Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China
Abstract The reconstruction models of hourly 10‐m wind speeds were developed for each of 2384 stations over China using stepwise regression, random forest and XGBoost machine learning approaches based on hourly observed and ERA5 reanalysis data from 2005 to 2021. The reconstruction procedures applie...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2023-11-01
|
| Series: | Earth and Space Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023EA003295 |
| _version_ | 1797448959546884096 |
|---|---|
| author | Chad Shouquan Cheng Shufeng Yang Jian Zhu Tao Yang Gaozhen Nie Jian Tang Yanyan Lu |
| author_facet | Chad Shouquan Cheng Shufeng Yang Jian Zhu Tao Yang Gaozhen Nie Jian Tang Yanyan Lu |
| author_sort | Chad Shouquan Cheng |
| collection | DOAJ |
| description | Abstract The reconstruction models of hourly 10‐m wind speeds were developed for each of 2384 stations over China using stepwise regression, random forest and XGBoost machine learning approaches based on hourly observed and ERA5 reanalysis data from 2005 to 2021. The reconstruction procedures applied observed hourly data to reduce the systematic biases of reanalysis data sets. Furthermore, the procedures employed the past dynamically consistent states of the atmosphere simulated by ERA5 reanalysis techniques to reduce/remove wind‐observed data impacts of long‐term non‐meteorological condition changes over time (e.g., urbanization around weather stations), which provide homogenous hourly wind speed data sets from 1959 to 2021. The systematic errors of the models' simulations derived from three approaches are similarly small, with almost two orders of magnitude smaller than ERA5 original data sets. The systematic errors of reconstructed data sets derived from stepwise regression are similar to its simulation; however, the biases from two machine learning methods are even much greater than ERA5 original data sets. This result implies that machine learning methods are not suitable for such typical time‐series predictions using the previous‐hour wind speed as a predictor to reconstruct wind speed data for the next hour. Therefore, stepwise regression was selected to reconstruct hourly wind speed data sets, which have much better quality than ERA5 reanalysis data with the median correctness increased by >50% and the median rRMSE decreased by 25%–50%. Consequently, the reconstructed wind speed data sets have great potential to be useful for more precisely assessing the characteristics/trends of wind energy resources in the past 60 years over China. |
| first_indexed | 2024-03-09T14:18:11Z |
| format | Article |
| id | doaj.art-e58a9042eedb4efaa1f232cba61c381b |
| institution | Directory Open Access Journal |
| issn | 2333-5084 |
| language | English |
| last_indexed | 2024-03-09T14:18:11Z |
| publishDate | 2023-11-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | Earth and Space Science |
| spelling | doaj.art-e58a9042eedb4efaa1f232cba61c381b2023-11-28T20:18:31ZengAmerican Geophysical Union (AGU)Earth and Space Science2333-50842023-11-011011n/an/a10.1029/2023EA003295Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over ChinaChad Shouquan Cheng0Shufeng Yang1Jian Zhu2Tao Yang3Gaozhen Nie4Jian Tang5Yanyan Lu6State Key Laboratory of Hydrology‐Water Resources and Hydraulic Engineering Center for Global Change and Water Cycle Hohai University Nanjing ChinaCollege of Hydrology and Water Resources Hohai University Nanjing ChinaState Key Laboratory of Hydrology‐Water Resources and Hydraulic Engineering Center for Global Change and Water Cycle Hohai University Nanjing ChinaState Key Laboratory of Hydrology‐Water Resources and Hydraulic Engineering Center for Global Change and Water Cycle Hohai University Nanjing ChinaNational Meteorological Center China Meteorological Administration Beijing ChinaNational Meteorological Center China Meteorological Administration Beijing ChinaKey Laboratory of Far‐shore Wind Power Technology of Zhejiang Province Hangzhou ChinaAbstract The reconstruction models of hourly 10‐m wind speeds were developed for each of 2384 stations over China using stepwise regression, random forest and XGBoost machine learning approaches based on hourly observed and ERA5 reanalysis data from 2005 to 2021. The reconstruction procedures applied observed hourly data to reduce the systematic biases of reanalysis data sets. Furthermore, the procedures employed the past dynamically consistent states of the atmosphere simulated by ERA5 reanalysis techniques to reduce/remove wind‐observed data impacts of long‐term non‐meteorological condition changes over time (e.g., urbanization around weather stations), which provide homogenous hourly wind speed data sets from 1959 to 2021. The systematic errors of the models' simulations derived from three approaches are similarly small, with almost two orders of magnitude smaller than ERA5 original data sets. The systematic errors of reconstructed data sets derived from stepwise regression are similar to its simulation; however, the biases from two machine learning methods are even much greater than ERA5 original data sets. This result implies that machine learning methods are not suitable for such typical time‐series predictions using the previous‐hour wind speed as a predictor to reconstruct wind speed data for the next hour. Therefore, stepwise regression was selected to reconstruct hourly wind speed data sets, which have much better quality than ERA5 reanalysis data with the median correctness increased by >50% and the median rRMSE decreased by 25%–50%. Consequently, the reconstructed wind speed data sets have great potential to be useful for more precisely assessing the characteristics/trends of wind energy resources in the past 60 years over China.https://doi.org/10.1029/2023EA003295hourly wind speed reconstructionmachine learningstepwise regressionhomogenous wind speed dataChina |
| spellingShingle | Chad Shouquan Cheng Shufeng Yang Jian Zhu Tao Yang Gaozhen Nie Jian Tang Yanyan Lu Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China Earth and Space Science hourly wind speed reconstruction machine learning stepwise regression homogenous wind speed data China |
| title | Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China |
| title_full | Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China |
| title_fullStr | Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China |
| title_full_unstemmed | Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China |
| title_short | Reconstruction of Near‐Surface Hourly Wind Speed Data Sets During the Period 1959–2021 Over China |
| title_sort | reconstruction of near surface hourly wind speed data sets during the period 1959 2021 over china |
| topic | hourly wind speed reconstruction machine learning stepwise regression homogenous wind speed data China |
| url | https://doi.org/10.1029/2023EA003295 |
| work_keys_str_mv | AT chadshouquancheng reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina AT shufengyang reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina AT jianzhu reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina AT taoyang reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina AT gaozhennie reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina AT jiantang reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina AT yanyanlu reconstructionofnearsurfacehourlywindspeeddatasetsduringtheperiod19592021overchina |