Differentiable modelling to unify machine learning and physical models for geosciences

Chaopeng Shen, Alison P. Appling, Pierre Gentine, Toshiyuki Bandai, Hoshin Gupta, Alexandre Tartakovsky, Marco Baity-Jesi, Fabrizio Fenicia, Daniel Kifer, Li Li, Xiaofeng Liu, Wei Ren, Yi Zheng, Ciaran J. Harman, Martyn Clark, Matthew Farthing, Dapeng Feng, Praveen Kumar, Doaa Aboelyazeed, Farshid RahmaniYalan Song, Hylke E. Beck, Tadd Bindas, Dipankar Dwivedi, Kuai Fang, Marvin Höge, Chris Rackauckas, Binayak Mohanty, Tirthankar Roy, Chonggang Xu, Kathryn Lawson

Research output: Contribution to journalArticlepeer-review

Abstract

Process-based modelling offers interpretability and physical consistency in many domains of geosciences but struggles to leverage large datasets efficiently. Machine-learning methods, especially deep networks, have strong predictive skills yet are unable to answer specific scientific questions. In this Perspective, we explore differentiable modelling as a pathway to dissolve the perceived barrier between process-based modelling and machine learning in the geosciences and demonstrate its potential with examples from hydrological modelling. ‘Differentiable’ refers to accurately and efficiently calculating gradients with respect to model variables or parameters, enabling the discovery of high-dimensional unknown relationships. Differentiable modelling involves connecting (flexible amounts of) prior physical knowledge to neural networks, pushing the boundary of physics-informed machine learning. It offers better interpretability, generalizability, and extrapolation capabilities than purely data-driven machine learning, achieving a similar level of accuracy while requiring less training data. Additionally, the performance and efficiency of differentiable models scale well with increasing data volumes. Under data-scarce scenarios, differentiable models have outperformed machine-learning models in producing short-term dynamics and decadal-scale trends owing to the imposed physical constraints. Differentiable modelling approaches are primed to enable geoscientists to ask questions, test hypotheses, and discover unrecognized physical relationships. Future work should address computational challenges, reduce uncertainty, and verify the physical significance of outputs.

Original languageEnglish (US)
Pages (from-to)552-567
Number of pages16
JournalNature Reviews Earth and Environment
Volume4
Issue number8
DOIs
StatePublished - Aug 2023
Externally publishedYes

ASJC Scopus subject areas

  • Pollution
  • Earth-Surface Processes
  • Atmospheric Science
  • Nature and Landscape Conservation

Fingerprint

Dive into the research topics of 'Differentiable modelling to unify machine learning and physical models for geosciences'. Together they form a unique fingerprint.

Cite this