Toward Data‐Driven Generation and Evaluation of Model Structure for Integrated Representations of Human Behavior in Water Resources Systems
Open Access
- 12 February 2021
- journal article
- research article
- Published by American Geophysical Union (AGU) in Water Resources Research
- Vol. 57 (2)
Abstract
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.Keywords
All Related Versions
This publication has 113 references indexed in Scilit:
- Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modellingJournal of Hydrology, 2009
- Hydro-economic models: Concepts, design, applications, and future prospectsJournal of Hydrology, 2009
- Distilling Free-Form Natural Laws from Experimental DataScience, 2009
- Automated reverse engineering of nonlinear dynamical systemsProceedings of the National Academy of Sciences, 2007
- Comparison of empirical methods for building agent-based models in land use scienceJournal of Land Use Science, 2007
- Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden NodesIEEE Transactions on Neural Networks, 2006
- Defining Uncertainty: A Conceptual Basis for Uncertainty Management in Model-Based Decision SupportIntegrated Assessment, 2003
- Strongly Typed Genetic ProgrammingEvolutionary Computation, 1995
- Prophecy, reality and uncertainty in distributed hydrological modellingAdvances in Water Resources, 1993
- The future of distributed models: Model calibration and uncertainty predictionHydrological Processes, 1992