Quantitative Estimation of Rainfall from Remote Sensing Data Using Machine Learning Regression Models

被引:2
|
作者
Mohia, Yacine [1 ]
Absi, Rafik [2 ]
Lazri, Mourad [1 ]
Labadi, Karim [2 ]
Ouallouche, Fethi [1 ]
Ameur, Soltane [1 ]
机构
[1] Univ Mouloud MAMMERI Tizi Ouzou UMMTO, Fac Genie Elect & Informat FGEI, Loboratoire Anal & Modelisat Phenomenes Aleatoires, LAMPA, Tizi Ouzou 15000, Algeria
[2] ECAM EPMI, LR2E Lab, Lab Quartz, F-95092 Cergy Pontoise, France
关键词
remote sensing; rainfall; MSG Satellite; SVR; RF; RR; regression; SATELLITE; CLASSIFICATION; NORTH; AREAS;
D O I
10.3390/hydrology10020052
中图分类号
TV21 [水资源调查与水利规划];
学科分类号
081501 ;
摘要
To estimate rainfall from remote sensing data, three machine learning-based regression models, K-Nearest Neighbors Regression (K-NNR), Support Vector Regression (SVR), and Random Forest Regression (RFR), were implemented using MSG (Meteosat Second Generation) satellite data. Daytime and nighttime data from a rain gauge are used for model training and validation. To optimize the results, the outputs of the three models are combined using the weighted average. The combination of the three models (hereafter called Com-RSK) markedly improved the predictions. Indeed, the MAE, MBE, RMSE and correlation coefficient went from 23.6 mm, 10.0 mm, 40.6 mm and 89% for the SVR to 20.7 mm, 5.5 mm, 37.4 mm, and 94% when the models were combined, respectively. The Com-RSK is also compared to a few methods using the classification in the estimation, such as the ECST Enhanced Convective Stratiform Technique (ECST), the MMultic technique, and the Convective/Stratiform Rain Area Delineation Technique (CS-RADT). The Com-RSK show superior performance compared to ECST, MMultic and CS-RADT methods.The Com-RSK is also compared to the two products of satellite estimates, namely CMORPH and CHIRPS. The results indicate that Com-RSK performs better than CMORPH and CHIRPS according to MBE, RMSE and CC (coefficient correlation). A comparison with three types of satellite precipitation estimation products, such as global product, regional product, and near real-time product, is performed. Overall, the methodology developed here shows almost the same results as regional product methods and exhibits better results than near real-time and global product methods.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] STRATIFIED MACHINE LEARNING MODELS FOR WHEAT YIELD ESTIMATION USING REMOTE SENSING DATA
    Khechba, Keltoum
    Belgiu, Mariana
    Laamrani, Ahmed
    Dong, Qi
    Stein, Alfred
    Chehbouni, Abdelghani
    IGARSS 2024-2024 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, IGARSS 2024, 2024, : 1946 - 1949
  • [2] Estimating Soil Quality Indicators Using Remote Sensing Data: An Application of Machine Learning Regression Models
    Diaz-Gonzalez, Freddy A.
    Vallejo, Victoria E.
    Vuelvas, Jose
    Patino, Diego
    2023 IEEE 6TH COLOMBIAN CONFERENCE ON AUTOMATIC CONTROL, CCAC, 2023, : 38 - 43
  • [3] Estimation of sugarcane evapotranspiration from remote sensing and limited meteorological variables using machine learning models
    Alavi, Mohammad
    Albaji, Mohammad
    Golabi, Mona
    Naseri, Abd Ali
    Homayouni, Saeid
    JOURNAL OF HYDROLOGY, 2024, 629
  • [4] Estimation of wheat tiller density using remote sensing data and machine learning methods
    Hu, Jinkang
    Zhang, Bing
    Peng, Dailiang
    Yu, Ruyi
    Liu, Yao
    Xiao, Chenchao
    Li, Cunjun
    Dong, Tao
    Fang, Moren
    Ye, Huichun
    Huang, Wenjiang
    Lin, Binbin
    Wang, Mengmeng
    Cheng, Enhui
    Yang, Songlin
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [5] Wheat yield estimation using remote sensing data based on machine learning approaches
    Cheng, Enhui
    Zhang, Bing
    Peng, Dailiang
    Zhong, Liheng
    Yu, Le
    Liu, Yao
    Xiao, Chenchao
    Li, Cunjun
    Li, Xiaoyi
    Chen, Yue
    Ye, Huichun
    Wang, Hongye
    Yu, Ruyi
    Hu, Jinkang
    Yang, Songlin
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [6] Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches
    Latif, Sarmad Dashti
    Hazrin, Nur Alyaa Binti
    Koo, Chai Hoon
    Ng, Jing Lin
    Chaplot, Barkha
    Huang, Yuk Feng
    El-Shafie, Ahmed
    Ahmed, Ali Najah
    ALEXANDRIA ENGINEERING JOURNAL, 2023, 82 : 16 - 25
  • [7] Soil organic carbon estimation using remote sensing data-driven machine learning
    Chen, Qi
    Wang, Yiting
    Zhu, Xicun
    PEERJ, 2024, 12
  • [8] Rapid Rice Yield Estimation Using Integrated Remote Sensing and Meteorological Data and Machine Learning
    Islam, Md Didarul
    Di, Liping
    Qamer, Faisal Mueen
    Shrestha, Sravan
    Guo, Liying
    Lin, Li
    Mayer, Timothy J. J.
    Phalke, Aparna R. R.
    REMOTE SENSING, 2023, 15 (09)
  • [9] Improved remote sensing reference evapotranspiration estimation using simple satellite data and machine learning
    Liu, Dan
    Wang, Zhongjing
    Wang, Lei
    Chen, Jibin
    Li, Congcong
    Shi, Yujia
    SCIENCE OF THE TOTAL ENVIRONMENT, 2024, 947
  • [10] Grassland Yield Estimation Using Transfer Learning from Remote Sensing Data
    Eder, Elias
    Riegler-Nurscher, Peter
    Prankl, Johann
    Prankl, Heinrich
    KUNSTLICHE INTELLIGENZ, 2023, 37 (2-4): : 187 - 194