Knowledge-guided Machine Learning: Current Trends and Future Prospects
It addresses the need for more reliable and interpretable ML models in scientific domains, but is incremental as it reviews existing trends rather than presenting new results.
This paper provides an overview of knowledge-guided machine learning (KGML), which integrates scientific knowledge with data in ML frameworks to improve generalizability, consistency, and explainability, particularly in environmental sciences.
This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current state of research in the emerging field of scientific knowledge-guided machine learning (KGML) that aims to use both scientific knowledge and data in ML frameworks to achieve better generalizability, scientific consistency, and explainability of results. We discuss different facets of KGML research in terms of the type of scientific knowledge used, the form of knowledge-ML integration explored, and the method for incorporating scientific knowledge in ML. We also discuss some of the common categories of use cases in environmental sciences where KGML methods are being developed, using illustrative examples in each category.