Estimation of soil temperature based on XGBoost and LSTM methods

Qing-liang LI; Kai-xuan CAI; Qing-tian GENG; Guang-jie LIU; Ming-yu SUN; Yu ZHANG; Fan-hua YU

doi:10.37188/OPE.20202810.2337

您当前的位置：

首页 >

文章列表页 >

Estimation of soil temperature based on XGBoost and LSTM methods

Information Sciences | 更新时间：2020-11-16

- Estimation of soil temperature based on XGBoost and LSTM methods
- Optics and Precision Engineering Vol. 28, Issue 10, Pages: 2337-2348(2020)
- 作者机构：
  
  长春师范大学计算机科学技术学院, 吉林长春 130032
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20202810.2337
  CLC： P401;P343.8
- Received：16 March 2020，
  
  Revised：24 May 2020，
  
  Accepted：24 May 2020，
  
  Published：25 October 2020
- 稿件说明：
移动端阅览
Qing-liang LI, Kai-xuan CAI, Qing-tian GENG, et al. Estimation of soil temperature based on XGBoost and LSTM methods[J]. Optics and precision engineering, 2020, 28(10): 2337-2348.
DOI：

Qing-liang LI, Kai-xuan CAI, Qing-tian GENG, et al. Estimation of soil temperature based on XGBoost and LSTM methods[J]. Optics and precision engineering, 2020, 28(10): 2337-2348. DOI： 10.37188/OPE.20202810.2337.

摘要

土壤温度是地球科学多个领域的重要变量。其时空变化受多种环境因素影响，这对土壤温度的准确预测带来巨大挑战。以机器学习为核心的数据驱动方法，在土壤温度预测中是重要研究领域，为基于物理过程模型提供重要补充。然而目前针对土壤温度影响因素量性研究较少，因此本文提出XGBoost-LSTM的数据驱动方法。基于极限梯度提升算法（XGBoost）分析土壤温度影响因素的重要性，然后根据影响因素重要性依次组合，并输入至长短期记忆网络（LSTM），得到最优预测模型并实现土壤温度预测。最后在长白山和海北两个气象站完成实验，本文方法的最优均方根误差为2.234、平均绝对误差为1.716、纳什效率系数为0.932、LMI系数为0.729和威尔莫特一致性指数为0.983。结果表明本文提出的XGBoost-LSTM预测模型与目前土壤温度中常用的数据驱动模型相比，均表现出更高的精确度。

Abstract

Soil temperature is an important variable in Earth sciences. The temporal and spatial variations in soil temperature are affected by numerous factors

resulting in various challenges in soil temperature prediction. For soil temperature prediction

the data-driven machine learning method is valuable and can be an important complement to physics-based process models. However

no extensive studies have been carried out on the importance of environmental factors on soil temperature. In this study

a data-driven XGBoost-LSTM method is proposed. The weights of the meteorological inputs are computed based on XGBoost

and then

the combination of meteorological inputs based on their weights is applied to obtain an optimal model by the LSTM method. An experiment is carried out at two stations in China (Changbai Mountain and Haibei). The most accurate performance for soil temperature estimation is attained

with highest values of NS = 0.932

WI = 0.983

and LMI = 0.729 and lowest values of RMSE and MAE of 2.234 and 1.716

respectively. These results show that the proposed model is generally superior to other state-of-the-art predictive models.

关键词

Keywords

references

Y FENG , N CUI , W HAO , 等 . Estimation of soil temperature from meteorological data using different machine learning models . Geoderma , 2019 . 338 67 - 77 . DOI: 10.1016/j.geoderma.2018.11.044 http://doi.org/10.1016/j.geoderma.2018.11.044 .

H SANIKHANIA , R C DEOB , Z M YASEENC , 等 . Non-tuned data intelligent model for soil temperature estimation:A new approach . Geoderma , 2018 . 330 52 - 64 . DOI: 10.1016/j.geoderma.2018.05.030 http://doi.org/10.1016/j.geoderma.2018.05.030 DOI: 10.1016/j.geoderma.2018.05.030 http://doi.org/10.1016/j.geoderma.2018.05.030 .

J Y CORNU , L DENAIX , J LACOSTE , 等 . Impact of temperature on the dynamics of organic matter and on the soil-to-plant transfer of Cd, Zn and Pb in a contaminated agricultural soil . Environmental Science and Pollution Research , 2016 . 23 2997 - 3007 . DOI: 10.1007/s11356-015-5432-4 http://doi.org/10.1007/s11356-015-5432-4 .

Y KIM , J C STILL , C V HANSON , 等 . Canopy skin temperature variations in relation to climate, soil temperature, and carbon flux at a ponderosa pine forest in central Oregon . Agricultural and Forest Meteorology , 2016 . 226 161 - 173 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0e3182e11b59bae11cbe2f01f140a915 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0e3182e11b59bae11cbe2f01f140a915 .

J YANGA , H BUSEN , H SCHERB , 等 . Modeling of radon exhalation from soil influenced by environmental parameters . Science of The Total Environment , 2019 . 656 1304 - 1311 . DOI: 10.1016/j.scitotenv.2018.11.464 http://doi.org/10.1016/j.scitotenv.2018.11.464 .

BHADANI P, VASHISHT V, SOIL MOISTURE. Temperature and humidity measurement using arduino[C]. The 9 th International Conference on Cloud Computing, Data Science & Engineering, Noida, India , 2019: 567-571.

G HU , Z LIN , X WU , 等 . An analytical model for estimating soil temperature profiles on the Qinghai-Tibet plateau of China . Journal of Arid Land , 2016 . 8 ( 2 ): 232 - 240 . DOI: 10.1007/s40333-015-0058-4 http://doi.org/10.1007/s40333-015-0058-4 .

L L LIANG , D A RIVEROS-IREGUI , R E EMANUEL , 等 . A simple framework to estimate distributed soil temperature from discrete air temperature measurements in data-scarce regions . Geophys. Res , 2017 . 119 407 - 417 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=01b660b112673ff89f206b8a4f4542e9 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=01b660b112673ff89f206b8a4f4542e9 .

徐英 , 谷雨 , 彭冬亮 , 等 . 基于DRGAN和支持向量机的合成孔径雷达图像目标识别 . 光学精密工程 , 2020 . 28 ( 3 ): 727 - 735 . http://ope.lightpublishing.cn/thesisDetails?columnId=2126352&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2126352&Fpath=&index=-1&l=zh .

Y XU , Y GU , D L PENG , 等 . SAR ATR based on disentangled representation learning generative adversarial networks and support vector machine . Opt. Precision Eng. , 2020 . 28 ( 3 ): 727 - 735 . http://ope.lightpublishing.cn/thesisDetails?columnId=2126352&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=2126352&Fpath=&index=-1&l=zh .

闫敬文 , 陈宏达 , 刘蕾 . 高光谱图像分类的研究进展 . 光学精密工程 , 2019 . 27 ( 3 ): 680 - 693 . http://ope.lightpublishing.cn/thesisDetails?columnId=1424316&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1424316&Fpath=&index=-1&l=zh .

J W YAN , H D CHEN , L LIU . Overview of hyperspectral image classification . Opt. Precision Eng. , 2019 . 27 ( 3 ): 680 - 693 . http://ope.lightpublishing.cn/thesisDetails?columnId=1424316&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1424316&Fpath=&index=-1&l=zh .

魏彤 , 周银鹤 . 基于机器学习识别与标记分水岭分割的盲道图像定位 . 光学精密工程 , 2019 . 27 ( 1 ): 201 - 210 . http://ope.lightpublishing.cn/thesisDetails?columnId=1424834&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1424834&Fpath=&index=-1&l=zh .

T WEI , Y H ZHOU . Blind sidewalk image location based on machine learning recognition and marked watershed segmentation . Opt. Precision Eng. , 2019 . 27 ( 1 ): 201 - 210 . http://ope.lightpublishing.cn/thesisDetails?columnId=1424834&Fpath=&index=-1&l=zh http://ope.lightpublishing.cn/thesisDetails?columnId=1424834&Fpath=&index=-1&l=zh .

G MIHALAKAKOU . On estimating soil surface temperature profiles . Energy and Buildings , 2002 . 34 ( 3 ): 251 - 259 . DOI: 10.1016/S0378-7788(01)00089-5 http://doi.org/10.1016/S0378-7788(01)00089-5 DOI: 10.1016/S0378-7788(01)00089-5 http://doi.org/10.1016/S0378-7788(01)00089-5 .

O KISI , H SANIKHANI . Modellinglong-termmonthlytemperaturesby several data-driven methods using geographical inputs . Int. J. Climatol , 2015 . 35 ( 13 ): 3834 - 3846 . DOI: 10.1002/joc.4249 http://doi.org/10.1002/joc.4249 .

S O HUR , W T KIM , KH JUNG , 等 . Estimation of Soil Surface Temperature by Heat Flux in Soil . Korean Journal of Soil Science & Fertilizer , 2004 . 37 ( 3 ): 131 - 135 . http://agris.fao.org/agris-search/search.do?recordID=KR2005011187 http://agris.fao.org/agris-search/search.do?recordID=KR2005011187 .

R MOAZENZADEH , B MOHAMMADI . Assessment of bio-inspired metaheuristic optimisation algorithms for estimating soil temperature . Geoderma , 2019 . 353 ( 11 ): 152 - 171 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ceb722825ed08acc1d27eb92703602e4 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=ceb722825ed08acc1d27eb92703602e4 .

M DELBARI , S SHARIFAZARI , E MOHAMMADI . Modeling daily soil temperature over diverse climate conditions in Iran-a comparison of multiple linear regression and support vector regression techniques . Theoretical and Applied Climatology , 2019 . 135 ( 3-4 ): 991 - 1001 . DOI: 10.1007/s00704-018-2370-3 http://doi.org/10.1007/s00704-018-2370-3 .

G LI , W LI , X TIAN , 等 . Short-term electricity load forecasting based on the xgboost algorithm . Smart Grid , 2017 . 7 ( 4 ): 274 - 285 . DOI: 10.12677/SG.2017.74031 http://doi.org/10.12677/SG.2017.74031 .

S JI , X WANG , W ZHAO , 等 . An Application of a Three-Stage XGBoost-Based Model to Sales Forecasting of a Cross-Border E-Commerce Enterprise . Mathematical Problems in Engineering , 2019 . 2019 ( Article ID 8503252 ): 1 - 15 . http://www.researchgate.net/publication/335848331_An_Application_of_a_Three-Stage_XGBoost-Based_Model_to_Sales_Forecasting_of_a_Cross-Border_E-Commerce_Enterprise http://www.researchgate.net/publication/335848331_An_Application_of_a_Three-Stage_XGBoost-Based_Model_to_Sales_Forecasting_of_a_Cross-Border_E-Commerce_Enterprise .

ALBERTOTORRES-BARRÁNA , Á ALONSO , J R DORRONSOROAB . Regression tree ensembles for wind energy and solar radiation prediction . Neurocomputing , 2017 . 326-327 ( 1 ): 151 - 160 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3b6de8d43af563baf8ad511be7675871 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=3b6de8d43af563baf8ad511be7675871 .

J ZHANG , Y ZHU , X ZHANG , 等 . Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas . Journal of Hydrology , 2018 . 561 ( 6 ): 918 - 929 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a60bf98e262c2b27998a0c1375c1cd47 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a60bf98e262c2b27998a0c1375c1cd47 .

X QING , Y NIU . Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM . Energy , 2018 . 148 ( 4 ): 461 - 468 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=d2d346ea1562178ac2662687a590107e http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=d2d346ea1562178ac2662687a590107e .

Q L LI , H B HAO , Y ZHAO , 等 . GANs-LSTM model for soil temperature estimation from meteorological:a new approach . IEEE ACCESS , 2020 . 8 59427 - 59443 . DOI: 10.1109/ACCESS.2020.2982996 http://doi.org/10.1109/ACCESS.2020.2982996 .

Views

270

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰