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

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.

References in corpus (6)

• A Contextual-Bandit Approach to Personalized News Article Recommendation
• A note on the group lasso and a sparse group lasso
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Boosted Decision Trees as an Alternative to Artificial Neural Networks for Particle Identification
• CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networks
• Generalized Dantzig Selector: Application to the k-support norm

Cited by in corpus (130)

• An overview of deep learning in medical imaging focusing on MRI
• A trans-disciplinary review of deep learning research for water resources scientists
• Explainable Machine Learning for Scientific Insights and Discoveries
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Seeing biodiversity: perspectives in machine learning for wildlife conservation
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales
• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Digital twin, physics-based model, and machine learning applied to damage detection in structures
• Deep Learning of Subsurface Flow via Theory-guided Neural Network
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
• Combining Physically-Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn from Mismatch?
• Physics-Guided Deep Neural Networks for Power Flow Analysis
• PINNeik: Eikonal solution using physics-informed neural networks
• A Physics-Informed Deep Learning Paradigm for Car-Following Models
• A Hybrid Science-Guided Machine Learning Approach for Modeling and Optimizing Chemical Processes
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
• A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Physics-informed neural networks for solving forward and inverse problems in complex beam systems
• DeepMoD: Deep learning for Model Discovery in noisy data
• Robust learning from noisy, incomplete, high-dimensional experimental data via physically constrained symbolic regression
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions
• On Recurrent Neural Networks for learning-based control: recent results and ideas for future developments
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions
• Predicting Water Temperature Dynamics of Unmonitored Lakes with Meta Transfer Learning
• Deep Learning for One-dimensional Consolidation
• Spatio-Temporal Data Mining: A Survey of Problems and Methods
• Towards a Collective Agenda on AI for Earth Science Data Analysis
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Digital Twin: Values, Challenges and Enablers
• Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
• Persistence in Complex Systems
• Model-data-driven constitutive responses: application to a multiscale computational framework
• Capabilities of Deep Learning Models on Learning Physical Relationships: Case of Rainfall-Runoff Modeling with LSTM
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• Physics-informed machine learning for Structural Health Monitoring
• Model fusion with physics-guided machine learning
• Interpreting recurrent neural networks behaviour via excitable network attractors
• Physics-Informed Echo State Networks
• Data-aided Underwater Acoustic Ray Propagation Modeling
• PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• Explainable Machine Learning with Prior Knowledge: An Overview
• Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)
• Physics-Informed Machine Learning Method for Large-Scale Data Assimilation Problems
• Time Series Predictions in Unmonitored Sites: A Survey of Machine Learning Techniques in Water Resources
• Real-time simulation of viscoelastic tissue behavior with physics-guided deep learning
• Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications
• A Lagrangian Dual-based Theory-guided Deep Neural Network
• Interpretable machine learning for high-dimensional trajectories of aging health
• LDSF: Lightweight Dual-Stream Framework for SAR Target Recognition by Coupling Local Electromagnetic Scattering Features and Global Visual Features
• Learning fluid physics from highly turbulent data using sparse physics-informed discovery of empirical relations (SPIDER)
• Knock Detection in Combustion Engine Time Series Using a Theory-Guided 1D Convolutional Neural Network Approach
• Integrating Domain Knowledge in Data-driven Earth Observation with Process Convolutions
• Physics-guided Design and Learning of Neural Networks for Predicting Drag Force on Particle Suspensions in Moving Fluids
• Structure Probing Neural Network Deflation
• Physics-Guided Neural Networks for Feedforward Control: An Orthogonal Projection-Based Approach
• Improved Surrogate Modeling of Fluid Dynamics with Physics-Informed Neural Networks
• Feature Guided Training and Rotational Standardisation for the Morphological Classification of Radio Galaxies
• Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks
• A Physics-Informed Deep Learning Model of the Hot Tail Runaway Electron Seed
• Accelerating Bayesian microseismic event location with deep learning
• Auto-Encoder Neural Network Incorporating X-Ray Fluorescence Fundamental Parameters with Machine Learning
• TDEFSI: Theory Guided Deep Learning Based Epidemic Forecasting with Synthetic Information
• Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles
• Fast and robust particle shuttling for quantum science and technology
• Point Neuron Learning: A New Physics-Informed Neural Network Architecture
• Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
• AdjointNet: Constraining machine learning models with physics-based codes
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• Physics-Informed Deep Learning for Traffic State Estimation
• A Physics-Informed Deep Learning Description of Knudsen Layer Reactivity Reduction
• Multi-Objective Physics-Guided Recurrent Neural Networks for Identifying Non-Autonomous Dynamical Systems
• A physics-based domain adaptation framework for modelling and forecasting building energy systems
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
• Can we integrate spatial verification methods into neural-network loss functions for atmospheric science?
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• Deep Neural Networks for Computational Optical Form Measurements
• Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
• AIR5: Five Pillars of Artificial Intelligence Research
• Scientific machine learning in Hydrology: a unified perspective
• A Data Scientist's Guide to Streamflow Prediction
• Iterative peak-fitting of frequency-domain data via deep convolution neural networks
• CIRA Guide to Custom Loss Functions for Neural Networks in Environmental Sciences -- Version 1
• Field-scale soil moisture estimated from Sentinel-1 SAR data using a knowledge-guided deep learning approach
• Generating artificial digital image correlation data using physics-guided adversarial networks
• Reduced order modeling of fluid flows: Machine learning, Kolmogorov barrier, closure modeling, and partitioning
• An Iterative Scientific Machine Learning Approach for Discovery of Theories Underlying Physical Phenomena
• Composed Physics- and Data-driven System Identification for Non-autonomous Systems in Control Engineering
• Living in the Physics and Machine Learning Interplay for Earth Observation
• MC-LSTM: Mass-Conserving LSTM
• Knowledge-Guided Dynamic Systems Modeling: A Case Study on Modeling River Water Quality
• A Physics-Data-Driven Bayesian Method for Heat Conduction Problems
• A Survey on Spatial and Spatiotemporal Prediction Methods
• Learning to Route via Theory-Guided Residual Network
• Numerical analysis of a deep learning formulation of elastic full waveform inversion with high order total variation regularization in different parameterization
• A Mechanism-Learning Deeply Coupled Model for Remote Sensing Retrieval of Global Land Surface Temperature
• Unifying Model-Based and Neural Network Feedforward: Physics-Guided Neural Networks with Linear Autoregressive Dynamics
• Learning interaction rules from multi-animal trajectories via augmented behavioral models
• SRoll3: A neural network approach to reduce large-scale systematic effects in the Planck High Frequency Instrument maps
• Data-Driven Theory-guided Learning of Partial Differential Equations using SimultaNeous Basis Function Approximation and Parameter Estimation (SNAPE)
• Theory-Guided Machine Learning for Process Simulation of Advanced Composites
• Predicting the flow field in a U-bend with deep neural networks
• Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective
• A Linear Algebraic Approach to Model Parallelism in Deep Learning
• Vehicle Emissions Prediction with Physics-Aware AI Models: Preliminary Results
• A Survey on Machine Learning Applied to Dynamic Physical Systems
• A kinetic-based regularization method for data science applications
• Training Deep Neural Networks with Constrained Learning Parameters
• Off-the-shelf deep learning is not enough: parsimony, Bayes and causality
• Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling
• Physics-Informed Machine Learning in Prognostics and Health Management: A Systematic Literature Review
• Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility
• Philosophy-informed Machine Learning
• Explanation from Specification
• Incorporating Expert Guidance in Epidemic Forecasting
• Paradigm Shift Through the Integration of Physical Methodology and Data Science
• Comparison of Deep Neural Networks and Deep Hierarchical Models for Spatio-Temporal Data
• Investigation of Nonlinear Model Order Reduction of the Quasigeostrophic Equations through a Physics-Informed Convolutional Autoencoder
• A comparison of data-driven approaches to build low-dimensional ocean models
• Tensor Learning-based Precoder Codebooks for FD-MIMO Systems
• An evolve-then-correct reduced order model for hidden fluid dynamics