Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data

2016/12/31 by Anuj Karpatne, Gowtham Atluri, James Faghmous +9 · 36 citations
Computer Science · Decision Sciences · Mathematics · #Data Analysis with R #Research Data Management Practices #Scientific Computing and Data Management #cs.AI #cs.LG #stat.ML

paper · pdf · doi:10.1109/tkde.2017.2720168

published as IEEE Transactions on Knowledge and Data Engineering, 29(10), pp.2318-2331. 2017

openalex publication_date 2017/06/29 · arxiv created 2017/11/13 · arxiv updated 2017/11/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of data science models in enabling scientific discovery. The overarching vision of TGDS is to introduce scientific consistency as an essential component for learning generalizable models. Further, by producing scientifically interpretable models, TGDS aims to advance our scientific understanding by discovering novel domain insights. Indeed, the paradigm of TGDS has started to gain prominence in a number of scientific disciplines such as turbulence modeling, material discovery, quantum chemistry, bio-medical science, bio-marker discovery, climate science, and hydrology. In this paper, we formally conceptualize the paradigm of TGDS and present a taxonomy of research themes in TGDS. We describe several approaches for integrating domain knowledge in different research themes using illustrative examples from different disciplines. We also highlight some of the promising avenues of novel research for realizing the full potential of theory-guided data science.

Citations

• A Sparse-Group Lasso
• A note on the group lasso and a sparse group lasso
• The future of distributed models: Model calibration and uncertainty prediction
• ImageNet classification with deep convolutional neural networks
• Boosted decision trees as an alternative to artificial neural networks for particle identification

Cited by

• Informed Learning for Estimating Drought Stress at Fine-Scale Resolution Enables Accurate Yield Prediction
• Physics-guided Emulators Reveal Resilience and Fragility under Operational Latencies and Outages
• Physics-augmented Multi-task Gaussian Process for Modeling Spatiotemporal Dynamics
• PHASE: Physics-Integrated, Heterogeneity-Aware Surrogates for Scientific Simulations
• Philosophy-informed Machine Learning
• Learning to Retrieve for Environmental Knowledge Discovery: An Augmentation-Adaptive Self-Supervised Learning Framework
• High-Resolution Global Land Surface Temperature Retrieval via a Coupled Mechanism-Machine Learning Framework
• Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models
• Knowledge distillation as a pathway toward next-generation intelligent ecohydrological modeling systems
• A Neural Network‐Based Estimate of the Seasonal to Inter‐Annual Variability of the Lake Superior Carbon Cycle
• Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
• Synergistic Integration of Flood Inundation Modeling Methods: A Review of Computational, Data‐Driven, Observational and Experimental, and Conceptual Models
• Bayesian Deep Learning for Convective Initiation Nowcasting Uncertainty Estimation
• WellPINN: Accurate Well Representation for Transient Fluid Pressure Diffusion in Subsurface Reservoirs with Physics-Informed Neural Networks
• From Physics to Foundation Models: A Review of AI-Driven Quantitative Remote Sensing Inversion
• Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models
• Artificial Intelligence for Atmospheric Sciences: A Research Roadmap
• Towards NoahMP-AI: Enhancing Land Surface Model Prediction with Deep Learning
• PMNO: A novel physics guided multi-step neural operator predictor for partial differential equations
• Learning mechanical systems from real-world data using discrete forced Lagrangian dynamics
• Multi-Source Dynamic Graph Learning for Compound-Flood Forecasting in Managed Coastal Systems
• Scientific machine learning in Hydrology: a unified perspective
• SAR-GTR: Attributed Scattering Information Guided SAR Graph Transformer Recognition Algorithm
• Physics-Informed Neural Network Method and Application to Nuclear Reactor Calculations: A Pilot Study
• Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
• Incorporating Expert Guidance in Epidemic Forecasting
• Three-dimensional reconstruction of complex lithological ore districts based on a divide-and-conquer strategy: A case study of the Jiaojia gold deposit
• Field-scale soil moisture estimated from Sentinel-1 SAR data using a knowledge-guided deep learning approach
• Physics-Informed Deep Learning for Traffic State Estimation
• Predicting Water Temperature Dynamics of Unmonitored Lakes With Meta‐Transfer Learning
• SRoll3: A neural network approach to reduce large-scale systematic effects in the Planck High-Frequency Instrument maps
• Fractional physics-informed neural networks for time-fractional phase field models
• Improvement of spatiotemporal generalization in radiocesium transfer models for wheat using symbolic regression
• Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition
• A Knowledge-guided Adversarial Defense for Resisting Malicious Visual Manipulation
• A Mechanism-Learning Deeply Coupled Model for Remote Sensing Retrieval of Global Land Surface Temperature

Related

• Physics is the New Data
• Data Science as a New Frontier for Design
• Paradigm Shift Through the Integration of Physical Methodology and Data Science
• A framework for understanding data science
• Perspective on Data Science