Preprints
https://doi.org/10.5194/hess-2023-264
https://doi.org/10.5194/hess-2023-264
08 Jan 2024
 | 08 Jan 2024
Status: this preprint is currently under review for the journal HESS.

Simulation-Based Inference for Parameter Estimation of Complex Watershed Simulators

Robert Hull, Elena Leonarduzzi, Luis De La Fuente, Hoang Viet Tran, Andrew Bennett, Peter Melchior, Reed M. Maxwell, and Laura E. Condon

Abstract. High-resolution, spatially distributed process-based (PB) simulators are widely employed in the study of complex watershed processes and their responses to a changing climate. However, calibrating these simulators to observed data remains a significant challenge due to several persistent issues including: (1) intractability stemming from the computational demands and complex responses of simulators, which renders infeasible calculation of the conditional probability of parameters and data, and (2) uncertainty stemming from the choice of simplified model representations of complex natural hydrologic processes. Here we demonstrate how Simulation-Based Inference (SBI) can help address both these challenges for parameter estimation. SBI uses a learned mapping between parameter space and observed data to estimate parameters for generation of calibrated model simulations. To demonstrate the potential of SBI in hydrologic modelling, we conduct a set of synthetic experiments to infer two common physical parameters, Manning's coefficient and hydraulic conductivity, using a representation of a snowmelt-dominated catchment in Colorado, USA. We introduce novel deep learning (DL) components to the SBI approach, including an 'emulator' as a surrogate for the process-based simulator to rapidly explore parameter responses. We also employ a density-based neural network to represent the joint probability of parameters and data without strong assumptions about its functional form. While addressing intractability, we also show that where uncertainty about model structure is significant, SBI can yield unreliable parameter estimates. Approaches to adopting the SBI framework to cases where model structure(s) may not be adequate are introduced using a performance-weighting approach.

Robert Hull, Elena Leonarduzzi, Luis De La Fuente, Hoang Viet Tran, Andrew Bennett, Peter Melchior, Reed M. Maxwell, and Laura E. Condon

Status: open (until 07 Mar 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2023-264', Anonymous Referee #1, 13 Feb 2024 reply
Robert Hull, Elena Leonarduzzi, Luis De La Fuente, Hoang Viet Tran, Andrew Bennett, Peter Melchior, Reed M. Maxwell, and Laura E. Condon

Model code and software

Repository for SBI in the Taylor RIver Basin Robert Hull https://github.com/rhull21/sbi_taylor

Robert Hull, Elena Leonarduzzi, Luis De La Fuente, Hoang Viet Tran, Andrew Bennett, Peter Melchior, Reed M. Maxwell, and Laura E. Condon

Viewed

Total article views: 257 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
189 57 11 257 8 4
  • HTML: 189
  • PDF: 57
  • XML: 11
  • Total: 257
  • BibTeX: 8
  • EndNote: 4
Views and downloads (calculated since 08 Jan 2024)
Cumulative views and downloads (calculated since 08 Jan 2024)

Viewed (geographical distribution)

Total article views: 250 (including HTML, PDF, and XML) Thereof 250 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 25 Feb 2024
Download
Short summary
Large-scale hydrologic a needed tool to explore complex watershed processes and how they may evolve under a changing climate. However, calibrating them can be difficult because they are costly to run and have many unknown parameters. We implement a state-of-the-art approach to model calibration with a set of experiments in the Upper Colorado River Basin.