Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin
Downscaling considerably alleviates the drawbacks of regional climate simulation by general circulation models (GCMs). However, little information is available regarding the downscaling using machine learning methods, specifically at hydrological basin scale. This study developed multiple machine le...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Advances in Meteorology |
| Online Access: | http://dx.doi.org/10.1155/2020/8680436 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832567454692278272 |
|---|---|
| author | Ren Xu Nengcheng Chen Yumin Chen Zeqiang Chen |
| author_facet | Ren Xu Nengcheng Chen Yumin Chen Zeqiang Chen |
| author_sort | Ren Xu |
| collection | DOAJ |
| description | Downscaling considerably alleviates the drawbacks of regional climate simulation by general circulation models (GCMs). However, little information is available regarding the downscaling using machine learning methods, specifically at hydrological basin scale. This study developed multiple machine learning (ML) downscaling models, based on a Bayesian model average (BMA), to downscale the precipitation simulation of 8 Coupled Model Intercomparison Project Phase 5 (CMIP5) models using model output statistics (MOS) for the years 1961–2005 in the upper Han River basin. A series of statistical metrics, including Pearson’s correlation coefficient (PCC), root mean squared error (RMSE), and relative bias (Rbias), were used for evaluation and comparative analyses. Moreover, the BMA and the best ML downscaling model were used to downscale precipitation in the 21st century under Representative Concentration Pathway 4.5 (RCP4.5) and RCP8.5 scenarios. The results show the following: (1) The performance of the BMA ensemble simulation is clearly better than that of the individual models and the simple mean model ensemble (MME). The PCC reaches 0.74, and the RMSE is reduced by 28%–60% for all the GCMs and 33% compared to the MME. (2) The downscaled models greatly improved station simulation performance. Support vector machine for regression (SVR) was superior to multilayer perceptron (MLP) and random forest (RF). The downscaling results based on the BMA ensemble simulation and SVR models were regarded as the best performing overall (PCC, RMSE, and Rbias were 0.82, 35.07, mm and −5.45%, respectively). (3) Based on BMA and SVR models, the projected precipitations show a weak increasing trend on the whole under RCP4.5 and RCP8.5. Specifically, the average rainfall during the mid- (2040–2069) and late (2070–2099) 21st century increased by 3.23% and 1.02%, respectively, compared to the base year (1971–2000) under RCP4.5, while they increased by 4.25% and 8.30% under RCP8.5. Additionally, the magnitude of changes during winter and spring was higher than that during summer and autumn. Furthermore, future work is recommended to study the improvement of downscaling models and the effect of local climate. |
| format | Article |
| id | doaj-art-72223d33767844e881f59edebaf94a4a |
| institution | Kabale University |
| issn | 1687-9309 1687-9317 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Meteorology |
| spelling | doaj-art-72223d33767844e881f59edebaf94a4a2025-02-03T01:01:31ZengWileyAdvances in Meteorology1687-93091687-93172020-01-01202010.1155/2020/86804368680436Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River BasinRen Xu0Nengcheng Chen1Yumin Chen2Zeqiang Chen3School of Resource and Environmental Science, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaSchool of Resource and Environmental Science, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaDownscaling considerably alleviates the drawbacks of regional climate simulation by general circulation models (GCMs). However, little information is available regarding the downscaling using machine learning methods, specifically at hydrological basin scale. This study developed multiple machine learning (ML) downscaling models, based on a Bayesian model average (BMA), to downscale the precipitation simulation of 8 Coupled Model Intercomparison Project Phase 5 (CMIP5) models using model output statistics (MOS) for the years 1961–2005 in the upper Han River basin. A series of statistical metrics, including Pearson’s correlation coefficient (PCC), root mean squared error (RMSE), and relative bias (Rbias), were used for evaluation and comparative analyses. Moreover, the BMA and the best ML downscaling model were used to downscale precipitation in the 21st century under Representative Concentration Pathway 4.5 (RCP4.5) and RCP8.5 scenarios. The results show the following: (1) The performance of the BMA ensemble simulation is clearly better than that of the individual models and the simple mean model ensemble (MME). The PCC reaches 0.74, and the RMSE is reduced by 28%–60% for all the GCMs and 33% compared to the MME. (2) The downscaled models greatly improved station simulation performance. Support vector machine for regression (SVR) was superior to multilayer perceptron (MLP) and random forest (RF). The downscaling results based on the BMA ensemble simulation and SVR models were regarded as the best performing overall (PCC, RMSE, and Rbias were 0.82, 35.07, mm and −5.45%, respectively). (3) Based on BMA and SVR models, the projected precipitations show a weak increasing trend on the whole under RCP4.5 and RCP8.5. Specifically, the average rainfall during the mid- (2040–2069) and late (2070–2099) 21st century increased by 3.23% and 1.02%, respectively, compared to the base year (1971–2000) under RCP4.5, while they increased by 4.25% and 8.30% under RCP8.5. Additionally, the magnitude of changes during winter and spring was higher than that during summer and autumn. Furthermore, future work is recommended to study the improvement of downscaling models and the effect of local climate.http://dx.doi.org/10.1155/2020/8680436 |
| spellingShingle | Ren Xu Nengcheng Chen Yumin Chen Zeqiang Chen Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin Advances in Meteorology |
| title | Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin |
| title_full | Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin |
| title_fullStr | Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin |
| title_full_unstemmed | Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin |
| title_short | Downscaling and Projection of Multi-CMIP5 Precipitation Using Machine Learning Methods in the Upper Han River Basin |
| title_sort | downscaling and projection of multi cmip5 precipitation using machine learning methods in the upper han river basin |
| url | http://dx.doi.org/10.1155/2020/8680436 |
| work_keys_str_mv | AT renxu downscalingandprojectionofmulticmip5precipitationusingmachinelearningmethodsintheupperhanriverbasin AT nengchengchen downscalingandprojectionofmulticmip5precipitationusingmachinelearningmethodsintheupperhanriverbasin AT yuminchen downscalingandprojectionofmulticmip5precipitationusingmachinelearningmethodsintheupperhanriverbasin AT zeqiangchen downscalingandprojectionofmulticmip5precipitationusingmachinelearningmethodsintheupperhanriverbasin |