A Framework for Deep Learning Emulation of Numerical Models With a Case Study in Satellite Remote Sensing
A Framework for Deep Learning Emulation of Numerical Models With a Case Study in Satellite Remote Sensing
复制标题
DOI：
10.1109/tnnls.2022.3169958
复制
发表时间：
2019-10
影响因子：
10.4
通讯作者：
Kate Duffy;T. Vandal;Weile Wang;R. Nemani;A. Ganguly
中科院分区：
文献类型：
--
作者：
Kate Duffy;T. Vandal;Weile Wang;R. Nemani;A. Ganguly
基于物理的数值模型代表了地球系统建模的最先进水平，并构成了我们产生洞察力和预测的最佳工具。尽管计算能力迅速增长，但对更高模型分辨率的感知需求压倒了最新一代的计算机，降低了建模人员生成模拟以了解参数敏感性并表征变异性和不确定性的能力。因此，代理模型通常被开发来捕捉成熟的数值模式的基本属性。近年来，许多学科的机器学习方法，特别是深度学习方法的成功，提供了复杂的非线性连接论表示可能能够捕捉到地球系统中潜在的复杂结构和非线性过程的可能性。基于DL的仿真指的是数值模型的函数逼近，其困难的测试是了解它们是否能够在计算效率方面与传统形式的代理模型相媲美，同时以可信的方式再现模型结果。在捕获复杂过程和时空依赖关系方面，通过此测试的DL仿真可能会比简单模型执行得更好。在这里，我们通过一个基于卫星的遥感的案例研究来检验这一假设，即DL方法可以可信地代表来自代理模型的模拟，并且具有类似的计算效率。我们的结果令人鼓舞，因为DL仿真以可接受的精度重现结果，而且通常性能更快。我们根据DL高性能实现的改进速度和对地球科学中更高分辨率模拟的日益增长的需求，讨论了我们的结果的更广泛的影响。
Numerical models based on physics represent the state of the art in Earth system modeling and comprise our best tools for generating insights and predictions. Despite rapid growth in computational power, the perceived need for higher model resolutions overwhelms the latest generation computers, reducing the ability of modelers to generate simulations for understanding parameter sensitivities and characterizing variability and uncertainty. Thus, surrogate models are often developed to capture the essential attributes of the full-blown numerical models. Recent successes of machine learning methods, especially deep learning (DL), across many disciplines offer the possibility that complex nonlinear connectionist representations may be able to capture the underlying complex structures and nonlinear processes in Earth systems. A difficult test for DL-based emulation, which refers to function approximation of numerical models, is to understand whether they can be comparable to traditional forms of surrogate models in terms of computational efficiency while simultaneously reproducing model results in a credible manner. A DL emulation that passes this test may be expected to perform even better than simple models with respect to capturing complex processes and spatiotemporal dependencies. Here, we examine, with a case study in satellite-based remote sensing, the hypothesis that DL approaches can credibly represent the simulations from a surrogate model with comparable computational efficiency. Our results are encouraging in that the DL emulation reproduces the results with acceptable accuracy and often even faster performance. We discuss the broader implications of our results in light of the pace of improvements in high-performance implementations of DL and the growing desire for higher resolution simulations in the Earth sciences.