchmark
- conservation-constrained regression
- dimensionally consistent feature pipeline
- uncertainty calibration study
Expected outcome
A reproducible implementation, clear baselines, a manageable dataset and physically meaningful validation.
Project pathway 2
M.Tech
Combine an engineering model, substantial data and rigorous comparison.
- neural operator generalization benchmark
- Bayesian physics-informed inverse problem
- multi-fidelity scientific data fusion
- equivariant learning for physical fields
Expected outcome
A thesis-quality study with held-out regimes, mechanistic and data-only baselines, ablation and uncertainty.
Project pathway 3
Ph.D.
Address a publishable methodological, multiscale or deployment research gap.
- reliable optimization theory for PIML
- benchmark suite for out-of-regime SciML
- probabilistic neural operators
- auditable scientific foundation models
Expected outcome
New methodology or validated engineering insight, multi-regime evidence, reproducible software and journal publications.
From idea to evidence
A Strong PIML Project Workflow
01
Define
Choose one Artificial Intelligence (AI) and Data Science question and a measurable engineering output.
02
Model
State the governing relationships, constraints or validated domain knowledge you will retain.
03
Compare
Build mechanistic and data-only baselines before the hybrid model.
04
Validate
Hold out experiments, conditions, assets, sites or regimes at the deployment level.
05
Publish
Report uncertainty, ablation, limitations, data lineage and reproducible code.
Read before you modelDiscuss Your Literature
Selected Publications and Why They Matter
Use this focused reading list to understand the general PIML framework, direct Artificial Intelligence (AI) and Data Science evidence and suitable hybrid modelling methods.
Literature review advice
Do not list papers only. Compare the engineering question, incorporated knowledge, data, split strategy, baselines, uncertainty and evidence level.
This source is included in the Artificial Intelligence (AI) and Data Science literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Artificial Intelligence (AI) and Data Science.
Read publication or record This source is included in the Artificial Intelligence (AI) and Data Science literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Artificial Intelligence (AI) and Data Science.
Read publication or record This source is included in the Artificial Intelligence (AI) and Data Science literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Artificial Intelligence (AI) and Data Science.
Read publication or record This source is included in the Artificial Intelligence (AI) and Data Science literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Artificial Intelligence (AI) and Data Science.
Read publication or record This source is included in the Artificial Intelligence (AI) and Data Science literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Artificial Intelligence (AI) and Data Science.
Read publication or record This source is included in the Artificial Intelligence (AI) and Data Science literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
How to use this paper: Use this paper to refine the research question, identify a defensible physical prior and compare evidence requirements for Artificial Intelligence (AI) and Data Science.
Read publication or record Build an interdisciplinary team
Where Artificial Intelligence (AI) and Data Science Can Collaborate
Computer Science
Scientific ML, optimization, trustworthy AI and reproducible research software.
Applied Mathematics
Differential equations, numerical methods, inverse problems and uncertainty.
Sensing & Control
Instrumentation, data acquisition, state estimation and responsible deployment.
Domain Laboratories
Experiments, calibration, validation evidence and practical expertise for Artificial Intelligence (AI) and Data Science.
Before you begin
Frequently Asked Research Questions
These answers help students avoid common scope, terminology and validation mistakes.
Still have a question?
Use the biweekly meeting form for research guidance.
Request accessNo. Artificial Intelligence (AI) and Data Science projects may use physics-guided features, hybrid residual models, differentiable simulators, neural operators, constrained architectures or data assimilation. State exactly what knowledge is incorporated.
Choose one engineering question, a measurable output and a defensible mechanistic baseline. Add learning only where data can identify an uncertainty or discrepancy.
A meaningful question, justified prior knowledge, deployment-level holdouts, strong baselines, ablation, uncertainty, reproducibility and honest limitations.
Simulation can broaden coverage, but simulation-only evidence cannot establish real-system accuracy. Use calibrated experiments, field measurements or trusted independent references appropriate to the claim.
Submit the biweekly members meeting form to discuss your project level, branch, data, model, validation plan and possible collaborators.
Take the next step
Bring your Artificial Intelligence (AI) and Data Science research idea to PIMLS
Join the biweekly members meeting for project guidance, collaboration and publication planning—or contact the Society directly.
Meeting participation is requested through the Google form. Complete it carefully so the Society can understand your research interest.