Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China
Precipitation estimates with high accuracy and fine spatial resolution play an important role in the field of meteorology, hydrology, and ecology. In this study, support vector machine (SVM) and back-propagation neural network (BPNN) machine learning algorithms were used to downscale the Integrated...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-06-01
|
| Series: | Frontiers in Earth Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/feart.2020.00146/full |
| _version_ | 1818609718100230144 |
|---|---|
| author | Xiaoxiao Min Xiaoxiao Min Ziqiang Ma Jintao Xu Jintao Xu Kang He Zhige Wang Qingliang Huang Jun Li |
| author_facet | Xiaoxiao Min Xiaoxiao Min Ziqiang Ma Jintao Xu Jintao Xu Kang He Zhige Wang Qingliang Huang Jun Li |
| author_sort | Xiaoxiao Min |
| collection | DOAJ |
| description | Precipitation estimates with high accuracy and fine spatial resolution play an important role in the field of meteorology, hydrology, and ecology. In this study, support vector machine (SVM) and back-propagation neural network (BPNN) machine learning algorithms were used to downscale the Integrated Multi-satellite Retrievals for Global Precipitation Measurement (GPM) (IMERG) data at daily scale through four events selected from 2017 and 2018 by establishing the relationships between precipitation and six environmental variables over Zhejiang, Southeastern China. The downscaled results were validated by ground observations, and we found that (1) generally, the SVM-based products had better performance and finer spatial textures than the BPNN-based products, the multiple linear regression (MLR)-based products, and the original IMERG; (2) all downscaled products decreased the degree of overestimation of the original IMERG at heavy-precipitation regions to a certain extent; (3) for heavy-precipitation events in the plum rain season, the downscaled products based on SVM and BPNN both improved prediction accuracy compared to the MLR-based products and the original IMERG considering the validations against ground observations. R2 maximally increased from 0.344 to 0.615 for the SVM-based products and from 0.344 to 0.435 for the BPNN-based products compared to the original IMERG; and (4) for typhoon precipitation events, the SVM-based products still showed better accuracy with R2 maximally increased from 0.492 to 0.615 compared to the original IMERG. In contrast, the performance of BPNN-based products was not satisfying and showed no significant differences with the performance of MLR-based products. This study provided a potential solution for generating downscaled satellite-based precipitation products at meteorological scales with finer accuracy and spatial resolutions. |
| first_indexed | 2024-12-16T15:02:59Z |
| format | Article |
| id | doaj.art-5d337193ff7f4f4ebe5aaca91ee9fc16 |
| institution | Directory Open Access Journal |
| issn | 2296-6463 |
| language | English |
| last_indexed | 2024-12-16T15:02:59Z |
| publishDate | 2020-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Earth Science |
| spelling | doaj.art-5d337193ff7f4f4ebe5aaca91ee9fc162022-12-21T22:27:14ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632020-06-01810.3389/feart.2020.00146527936Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern ChinaXiaoxiao Min0Xiaoxiao Min1Ziqiang Ma2Jintao Xu3Jintao Xu4Kang He5Zhige Wang6Qingliang Huang7Jun Li8Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, ChinaInstitute of Agricultural Remote Sensing and Information Technology Application, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, ChinaInstitute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, ChinaInstitute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing, ChinaInstitute of Agricultural Remote Sensing and Information Technology Application, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, ChinaCivil and Environmental Engineering, University of Connecticut, Storrs, CT, United StatesInstitute of Agricultural Remote Sensing and Information Technology Application, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, ChinaShaoxing Hydrological Management Center, Shaoxing, ChinaHangzhou TianLiang Detection Technology Co., Ltd, Hangzhou, ChinaPrecipitation estimates with high accuracy and fine spatial resolution play an important role in the field of meteorology, hydrology, and ecology. In this study, support vector machine (SVM) and back-propagation neural network (BPNN) machine learning algorithms were used to downscale the Integrated Multi-satellite Retrievals for Global Precipitation Measurement (GPM) (IMERG) data at daily scale through four events selected from 2017 and 2018 by establishing the relationships between precipitation and six environmental variables over Zhejiang, Southeastern China. The downscaled results were validated by ground observations, and we found that (1) generally, the SVM-based products had better performance and finer spatial textures than the BPNN-based products, the multiple linear regression (MLR)-based products, and the original IMERG; (2) all downscaled products decreased the degree of overestimation of the original IMERG at heavy-precipitation regions to a certain extent; (3) for heavy-precipitation events in the plum rain season, the downscaled products based on SVM and BPNN both improved prediction accuracy compared to the MLR-based products and the original IMERG considering the validations against ground observations. R2 maximally increased from 0.344 to 0.615 for the SVM-based products and from 0.344 to 0.435 for the BPNN-based products compared to the original IMERG; and (4) for typhoon precipitation events, the SVM-based products still showed better accuracy with R2 maximally increased from 0.492 to 0.615 compared to the original IMERG. In contrast, the performance of BPNN-based products was not satisfying and showed no significant differences with the performance of MLR-based products. This study provided a potential solution for generating downscaled satellite-based precipitation products at meteorological scales with finer accuracy and spatial resolutions.https://www.frontiersin.org/article/10.3389/feart.2020.00146/fullprecipitationIMERGdownscalingSVMBPNN |
| spellingShingle | Xiaoxiao Min Xiaoxiao Min Ziqiang Ma Jintao Xu Jintao Xu Kang He Zhige Wang Qingliang Huang Jun Li Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China Frontiers in Earth Science precipitation IMERG downscaling SVM BPNN |
| title | Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China |
| title_full | Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China |
| title_fullStr | Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China |
| title_full_unstemmed | Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China |
| title_short | Spatially Downscaling IMERG at Daily Scale Using Machine Learning Approaches Over Zhejiang, Southeastern China |
| title_sort | spatially downscaling imerg at daily scale using machine learning approaches over zhejiang southeastern china |
| topic | precipitation IMERG downscaling SVM BPNN |
| url | https://www.frontiersin.org/article/10.3389/feart.2020.00146/full |
| work_keys_str_mv | AT xiaoxiaomin spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT xiaoxiaomin spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT ziqiangma spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT jintaoxu spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT jintaoxu spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT kanghe spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT zhigewang spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT qinglianghuang spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina AT junli spatiallydownscalingimergatdailyscaleusingmachinelearningapproachesoverzhejiangsoutheasternchina |