Increasingly available and a virtually uninterrupted supply of satellite-estimatedrainfall data is gradually becoming a cost-effective source of input for flood predictionunder a variety of circumstances. However, most real-time and quasi-global satelliterainfall products are currently available at spatial scales ranging from 0.25^o to 0.50^o andhence, are considered somewhat coarse for dynamic hydrologic modeling of basin-scaleflood events. This study assesses the question: what are the hydrologic implications ofuncertainty of satellite rainfall data at the coarse scale? We investigated this question onthe 970 km² Upper Cumberland river basin of Kentucky. The satellite rainfall productassessed was NASA’s Tropical Rainfall Measuring Mission (TRMM) Multi-satellitePrecipitation Analysis (TMPA) product called 3B41RT that is available in pseudo real timewith a latency of 6-10 hours. We observed that bias adjustment of satellite rainfall data canimprove application in flood prediction to some extent with the trade-off of more falsealarms in peak flow. However, a more rational and regime-based adjustment procedureneeds to be identified before the use of satellite data can be institutionalized among floodmodelers.

Monitoring and managing groundwater resources is critical for sustaining livelihoods and supporting various human activities, including irrigation and drinking water supply. The most common method of monitoring groundwater is well water level measurements. These records can be difficult to collect and maintain, especially in countries with limited infrastructure and resources. However, long-term data collection is required to characterize and evaluate trends. To address these challenges, we propose a framework that uses data from the Gravity Recovery and Climate Experiment (GRACE) mission and downscaling models to generate higher-resolution (1 km) groundwater predictions. The framework is designed to be flexible, allowing users to implement any machine learning model of interest. We selected four models: deep learning model, gradient tree boosting, multi-layer perceptron, and k-nearest neighbors regressor. To evaluate the effectiveness of the framework, we offer a case study of Sunflower County, Mississippi, using well data to validate the predictions. Overall, this paper provides a valuable contribution to the field of groundwater resource management by demonstrating a framework using remote sensing data and machine learning techniques to improve monitoring and management of this critical resource, especially to those who seek a faster way to begin to use these datasets and applications.

This study introduces a dual-phase approach utilizing Artificial Neural Networks (ANNs) to overcome the challenges of groundwater monitoring at regional scales. Traditional well-based methods provide limited spatial coverage, while GRACE satellite data, despite its value for large-scale hydrological analysis, suffers from low spatial resolution (~300 km), limiting its application for local-scale assessments. Existing downscaling methods such as geographically weighted regression and Random Forests are computationally intensive and often lack adaptability to complex groundwater systems. In this study, Phase 1 refines GRACE data using ANNs to achieve a 4×4 km spatial resolution, addressing the resolution challenge for regional applications. Phase 2 integrates the downscaled GRACE data with groundwater well observations and climatic factors to predict groundwater levels with high accuracy (R² = 0.9885). This dual-phase framework demonstrates significant improvements over existing methods, providing an efficient and scalable solution for groundwater monitoring in hydrologically complex regions. The findings highlight the potential of machine learning to enhance groundwater resource management, particularly in addressing water scarcity and climate variability challenges. Doi: 10.28991/CEJ-2025-011-02-01 Full Text: PDF

The importance of high-resolution and continuous hydrologic data for monitoring and predicting water levels is crucial for sustainable water management. Monitoring Total Water Storage (TWS) over large areas by using satellite images such as Gravity Recovery and Climate Experiment (GRACE) data with coarse resolution (1°) is acceptable. However, using coarse satellite images for monitoring TWS and changes over a small area is challenging. In this study, we used the Random Forest model (RFM) to spatially downscale the GRACE mascon image of April 2020 from 0.5° to ~5 km. We initially used eight different physical and hydrological parameters in the model and finally used the four most significant of them for the final output. We executed the RFM for Mississippi Alluvial Plain. The validating data R² for each model was 0.88. Large R² and small RMSE and MAE are indicative of a good fit and accurate predictions by RFM. The result of this research aligns with the reported water depletion in the central Mississippi Delta area. Therefore, by using the Random Forest model and appropriate parameters as input of the model, we can downscale the GRACE mascon image to provide a more beneficial result that can be used for activities such as groundwater management at a sub-county-level scale in the Mississippi Delta.

The objective of this study was to investigate spatial downscaling of satellite rainfall data for streamflow prediction in a medium-sized (970 km2) river basin prone to flooding. The spatial downscaling scheme used in the study was based on the principle of scale invariance. It reproduced the rainfall variability at finer scales while being conditioned on the large-scale rainfall. Two Tropical Rainfall Measuring Mission (TRMM)-based real-time global satellite rainfall products were analyzed: 1) the infrared (IR)-based 3B41RT product available at 1 hourly and 0.25° scales and 2) the combined passive microwave (PMW) and IR-based 3B42RT product available at 3 hourly and 0.25° scales. The conceptual Hydrologic Engineering Center-Hydrologic Modeling System (HEC-HMS) was used for the simulation of streamflow. It was found that propagation of spatially downscaled satellite rainfall in the hydrologic model increased simulation uncertainty in streamflow as rainfall grid scales became smaller than 0.25°. T... Abstract The objective of this study was to investigate spatial downscaling of satellite rainfall data for streamflow prediction in a medium-sized (970 km2) river basin prone to flooding. The spatial downscaling scheme used in the study was based on the principle of scale invariance. It reproduced the rainfall variability at finer scales while being conditioned on the large-scale rainfall. Two Tropical Rainfall Measuring Mission (TRMM)-based real-time global satellite rainfall products were analyzed: 1) the infrared (IR)-based 3B41RT product available at 1 hourly and 0.25° scales and 2) the combined passive microwave (PMW) and IR-based 3B42RT product available at 3 hourly and 0.25° scales. The conceptual Hydrologic Engineering Center-Hydrologic Modeling System (HEC-HMS) was used for the simulation of streamflow. It was found that propagation of spatially downscaled satellite rainfall in the hydrologic model increased simulation uncertainty in streamflow as rainfall grid scales became smaller than 0.25°. T...