Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 468

The DOI matches its Crossref record; 145 of the 145 references it cites were found in a registry or an index.

Differentiable modelling to unify machine learning and physical models for geosciences

Open access
Shen, Chaopeng, Appling, Alison P., Gentine, Pierre, Bandai, Toshiyuki, Gupta, Hoshin, Tartakovsky, Alexandre, Baity-Jesi, Marco, Fenicia, Fabrizio, Kifer, Daniel, Li, Li, Liu, Xiaofeng, Ren, Wei, Zheng, Yi, Harman, Ciaran J., Clark, Martyn, Farthing, Matthew, Feng, Dapeng, Kumar, Praveen, Aboelyazeed, Doaa, Rahmani, Farshid, Song, Yalan, Beck, Hylke E., Bindas, Tadd, Dwivedi, Dipankar, Fang, Kuai, Höge, Marvin, Rackauckas, Chris, Mohanty, Binayak, Roy, Tirthankar, Xu, Chonggang, Lawson, Kathryn·2023·Nature Reviews Earth & Environment

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. Differentiable modelling is an approach that flexibly integrates the learning capability of machine learning with the interpretability of process-based models. This Perspective highlights the potential of differentiable modelling to improve the representation of processes, parameter estimation, and predictive accuracy in the geosciences.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s43017-023-00450-9

Cites

145 of 145 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 145 references

Research works printed but not linked: 29

  1. Lepore, C., Arnone, E., Noto, L. V., Sivandran, G. & Bras, R. L. Physically based modeling of rainfall-triggered landslides: a case study in the Luquillo forest, Puerto Rico. Hydrol. Earth Syst. Sci. 17, 3371–3387 (2013). · doi:10.5194/hess-17-3371-2013
  2. Weyant, J. et al. in Climate Change 1995: Social and Economic Dimensions of Climate Change (eds Bruce, J. P., Lee, H. & Haites, E. F.) 367–396 (IPCC, Cambridge Univ. Press, 1996).
  3. IPCC. Climate Change 2021: The Physical Science Basis (eds Masson-Delmotte, V. et al.) (Cambridge Univ. Press, 2021).
  4. van Kampenhout, L. et al. Improving the representation of polar snow and firn in the Community Earth System Model. J. Adv. Modeling Earth Syst. 9, 2583–2600 (2017). · doi:10.1002/2017ms000988
  5. Hunt, R. J., Fienen, M. N. & White, J. T. Revisiting ‘An exercise in groundwater model calibration and prediction’ after 30 years: insights and new directions. Groundwater 58, 168–182 (2020). · doi:10.1111/gwat.12907
  6. Wagener, T., Wheater, H. S. & Gupta, H. V. in Calibration of Watershed Models 29–47 (Wiley, 2003). · doi:10.1029/ws006p0029
  7. Trancoso, R., Larsen, J. R., McVicar, T. R., Phinn, S. R. & McAlpine, C. A. CO2–vegetation feedbacks and other climate changes implicated in reducing base flow. Geophys. Res. Lett. 44, 2310–2318 (2017). · doi:10.1002/2017gl072759
  8. Krizhevsky, A., Sutskever, I. & Hinton, G. E. in Advances in Neural Information Processing Systems vol. 25 (eds Bartlett, P. et al.) 1097–1105 (Curran Associates, 2012).
  9. Lecun, Y. & Bengio, Y. Convolutional networks for images, speech, and time-series. in The Handbook of Brain Theory and Neural Networks (ed. Arbib, M. A.) 255–258 (MIT Press, 1995).
  10. Bhowmik, M., Singh, M., Rao, S. & Paul, S. DeepClouds.ai: deep learning enabled computationally cheap direct numerical simulations. Preprint at https://doi.org/10.48550/arXiv.2208.08956 (2022). · arXiv · doi:10.48550/arxiv.2208.08956
  11. Lin, G.-Y., Chen, H.-W., Chen, B.-J. & Yang, Y.-C. Characterization of temporal PM2.5, nitrate, and sulfate using deep learning techniques. Atmos. Pollut. Res. 13, 101260 (2022). · doi:10.1016/j.apr.2021.101260
  12. Afzaal, H., Farooque, A. A., Abbas, F., Acharya, B. & Esau, T. Groundwater estimation from major physical hydrology components using artificial neural networks and deep learning. Water 12, 5 (2020). · doi:10.3390/w12010005
  13. Fleming, S. W., Watson, J. R., Ellenson, A., Cannon, A. J. & Vesselinov, V. C. Machine learning in Earth and environmental science requires education and research policy reforms. Nat. Geosci. 14, 878–880 (2021). · doi:10.1038/s41561-021-00865-3
  14. Zitzler, E., Laumanns, M. & Thiele, L. SPEA2: Improving the Strength Pareto Evolutionary Algorithm. TIK Report vol. 103 (ETH Zurich, 2001); https://www.research-collection.ethz.ch/handle/20.500.11850/145755.
  15. Baydin, A. G., Pearlmutter, B. A., Radul, A. A. & Siskind, J. M. Automatic differentiation in machine learning: a survey. J. Mach. Learn. Res. 18, 1–43 (2018).
  16. Goodfellow, I., Bengio, Y. & Courville, A. in Deep Learning (ed. Goodfellow, I.) Ch. 4 (MIT Press, 2016).
  17. Paszke, A. et al. Automatic differentiation in PyTorch. In 31st Conference on Neural Information Processing Systems (NIPS 2017) (NIPS, 2017).
  18. Abadi, M. et al. Tensorflow: a system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16) 265–283 (USENIX Association, 2016).
  19. Johnson, S. G. Notes on Adjoint Methods for 18.335 (2021). · doi:10.1038/s41592-021-01122-6
  20. Pal, A., Edelman, A. & Rackauckas, C. Mixing implicit and explicit deep learning with skip DEQs and infinite time neural ODEs (continuous DEQs). Preprint at https://doi.org/10.48550/arXiv.2201.12240 (2022). · arXiv · doi:10.48550/arxiv.2201.12240
  21. Chen, R. T. Q., Rubanova, Y., Bettencourt, J. & Duvenaud, D. Neural ordinary differential equations. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, 6572–6583 (Curran Associates, 2018).
  22. O’Neill, P. E. et al. SMAP enhanced L3 radiometer global and polar grid daily 9 km EASE-grid soil moisture, Version 5 (SPL3SMP_E) (2021); https://doi.org/10.5067/4DQ54OUIJ9DL. · doi:10.5067/4dq54ouij9dl
  23. Feng, D., Beck, H., Lawson, K. & Shen, C. The suitability of differentiable, learnable hydrologic models for ungauged regions and climate change impact assessment. Hydrology and Earth System Sciences Discussions 1–28 (European Geoscience Union, 2022); https://doi.org/10.5194/hess-2022-245. · doi:10.5194/hess-2022-245
  24. Onken, D. & Ruthotto, L. Discretize-optimize vs. optimize-discretize for time-series regression and continuous normalizing flows. Preprint at https://arxiv.org/abs/2005.13420 (2020). · arXiv
  25. Neupauer, R. M. & Wilson, J. L. Adjoint-derived location and travel time probabilities for a multidimensional groundwater system. Water Resour. Res. 37, 1657–1668 (2001). · doi:10.1029/2000wr900388
  26. Aboelyazeed, D. et al. A differentiable ecosystem modeling framework for large-scale inverse problems: demonstration with photosynthesis simulations. Biogeosci. Discuss. https://doi.org/10.5194/bg-2022-211 (2022). · doi:10.5194/bg-2022-211
  27. Khandelwal, A. et al. Physics guided machine learning methods for hydrology. https://arxiv.org/abs/2012.02854 (2020). · arXiv
  28. Hochreiter, S., Bengio, Y., Frasconi, P. & Jürgen S. in A Field Guide to Dynamical Recurrent Neural Networks (eds Kremer, S. C. & Kolen, J. F.) 237–244 (IEEE, 2001).
  29. Krapu, C. & Borsuk, M. A differentiable hydrology approach for modeling with time-varying parameters. Water Resour. Res. 58, e2021WR031377 (2022). · doi:10.1029/2021wr031377

Cited by

See all 468

Metadata

Authors
Shen, C., Appling, A. P., Gentine, P., Bandai, T., Gupta, H., Tartakovsky, A., Baity-Jesi, M., Fenicia, F., Kifer, D., Li, L., Liu, X., Ren, W., Zheng, Y., Harman, C. J., Clark, M., Farthing, M., Feng, D., Kumar, P., Aboelyazeed, D., Rahmani, F., Song, Y., Beck, H. E., Bindas, T., Dwivedi, D., Fang, K., Höge, M., Rackauckas, C., Mohanty, B., Roy, T., Xu, C., & Lawson, K.
Venue
Nature Reviews Earth & Environment
Published
2023-07-11
Volume
4
Issue
8
Pages
552-567
ISSN
2662-138X (ISSN-L)
OpenAlex
W4383955976
Cited by
468
References
145
FWCI
10.69
Type
journal article
Language
en
Open access
green
Licence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Differentiable modelling to unify machine learning and physical models for geosciences. https://app.cochat.ai/papers/10.1038/s43017-023-00450-9
The paper
Shen, C., Appling, A. P., Gentine, P., Bandai, T., Gupta, H., Tartakovsky, A., Baity-Jesi, M., Fenicia, F., Kifer, D., Li, L., Liu, X., Ren, W., Zheng, Y., Harman, C. J., Clark, M., Farthing, M., Feng, D., Kumar, P., Aboelyazeed, D., . . . Lawson, K. (2023). Differentiable modelling to unify machine learning and physical models for geosciences. Nature Reviews Earth & Environment. https://doi.org/10.1038/s43017-023-00450-9

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.