Computer Model Calibration with Time Series Data Using Deep Learning and Quantile Regression

• Activity Number: 348 - ENVR Student Paper Award Winners
• Type: Topic-Contributed
• Date/Time: Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
• Sponsor: Section on Statistics and the Environment
• Author(s): Saumya Bhatnagar* and Won Chang and Seonjin Kim and Jiali Wang
• Companies: University of Cincinnati and University of Cincinnati and Miami University and Argonne National Laboratory
• Keywords: Computer Model Calibration; Deep Learning; Long-Short Term Memory Network; Data-Model Discrepancy

Abstract

Computer model calibration is a formal statistical procedure to infer input parameters by combining information from model runs and observational data. The existing standard calibration framework suffers from inferential issues when the model output and observational data are high dimensional dependent data such as large time series due to difficulty in building an emulator and non-identifiability between effects from input parameters and data-model discrepancy. To overcome these challenges, we propose a new calibration framework based on a deep neural network (DNN) with long-short term memory layers that directly emulates the inverse relationship between the model output and input parameters. Adopting the ‘learning with noise’ idea we train our DNN model to filter out the effects from data model discrepancy on input parameter inference. We also formulate a new way to construct interval predictions for DNN using quantile regression to quantify the uncertainty in input parameter estimates. Through a simulation study and real data application with WRF-hydro model we show our approach can yield accurate point estimates and well calibrated interval estimates for input parameters.