Given their tremendous success in commercial applications, machine learning (ML) models are increasingly being considered as alternatives to science-based models in many disciplines. Yet, these "black-box" ML models have found limited success due to their inability to work well in the presence of limited training data and generalize to unseen scenarios. As a result, there is a growing interest in the scientific community on creating a new generation of methods that integrate scientific knowledge in ML frameworks. This emerging field, called scientific knowledge-guided ML (KGML), seeks a distinct departure from existing "data-only" or "scientific knowledge-only" methods to use knowledge and data at an equal footing. Indeed, KGML involves diverse scientific and ML communities, where researchers and practitioners from various backgrounds and application domains are continually adding richness to the problem formulations and research methods in this emerging field. Knowledge Guided Machine Learning: Accelerating Discovery using Scientific Knowledge and Data provides an introduction to this rapidly growing field by discussing some of the common themes of research in KGML using illustrative examples, case studies, and reviews from diverse application domains and research communities as book chapters by leading researchers. KEY FEATURES First-of-its-kind book in an emerging area of research that is gaining widespread attention in the scientific and data science fields Accessible to a broad audience in data science and scientific and engineering fields Provides a coherent organizational structure to the problem formulations and research methods in the emerging field of KGML using illustrative examples from diverse application domains Contains chapters by leading researchers, which illustrate the cutting-edge research trends, opportunities, and challenges in KGML research from multiple perspectives Enables cross-pollination of KGML problem formulations and research methods across disciplines Highlights critical gaps that require further investigation by the broader community of researchers and practitioners to realize the full potential of KGML Cover Half Title Series Page Title Page Copyright Page Contents About the Editors List of Contributors 1. Introduction 2. Targeted Use of Deep Learning for Physics and Engineering 3. Combining Theory and Data-Driven Approaches for Epidemic Forecasts 4. Machine Learning and Projection-Based Model Reduction in Hydrology and Geosciences 5. Applications of Physics-Informed Scientific Machine Learning in Subsurface Science: A Survey 6. Adaptive Training Strategies for Physics-Informed Neural Networks 7. Modern Deep Learning for Modeling Physical Systems 8. Physics-Guided Deep Learning for Spatiotemporal Forecasting 9. Science-Guided Design and Evaluation of Machine Learning Models: A Case-Study on Multi-Phase Flows 10. Using the Physics of Electron Beam Interactions to Determine Optimal Sampling and Image Reconstruction Strategies for High Resolution STEM 11. FUNNL: Fast Nonlinear Nonnegative Unmixing for Alternate Energy Systems 12. Structure Prediction from Scattering Profiles: A Neutron-Scattering Use-Case 13. Physics-Infused Learning: A DNN and GAN Approach 14. Combining System Modeling and Machine Learning into Hybrid Ecosystem Modeling 15. Physics-Guided Neural Networks (PGNN): An Application in Lake Temperature Modeling 16. Physics-Guided Recurrent Neural Networks for Predicting Lake Water Temperature 17. Physics-Guided Architecture (PGA) of LSTM Models for Uncertainty Quantification in Lake Temperature Modeling Index "Machine Learning (ML) methods are increasingly being used as alternatives or surrogates to scientific models to explain real-world phenomena in a number of disciplines. However, given the limited ability of "black-box" ML methods to learn generalizable and scientifically consistent patterns from limited volumes of data, there is a growing realization in the scientific and data science communities to incorporate scientific knowledge in the ML process. This emerging paradigm combining scientific knowledge and data at an equal footing is labeled Science-Guided ML (SGML). By using scientific consistency as an essential criterion for assessing generalizability of ML models, SGML aims to go far and beyond conventional standards of black-box ML in modeling scientific systems. SGML also aims to accelerate scientific discovery using data by informing scientific models with better estimates of latent quantities, augmenting modeling components, and/or discovering new scientific laws. Knowledge Guided Machine Learning: Accelerating Discovery using Scientific Knowledge and Data provides an introduction to this rapidly growing field by discussing some of the common themes of research in SGML, using illustrative examples and case studies from diverse application domains and research communities as contributed book chapters"-- Provided by publisher
