A Machine Learning Approach for Improving the Accuracy of Gridded Precipitation With Uncertainty Quantification

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.

Authors

Institutions

Publication Details

Journal
International Journal of Climatology
Published
2025-10-17
DOI
https://doi.org/10.1002/joc.70161
Primary Topic
Precipitation Measurement and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Machine Learning Approach for Improving the Accuracy of Gridded Precipitation With Uncertainty Quantification

Hung T. Pham, Lê Hoàng Tú, Thanh Ngo‐Duc, Manh‐Hung Le et al.
International Journal of Climatology
Precipitation Measurement and Analysis
article

A Machine Learning Approach for Improving the Accuracy of Gridded Precipitation With Uncertainty Quantification

Hung T. Pham, Lê Hoàng Tú, Thanh Ngo‐Duc, Manh‐Hung Le, Thanh Duc Dang, Đoàn Văn Bình, John Bolten, Tan Phan‐Van, Vinh Ngoc Tran, Binh Quang Nguyen, Hong Xuan, Hung Nguyen, Hoang Tran, Trinh Van Le, Van Tam Nguyen, Venkataraman Lakshmi
article en

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.

International Journal of ClimatologyVol. 46(1)
Goddard Space Flight Center (US), Helmholtz Centre for Environmental Research (DE), Pacific Northwest National Laboratory (US), Lamont-Doherty Earth Observatory (US), University of Illinois Urbana-Champaign (US), Vietnam National University, Hanoi (VN), University of Michigan (US), Environmental Molecular Sciences Laboratory (US), University of Da Nang (VN), Bình Dương University (VN), National Institute of Water and Atmospheric Research (NZ), University of Virginia (US), Vietnam Academy of Science and Technology (VN), Columbia University (US), Nong Lam University Ho Chi Minh City (VN), Vietnamese-German University (VN), Science Applications International Corporation (United States) (US), Hanoi University of Science and Technology (VN)
Openalex Percentile: Top 66%
Precipitation Measurement and Analysis
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.