Estimation of the rice water footprint based on machine learning algorithms
文献类型：期刊论文
| 作者 | Mokhtar, Ali1,2,3; Elbeltagi, Ahmed4; Maroufpoor, Saman5; Azad, Nasrin6; He, Hongming1,3; Alsafadi, Karam7; Gyasi-Agyei, Yeboah8; He, Wenming9,10 |
| 刊名 | COMPUTERS AND ELECTRONICS IN AGRICULTURE
 |
| 出版日期 | 2021-12-01 |
| 卷号 | 191页码:15 |
| 关键词 | Water footprint Rice production Climate change GCMs Machine learning |
| ISSN号 | 0168-1699 |
| DOI | 10.1016/j.compag.2021.106501 |
| 通讯作者 | He, Hongming(hongming.he@yahoo.com) ; He, Wenming(hwmjim@163.com) |
| 英文摘要 | It is essential to investigate the impact of climate change on the water footprint (WF) of rice from both historical simulation and future projections. In this study, four machine learning (ML) models, including random tree (RT), random forest (RF), additive regression (AR) and reduced error pruning tree (REPT) were used to model blue and green water footprint (BWFP and GWFP) for the present and future stages in the Yunnan Province, southwest China. Climate variables of daily precipitation, temperature, solar radiation, sunshine hours, wind speed, relative humidity and vapor pressure deficit data, yield and sown areas of rice were collected form 16 districts from 1990 to 2018. Six different scenarios (Sc1-Sc6) with different combinations of climate variables, crop coefficient and sown areas were used as inputs of the ML models for each of blue and green water footprint. Also, future climate projections of maximum (Tmax) and minimum (Tmin) temperatures, precipitation and sunshine were adopted for two different emission scenarios, RCP 4.5 and 8.5 from 2021to 2050, based on Geophysical Fluid Dynamics Laboratory (GFDL-ESM2M) model. For BWFP, the RT model in Sc1 with inputs of solar radiation, humidity, and vapor pressure deficit, was superior to the other scenarios with root mean square error (RMSE) and mean average percentage error (MAPE) values of 11.82 (m(3) ton(-1)) and 0.5%, respectively. Sc4 (sown area, Tmin, sunshine hours) and Sc5 (sown area, Tmin, Tmax, crop coefficient) were the best two scenarios for all models applied for BWFP, while addition of precipitation to these two scenarios were the best for GWFP. Further, GWFP was highly negative anomaly in 2011 by 46%, 34% and 32% for the districts 5, 1 and 2 respectively, followed by 2010. Predictions of variable trends in the future showed that crop evapotranspiration during the growing season would increase in all the districts, although effective precipitation (Peff) would have both decreasing and increasing trends. Furthermore, BWFP and GWFP will have an upward trend in the future based on RCP4.5 in Sc4. This investigation addresses water footprint prediction which may assist in mitigation plans such as policies for sustainable water-use and development plans for food security. |
| WOS关键词 | CLIMATE-CHANGE ; ADDITIVE REGRESSION ; NEURAL-NETWORK ; RANDOM FOREST ; WINTER-WHEAT ; CHINA ; PRECIPITATION ; RIVER ; YIELD ; REQUIREMENTS |
| 资助项目 | Second Tibetan Plateau Scientific Expedition and Research Program[SQ2019QZKK2003] ; Strategic Priority Science and Technology Project of The Chinese Academy of Sciences (Category A)[ZDA23020600] ; Guangdong Rural Science and Technology Commissioner Project of China[319B0203] ; Key Platforms and Scientific Research Projects in Universities in Guangdong Province of China[2018KTSCX212] |
| WOS研究方向 | Agriculture ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000759173000006 |
| 出版者 | ELSEVIER SCI LTD |
| 资助机构 | Second Tibetan Plateau Scientific Expedition and Research Program ; Strategic Priority Science and Technology Project of The Chinese Academy of Sciences (Category A) ; Guangdong Rural Science and Technology Commissioner Project of China ; Key Platforms and Scientific Research Projects in Universities in Guangdong Province of China |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/170990]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | He, Hongming; He, Wenming |
| 作者单位 | 1.East China Normal Univ, Minist Educ, Sch Geog Sci, Key Lab Geog Informat Sci, Shanghai, Peoples R China 2.Cairo Univ, Fac Agr, Dept Agr Engn, Giza 12613, Egypt 3.Chinese Acad Sci & Minist Water Resources, Northwest Agr & Forestry Univ, Inst Soil & Water Conservat, State Key Lab Soil Eros & Dryland Farming Loess P, Yangling 712100, Shaanxi, Peoples R China 4.Mansoura Univ, Fac Agr, Agr Engn Dept, Mansoura 35516, Egypt 5.Zhejiang Univ, Coll Environm & Resource Sci, Hangzhou 310058, Peoples R China 6.Univ Tehran, Dept Irrigat & Reclamat Engn, Tehran, Iran 7.Urmia Univ, Dept Water Engn, Orumiyeh, Iran 8.Nanjing Univ Informat Sci & Technol, Sch Geog Sci, Nanjing 210044, Peoples R China 9.Griffith Univ, Sch Engn & Built Environm, Nathan, Qld 4111, Australia 10.Jiaying Univ, Sch Chem & Environm, Guangdong Prov Key Lab Conservat & Precis Utiliza, Meizhou 514015, Guangdong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Mokhtar, Ali,Elbeltagi, Ahmed,Maroufpoor, Saman,et al. Estimation of the rice water footprint based on machine learning algorithms[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2021,191:15. |
| APA | Mokhtar, Ali.,Elbeltagi, Ahmed.,Maroufpoor, Saman.,Azad, Nasrin.,He, Hongming.,...&He, Wenming.(2021).Estimation of the rice water footprint based on machine learning algorithms.COMPUTERS AND ELECTRONICS IN AGRICULTURE,191,15. |
| MLA | Mokhtar, Ali,et al."Estimation of the rice water footprint based on machine learning algorithms".COMPUTERS AND ELECTRONICS IN AGRICULTURE 191(2021):15. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。