Skip to main content
ARS Home » Plains Area » Fort Collins, Colorado » Center for Agricultural Resources Research » Water Management and Systems Research » Research » Publications at this Location » Publication #383714
Research Project: Response of Ecosystem Services in Agricultural Watersheds to Changes in Water Availability, Land Use, Management, and Climate

Location: Water Management and Systems Research

Title: Bridging technology transfer boundaries: Integrated cloud services deliver results of nonlinear process models as surrogate model ensembles

Author
item SERAFIN, FRANCESCO - Colorado State University
item DAVID, OLAF - Colorado State University
item CARLSON, JACK - Colorado State University
item Green, Timothy
item RIGON, RICCARDO - Colorado State University

Submitted to: Environmental Modelling & Software
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/10/2021
Publication Date: 10/18/2021
Citation: Serafin, F., David, O., Carlson, J.R., Green, T.R., Rigon, R. 2021. Bridging technology transfer boundaries: Integrated cloud services deliver results of nonlinear process models as surrogate model ensembles. Environmental Modelling & Software. 146. Article e105231. https://doi.org/10.1016/j.envsoft.2021.105231.
DOI: https://doi.org/10.1016/j.envsoft.2021.105231

Interpretive Summary: Computer models simulate environmental processes to inform planning, consulting, regulatory and government institutions. However, research models are often poorly suited to such applications due to their complexity, data requirements, and factors such as institutional capacities. This contribution provides a computational framework to help streamline model setup, reduce runtime, and improve model infrastructure efficiency. We capture the intrinsic knowledge of a process-based model into an ensemble of artificial neural networks. This automated process is validated and secured using blockchain technology. Finally, we present an example wherein peak surface runoff provided by the curve number model is emulated with artificial intelligence.

Technical Abstract: Conceptual and process-based environmental models are often essential to implement projects in planning, consulting, regulatory and government institutions. Research models are often poorly suited to such applications due to their complexity, data requirements, operational boundaries, and factors such as institutional capacities. This contribution provides a framework to help mitigate research model complexity, streamline data and parameter setup, reduce runtime, and improve model infrastructure efficiency. Using a surrogate modeling approach, we capture the intrinsic knowledge of a conceptual or process-based model into an ensemble of artificial neural networks. Our extended modeling framework interacts with machine learning libraries to derive model surrogates for each modeling solution. This automated process is validated and secured using blockchain technology. After describing the methods and implementation, we present an example wherein hydrologic peak discharge provided by the curve number model is emulated with a surrogate model ensemble.