A Machine Learning Approach for Improving the Accuracy of Gridded Precipitation With Uncertainty Quantification
Year: 2025
Type: article
Abstract: ABSTRACT The proliferation of gridded precipitation datasets produced through diverse methods has led to user confusion due to discrepancies in values for identical locations and times, underscoring the inherent uncertainty in current precipitation data. However, quantifying this uncertainty remains challenging since most datasets are deterministic and offer no easy mechanism for such quantification. This study proposes a novel machine learning (ML) approach that involves merging multiple satellite‐based gridded precipitation datasets and rain gauge observations. The ultimate goal is to create an improved high‐resolution (0.1°) daily precipitation product for Vietnam (2001–2010) that includes uncertainty quantification. By combining eXtreme gradient boosting (XGB) with quantile regression, we generate both deterministic estimates along with the associated uncertainty intervals. The resulting dataset, VNpu (Vietnam Precipitation with Uncertainty), outperforms individual input products, benchmark interpolation methods and an existing gauge‐based product (VnGP), particularly for heavy and extreme rainfall events. The VNpu provides spatiotemporally varying uncertainty ranges, with larger uncertainties in sparse gauge coverage areas. The analysis of ML interpretability reveals the complementary nature of multiple precipitation inputs (IMERG and MERRA2) and auxiliary topographic information. This study not only highlights the necessity of gridded precipitation products with uncertainty estimates but also demonstrates the value of ML approaches in developing improved precipitation products for data‐scarce regions.
DOI: 10.1002/joc.70161
Institutions: University of Michigan, Leidos (United States), Goddard Space Flight Center, Science Applications International Corporation (United States), Helmholtz Centre for Environmental Research, Thu Dau Mot University, Nong Lam University Ho Chi Minh City, Lamont-Doherty Earth Observatory, University of Illinois Urbana-Champaign, Columbia University, University of Da Nang, Vietnamese-German University, Pacific Northwest National Laboratory, National Institute of Water and Atmospheric Research, Vietnam National University, Hanoi, VNU University of Science, Trường Đại học Khoa học và Công nghệ Hà Nội, Vietnam Academy of Science and Technology, Hanoi University of Science and Technology, University of Virginia
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
SDG: Climate action
Open Access status: hybrid
Estimated APC paid: $3,920
Awards: [22-000002698] DECISION-MAKING WITH UNCERTAINTY FOR DOD INSTALLATIONS UNDER CLIMATE CHANGE IMPACTS ON FLOOD RISKS, Phát triển tham số vùng hướng đến xây dựng mô hình đánh giá tài nguyên nước quốc gia cho Việt Nam, Collaborative Research: Understanding Urban Resilience to Pluvial Floods Using Reduced-Order Modeling
OpenAlex ID: W4415301905