Differentiable modelling to unify machine learning and physical models for geosciences-猫眼课题宝

DOI：

10.1038/s43017-023-00450-9

发表时间：

2023-07

期刊：

Nature Reviews Earth & Environment

影响因子：

42.1

通讯作者：

中科院分区：

地球科学1区

文献类型：

作者：

Chaopeng Shen;A. Appling;P. Gentine;Toshiyuki Bandai;H. Gupta;A. Tartakovsky;M. Baity-Jesi;F. Fenicia;Daniel Kifer;Li Li-Li;Xiaofeng Liu;Wei Ren;Y. Zheng;C. Harman;M. Clark;M. Farthing;D. Feng;Praveen Kumar;Doaa Aboelyazeed;F. Rahmani;Yalan Song;H. Beck;Tadd Bindas;D. Dwivedi;K. Fang;Marvin Höge;Christopher Rackauckas;B. Mohanty;Tirthankar Roy;Chonggang Xu;K. Lawson

基于过程的建模在地球科学的许多领域提供了可解释性和物理一致性，但难以有效地利用大型数据集。机器学习方法，特别是深度网络，具有强大的预测能力，但无法回答特定的科学问题。在这个角度来看，我们探索微分建模作为一种途径，以消除基于过程的建模和机器学习之间的障碍，在地球科学和水文建模的例子证明其潜力。“可微”是指准确有效地计算模型变量或参数的梯度，从而发现高维未知关系。微分建模涉及将（灵活数量的）先验物理知识连接到神经网络，推动物理信息机器学习的边界。它提供了比纯粹数据驱动的机器学习更好的可解释性，可推广性和外推能力，实现了类似的准确性水平，同时需要更少的训练数据。此外，可区分模型的性能和效率随着数据量的增加而扩展。在数据稀缺的情况下，由于受到物理限制，可微模型在产生短期动态和十年期趋势方面优于机器学习模型。微分建模方法的准备，使地球科学家提出问题，测试假设，并发现未被识别的物理关系。未来的工作应该解决计算挑战，减少不确定性，并验证输出的物理意义。

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 to unify machine learning and physical models for geosciences

文献摘要

相似文献