Probabilistic Inverse Modeling: An Application in Hydrology
This work addresses the need for explainable and trustworthy inverse models in hydrology to assist water managers in handling data noise and reducing costs, though it is incremental in nature.
The paper tackles the problem of reconstructing robust hydrology basin characteristics from noisy or missing data to improve streamflow prediction, achieving a 6% improvement in R², 17% reduction in uncertainty, and 4% higher coverage rate.
The astounding success of these methods has made it imperative to obtain more explainable and trustworthy estimates from these models. In hydrology, basin characteristics can be noisy or missing, impacting streamflow prediction. For solving inverse problems in such applications, ensuring explainability is pivotal for tackling issues relating to data bias and large search space. We propose a probabilistic inverse model framework that can reconstruct robust hydrology basin characteristics from dynamic input weather driver and streamflow response data. We address two aspects of building more explainable inverse models, uncertainty estimation and robustness. This can help improve the trust of water managers, handling of noisy data and reduce costs. We propose uncertainty based learning method that offers 6\% improvement in $R^2$ for streamflow prediction (forward modeling) from inverse model inferred basin characteristic estimates, 17\% reduction in uncertainty (40\% in presence of noise) and 4\% higher coverage rate for basin characteristics.