استفاده از شاخص‌های طیفی در برآورد رطوبت سطحی خاک براساس الگوریتم یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه خاکشناسی ، دانشکده کشاورزی، دانشگاه گیلان، رشت، ایران

2 گروه خاکشناسى، دانشکده کشاورزى، دانشگاه گیلان، رشت، ایران

3 پژوهشکده حفاظت خاک و آبخیزداری، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران

4 موسسه تحقیقات خاک و اب کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، کرج، ایران

5 گروه خاکشناسی، دانشکده کشاورزی، دانشگاه بوعلی سینا، همدان، ایران

10.22059/ijswr.2022.333856.669130

چکیده

اطلاع دقیق از میزان رطوبت سطح خاک و توزیع مکانی و زمانی آن می­تواند منجر به بهره­برداری بهینه از امکانات زمین گردد. هدف از پژوهش حاضر برآورد رطوبت سطحی خاک به­وسیله پارامترهای زودیافت خاک و شاخص­های طیفی حاصل از سنجنده سنتینل[1]-2 با دو روش شبکه عصبی مصنوعی (ANN) و رگرسیون بردار پشتیبان (SVM) است. به تعداد 124 نمونه خاک از سه منطقه ایران (تهران، گرمسار و لرستان) برداشته شد. پس از نرمال­سازی داده­های موردنظر، معنی­داری همبستگی متغیرهای ورودی (شاخص­های طیفی و خصوصیات پایه­ای خاک) با خروجی (رطوبت سطحی) از نظر آماری بررسی گردید. سپس، مدل­سازی با روش­های مذکور انجام و نتایج مورد ارزیابی قرار گرفت. نتایج نشان داد که روش ANN کارایی بهتری نسبت به روش SVM دارد. در روش ANN، میانگین مقادیر، ریشه میانگین مربعات خطا (RMSE)، آکائیک (AIC)، ضریب تعیین (R2)، و ضریب بهبود نسبی (RI) به ترتیب در مرحله آموزش 033/0، 538-، 71/0 و 25/21 و در مرحله آزمون 410/0، 266-، 69/0 و 06/16 به دست آمدند. همچنین مقادیر میانگین RMSE، AIC، R2 و RI در روش SVM به ترتیب در مرحلۀ آموزش 035/0، 474-، 71/0 و 16/35 و در مرحلۀ آزمون 046/0، 252-، 63/0 و 21/20 به دست آمدند. در این پژوهش شاخص رنگ خاک (CI) نسبت به سایر شاخص­های طیفی با روش ANN بادقت بالاتری رطوبت خاک را برآورد کرده است؛ بنابراین روش شبکه عصبی مصنوعی با ایجاد ارتباط غیرخطی بین رطوبت سطح خاک و پارامترهای ورودی قادر به برآورد رطوبت خاک با دقت قابل‌قبول در منطقه موردمطالعه است.
 
[1]. Sentinel-2 Satellite

کلیدواژه‌ها


عنوان مقاله [English]

The Use of Spectral Indices to Estimate Soil Surface Moisture using Machine Learning Algorithms

نویسندگان [English]

  • Azadeh Sedaghat 1
  • Mahmoud Shabanpour 2
  • Aliakbar Noroozi 3
  • Alireza Fallah Nosratabad 4
  • Hossein Bayat 5
1 Department of Soil Science, Faculty of Agriculture, University of Guilan, Rasht, Iran
2 Department of Soil Science, University of Guilan, Iran
3 Watershed Management Research Institute, Tehran, Iran
4 Soil and Water Research Institute, Agricultural Research, Education and Extension Organization, Karaj, Iran
5 Department of Soil Science, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran
چکیده [English]

Detailed information about soil moisture and its spatial and temporal distribution provides opportunity for optimized land resources utilization. Our study aimed to estimate soil surface moisture through readily availabile soil parameters and spectral index obtained from Sentinel-2 sensors using two methods, artificial neural networks (ANN) and support vector regression (SVM). There were 124 soil samples collected from three regions of Iran (Tehran, Garmsar, and Lorestan). After normalizing the data, the significance of the correlation between input variables (spectral indices and basic soil properties) and output variables (surface moisture) was evaluated statistically. In the next step, the mentioned methods were used to perform a modeling process, and the results were evaluated. The results showed that the ANN method outperformed the SVM method. Based on ANN technique, the Root Mean Square Error (RMSE), Akaike Information Criterion (AIC), coefficient of determination (R2) and Relative Improvement (RI) in the training step were 0.033, -538, 0.71, 21.25, and in the testing step they were 0.410, -266, 0.69, and 16.06, respectively. Also, RMSE, AIC, R2, and RI in the SVM method in training step were respectively 0.035, -474, 0.71, and 35.16 and in testing step were respectively 0.046, 252, 0.63, and 20.21. Using the ANN method, soil color index (CI) has been shown to estimate soil moisture more accurately than other spectral indices. Therefore, the ANN method constructs a nonlinear relationship between soil surface moisture and input parameters, which enables soil moisture to be estimated with acceptable accuracy in the study area.

کلیدواژه‌ها [English]

  • transfer functions
  • Soil color index
  • Salinity index
  • Soil temperature index
  • Soil surface moisture
Abbas, A. and Khan, S. (2007). Using remote sensing techniques for appraisal of irrigated soil salinity. Int. Congr. Model. Simul.(MODSIM), Model. Simul. Soc. Aust. New Zealand, Bright, (January), (pp. 2632-2638).‏
Adab, H. (2015). Estimation of the Instantaneous Soil Surface Moisture Content in Cold Seasons by using Optical and Thermal Remote Sensing Data under Clear Sky. Water and Soil Science. 21 (2):175-191 (In Farsi).
Adab, H., Morbidelli, R., Saltalippi, C., Moradian, M. and Ghalhari, G. A. F. (2020). Machine learning to estimate surface soil moisture from remote sensing data. Water, 12(11), 3223.
Akaike, H. (1974). A new look at the statistical model identification. IEEE transactions on automatic control. 19, 716–723.
Ahmad, S., Kalra. A. and Stephen, H. (2010). Estimating soil moisture using remote sensing data: A machine learningapproach. Advances in water resources. 33(1): 69-80.
Agyare, W. A., Park, S. J. and Vlek, P. L. G. (2007). Artificial neural network estimation of saturated hydraulic conductivity. Vadose Zone Journal. 6(2): 423-431.
Alavi Panah, K. (2007) Thermal remote sensing and its application in earth sciences. University of Tehran Press. (In Farsi).
Al Masmoudi, Y., Bouslihim, Y., Doumali, K., El Aissaoui, A. and Namr, K. I. (2021). Application of the random forest model to predict the plasticity state of vertisols. Journal of Ecological Engineering, 22(2)
Allbed, A., Kumar, L. and Sinha, P. (2018). Soil salinity and vegetation cover change detection from multi-temporal remotely sensed imagery in Al Hassa Oasis in Saudi Arabia. Geocarto International, 33 (8), 830-846.
Allbed, A. and Kumar, L. (2013). Soil salinity mapping and monitoring in arid and semi-arid regions using remote sensing technology: a review. Advances in remote sensing, 2(4): 373.
Aslami, F., Ghorbani, A., Sobhani, B. and Panahandeh, M. (2015). Comparing artificial neural network, support vector machine and object-based methods in preparation land use/cover maps using landsat-8 images. RS & GIS techniques in natural resources, 6:1-14 (In Farsi).
Asner, G.P. (1998). Biophysical and biochemical sources of variability in canopy reflectance. Remote sening of environment. 64(3), 234-253
Avdan, U. and Jovanovska, G. (2016). Algorithm for Automated Mapping of Land Surface Temperature Using LANDSAT 8 Satellite Data. Journal of Sensors, 2016, 1–8.
Babaeian, E., Homaee, M., Montzka, C., Vereecken, H. and Norouzi, A. A. (2015). Towards retrieving soil hydraulic properties by hyperspectral remote sensing. Vadose Zone Journal, 14(3), vzj2014-07.
Babaeian, E., Sadeghi, M., Franz, T.E., Jones, S. and Tuller, M. (2018). Mapping soilmoisturewith the OPtical TRApezoid Model (OPTRAM) based on long-term MODIS observations. Remote Sens. Environ. 211, 425–440.
Basirat, M, and Mousavi, S. M. (2022). Effect of Foliar Application of Silicon and Salicylic Acid on Regulation of Yield and Nutritional Responses of Greenhouse Cucumber Under High Temperature. Journal of Plant Growth Regulation, 1-11
Basirat, M., Mousavi, S. M. and Abbaspour, M.(2022). Evaluation of the Interaction of Potassium Salicylate and Potassium Silicate on Yield, Nutritional Status, and Quality of Greenhouse Cucumber under Cold Stress Condition. Iranian Journal of Soil Research, 35(3): 287-301.
Basirat, M., Mousavi, S. M., Abbaszadeh, S., Ebrahimi, M, and Zarebanadkouki, M. (2019). The rhizosheath: a potential root trait helping plants to tolerate drought stress. Plant and Soil, 445(1), 565-575.
Bayat, H., Ebrahimzadeh, G. amd Mohanty, B. P. (2021). Investigating the capability of estimating soil thermal conductivity using topographical attributes for the Southern Great Plains, USA. Soil and Tillage Research, 206, 104811.
Bayat, H., Sedaghat, A., Sinegani, A. A. S. and Gregory, A. S. (2015). Investigating the relationship between unsaturated hydraulic conductivity curve and confined compression curve. Journal of Hydrology, 522, 353-368.
Berry, W.D. (1993) Understanding Regression Assumptions. Sage Publications, London.
Bouma J. (1989). Using soil survey data for qualitative land evaluation, Advances in Soil Science, 9: 177-213.
Bousbih, S., Zribi, M., El Hajj, M., Baghdadi, N., Lili-Chabaane, Z., Gao, Q. and Fanise, P. (2018). Soil moisture and irrigation mapping in a semi-arid region, based on the synergetic use of Sentinel-1 and Sentinel-2 data. Remote Sensing 10, 1953.
Douaoui E. K., Nicolasb H. and Walter, C. (2006). Detecting Salinity Hazards within a Semiarid Context by Means of Combining Soil and Remote-Sensing Data, Geoderma, Vol. 134, No. 1-2, pp. 217-230.
Escorihuela, M. J. and Quintana-Seguí, P. (2016). Comparison of remote sensing and simulated soil moisture datasets in Mediterranean landscapes. Remote sening of environment, 180, 99-114.‏
Gardner, W. H. (1986). Water content. Methods of Soil Analysis: Part 1 Physical and Mineralogical Methods, 5, 493-544.
Ghanbarian-Alavijeh, B. and Millán, H.A. (2010). Point pedotransfer functions for estimating soil water retention curve. International Agrophysics. 24(3), 243-251.
Gee, G. W. and Or, D. (2002) 2.4 Particle-size analysis. Methods of soil analysis. Part, 4(598), 255-293.
Gill, M., Kemblowski, M.W. and McKee, M. (2007). Soil moisture data assimilation using support vector machines and ensemble Kalman filter 1. JAWRA Journal of the American Water Resources Association. 43, 1004-1015.
Gopinathan, K.K. (1988). A general formula for computing the coefficients of the correlation connecting global solar radiation to sunshine duration. Solar energy. 41, 499-502.
Grossman, R. B. and Reinsch, T. G. (2002). 2.1 Bulk density and linear extensibility.Methods of soil analysis: Part 4 physical methods, 5, 201-228.‏
Hagan, M.T.; Demuth, H.B. and Beale, M.H. (1996). Neural Network. Design PWS Publishing Co.
 Holtgrave, A.K., Förster, M., Greifeneder, F., Notarnicola, C. and Kleinschmit, B. (2018). Estimation of soil moisture in vegetation-covered floodplains with Sentinel-1 SAR data using support vector regression. PFG–Journal of Photogrammetry, Remote Sensing and Geoinformation Science 86, 85–101.
Hocking, R.R. (2013). Methods and Applications of Linear Models: Regression and the Analysis Of Variance. John Wiley & Sons.
Hwang, SIl., Kwang, PL., Dong, SL. and Susan, EP. (2002). Models for estimating soil particle-size distributions. Soil Science Society of America Journal. 66:1143–1150.
Keskin, H., Grunwald, S. and Harris, W. G. (2019). Digital mapping of soil carbon fractions with machine learning. Geoderma 339, 40-58.
Lafdani, E. K., Nia, A. M. and Ahmadi, A. (2013). Daily suspended sediment load prediction using artificial neural networks and support vector machines. Journal of Hydrology, 478, 50-62.
Luo, W., Xu, X., Liu, W., Liu, M., Li, Z., Peng, T., Xu, Ch., Zhang, Y. and Zhang, R. (2019). UAV based soil moisture remote sensing in a karst mountainous catchment. Catena, 174, 478-489.‏
Mandal, U.K. (2016). SPECTRAL COLOR INDICES BASED GEOSPATIAL MODELING OF SOIL ORGANIC MATTER IN CHITWAN DISTRICT, NEPAL. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences, 41.
McLean, E. (1983). Soil pH and lime requirement. Methods of soil analysis: Part 2 Chemical and microbiological properties. 9:199-224.
Moreira de Melo, T. and Pedrollo, O. C. (2015). Artificial Neural Networks for Estimating Soil Water Retention Curve Using Fitted and Measured Data. Applied and Environmental Soil Science. 1-16.
Mousavi, S. M., Srivastava, A. K. and Cheraghi, M. (2022). Soil health and crop response of biochar: an updated analysis. Archives of Agronomy and Soil Science, 1-26
Nelson, D., and Sommers, L.E. (1983). Total carbon, organic carbon, and organic matter. Methods of soil analysis: Part 2 chemical and microbiological properties. 9:539-579.
Noroozi Angnaei, A., Khalafi Khatbasra, M.J. and Karimi Sorand, M. (2017). Investigation the performance of data-based methods in estimating the important moisture points in Shahroud region. Journal of Irrigation Sciences and Engineering, 29-44. (In Farsi)
Picton, P. ( 2000) Neural Networks, 2nd edn. Palgrave, New York.
Rhoades, J. (1996). Salinity: Electrical conductivity and total dissolved solids. Methods of soil analysis: Part 3 Chemical methods. 5:417-435
Rastgou, M., Bayat, H., Mansoorizadeh, M., Gregory, A. S. and Agriculture, E. i. (2020). Estimating the soil water retention curve: Comparison of multiple nonlinear regression approach and random forest data mining technique. Computers and Electronics in Agriculture, 174, 105502.
Rosenbaum, U., Bogena, H.R., Herbst, M., Huisman, J.A., Peterson, T.J., Weuthen, A., Western, A. W. and vereecken, H. (2012). Seasonal and event dynamics of spatial soil moisture patterns at the small catchment scale, water Resources Research, Vol. 48, W10544: 1-22.
Sadeghi, M., Babaeian, E., Tuller, M. and Jones, S. B. (2017). The optical trapezoid model: A novel approach to remote sensing of soil moisture applied to Sentinel-2 and Landsat-8 observations. Remote sensing of environment, 198, 52-68.
Santra, P., Kumar, M., Kumawat, R. N., Painuli, D. K., Hati, K. M., Heuvelink, G. B. M. and Batjes, N. H. (2018). Pedotransfer functions to estimate soil water content at field capacity and permanent wilting point in hot Arid Western India. Journal of Earth System Science, 127(3), 1-16.
Sayão, V.M., Demattê, J.A., Bedin, L.G., Nanni, M.R. and Rizzo, R. (2018). Satellite land surface temperature and reflectance related with soil attributes. Geoderma 325, 125–140.
Sedaghat, A., Bayat, H., and Sinegani, A. S. (2016). Estimation of soil saturated hydraulic conductivity by artificial neural networks ensemble in smectitic soils. Eurasian Soil Science. 49, 347-357.
Seo, S. (2006) A review and comparison of methods for detecting outliers in univariate data sets, Thesis for Master of Science in Field of Public Health University of Pittsburgh, (pp. 1-59).
Sims, D. A., and Gamon, J. A. (2003). Estimation of Vegetation Water Content and Photosynthetic Tissue Area from Spectral Reflectance: A Comparison of Indices Based on Liquid Water and Chlorophyll Absorption Features. Remote Sensing of Environment 84: 526–537.
Singh, A., Haghverdi, A., Öztürk, H.S. and Durner, W. (2020). Developing Pseudo Continuous Pedotransfer Functions for International Soils Measured with the Evaporation Method and the HYPROP System: I. The Soil Water Retention Curve. Water, 12(12), 3425.
Shanani Hoveyzeh, S.M., and Heidar, Z. (2015). Investigation of Land Use Changes During the Past Two Last Decades (Case Study: Abolabas Basin), Journal of Watershed Management Research, 7: 237-234, (In Farsi).
Small, E.E. and Kurc, S. (2001). The influence of soil moisture on the surface energy balance in semiarid environments (pp. 318): New Mexico Water Resources Research Institute, New Mexico State University.
Soleimani, M., Kafi, M., Ziaei, M., Shabahang, J. and Davari, K. (2008). The influence of drought stress on the quantitative and qualitative properties of seeds of two native halofit plants of kochia under irrigation with saline water. Journal of Agricultural Sciences and Natural Resources. 15 (5), (In Farsi).
Souza, E. d., Fernandes, E. I., Schaefer, C. E. G. R., Batjes, N. H., Santos, G. R. d. and Pontes, L. M. (2016). Pedotransfer functions to estimate bulk density from soil properties and environmental covariates: Rio Doce basin.  73, 525-534.
Petropoulos, G.P., Knorr, W., Scholze, M., Boschetti, L., and Karantounias, G. (2010). Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective postfire assessment: a case study from the Greek wild land fires of 2007. Natural hazards and earth system sciences, 10: 305-317.
Sun, ZJ., Young, G.D., McFarlane, R. and Chambers, B.M. (2000). The effect of soil electrical conductivity on moisture determination using time domain- reflectometry in sandy soil.Canadian Journal of Soil Science 80(1): 13–22.
Szabó, B., Szatmári, G., Takács, K., Laborczi, A., Makó, A., Rajkai, K. and Pásztor, L. (2019). Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics. Hydrology and Earth System Sciences, 23(6), 2615-2635.
Tietje, O. and Hennings, V. (1996). Accuracy of the saturated hydraulic conductivity prediction by pedo-transfer functions compared to the variability within FAO textural classes. Geoderma 69, 71-84.
Twarakavi, N.K., Simůnek, J. and Schaap, M. (2009). Development of pedotransfer functions for estimation of soil hydraulic parameters using support vector machines. Soil Science Society of America Journal. 73, 1443–1452.
Ungaro, F., Calzolari, C. and Busoni, E. (2005). Development of pedotransfer functions using a group method of data handling for the soil of the Pianura Padano-Veneta region of North Italy: water retention properties. Geoderma 124, 293–317.
Vapnik, V.N. (2000) The nature of statistical learning theory, ser. Statistics for engineering and information science, vol 21. Springer, New York, (pp 1003–1008).
Xia, L., Song, X., Leng, P., Wang, Y., Hao, Y. and Wang, Y. (2019). A comparison of two methods for estimating surface soil moisture based on the triangle model using optical/thermal infrared remote sensing over the source area of the Yellow River. International Journal of Remote Sensing, 40(5-6), 2120-2137.
Zhang, N., Hong, Y., Qin, Q. and Liu, L. (2013). VSDI: a visible and shortwave infrared drought index for monitoring soil and vegetation moisture based on optical remote sensing .International journal of remote sensing. 34 (13), 4585–4609.
Zhao, Y., Peth, S., Wang, X. Y., Lin, H. and Horn, R. (2010). Controls of surface soil moisture spatial patterns and their temporal stability in a semi‐arid steppe. Hydrological Processes, 24(18), 2507-2519.