نقشه‌برداری رقومی اجزا بافت خاک در بخشی از اراضی دشت خوزستان با استفاده از برخی مدل‌های یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم و مهندسی خاک، دانشکده کشاورزی،دانشگاه شهید چمران اهواز، خوزستان، ایران

2 هیات علمی گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه شهید چمران اهواز- خوزستان، ایران

3 عضو هیئت علمی گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه شهید چمران اهواز، خوزستان، ایران

چکیده

مطالعه حاضر با هدف ارزیابی و مقایسه کارائی مدل‌های ماشین بردار پشتیبان (SVM) و جنگل تصادفی (RF) با استفاده از رویکرد نقشه‌برداری رقومی خاک (DSM) برای پیش‌بینی اجزا بافت خاک در بخشی از اراضی استان خوزستان انجام شد. در بهمن سال 1399، به‌منظور تعیین بافت خاک، 200 نمونه از خاک سطحی (عمق 10-0 سانتی متری) به صورت تصادفی طبقه‌بندی شده جمع‌آوری شدند. متغیرهای کمکی شامل مشتقات اولیه و ثانویه مدل رقومی ارتفاع (DEM) شامل (شیب، جهت شیب، شاخص شبکه آبراهه‌ای و ...) و شاخص‌های طیفی و گیاهی سنجش از دور (RS) بودند که انتخاب دسته مناسب از آنها با استفاده از روش تجزیه مولفه‌های اصلی (PCA) انجام گرفت. بر اساس روش PCA، نه متغیر توپوگرافی از DEM و هشت شاخص پوشش گیاهی از RS برای پیش‌بینی اجزا بافت خاک (شن، سیلت و رس) انتخاب گردیدند. کارایی مدل‌ها با استفاده از آماره‌های ضریب تبیین (R2) و ریشه‌ی میانگین مربعات خطا (RMSE) مورد ارزیابی قرار گرفت. نتایج نشان داد مدل جنگل تصادفی از دقت بالاتر و خطا کمتری نسبت به مدل ماشین بردار پشتیبان (SVM) برخوردار است، به‌طوری‌که میزان R2 در این مدل برای شن 80/0، سیلت 81/0 و رس 78/0 و ریشه‌ی میانگین مربعات خطا (RMSE) در پیش‌بینی این ذرات به ترتیب 02/6، 89/5 و 02/6 بود. این درحالی است که R2 و RMSE در مدل ماشین بردار پشتیبان به ترتیب برای شن 39/0 و 70/13، سیلت 45/0 و 70/10 و رس46/0 و 32/9 بود. همچنین اهمیت نسبی متغیرهای استفاد شده در پیش‌بینی اجزای بافت خاک نشان داد شاخص شوری، شاخص روشنایی و شبکه آبراهه‌ای به همراه باند 6 ماهواره لندست 8 مهم‌ترین متغیرهای محیطی پیش‌بینی کننده ذرات رس، سیلت و ماسه بودند. بنابراین پیشنهاد می‌شود از مدل جنگل تصادفی به عنوان روشی مفید و قابل اعتماد در تهیه نقشه‌های رقومی بافت خاک در منطقه مورد مطالعه استفاده شود.

کلیدواژه‌ها

عنوان مقاله [English]

Digital mapping of soil texture components in part of Khuzestan plain lands using machine learning models

نویسندگان [English]

  • Nasim Sahraei 1
  • Ahmad Landi 2
  • Saeid Hojati 3
1 Department of Soil Science and Engineering, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Khuzestan, Iran
2 Professor at Department of Soil Science, Faculy of Agriculture, Shahid Chamran University of Ahvaz, Khuzestan, Iran
3 Associate Professor, Department of Soil Science, College of Agriculture, Shahid Chamran University of Ahvaz
چکیده [English]

This study aims to evaluate and to compare the efficiency of support vector machine (SVM) and random forest (RF) models using digital soil mapping approach to predict soil texture in part of Khuzestan province. In February 2021, before determining soil texture, 200 soil samples were taken using stratified random sampling from the surface layer )0-10 cm(. Auxiliary variables included primary and secondary derivatives of digital elevation model (DEM), remote sensing spectral indices (RS), from which the appropriate category was selected using principal component analysis (PCA). Based on PCA method, nine topographic variables from DEM and eight vegetation indices and spectra from RS were selected to predict soils texture components (sand, silt, and clay). The efficiency of the models was evaluated using the coefficient of determination (R2) and the root mean squared of the error (RMSE). The results indicated that the random forest model had higher accuracy and less error than the support vector machine model (SVM), so that values of R2 in this model were 0.80 for sand, 0.81 for silt, and 0.78 for clay, and the RMSE in the prediction of these particles were 6.02, 5.89 and 6.02, respectively. While the R2 and RMSE in the support vector machine model for prediction of sand, silt and clay were (0.39, 13.70), (0.45, 10.70), and (0.46, 9.32), respectively. Also, the results of this evaluation showed that salinity index, brightness index, and channel network in addition of the 6-band Landsat 8 satellite or the far infrared band were the most important environmental variables predicting clay, silt, and sand particles. In conclusion, we suggest using Random Forest model as a useful and reliable method in preparing digital maps of soil texture in the study area.

کلیدواژه‌ها [English]

  • Spatial Modeling
  • Remote Sensing
  • Soil Texture
  • Support Vector Machine
  • Random Forest

مراجع

Abyat A, Azhdari A, Jodaki M, Darvishi Khatoni J., (2017). Study and separation of Quaternary sedimentary environments in Khuzestan plain, Iranian Journal of Advanced Applied Geology, 7(3), 49-64 (In Persian with English Abstract).
Bagheri Bodaghabadi, M., Antonio Martinez-Casasnovas, J., Salehi, M. H., Mohammadi, J., Esfandiarpoor Borujeni, I., Toomanian, N., & Gandomkar, A.,(2015). Digital soil mapping using artificial neural networks and terrain-related attributes. Pedosphere, 25, 580–591.
Bannai, M.H., (1998). Soil moisture and temperature map, Soil and Water Research Institute of Iran.
Bousbih, S., Zribi, M., Pelletier, C., Gorrab, A., Lili-Chabaane, Z., Baghdadi, N., Ben Aissa, N., & Mougenot, B., (2019). Soil texture estimation using radar and optical data from sentinel-1 and sentinel-2. Remote Sensing, 11, 1520.
Brown, D.J., & Shepherd K.D., Walsh M.G., Mays M.D., and Reinsch, T.G., (2006). Global soil characterization with VNIR diffuse reflectance spectroscopy. Geoderma, 132(3-4), 273-290.
Camera, C., Zomeni, Z., Noller, J. S., Zissimos, A. M., Christoforou, I. C., & Bruggeman, A., (2017). A high resolution map of soil types and physical properties for Cyprus: A digital soil mapping optimization. Geoderma, 285, 35–49.
Castaldi, F.; Palombo, A.; Santini, F.; Pascucci, S.; Pignatti, S.; Casa, R., (2016). Evaluation of the potential of the current and forthcoming multispectral and hyperspectral imagers to estimate soil texture and organic carbon. Remote Sensing. Environment, 179, 54–65.
Conrad, O., Bechtel, B., Bock, M., Dietrich, H., Fischer, E., Gerlitz, L., Wehberg, J., Wichmann, V., Bohner, ¨ J., (2015). System for Automated Geoscientific analyses (SAGA) v. 2.1.4. Geosci. Model Dev. 8, 1991–2007.
Dharumarajan S, Hegde R., (2022). Digital mapping of soil texture classes using Random Forest classification algorithm. Soil Use Manage 38:135–149.
Douaoui, A.E.K., Nicolas, H., Walter, C., (2006). Detecting salinity hazards within a semiarid context by means of combining soil and remote-sensing data. Geoderma 134, 217–230.
Foody, G.M., Cutler, M.E., McMorrow, J., Pelz, D., Tangki, H., Boyd, D.S., Douglas, I., (2001). Mapping the biomass of Bornean tropical rain forest from remotely sensed data. Glob. Ecol. Biogeogr. 10, 379–387.
Friedman, J.H., Meulman, J.J., (2003). Multiple additive regression trees with application in epidemiology. Stat. Med. 22 (9), 1365–1381.
Gomez, C., Dharumarajan, S., Féret, J. B., Lagacherie, P., Ruiz, L., & Sekhar, M., (2019). Use of Sentinel-2 time-series images for classification and uncertainty analysis of inherent biophysical property: Case of soil texture mapping. Remote Sensing, 11, 565.
Gomez, C.; Adeline, K.; Bacha, S.; Driessen, B.; Gorretta, N.; Lagacherie, P.; Roger, J.M.; Briottet, X., (2018). Sensitivity of clay content prediction to spectral configuration of VNIR/SWIR imaging data, from multispectral to hyperspectral scenarios. Remote Sensing. Environment, 204, 18–30.
Grinand, C., Arrouays, D., Laroche, B., Martin, M.P., (2008). Extrapolating regional soil land-scapes from an existing soil map: sampling intensity, validation procedures and integration of spatial context. Geoderma 143, 180–190.
Hengl, T., de Jesus, J. M., Heuvelink, G. B. M., Gonzalez, M. R., Kilibarda, M., Blagotic, A., Shangguan, W., Wright, M. N., Geng, X., Bauer-Marschallinger, B., Guevara, M. A., Vargas, R., MacMillan, R. A., Batjes, N. H., Leenaars, J. G. B., Ribeiro, E., Wheeler, I., Mantel, S., & Kempen, B. , (2017). Soil grids 250m: Global gridded soil information based on machine learning. PLoS One, 12, e0169748.
Heung, B., Ho, H. C., Zhang, J., Knudby, A., Bulmer, C. E., and Schmidt, M. G., (2016): An overview and comparison of machine-15learning techniques for classification purposes in digital soil mapping, Geoderma, 265, 62-77.
Khaledian, Y., & Miller, B.A., (2020). Selecting appropriate machine learning methods for digital soil mapping. Applied Mathematical Modelling, 81, 401–418.
Khan, N.M., Rastoskuev, V.V., Sato, Y., Shiozawa, S., (2005). Assessment of hydrosaline land degradation by using a simple approach of remote sensing indicators. Agric. Water Manag. 77, 96–109.
Li, Q., Meng, Q., Cai, J., Yoshino H., and Mochida, A., (2009). Applying support vector machine to predict hourly cooling load in the building. Applied Energy. 86: 2249-2256
Liao, K., Xu, S., Wu, J., & Zhu, Q., (2013). Spatial estimation of surface soil texture using remote sensing data. Soil Science Plant Nutrient, 59(4), 488–500.
McBratney, A. B., Mendonça-Santos, M. L., & Minasny, B., (2003). On digital soil mapping. Geoderma, 117, 3–52.
Mehrabi-Gohari, E., Matinfar, H. R., Jafari, A., Taghizadeh-Mehrjardi, R., & Triantafilis, J., (2019). The spatial prediction of soil texture fractions in arid regions of Iran. Soil System, 3(4), 65.
Momtaz, H. R., A. A. Jafarzadah, H. Torabi, S. Oustan, A. Samadi, N. Davatgar and R. J. Gilkes., (2009). An assessment of the variation in soil properties within and between landforms in Amol region, Iran. Geoderma 149: 10-18.
Mountrakis, G.; Im, J.; Ogole, C., (2011). Support vector machines in remote sensing: A review. ISPRS J. Photogramm. Remote Sensing, 66, 247–259.
Mousavi, S. R., Sarmadian, F., & Rahmani, A., (2020). Modeling and Prediction of Soil Classes Using Boosting Regression Tree and Random Forests Machine Learning Algorithms in Some Part of Qazvin Plain. Iranian Journal of Soil and Water Research, 50(10), 2525-2538 (In Persian).
Okun, O., & Priisalu, H.; (2007). Random forest for gene expression based cancer classification: Overlooked issues. In J. Marti et al., (Eds.). Pattern recognition and image analysis: Third Iberian Conference, IbPRIA 2007, Girona, Spain. 6–8 June. Springer, Berlin. p. 483–490
Pahlavan-Rad, M.R., Akbarimoghaddam, A., (2018). Spatial variability of soil texture fractions and pH in a flood plain (case study from eastern Iran). Catena 160, 275–281
Parviz, L.; (2017). Evaluation the Preprocessing Effect of Satellite Images Input Parameters in to Artificial Neural Network for Soil Texture Determination. Iranian Journal of Applied Soil Research, 5(2), 66-80 (In Persian).
Ramcharan, A., Hengl, T., Nauman, T., Brungard, C., Waltman, S., Wills, S., & Thompson, J.; (2018). Soil property and class maps of the conterminous United States at 100-meter spatial resolution. Soil Science Society of America Journal, 82(1), 186–201.
Rondeaux, Geneviève, et al.; (1996).Optimization of Soil-Adjusted Vegetation Indices. Remote Sensing of Environment, vol. 55, no. 2, 95–107.
Taalab, K., Corstanje, R., Zawadzka, J., Mayr, T., Whelan, M. J., Hannam, J. A., & Creamer, R.; (2015). On the application of Bayesian networks in digital soil mapping. Geoderma, 259, 134–148.
Taghizadeh-Mehrjardi, R., Sarmadian, F., Minasny, B., Triantafilis, J., & Omid, M.; (2014). Digital mapping of soil classes using decision tree and auxiliary data in the Ardakan region, Iran. Arid Land Research and Management, 28, 147–168.
Taghizadeh-Mehrjardi, R., Toomanian, N., Khavaninzadeh, A. R., Jafari, A., & Triantafilis, J.; (2016). Predicting and mapping of soil particle-size fractions with adaptive neuro-fuzzy inference and ant colony optimization in central Iran. European Journal of Soil Science, 67, 707–725.
Taghizadeh-Mehrjardi, R., Mahdianpari, M., Mohammadimanesh, F., Behrens, T., Toomanian, N., Scholten, T., & Schmidt, K.; (2020). Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran. Geoderma, 376, 114552.
Vagen, T.G., Leigh, A., Winowiecki, L.A., Tondoh, J.E., Desta, L.T., Gumbricht, T., (2016). Mapping of soil properties and land degradation risk in Africa using MODIS re-flectance. Geoderma 263, 216–225
Vapnik, V.N. The Nature of Statistical Learning Theory; Springer-Verlag: Berlin/Heidelberg, Germany, (1995); Volume 8, ISBN 0387945598.
Wang, B., Waters, C., Origill, S., Gray, J., Cowie, A., Clark, A., Liu, D.L., (2018). High resolution mapping of soil organic carbon stocks using remote sensing variables in the semi-arid rangelands of eastern Australia. Science of the Total Environment. 630, 367–378.
Wilding, L.; (1985). Spatial variability: its documentation, accommodation and implication to soil surveys. pp. 166-194.
Wu, W., Li, A.-D., He, X.-H., Ma, R., Liu, H.-B., & Lv, J.-K.; (2018). A comparison of support vector machines, artificial neural network and classification tree for identifying soil texture classes in southwest China. Computers and Electronics in Agriculture, 144, 86–93.
Yang, R.M., Zhang, G.L., Liu, F., Lu, Y.Y., Yang, F., Yang, F., Yang, M., Zhao, Y.G., & Li, D.C.; (2016). Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem. Ecological Indices, 60, 870–878.
Zhang, M., & Shi, W.; (2019). Systematic comparison of five machine-learning methods in classification and interpolation of soil particle size fractions using different transformed data. Hydrology and Earth System Sciences Discussion; 2018-584
Zhang, Y., Sui, B., Shen, H., a nd Ouyang, L.; (2019). Mapping stocks of soil total nitrogen using remote sensing data, A comparison of random forest models with different predictors. Computers and Electronics in Agriculture, 160: 23-30
Zolfaghari, A. A., Yazdani, M. R., Khosravi. M. and Mahmoudi S. M.; (2019). Comparison of Different Data Mining Methods for Digital Mapping of Soil Particle-size Fractions in Lands of Semnan Plain. Iranian Journal of Soil and Water Research, 51(2), 375-385 (In Persian).
تحقیقات آب و خاک ایران
دوره 53، شماره 10
دی 1401
صفحه 2261-2276

فایل ها

هم رسانی

ارجاع به این مقاله

آمار