Summary
This survey synthesises the emerging field of physics-guided machine learning, examining how traditional physics-based modelling can be integrated with state-of-the-art ML techniques to address complex engineering and environmental problems. The authors provide a structured taxonomy of existing methodologies and highlight disciplinary knowledge gaps and cross-disciplinary opportunities for future research.
Regional applicability
This is a methodological review focused on computational and modelling frameworks rather than agricultural or food systems specifically. Applicability to UK farming and soil health research would depend on whether the reviewed ML-physics integration approaches have been applied to agricultural systems; the abstract does not indicate sector-specific focus.
Key measures
Taxonomy of physics-guided ML models and hybrid physics-ML frameworks; classification of application-centric objective areas
Outcomes reported
A structured overview and taxonomy of methodologies integrating physics-based modelling with machine learning techniques. The review identifies application areas, classes of hybrid approaches, and knowledge gaps across disciplines.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.