Toward Data‐Driven Generation and Evaluation of Model Structure for Integrated Representations of Human Behavior in Water Resources Systems
Toward Data‐Driven Generation and Evaluation of Model Structure for Integrated Representations of Human Behavior in Water Resources Systems
复制标题
DOI：
10.1029/2020wr028148
复制
发表时间：
2020-06
影响因子：
5.4
通讯作者：
Liam Ekblad;J. Herman
中科院分区：
文献类型：
--
作者：
Liam Ekblad;J. Herman
水资源系统中人类行为的模拟受到模型结构和参数不确定性的挑战。描述这些系统的观测结果越来越多，这为使用数据驱动方法推断一组合理的模型结构提供了机会。本研究开发了一个三阶段的方法来推断模型结构和参数化的数据：问题定义，模型生成和模型评估，说明在图拉雷盆地，加州的土地利用决策的案例研究。我们将广义决策问题编码为从高维数据空间到感兴趣的动作的任意映射，并使用多目标遗传编程来搜索执行这种映射的函数族，用于回归和分类任务。为了便于发现既现实又可解释的模型，该算法基于以下多目标优化来选择模型结构：（1）它们在训练集上的性能;（2）复杂性，通过组成模型的变量、常数和操作的数量来衡量。在训练之后，最优模型结构根据其推广到保持的测试数据的能力进行进一步评估，并根据其性能，复杂性和推广属性进行聚类。最后，我们通过在模型输入和模型集群内执行敏感性分析来诊断好的和坏的泛化的原因。这项研究作为一个模板，为构建强大的数据驱动模型结构来描述人类在水资源系统中的行为提供信息并自动化问题相关任务。
Simulations of human behavior in water resources systems are challenged by uncertainty in model structure and parameters. The increasing availability of observations describing these systems provides the opportunity to infer a set of plausible model structures using data‐driven approaches. This study develops a three‐phase approach to the inference of model structures and parameterizations from data: problem definition, model generation, and model evaluation, illustrated on a case study of land use decisions in the Tulare Basin, California. We encode the generalized decision problem as an arbitrary mapping from a high‐dimensional data space to the action of interest and use multiobjective genetic programming to search over a family of functions that perform this mapping for both regression and classification tasks. To facilitate the discovery of models that are both realistic and interpretable, the algorithm selects model structures based on multiobjective optimization of (1) their performance on a training set and (2) complexity, measured by the number of variables, constants, and operations composing the model. After training, optimal model structures are further evaluated according to their ability to generalize to held‐out test data and clustered based on their performance, complexity, and generalization properties. Finally, we diagnose the causes of good and bad generalization by performing sensitivity analysis across model inputs and within model clusters. This study serves as a template to inform and automate the problem‐dependent task of constructing robust data‐driven model structures to describe human behavior in water resources systems.