https://scholars.lib.ntu.edu.tw/handle/123456789/572993
標題: | Gap-filling of surface fluxes using machine learning algorithms in various ecosystems | 作者: | Huang I.-H CHENG-I HSIEH |
關鍵字: | Decision trees; Deep learning; Deep neural networks; Filling; Hysteresis; Learning algorithms; Learning systems; Meteorology; Multilayer neural networks; Support vector machines; Surface measurement; Water vapor; Input factors; Meteorological data; Ml algorithms; Model performance; Multi-layer perception; Net radiation; Sensible heat; Water vapor flux; Ecosystems; accuracy assessment; algorithm; carbon dioxide; machine learning; numerical model; paddy field; perception; performance assessment; support vector machine | 公開日期: | 2020 | 卷: | 12 | 期: | 12 | 起(迄)頁: | 1-24 | 來源出版物: | Water (Switzerland) | 摘要: | Five machine learning (ML) algorithms were employed for gap-filling surface fluxes of CO2, water vapor, and sensible heat above three different ecosystems: grassland, rice paddy field, and forest. The performance and limitations of these ML models, which are support vector machine, random forest, multi-layer perception, deep neural network, and long short-term memory, were investigated. Firstly, the accuracy of gap-filling to time and hysteresis input factors of ML algorithms for different ecosystems is discussed. Secondly, the optimal ML model selected in the first stage is compared with the classic method—the Penman–Monteith (P–M) equation for water vapor flux gap-filling. Thirdly, with different gap lengths (from one hour to one week), we explored the data length required for an ML model to perform the optimal gap-filling. Our results demonstrate the following: (1) for ecosystems with a strong hysteresis between surface fluxes and net radiation, adding proceeding meteorological data into the model inputs could improve the model performance; (2) the five ML models gave similar gap-filling performance; (3) for gap-filling water vapor flux, the ML model is better than the P–M equation; and (4) for a gap with length of half day, one day, or one week, an ML model with training data length greater than 1300 h would provide a better gap-filling accuracy. ? 2020 by the authors. Licensee MDPI, Basel, Switzerland. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100064031&doi=10.3390%2fw12123415&partnerID=40&md5=45e943dedc010e4f2655999cf00cba41 https://scholars.lib.ntu.edu.tw/handle/123456789/572993 |
ISSN: | 20734441 | DOI: | 10.3390/w12123415 |
顯示於: | 生物環境系統工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。