Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution

The downscaling technique produces high spatial resolution precipitation distribution in order to analyze impacts of climate change in data-scarce regions or local scales. In this study, based on three statistical learning algorithms, such as support vector machine (SVM), random forest regression (R...

Full description

Saved in:
Bibliographic Details
Main Authors: Yichen Wu, Zhihua Zhang, M. James C. Crabbe, Lipon Chandra Das
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Advances in Meteorology
Online Access:http://dx.doi.org/10.1155/2022/3140872
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850156941598261248
author Yichen Wu
Zhihua Zhang
M. James C. Crabbe
Lipon Chandra Das
author_facet Yichen Wu
Zhihua Zhang
M. James C. Crabbe
Lipon Chandra Das
author_sort Yichen Wu
collection DOAJ
description The downscaling technique produces high spatial resolution precipitation distribution in order to analyze impacts of climate change in data-scarce regions or local scales. In this study, based on three statistical learning algorithms, such as support vector machine (SVM), random forest regression (RF), and gradient boosting regressor (GBR), we proposed an efficient downscaling approach to produce high spatial resolution precipitation. In order to demonstrate efficiency and accuracy of our models over traditional multilinear regression (MLR) downscaling models, we did a downscaling analysis for daily observed precipitation data from 34 monitoring sites in Bangladesh. Validation revealed that R2 of GBR could reach 0.98, compared with RF (0.94), SVM (0.88), and multilinear regression (MLR) (0.69) models, so the GBR-based downscaling model had the best performance among all four downscaling models. We suggest that the GBR-based downscaling models should be used to replace traditional MLR downscaling models to produce a more accurate map of high-resolution precipitation for flood disaster management, drought forecasting, and long-term planning of land and water resources.
format Article
id doaj-art-3325c017d7e8461fb3cf7f731c1010c7
institution OA Journals
issn 1687-9317
language English
publishDate 2022-01-01
publisher Wiley
record_format Article
series Advances in Meteorology
spelling doaj-art-3325c017d7e8461fb3cf7f731c1010c72025-08-20T02:24:21ZengWileyAdvances in Meteorology1687-93172022-01-01202210.1155/2022/3140872Statistical Learning-Based Spatial Downscaling Models for Precipitation DistributionYichen Wu0Zhihua Zhang1M. James C. Crabbe2Lipon Chandra Das3Climate Modeling LaboratoryClimate Modeling LaboratoryWolfson CollegeClimate Modeling LaboratoryThe downscaling technique produces high spatial resolution precipitation distribution in order to analyze impacts of climate change in data-scarce regions or local scales. In this study, based on three statistical learning algorithms, such as support vector machine (SVM), random forest regression (RF), and gradient boosting regressor (GBR), we proposed an efficient downscaling approach to produce high spatial resolution precipitation. In order to demonstrate efficiency and accuracy of our models over traditional multilinear regression (MLR) downscaling models, we did a downscaling analysis for daily observed precipitation data from 34 monitoring sites in Bangladesh. Validation revealed that R2 of GBR could reach 0.98, compared with RF (0.94), SVM (0.88), and multilinear regression (MLR) (0.69) models, so the GBR-based downscaling model had the best performance among all four downscaling models. We suggest that the GBR-based downscaling models should be used to replace traditional MLR downscaling models to produce a more accurate map of high-resolution precipitation for flood disaster management, drought forecasting, and long-term planning of land and water resources.http://dx.doi.org/10.1155/2022/3140872
spellingShingle Yichen Wu
Zhihua Zhang
M. James C. Crabbe
Lipon Chandra Das
Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution
Advances in Meteorology
title Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution
title_full Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution
title_fullStr Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution
title_full_unstemmed Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution
title_short Statistical Learning-Based Spatial Downscaling Models for Precipitation Distribution
title_sort statistical learning based spatial downscaling models for precipitation distribution
url http://dx.doi.org/10.1155/2022/3140872
work_keys_str_mv AT yichenwu statisticallearningbasedspatialdownscalingmodelsforprecipitationdistribution
AT zhihuazhang statisticallearningbasedspatialdownscalingmodelsforprecipitationdistribution
AT mjamesccrabbe statisticallearningbasedspatialdownscalingmodelsforprecipitationdistribution
AT liponchandradas statisticallearningbasedspatialdownscalingmodelsforprecipitationdistribution