تهیه نقشه رقومی اجزاء بافت خاک با استفاده از مدل‌‌ ترکیبی رگرسیون کریجینگ و کریجینگ باقی‌مانده شبکه عصبی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 بخش تحقیقات فنی و مهندسی مرکز تحقیقات وآموزش کشاورزی و منابع طبیعی سیستان، زابل

2 بخش تحقیقات خاک و آب، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی گلستان. سازمان تحقیقات، آموزش و ترویج کشاورزی

3 دانشیار گروه مهندسی آب دانشگاه زابل

10.22092/ijsr.2025.367274.763

چکیده

هدف از انجام این پژوهش تهیه نقشه رقومی اجزاء بافت خاک اراضی کشاورزی دشت سیستان با وسعت 1300 کیلومترمربع با استفاده از مدل‌های رگرسیون کریجینگ و مدل ترکیبی رگرسیون‌کریجینگ و کریجینگ باقی‌مانده شبکه عصبی‌مصنوعی (RKNNRK)می‌باشد. برای این منظور تعداد 160 نمونه لایه‌سطحی (cm30-0) از سری‌های مختلف خاک گرفته شد و درصد اجزاء بافت خاک در آزمایشگاه اندازه گیری گردید. با توجه به این که بافت خاک یک داده مرکب است، وقتی اجزاء آن جداگانه تخمین زده می‌شوند تضمینی برای اینکه جمع سه جزء برابر 100 شود وجود ندارد، از این‌رو قبل از مدل‌سازی، اجزء بافت خاک با استفاده از تابع لگاریتمی (alr) تبدیل شدند. از تصاویر باندهای 1 تا 8 ماهواره لندست 8 و شاخص‌های پوشش گیاهی، روشنایی، درصد رس و اندازه ذرات خاک به عنوان متغیر‌های کمکی برای درون‌یابی اجزاء بافت خاک استفاده گردید. 80 درصد داده‌ها برای پیش‌بینی و 20 درصد برای اعتبارسنجی اختصاص یافت. نتایج نشان داد که جزء رس خاک هم‌بستگی مکانی متوسط و اجزاء سیلت و شن خاک ساختار مکانی قوی دارند. مدل نمایی بیشترین انطباق را با نیم‌تغییرنمای تجربی با هر سه جزء شن، سیلت و رس خاک و اجزاء تبدیل شده بافت خاک شاملSiltalr و Clayalr دارد. همچنین داده‌های Siltalr و Clayalr نیز از هم‌بستگی مکانی قوی در منطقه مورد مطالعه برخوردار بودند. نتایج نشان داد که روش RKNNRK با آماره RMSE برابر 04/15، 30/14 و 18/7 به ترتیب برای اجزاء شن، سیلت و رس خاک دقت بالاتری در پیش بینی اجزاء بافت خاک در مقایسه با مدل رگرسیون کریجینگ داشت. بطوریکه این مقادیر به ترتیب 10، 6/10 و 5/3 درصد نسبت به مقادیر متناظر آن در روش رگرسیون کریجینگ کاهش دارد. بنابراین روش RKNNRK در تلفیق با داده‌های سنجش از دور بر دقت پیش‌بینی نقشه‌های رقومی اجزاء بافت خاک افزوده است و به‌عنوان یک روش مناسب قابل توصیه می‌باشد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Digital mapping of soil texture fractions using regression kriging and neural network residual kriging model

نویسندگان [English]

  • mohammad shahriari 1
  • mohammad reza pahlavan rad 2
  • masooume delbari 3
  • peyman afrasiab 3
1 Researcher, Agricultural Engineering Research Department, Agricultural and Natural Resources Research and Education Center, AREEO, Zabol, Iran.
2 Soil and Water Research Department, Golestan Agricultural and Natural Resources Research and Education Center, AREEO, Gorgan, Iran
3 Associate Professor of Irrigation and Drainage Engineering Department of Water Engineering Faculty of Water and Soil University of Zabol, Iran
چکیده [English]

The aim of this study was to predict Digital mapping of soil texture fractions in Sistan flood plain of agiculture land at a regional scale (area 1300 km2). A regression kriging (RK) with neural network residual kriging (RKNNRK) was used to examine the relation between auxiliary variables and the soil texture components. Soil texture fractions including percentage of sand, silt and clay content were measured for 160 soil samples collected from surface layer (0-30 cm) of various soil series in agriculture land of Sistan plain. The additive log-ratio (alr) transformation was applied to transform texture components prior to prediction. Remotely sensed data including Landsat 8’s Band (1-8), Band 8 and Band 4/ Band 8, Band 4/ Band 3, NDVI index, brightness index, clay index, grain size index (GSI) were used as auxiliary variables for interpolation of soil texture fractions. 80 % of data was used for prediction and 20 % of data was used for validation, and RMSE, ME and MAE were used for evaluation. Result shows the values of RMSE of estimating percentage of sand, silt and clay at validation sites using RKNNRK method were 15.04, 14.30 and 7.18 %, respectively that the values of RMSE of estimation by a RK model were 10, 10.6 and 3.5 % higher than those obtained by RKNNRK model. Both siltalr and clayalr show a strong exponential-type spatial correlation. A strong spatial correlation is seen for siltalr and clayalr. The residuals follow an exponential model of spatial structure for RK, and a spherical structure for RKNNRK. So, RKNNRK model have higher accuracy when combined by remotely sensed data and it is a suitable method for mapping soil texture fractions in flood plain at regional scale.

کلیدواژه‌ها [English]

  • Auxiliary Variables
  • Neural Network Residual Kriging
  • Remote Sensing
  • Soil Texture Fraction
  • Spatial Variation
  • Regression Kriging

مراجع

  1. Aitchison, J., 1986. The Statistical Analysis of Compositional Data. Chapman and Hall, London, UK, pp. 416.
  2. Akpa, S.I.C., Odeh, I.O.A., Bishop, T.F.A., Hartemink, A.E., 2014. Digital mapping of soil particle size fractions for Nigeria. Soil Sci. Soc. Am. J. 78, 1953–1966.
  3. Azizi, K., Garosi, Y., Ayoubi, S., and Tajik, S. 2023. Integration of Sentinel-1/2 and topographic attributes to predict the spatial distribution of soil texture fractions in some agricultural soils of western Iran. Soil Tillage Res. 229, 105681.
  4. Amirian-Chakan, A., Minasny, B., Taghizadeh-Mehrjardi, R., Akbarifazli, R., Darvishpasand, Z., Khordehbin, S., Some practical aspects of predicting texture data in digital soil mapping.
  5. Ben-Dor, E., Taylor, R.G., Hill, J., Demattê, J.A.M., Whiting, M.L., Chabrillat, S., Sommer, S., Donald, L.S., 2008. Imaging spectrometry for soil applications. Adv. Agron. 97, 321–392.
  6. Boettinger, J.L., Ramsey, R.D., Bodily, J.M., Cole, N.J., Kienast_Brown, S., Nield, S.J., Saundes, A.M., Stum, A.K., 2008. Landsat spectral data for digital soil mapping. In: Hartemink, A.E., McBratney, A.B., Mendonca Santos, M.L. (Eds.), Digital Soil MappingWith Limited Data. Springer science, Australia, pp. 193–203.
  7. Carvalho Junior, W., Lagacherie, P., Chagas, C.S., Calderano Filho, B., Bhering, S.B., 2014. A regional-scale assessment of digital mapping of soil attributes in a tropical hillslope environment. Geoderma 232, 479–486.
  8. Chagas, C.S., Junior, W.C., Bhering, S.B and Filho, B.C. 2016. Spatial prediction of soil surface texture in a semiarid region using random forest and multiple linear regressions. Catena, 139: 232–240
  9. Dobarco, M.R., Orton, T.G., Arrouays, D., Lemercier, B., Paroissien, J.B., Walter, C., Saby, N.P., 2016. Prediction of soil texture using descriptive statistics and area-to-point kriging in Region Centre (France). Geoderma Regional, 7, 279-292.
  10. Dai, F., Zhou, Q., Lv, Z., Wang, X., Liu, G., 2014. Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau, Ecological Indicators, 45, 184–194.
  11. Dhiman, G., Bhattacharya, J., and Roy, S. 2023. Soil textures and nutrients estimation using remote sensing data in north India - Punjab region. Procedia Comput. Sci. 218, 2041–2048.
  12. Dornik, A., Cheţan, M. A., Drăguţ, L., Dicu, D. D., and Iliuţă, A. (2022). Optimal scaling of predictors for digital mapping of soil properties. Geoderma 405, 115453.
  13. Dunkl, I., Ließ, M. 2022. On the benefits of clustering approaches in digital soil mapping: An application example concerning soil texture regionalization. 8, 541–558.
  14. 2022. The state of the world’s land and water resources for food and agriculture 2021 – systems at breaking point. Rome, Italy: FAO.
  15. He, W., Xiao, Z., Lu, Q., Wei, , Liu, X. Digital Mapping of Soil Particle Size Fractions in the Loess Plateau, China, Using Environmental Variables and Multivariate Random Forest. Remote Sens. 2024, 16, 785.
  16. Huang, J., Subasinghe, R., Triantafilis, J., 2014. Mapping particle-size fractions as a composition using additive log-ratio transformation and ancillary data. Soil Science Society of America Journal 78 (6), 1967–
  17. Islam, K., Singh, B., McBratney, A., 2003. Simultaneous estimation of several soil propertiesby ultra-violet, visible, and near infrared reflectance spectroscopy. Aust. J. Soil Res. 41, 1101–1114.
  18. Keshavarzi, A., del Árbol, M. Á. S., Kaya, F., Gyasi-Agyei, Y., and Rodrigo-Comino, J. 2022. Digital mapping of soil texture classes for efficient land management in the Piedmont plain of Iran. Soil Use Manag. 38 (4), 1705–1735.
  19. Lark, R.M., Bishop, T.F.A., 2007. Cokriging particle size fractions of the soil. Eur. J. Soil 58, 763–774.
  20. Liao, K., Xu, S., Wu, J., Zhu, Q., 2013. Spatial estimation of surface soil texture using remote sensing data. Soil Sci. Plant Nutr. 59, 488–500.
  21. Li, Q., Hu, Z., Zhang, F., Song, D., Liang, Y., and Yu, Y. 2023. Multispectral remote sensing monitoring of soil particle-size distribution in arid and semi-arid mining areas in the middle and upper reaches of the yellow river basin: a case study of wuhai city, Inner Mongolia autonomous region. Remote Sens. 15 (8), 2137.
  22. Mgohele R.N., Massawe B.H.J., Shitindi M.J., Sanga HG and Omar M.M. 2024. Prediction of soil texture using remote sensing data. A systematic review. Remote Sens. 5:1461537.
  23. Mirzaee, S.; Ghorbani-Dashtaki, S.; Mohammadi, J.; Asadi, H.; Asadzadeh, F. Spatial variability of soil organic matter using remote sensing data. Catena 2016, 145, 118–127.
  24. Odeh, I.O., Todd, A.J., Triantafilis, J., 2003. Spatial prediction of soil particle-size fractions as compositional data. Soil Sci. 168, 501–
  25. Mallah, S., Delsouz Khaki, B., Davatgar, N., Scholten, T., Amirian-Chakan, A., Emadi, M., et al. (2022). Predicting soil textural classes using random forest models: learning from imbalanced dataset. Agronomy 12 (Issue 11), 2613.
  26. Padarian, J., Pérez-Quesada, J. and Seguel, O., 2012. Modelling the distribution of organic carbon in the soils of Chile. In: Minasny B, Malone BP, McBratney AB (eds), Digital Soil Assessments and Beyond Proceedings of the 5th Global Workshop on Digital Soil Mapping Taylor and Francis Group, London, pp 329–333
  27. Pahlavan-Rad, M.R., K.H. Dahmardeh, M. Hadizadeh, G. Keykha, N. Mohammadnia, M. Gangali, M. Keikha, N. Davatgar, C. Brungard. 2020. Prediction of soil water infitration using multiple linear regression and random forest in a dry flod plain, eastern Iran. Catena, 194(2020) 104715
  28. 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–
  29. Poggio, L., Gimona, A. 3D mapping of soil texture in Scotland. Geoderma Reg. 2017, 9, 5–16.
  30. Robertson, G.P. 2000. GS+: Geostatistics for the environment sciences. GS+ User´s Guide Version 5: Plainwell, Gamma design software, 200 p.
  31. Song, Y.Q., yang, L.A., li, B., Hu, Y.M., wang, A.L., Zho, W., Cui, X.S. and liu, Y.L., 2017. Spatial Prediction of Soil Organic Matter Using a Hybrid Geostatistical Model of an Extreme Learning Machine and Ordinary Kriging. Sustainability, 754, 1-17
  32. Tarasov, D.A., Buevich, A.G., Sergeev, A.P., Shichkin, A.V., 2017. High variation topsoil pollution forecasting in the Russian Subarctic: Using artificial neural networks combined with residual kriging, Applied Geochemistry, xxx, 1-10
  33. Vaudour, E., Gomez, C., Fouad, Y., Lagacherie, P. Sentinel-2 image capacities to predict common topsoil properties of temperate and Mediterranean agroecosystems. Remote Sens. Environ. 2019, 223, 21–33.
  34. Wang, Z., Shi, W., 2017. Mapping soil particle-size fractions: a comparison of compositional kriging and log-ratio kriging. J. Hydrol. 546, 526–
  35. Wu, W., Yang, Q., Lv, J., Li, A., Liu, H. Investigation of remote sensing imageries for identifying soil texture classes using classification methods. IEEE Trans. Geosci. Remote Sens. 2019, 57, 1653–1663.
  36. Xiao, J., Shen, Y., Tateishi, R., Bayaer, W., 2006. Development of topsoil grain size index for monitoring desertification in arid land using remote sensing. Int. J. Remote Sens. 12, 2411–2422.
  37. Zeraatpisheh, M., Ayoubi, S., Jafari, A., Tajik, S., and Finke, P. 2019. Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma 338, 445–452.
  38. Zhang, SW., Shen, C.Y., Chen, X.Y., Ye, H.C., Huang, Y.F. and Lai, S. 2013. Spatial Interpolation of Soil Texture Using Compositional Kriging and Regression Kriging with Consideration of the Characteristics of Compositional Data and Environment Variables. Journal of Integrative Agriculture, 12(9): 1673-1683.
  39. Zheng, M., Wang, X., Li, S., Zhu, B., Hou, J., Song, K. Soil Texture Mapping in Songnen Plain of China Using Sentinel-2 Imagery. Remote 2023, 15, 5351.
  40. Zhou, Y., Wu, W., Liu, H. Exploring the Influencing Factors in Identifying Soil Texture Classes Using Multitemporal Landsat-8 and Sentinel-2 Data. Remote Sens. 2022, 14,

 

 

پژوهش های خاک
دوره 38، شماره 4
اسفند 1403
صفحه 395-414

فایل ها

هم رسانی

ارجاع به این مقاله

آمار