数字农科院2.0

Evaluation Of Catboost Method For P.rediction Of Reference Evapotranspiration I n Humid Regions

文献类型： 外文期刊

作者： Wu, Lifeng;Yu, Xiang;Zhou, Hanmi;Huang, Guomin;Fan, Junliang;Huang, Guomin;Zhang, Weiqiang;Zeng, Wenzhi;Ma, Xin;Wu, Lifeng

作者机构：

关键词： Random forests; Support vector machine; Gradient boosting decision tree; Computational complexity; Model comparison; CatBoost

期刊名称： JOURNAL OF HYDROLOGY

ISSN： 0022-1694

年卷期： 2019 年 574 卷

页码：

摘要： Accurate estimation of reference evapotranspiration (ET0) is critical for water resource management and irrigation scheduling. This study evaluated the potential of a new machine learning algorithm using gradient boosting on decision trees with categorical features support (i.e., CatBoost) for accurately estimating daily ET0 with limited meteorological data in humid regions of China. Two other commonly used machine learning algorithms, Random Forests (RF) and Support Vector Machine (SVM), were also assessed for comparison. Eight input combinations of daily meteorological data [including both complete and incomplete combinations of solar radiation (R-s), maximum and minimum temperatures (T-max and T-min), relative humidity (H-r) and wind speed (U)] from five weather stations during 2001-2015 in South China were applied for model training and testing. The results showed that all the three algorithms could achieve satisfactory accuracy for ET0 estimation in subtropical China using R-s, T-max and T-min, or U, H-r, T-max, and T-min as inputs, under the circumstances of lacking complete meteorological parameters. The increases in testing RMSE and MAPE over training RMSE and MAPE showed positive correlations with the number of input parameters to the machine learning models. For the local models, among the three algorithms, SVM offered the best prediction accuracy and stability with incomplete combinations of meteorological parameters as inputs, while CatBoost performed best with the complete combination of parameters. Patterns of the generalized models were almost the same as the local models, but the former ones showed less than 10% decreases in RMSE or MAPE in comparison with the latter ones. In addition, the computing time and memory usage for data processing of CatBoost were much less than those of RF and SVM. Overall, as a tree-based algorithm, CatBoost made significant improvements in accuracy, stability and computational cost when compared to RF. Therefore, the CatBoost algorithm has a very high potential for ET0 estimation in humid regions of China, and even possibly in other parts of the world with similar humid climates.

分类号：

  • 相关文献

[1]Early Detection Of Water Stress I.n Maize Based On D igital Images. Zhuang, S, Wang, P, Jiang, B, Li, MS, Gong, ZH. 2017

[2]Dynamic environment prediction on unmanned mobile manipulator robot via ensemble convolutional randomization networks. Dai Y., Wang J., Li J.. 2022

[3]Accuracy Comparison Of Dry Matter I.ntake Prediction Models Evaluated B y A Feeding Trial Of Lactating Dairy Cows Fed Two Total Mixed Rations With Different Forage Source. Pan, XH, Yang, L, Beckers, Y, Xiong, BH, Jiang, LS. 2017

[4]Machine Learning Models To Quantify And Map Daily Global Solar Radiation And Photovoltaic Power. Feng, Y, Hao, WP, Li, HR, Cui, NB, Gong, DZ, Gao, LL. 2020

[5]Comparison Of Models For Genetic E.valuation Of Number Of I nseminations To Conception In Danish Holstein Cows. Guo, G, Hou, YL, Zhang, Y, Su, GS. 2017

[6]Evaluation of random forests and generalized regression neural networks for daily reference evapotranspiration modelling. Feng, Yu,Cui, Ningbo,Zhang, Qingwen,Zhao, Lu,Feng, Yu,Cui, Ningbo,Zhang, Qingwen,Zhao, Lu,Feng, Yu,Gong, Daozhi.

[7]Comparison of artificial intelligence and empirical models for estimation of daily diffuse solar radiation in North China Plain. Feng, Yu,Cui, Ningbo,Zhang, Qingwen,Zhao, Lu,Feng, Yu,Cui, Ningbo,Zhang, Qingwen,Zhao, Lu,Feng, Yu,Gong, Daozhi.

[8]Ion mobility spectrometry fingerprints: A rapid detection technology for adulteration of sesame oil. Zhang, Liangxiao,Shuai, Qian,Li, Peiwu,Zhang, Qi,Ma, Fei,Zhang, Wen,Ding, Xiaoxia,Shuai, Qian,Zhang, Qi,Ma, Fei,Li, Peiwu,Zhang, Qi,Ma, Fei,Li, Peiwu,Ding, Xiaoxia,Zhang, Liangxiao,Li, Peiwu,Zhang, Wen,Zhang, Liangxiao. 2016

[9]Insight from untargeted metabolomics: Revealing the potential marker compounds changes in refrigerated pork based on random forests machine learning algorithm. Minghui Gu,Cheng Li,Li Chen,Shaobo Li,Naiyu Xiao,Dequan Zhang,Xiaochun Zheng. 2023

[10]Metabolomics for origin traceability of lamb: An ensemble learning approach based on random forest recursive feature elimination. Chongxin Liu,Simona Grasso,Nigel Patrick Brunton,Qi Yang,Shaobo Li,Li Chen,Dequan Zhang. 2025

[11]Automated Spectral Feature Extraction From H.yperspectral Images To Differentiate W eedy Rice And Barnyard Grass From A Rice Crop. Pieters, Jan G.,Zhang, Yanchao,Lu, Yongliang,He, Yong,Gao, Junfeng,Cen, Haiyan,Yu, Xiaoyue,He, Yong. 2019

[12]Estimates Of Rice Lodging Using I.ndices Derived From Uav V isible And Thermal Infrared Images. Guo, Wenshan,Jiang, Min,Jin, Xiuliang,Li, Rui,Zhong, Xiaochun,Zhou, Ping,Liu, Tao,Liu, Shengping,Sun, Chengming. 2018

[13]Feature Extraction And Classification Of A.nimal Blood Spectra With S upport Vector Machine. Zhou Lin-hua,Lu Peng-fei,Fan Ya,Zhao Si-yan,Kong Zhi-feng,Gao Bin,Liu Lin-na,Qian Jun. 2017

[14]Verification And Predicting Temperature And H.umidity In A Solar G reenhouse Based On Convex Bidirectional Extreme Learning Machine Algorithm. Zou, WD, Yao, FX, Zhang, BH, He, CX, Guan, ZX. 2017

[15]Global Land Surface Evapotranspiration Estimation F.rom Merra Dataset And M odis Product Using The Support Vector Machine. Liu, M, Tang, RL, Li, ZL, Yao, YJ, Yan, GJ. 2017

[16]A Segmenting Method For Greenhouse C.ucumber Downy Mildew Images B ased On Visual Spectral And Support Vector Machine. Ma, JC, Du, KM, Zheng, FX, Zhang, LX, Sun, ZF. 2018

[17]Near Infrared Spectral Analysis Algorithms For Traceability Of Fishmeal Origin. Li, QB, Bi, ZQ, Shi, DD. 2020

[18]Evaluation Of Artificial Intelligence Models F.or Actual Crop Evapotranspiration M odeling In Mulched And Non-Mulched Maize Croplands. Tang, DH, Feng, Y, Gong, DZ, Hao, WP, Cui, NB. 2018

[19]Research On Nondestructive Testing Of Corn Seed Vigor Based On Thz-Tds Reflection Imaging. Wu, JZ, Li, XQ, Liu, CL, Yu, L, Sun, XR, Sun, LJ. 2020

[20]Source apportionment of heavy metals in sediments and soils in an interconnected river-soil system based on a composite fingerprint screening approach. Ruihui Chen,Qianru Zhang,Haiyang Chen,Weifeng Yue,Yanguo Teng. 2021

作者其他论文 更多>>