Estimation of Surface and Depth Soil Temperature from Meteorological Data Using Machine Learning Techniques in Hyper Arid Climate

Document Type : Original Article

Authors

zabol university

Abstract

Accurate estimation of temperature at various soil depths is crucial for land-atmosphere interactions. In this study, the application of six different machine learning models including artificial neural network (ANN), decision tree (DT), cubist (CB), random forest (RF), support vector machine (SVM) and linear regression (LR) for modeling of daily soil temperature was studied at six different depths of 5, 10, 20, 30, 50 and 100 cm in Kerman. A set of accessible meteorological data including maximum and minimum temperatures, relative humidity, dew point, evapotranspiration and atmospheric pressure were used as input to the models. The degree of importance and correlational analysis was performed for the input variables based on the data of the 18-year statistical period. According to the results, the performance of all six models based on evaluation criteria (R2 >0.86, RMSE <2.8 ◦c and Bias <0.14 ◦c) was acceptable at all depths. However, RF, ANN and SVM showed very high efficiency in estimating soil temperature (R2 <0.97). Also, the DT model and then the LR model performed lower than the others. Examination of the importance of variables showed that among the input parameters, maximum and minimum temperature had the greatest effect on predicting soil temperature in all models. Finally, it can be safely acknowledged that machine learning models such as random forest, artificial neural network and support vector machine have the ability to estimate surface and depth soil temperatures in arid climates in the absence of measuring equipment. A set of meteorological data including maximum and minimum temperature, relative humidity, dew point, evapotranspiration and atmospheric pressure were used as input to the models.

Keywords

References

Ajamzadeh A., Mollaeinia M.R., and Ghandahari Gh. 2017. Comparison of artificial intelligence methods in predicting daily Time Series of minimum and maximum temperature and precipitation in tangab dam station (Fars Province). Geographical Space, 59: 205-228. (In Persian)
Bahmani F., Piri-Sahragard H., and Piri J. 2018. Application of artificial intelligence methaods to estimate soil daily temperature in arid and semi-arid climates. Iranian Journal of Range and Desert Research, 26 (1): 201-213. (In persian)
Bameri A., Khormali F., Kiani F., and Dehghani AA. 2015. Spatial variability of soil organic carbon in different hillslope positions in Toshan area, Golestan Province, Iran: geostatistical approaches. Journal of Mountain Science, 12(6). DOI: 10.1007/s11629-014-3213-z.
Delbari M., Sharifazari S., and Mohammadi E. 2019. 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, 135(3-4): 991- 1001.
Fan A.W., and Liu W. 2003. Simulation of the daily change of soil temperature under different conditions. Heat Transfer—Asian Research, 32(6):533–544.
Fathololoumi S., Vaezi A.R., Alavipanah S.K., Montzka C., Ghorbani A., and Biswas A. 2020. Soil temperature modeling using machine learning techniques. Desert, 25(2): 185-199.
Feng Y., Cui N., Hao W., Gao L., and Gong D. 2019. Estimation of soil temperature from meteorological data using different machine learning models. Geoderma, 338: 67–77.
Granata F., Papirio S., Esposito G., Gargano R., and Marinis G. 2017. Machine learning algorithms for the forecasting of wastewater quality indicators. Water. 9(105), doi:10.3390/w9020105.
Hasani Z., Mirabbasi-Najafabadi R., and Ghasemi A.R. 2018. Prediction of groundwater quality of Khanmirza plain using decision tree method. Hydrogeology, 3(1): 99-110. (In Persian)
IRIMO (2007) I.R. of Iran meteorological organization, data center. Official home page: http://www.irimo.ir/eng/.
Kim S., and Singh V.P. 2014. Modeling daily soil temperature using data driven models and spatial distribution. Theoretical and Applied Climatology, 118(3):465–479.
Ma W., Tan K., and Du P. 2016. Predicting soil heavy metal based on random forest model. IGARSS: 4331-4334. 978-1-5090-3332-4/16/$31.00 ©2016 IEEE.
Malone B. 2013. Use R for Digital Soil Mapping. Soil Security Laboratory. The University of Sydney. PP: 217.
Mehdizadeh S., Ahmadi F., and Kozekalani Sales A. 2020b. Modelling daily soil temperature at different depths via the classical and hybrid models. Meteorological Applications, 27:e1941. DOI: 10.1002/met.1941.
Mehdizadeh S., Fathian F., Sadegh Safari M.J., and Khosravi A. 2020a. Developing novel hybrid models for estimation of daily soil temperature at various depths. Soil & Tillage Research, 197(104513): 1-12.
Mirakzehi Kh., Shahriari A., Pahlavan-Rad M.R., and Bameri A. 2017. Application of random forest method for predicting soil classes in low relief lands (Case study: Hirmand county). Journal of Water and Soil Conservation, 24(1): 67-84. (In Persian)
Noi P.T., Degener J., and Kappas M. 2017. Comparison of multiple linear regression, cubist regression, and random forest algorithms to estimate daily air surface temperature from dynamic combinations of MODIS LST data. Remote Sensing. 9(398). doi:10.3390/rs9050398.
Norouzi H., Nadiri A.A., Asghari Mogaddam A., and Gharekhani M. 2017. Prediction of transmissivity of malikan plain aquifer using random forest method. Water and Soil Science, 27(2):61-75. (In Persian)
Omidvar K., Shafie Sh., Taghizadeh Z., and Alipour M. 2014. Evaluating the efficiency of the decision tree model in predicting rainfall in Kermanshah synoptic station. Journal of Applied Researches in Geographical Sciences, 34: 89-110. (In Persian)
Ozturk M., Salman O., and Koc M. 2011. Artificial neural network model for estimating the soil temperature. Canadian Journal of Soil Science, 91(4): 551-562.
Quinlan R. 1993. Combining instance based and model based learning. In Proceedings of the Tenth International Conference on Machine Learning. Amherst. MA. USA. 27–29. pp. 236–243.
Rezaei M., Sameni A., and Fallah-Shamsi S.R. 2018. Advanced machine learning methods for wind erosion monitoring in southern Iran. Journal of Environmental Erosion Research, Vol: 29(8:1): 39-58. (In Persian)
Samadianfard S., and Panahi S. 2018. Estimating daily reference evapotranspiration using data mining methods of support vector regression and M5 model tree. Journal of Watershed Management Research, 10(18):157-167. (In Persian)
Samadianfard S., Ghorbani M.A., and Mohammadi B. 2018. Forecasting soil temperature at multiple-depth with a hybrid artificial neural network model coupledhybrid firefly optimizer algorithm. Information Processing in Agriculture, 5: 465–476.
Sattari M.T., Avram A., Apaydin H., and Matei O. 2020. Soil temperature estimation with meteorological parameters by using tree-based hybrid data mining models. Mathematics, 8, 1407. doi:10.3390/math8091407.
Sattari M.T., Dodangeh E., and Abraham J.  2017. Estimation of daily soil temperature via data mining techniques in semi-arid climate conditions. Earth Sciences Research Journal, 21(2): 85 – 93.
Sihag P., Esmaeilbeiki F., Singh B., and Pandhiani S.M.  2020. Model-based soil temperature estimation using climatic parameters: The case of Azerbaijan Province, Iran. Geology, Ecology, and Landscapes, 4(3): 203-215.
Tabari H., Hosseinzadeh-Talaee P., and Willems P. 2015. Short‐term forecasting of soil temperature using artificial neural network. Meteorological Applications, 22(3), 576-585.
Tabari H., Sabziparvar AA., and Ahmadi M. 2011. Comparison of artificial neural network and multivariate linear regression methods for estimation of daily soil temperature in an arid region. Meteorology and Atmospheric Physics Journal, 110(3):135–142.
Wilding, L.P., Smeck, N. E., and Hall, G.F. 1983. Pedogenesis and Soil taxonomy. I. Concepts and Interactions. Elsevier Publishing Company, 303p.
Wu W., Tang X.P., Guo N.J., Yang C., Liu H.B., and Shang Y.F. 2013. Spatiotemporal modeling of monthly soil temperature using artificial neural networks. Theoretical and Applied Climatology, 113(3–4):481–494.
Zadmehr H., and Farrokhian-Firouzi A. 2020. Estimating soil temperature from metrological data using extreme learning machine, artificial neural network and multiple linear regression models. Iranian Journal of Soil and Water Research, 51(4): 895-906. (In Persian)
Zhou J., Li E., Wei H., Li Ch., Qiao Q., and Jahed-Armaghani, D. 2019. Random forests and cubist algorithms for predicting shear strengths of rockfill materials. Applied Sciences. 9(1621), doi:10.3390/app9081621.
Zhu X., Wu G. Coulon F., Wu L., and Chen D. 2018. Correlating asphaltene dimerization with its molecular structure by potential of mean force calculation and data mining. Energy Fuel. 32:5779–5788.
Zounemat-Kermani M. 2013. Hydrometeorological parameters in prediction of soil temperature by means of artificial neural network: case study in wyoming. Journal of Hydrologic Engineering, 18: 707–718.
Applied Soil Research
Volume 10, Issue 1
June 2022
Pages 54-68

Files

History

  • Receive Date: 25 January 2021
  • Revise Date: 08 April 2021
  • Accept Date: 17 April 2021

Share

How to cite

Statistics