Abstract
Satellite remote sensing provides useful gridded data for the conceptual modelling of hydrological processes such as precipitation–runoff relationship. Structurally flexible and computationally advanced AI-assisted data-driven (DD) models foster these applications. However, without linking concepts between variables from many grids, the DD models can be too large to be calibrated efficiently. Therefore, effectively formulized, collective input variables and robust verification of the calibrated models are desired to leverage satellite data for the strategic DD modelling of catchment runoff. This study formulates new satellite-based input variables, namely, catchment- and event-specific areal precipitation coverage ratios (CCOVs and ECOVs, respectively) from the Global Precipitation Mission (GPM) and evaluates their usefulness for monthly runoff modelling from five mountainous Karkheh sub-catchments of 5000–43,000 km2 size in west Iran. Accordingly, 12 different input combinations from GPM and MODIS products were introduced to a generalized deep learning scheme using artificial neural networks (ANNs). Using an adjusted five-fold cross-validation process, 420 different ANN configurations per fold choice and 10 different random initial parameterizations per configuration were tested. Runoff estimates from five hybrid models, each an average of six top-ranked ANNs based on six statistical criteria in calibration, indicated obvious improvements for all sub-catchments using the new variables. Particularly, ECOVs were most efficient for the most challenging sub-catchment, Kashkan, having the highest spacetime precipitation variability. However, better performance criteria were found for sub-catchments with lower precipitation variability. The modelling performance for Kashkan indicated a higher dependency on data partitioning, suggesting that long-term data representativity is important for modelling reliability.
Highlights
Managing surface water resources is challenged by prolonged droughts and intensified floods under a changing climate
The statistical results for the testing points were compared to those obtained from a reference combination of inputs that did not use catchment-specific precipitation coverage ratios (CCOVs) and ECOVs but were still from the same class of inputs
The study formalized new input variables based on the gridded remote sensing (RS)-based data and simple hydrological notions for better modelling of catchment response to precipitation with a conceptualized Artificial Intelligence (AI)-assisted DD approach, primarily useful in sparsely gauged catchments
Summary
Managing surface water resources is challenged by prolonged droughts and intensified floods under a changing climate. The estimated inflow, combined with the known storage capacity and rule curves of the reservoir, is used to calculate the water loss due to evaporation under different hydrological scenarios. Rainfall–runoff models are useful computer tools for inflow simulation primarily by relating precipitation and discharge (runoff) data in a catchment. IHACRES, for example, is a widely used lumped model, e.g., [7,13,26,27,28,29] It applies a non-linear loss function to estimate the catchment-scale excess rainfall and a linear UH module to convert the excess rainfall to runoff using a grid search parameterization in user-specified steps and ranges of some parameters. In view of the above, this study introduces areal precipitation coverage ratios, derived from the original, smallest RS grids, as new input variables to the ANN to compensate for the lost variation due to the use of average precipitation over sub-catchments. An adjusted cross-validation and verification process, as well as different configurations and random initial parameterizations of the ANN models were evaluated to avoid overfitting and ensure the generalization of the outputs
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
