数字农科院2.0

Estimation Of Soil Temperature From M.eteorological Data Using Different M achine Learning Models

文献类型： 外文期刊

作者： Feng, Y; Cui, NB; Hao, WP; Gao, LL; Gong, DZ

作者机构：

关键词： Soil temperature; Machine learning models; Soil depth; Extreme learning machine

期刊名称： GEODERMA

ISSN： 0016-7061

年卷期： 2019 年 338 卷

页码：

收录情况： JCR（2021版） ; EI（2021版）

摘要： Soil temperature (T-s) plays a key role in physical, biological and chemical processes in terrestrial ecosystems. Accurate estimation of T-s at various soil depths is crucial for land-atmosphere interactions. This study investigated the applicability of four different machine learning models, extreme learning machine (ELM), generalized regression neural networks (GRNN), backpropagation neural networks (BPNN) and random forests (RF), for modeling half-hourly T-s at four different depths of 2 cm, 5 cm, 10 cm, and 20 cm on the Loess Plateau of China. A field experiment was conducted to measure half-hourly T-s and meteorological variables. Air temperature, wind speed, relative humidity, solar radiation, and vapor pressure deficit were used as inputs to train the models for estimation of half-hourly T-s. The results showed ELM, GRNN, BPNN and RF models provided desirable performance in modeling half-hourly T-s at all depths, with root mean square error values ranging 2.26-2.95, 2.36-3.10, 2.32-3.04 and 2.31-3.00 degrees C, mean absolute error values ranging 1.76-2.26, 1.83-2.31, 1.80-2.32 and 1.79-2.26 degrees C, Nash-Sutcliffe coefficient values ranging 0.856-0.930, 0.841-0.924, 0.847-0.927 and 0.850-0.927, and concordance correlation coefficient values ranging 0.925-0.965, 0.925-0.963, 0.928-0.963, and 0.924-0.961 for the ELM, GRNN, BPNN, and RF models, respectively. There was a statistically significant agreement (P < 0.001) between the measured and modeled values at both half-hour and daily timescales, and the box plots showed the distributional differences between the measured and modeled values were small. Generally, the ELM model had slightly better performance with much better computation speed than GRNN, BPNN as well as RF models at half-hourly timescales, thus the ELM model was highly recommended to estimate T-s at different soil depths.

分类号：

  • 相关文献

[1]Evaluation of Machine Learning Models for Daily Reference Evapotranspiration Modeling Using Limited Meteorological Data in Eastern Inner Mongolia, North China. Zhang H., Meng F., Xu J., Liu Z., Meng J.. 2022

[2]Evaluation Of Temperature-Based Machine Learning A.nd Empirical Models For P redicting Daily Global Solar Radiation. Feng, Y, Gong, DZ, Zhang, QW, Jiang, SZ, Zhao, L, Cui, NB. 2019

[3]Estimation Of Maize Evapotranspiration Using E.xtreme Learning Machine And G eneralized Regression Neural Network On The China Loess Plateau. Feng, Y, Gong, DZ, Mei, XR, Cui, NB. 2017

[4]Comparison Of Artificial Intelligence And E.mpirical Models For Estimation O f Daily Diffuse Solar Radiation In North China Plain. Feng, Y, Cui, NB, Zhang, QW, Zhao, L, Gong, DZ. 2017

[5]Development Of Data-Driven Models For P.rediction Of Daily Global H orizontal Irradiance In Northwest China. Feng, Y, Cui, NB, Chen, YX, Gong, DZ, Hu, XT. 2019

[6]Modeling Reference Evapotranspiration Using Extreme L.earning Machine And Generalized R egression Neural Network Only With Temperature Data. Feng, Y, Peng, Y, Cui, NB, Gong, DZ, Zhang, KD. 2017

[7]Rapid Determination By Near Infrared S.pectroscopy Of Theaflavins-To-Thearubigins Ratio D uring Congou Black Tea Fermentation Process. Dong, CW, Li, J, Wang, JJ, Liang, GZ, Jiang, YW, Yuan, HB, Yang, YQ, Meng, HW. 2018

[8]Dynamics of ammonia oxidizers in response to different fertilization inputs in intensively managed agricultural soils. Li X.,Wang Y.,Zhang Y.,Lang M.,Christie P.,Bei S.,Zhang J.. 2021

[9]Distribution Characteristics Of Iron, Carbon, N.itrogen And Phosphorus In T he Surface Soils Of Different Land Use Types Near Xingkai Lake. Wang, LY, Yu, XF, Xue, ZS, Huo, LL, Jiang, M, Lu, XG, Zou, YC. 2019

[10]Effects of single and mixed plant types on soil carbon and nitrogen dynamics in homestead agroforestry systems in Northern Bangladesh. Jaman M.S.,Muraina T.O.,Dam Q.,Zhang X.,Jamil M.,Bhattarai S.,Islam F.. 2021

[11]Molecular ecological network analysis of the response of soil microbial communities to depth gradients in farmland soils. Wang, Zhong-Liang,Yu, Hang,Zhang, Guilong,Zheng, Wei,Yu, Hang,Xue, Dongmei,Wang, Yidong. 2020

[12]Hybrid Particle Swarm Optimization With Extreme Learning Machine For Daily Reference Evapotranspiration Prediction From Limited Climatic Data. Zhu, B, Feng, Y, Gong, DZ, Jiang, SZ, Zhao, L, Cui, NB. 2020

[13]Degradation Characteristics Of Maize Straw Under Different Buried Depths In Northeast Black Soil And Their Effects On Soil Carbon And Nitrogen. Kuang, EJ, Xu, MG, Colinet, G, Chi, FQ, Su, QR, Zhu, BG, Zhang, JM. 2020

[14]EFFECT OF FARMLAND SURFACE COVERED POROUS MULCH MATERIALS ON SOIL WATER, HEAT AND WATER USE EFFICIENCY OF MAIZE. Feng, L. S.,Sun, Z. X.,Zheng, J. M.,Yang, N.,Bai, W.,Feng, C.,Yan, C. R.,Zheng, M. Z.. 2015

[15]Effects of soil temperature on degradation of oxytetracycline in soils. Li Zhao-jun,Fan Fei-fei,Long Jian. 2013

[16]Temperature-mediated developmental delay may limit yield of cotton in relay intercrops with wheat. L. Zhang,W. van der Werf,S. Zhang,B. Li,J.H.J. Spiertz. 2008

[17]An Evaluation of Minimum Tillage in the Corn-wheat Cropping System in Hebei Province, China: Wheat productivity and water conservation. Yang, Xiaomei,Yin, Changbin,Li, Guichun,Chien, Hsiaoping,Nagumo, Fujio. 2016

[18]Effect of mulch and irrigation practices on soil water, soil temperature and the grain yield of maize (Zea mays L) in Loess Plateau, China. Liu Yi,Shen Yufang,Yang Shenjiao,Li Shiqing,Liu Yi,Chen Fang,Yang Shenjiao. 2011

[19]Effect of alternative tillage and residue cover on yield and water use efficiency in annual double cropping system in North China Plain. He Jin,Wang Qingjie,Li Hongwen,Gao Huanwen,Liu Lijin.

[20]Root Water Uptake Model Considering Soil Temperature. Lv, Guohua,Liu, Buchun,Song, Jiqing,Hu, Wei,Kang, Yaohu,Li, Lan.

作者其他论文 更多>>