Predicting seasonal soil depth temperature changes in the Yazd- Ardakan plain using Landsat 8 satellite images and Artificial Neural Network technique

Document Type : Research Paper

Authors

1 Ph.D. Student of Combating Desertification, Department of Arid Lands Management, Faculty of Natural Resources and Desert Studies, Yazd University, Yazd, Iran.

2 Assistant Professor of Department of Arid Lands Management, Faculty of Natural Resources and Desert Studies, Yazd University, Yazd, Iran.

10.29252/aridbiom.2020.1818

Abstract

Soil temperature is a key factor that controls physical, chemical and biological properties of soil and its processes. Since soil temperature is measured at synoptic stations and data availability, especially in arid lands, is limited, capability of satellite images to estimate soil temperature at different depths evaluated in the Yazd-Ardakan basin, as the study area. Daily soil temperature at 5, 10, 20, 30, 50 and 100 cm depth measured at synoptic stations of Yazd, Meybod, and Mehriz for the periods of 2014 to 2016, and Landsat 8 satellite images of were used as the main data in this research. Then, using split-window surface temperature, Land Surface Temperature (LST) maps were estimated. Temperature trend from soil surface to a depth of 100 cm were examined seasonally. Using simple linear regression and artificial neural network techniques, the relationship between temperature of surface soil and soil temperatures at different depths were predicted. Results showed that the artificial neural networks had greater accuracy than the linear regression method in all seasons. The lowest accuracy of this method is related to the soil temperature at 5 cm depth. Artificial neural networks can be used for predicting of soil temperature till depth of 100 cm, using land surface temperature obtained by Landsat 8 images. To validate the results, soil temperatures at depth of 30 cm for 16 selected points in the study area were compared with estimated soil temperature using Landsat images and artificial neural network. Absolute error of measurements show that the maximum error was observed to depth of 30 cm (3.7 ℃). Therefore, using the measured soil surface temperature by applying the split-windows and artificial neural network can be used to predict soil temperature.

Keywords

References

[1]. Alizamir, M., Kisi, O., Ahmed, A., Mert, C., Fai, C., Kim, S., & El-Shafie, A. (2020). Advanced machine learning model for better prediction accuracy of soil temperature at different depths. Plos One, 15(4), e0231055.
[2]. Amir Moradi, K., & Bahmani, O. (2014). Prediction of Daily Soil Temperatures with Artificial Neural Network.  Soil Research, 28(3), 543-556. (in Farsi)
[3]. Amini, F. Z., Ghorbani, M. A., & Darbandi, S. (2014). Evaluation of Genetic Programming in Estimation of Soil Temperature, Geographic Space, 4(47), 19-38. (in Farsi)
[4]. Araghi, A., Mousavi‐Baygi, M. Adamowski, J. Martinez, C. & VanderPloeg, M. (2017). Forecasting soil temperature based on surface air temperature using a wavelet artificial neural network. Meteorological Applications, 24(4), 603-611.
[5]. Asakereh, H., & Sayadi, F. (2017). Analysis and Forecasting Drought Days Using Artificial Neural Networks ‎Model (Case Study: Station Tehran). Geography and Planning, 21(60), 161-167. (in Farsi)
[6]. Baaghideh, M., Entezari, A., & Kordi, A. (2019). Investigation of the Relationship between Soil Temperature and Climate Parameters in the Northwest of Iran (1992-2015). Geography and Regional Development, 16(1), 307-279.
[7]. Becker, F., & Li, Z. (1990). Towards a local split window method over land surfaces. Remote Sensing. 11, 369–393.
[8]. Behyar, M., & Kamali, G. (2001). Projection of minimum soil temperature and frost and frost control methods in Chaharmahal Bakhtiari province, Meteorological and Baroque Research Institute 3(23), 81-102. (in Farsi)
[9]. Carlson, T., & Ripley, D. A. (1997). On the relation between NDVI, fractional vegetation cover, and leaf area index, Remote Sensing of Environment, 62, 241-252.
[10].Chander, G., Markham, B., & Helder, D. (2009). Summary of current radiometric calibration coefficients for Landsat MSS, TM, ETM +, and EO-1 ALI sensors. Remote Sensing of Environment, 113(5), 893-903
[11].Chedin, A., Scott, N., & Berroir, A. (1982). A single-channel, double-viewing angle method for sea surface temperature determination from coincident Meteosat and TIROS-N radiometric measurements‚ Applied Meteorology, 4(21) ‚ 613-618.
[12].Dymond, J., Stephens, P., & Newsome, P (1992). Percentage vegetation cover of a degrading rangeland from SPOT. Remote Sensing. 13, 1999–2007.
[13].Ebrahimi Heravi, B., Rangzan, K., Riahi Bakhtiari, H., & Taghizadeh, A. (2015). Determination of urban surface temperature using LandSat images (Case study: Karaj). RS and GIS for Natural Resources, 6(2), 19-32. (in Farsi)
[14].Fangueiro, D., Kidd, P.S., Alvarenga, P., Beesley, L., & Varennes, A. (2018). Chapter 10 Strategies for Soil Protection and Remediation, in: “Soil Pollution: From Monitoring to Remediation”, Edited by: Duarte, A.C., Cachada, A. and Rocha-Santos, T.A.P. Elsevier. 251–281.
[15].Feng, Y., Cui, N., Hao, W., Gao, L., & Gong, D. (2019). Estimation of soil temperature from meteorological data using different machine learning models. Geoderma, 338, 67-77
[16].Gao, Z., Bian, L., Hu, Y., Wang, L., & Fan, J. (2007). Determination of soil temperature in an arid region, Arid Environments. 71, 157-168.
[17].García-Santos, V., Cuxart, J., Martínez-Villagrasa, D., Jiménez, M.A., & Simó, G, (2018). Comparison of Three Methods for Estimating Land Surface Temperature from Landsat 8-TIRS Sensor Data. Remote Sensing. 10, 1450.
[18].Ghuman, B.S., & Lal, R. (1982). temperature regime of a tropical soil in relation to surface condition and air temperature and its Fourier analysis, Soil Science, 134, 133-140.
[19].Gillespie, A., Rokugawa, S., Matsunaga, T., Cothern, J.S., Hook, S., & Kahle, A.B. (1998). A temperature and emissivity separation algorithm for Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images‚ IEEE transactions on geoscience and remote sensing, 4(36)‚ 1113- 1126.
[20].Hagan, MT., & Menhaj, MB. (1994). Training feedforward network with the Marquardt algorithm. IEEE Trans on Neural Networks. 5, 989-993
[21].Harrison-murray, R., & Lal, R. (1979). High soil temperatures and response of maize to mulching in the lowland humid tropics. In: Greenland, D.J., Lal, R. (Eds), Soil Conservation and Management in the Humid Tropics. Wiley, New York.
[22].Hook, S., Gabell, A., Green, A., & Kealy, P. (1992). A comparison of techniques for extracting emissivity information from thermal infrared data for geologic studies‚ Remote sensing of Environment, 2(42)‚ 123-135.
[23]. https://earthexplorer.usgs.gov/.
[24].Huang, R., Huang, J. X., Zhang, C., Wen, Z., Chen, Y., Zhu, D., & Mansaray, L. (2020). Soil temperature estimation at different depths, using remotely-sensed data. Integrative Agriculture, 19(1), 277-290.
[25].Jiménez-Muñoz, J., & Sobrino, J. (2010). Split-Window Coefficients for Land Surface Temperature retrieval from Low-Resolution Thermal Infrared Sensors, IEEE Geoscience and Remote Sensing Letters, 5, 806–809.
[26].Jiménez-Muñoz, J., Sobrino, J., Jiménez, D., Mattar, C., & Cristóbal, J. (2014). Land Surface Temperature Retrieval Methods from Landsat-8 Thermal Infrared Sensor Data. IEEE Geoscience and Remote Sensing Letters, 11, 1840–1843.
[27].Jouybari, Y., Moghaddam, M., Akhoondzadeh, M., & Saradjian, R. (2015). A Split-Window Algorithm for Estimating LST from Landsat-8 Satellite Images. Geomatics Science and Technology. 5(1), 215-226. (in Farsi)
[28].Khoshhal dastjerdi, J., & Hosseini, S. (2010). Application of Artificial Neural Network in Climatic Elements Simulation and Drought Cycle Predication (Case Study: Isfahan Province). Geography and Environmental Planning, 21(3), 107-120. (in Farsi)
[29].Kisi, O., Tombul, M., & Kermani, M. (2015). Modeling soil temperatures at different depths by using three different neural computing techniques. Theoretical and applied climatology, 121(1-2), 377-387.
[30].Kuenzer, C., & Dech, S. (2013). Thermal Infrared Remote Sensing, Sensord, Methods, Applications, 17. Springer, 546.
[31].Li, Q., Hao, H., Zhao, Y., Geng, Q., Liu, G., Zhang, Y., & Yu, F. (2020). GANs-LSTM model for soil temperature estimation from meteorological: A new approach. IEEE Access.
[32].Li, Z.-L., Tang, B.-H., Wu, H., Ren, H., Yan, G., Wan, Z., Sobrino, J. A. (2013). Satellite-derived land surface temperature: Current status and perspectives. Remote Sensing of Environment, 131, 14-37.
[33].Ma, X.L., Wan, Z., Moeller, C., Menzel, W.P., & Gumley, L.E. (2002). Simultaneous retrieval of atmospheric profiles, land- surface temperature and surface emissivity from moderate-resolution imaging spectroradiometer thermal infrared data: Extension of a two-step physical algorithm‚ Applied Optics, 5(41) ‚ 909-924.
[34]. Mamdani, E.H., & Assilian, S., (1975). An experiment in linguistic synthesis with a fuzzy logic controller. Man-Machine Studies, 7(1), 1-13.
[35].Masiello, G., Serio, C., De Feis, I., Amoroso, M., Venafra, S., Trigo, I., & Watts, P. (2013). Kalman filter physical retrieval of surface emissivity and temperature from geostationary infrared radiances‚ Atmospheric Measurement Techniques, 12(6), 3613-3634.
[36].Mazidi, A., & Falahzade, F. (2010). Annual soil temperature trend at Yazd station, geography and development, 24, 39-50. (in Farsi)
[37].McMillin, L. M. (1975). Estimation of sea surface temperatures from two infrared window measurements with different absorption. Geophysical Research, 80(36), 5113-5117.
[38].Nafaji mod, M., Alizade, A., Mohamadian, A., & Mosavi, j. (2009). Investigation of relationship between air and soil temperature at different depths and estimation of the freezing depth (Case study: Khorasan Razavi). Water and Soil, 22(2), 456-466. (in Farsi)
[39].Nayak, P.C., Sudheer, K.P., Rangan, D.M., & Ramasatri, K.S. (2004). A neuro-fuzzy computing technique for modeling hydrological time series. Hydrology, 291, 52-66.
[40].Neinavaz, E., Skidmore, A. K., & Darvishzadeh, R. (2020). Effects of prediction accuracy of the proportion of vegetation cover on land surface emissivity and temperature using the NDVI threshold method. Applied Earth Observation and Geoinformation, 85, 1-13.
[41].Neteler, M. (2010). Estimating daily land surface temperatures in mountainous environments by reconstructed MODIS LST data. Remote Sensing, 2(1), 333-351.
[42].Parsafar, N., & Marofi, S. (2011). Estimation of Soil Temperature from Air Temperature Using Regression Models, Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System (Case Study: Kermanshah Region). Water and Soil Science, 21(3), 139-152. (in Farsi)
[43].Sabziparvar, A., Zare-Abyaneh, H., & Bayat-Varkeshi, M. (2010). A model Comparison between Predicted Soil Temperatures Using ANFIS Model and Regression Methods in Three Different Climates. Water and Soil, 24(2), 274-285. (in Farsi)
[44].Salih, M., Jasim, O., Hassoon, K., & Abdalkadhum, A. (2018). Land Surface Temperature Retrieval from LANDSAT-8 Thermal Infrared Sensor Data and Validation with Infrared Thermometer Camera. International Engineering & Technology, 7(4.20), 608-612.
[45].Shati, F., Prakash, S., Norouzi, H., & Blake, R. (2018). Assessment of differences between near-surface air and soil temperatures for reliable detection of high-latitude freeze and thaw states. Cold Regions Science and Technology, 145, 86-92.
[46].Singh, V.K., Singh, B.P., Kisi, O., & Kushwaha, D.P. (2018). Spatial and multi-depth temporal soil temperature assessment by assimilating satellite imagery, artificial intelligence and regression-based models in arid area. Computers and Electronics in Agriculture, 150, 205-219.
[47].Sobrino, J., Li, Z., Stoll, M., & Becker, F. (1996). Multi-channel and multi-angle algorithms for estimating sea and land surface temperature with ATSR data. Remote Sensing, 17(11), 2089-2114.
[48].Sun, D., & Pinker, R. (2007). Retrieval of surface temperature from the MSG‐ SEVIRI observations: Part I. Methodology‚ Remote Sensing, 23(28)‚ 5255- 5272.
[49].Talaee, P. H. (2014). Daily soil temperature modeling using neuro-fuzzy approach. Theoretical and applied climatology, 118(3), 481-489.
[50].Tiba, C. H., & Raquel, G. (2006), Numerical Procedure for Estimating Temperature in Solarized Soils, Pesquisa Agropecuária Brasileira, 3, 533 – 537.
[51].Van Wambeke, A., (1992). Soils of the Tropics, Properties and Appraisal. Donnelley and Sons, Mexico.
[52].Veysi, S., Naseri, A., Hamzeh, S., & Moradi, P. (2016). Estimation of sugarcane field temperature using Split Window Algorithm and OLI LandSat 8 satellite images. RS and GIS for Natural Resources, 7(1), 27-40. (in Farsi)
[53].Vlassova, L., Perez-Cabello, F., Nieto, H., Martín, P., Riaño, D., & Riva, J. (2014). Assessment of methods for land surface temperature retrieval from Landsat-5 TM images applicable to multiscale tree-grass ecosystem modeling. Remote Sensing, 6(5), 4345-4368.
[54].Wan‚ Z., & Li, Z.L., (1997). A physics-based algorithm for retrieving land-surface emissivity and temperature from EOS/MODIS data‚ IEEE transactions on geoscience and remote sensing, 35(4), 980-996.
[55].Yang, C. C., Parsher, S. O., Mehuys, G. R., & Panti, N. K. (1997). Application of artificial neural networks for simulation of soil temperature. Agricultural Engineering. 40(3), 649-656.
[56].Zadmehr, H., & Farrokhian Firouzi, A. (2020). Estimation of Soil Temperature from Metrological Data Using Extreme Learning Machine, Artificial Neural Network, and Multiple Linear Regression Models.  Soil and Water Research. (in Farsi)
Journal of Arid Biome
Volume 9, Issue 2
March 2020
Pages 85-102

Files

Share

How to cite

Statistics