مقایسه روش‌های هوش مصنوعی و زمین آمار در پیش‌بینی شوری سطحی خاک در قرقری، هیرمند

پیری, حلیمه; مبارکی, مجتبی

doi:10.22034/jewe.2022.312194.1656

نوع مقاله : مقاله پژوهشی

نویسندگان

¹ استادیار، گروه مهندسی آب، دانشکده آب و خاک، دانشگاه زابل، زابل، ایران

² کارشناسی ارشد، گروه مهندسی آب، دانشکده آب و خاک، دانشگاه زابل، زابل، ایران

https://doi.org/10.22034/jewe.2022.312194.1656

چکیده

در ایـن پژوهش از روش زمینآمار و روشهای هوش مصنوعی شامل شبکه عصبی مصنوعی، درخت تصمیم و ماشین بردار پشتیبان برای پیشبینی شوری خاک اراضی قرقری شهرستان هیرمند استفاده شد. برای این منظور تعداد 130 نمونه خاک از عمق صفر تا cm 30 خاک برداشت شد. نمونههای برداشت‌شده به آزمایشگاه منتقل و هدایت الکتریکی با استفاده از دستگاه هدایتسنج اندازهگیری شد. مقادیر شوری خاک با استفاده از روش زمینآمار و روشهای هوش مصنوعی، برآورد شد. روشهای زمـینآمـاری و هوش مصنوعی برازش و بهترین مدل انتخاب و با استفاده از اعتبارسنجی مستقل دقت روشها باهم مقایسه شد. نتایج نشان داد روشهای هوش مصنوعی نسبت به روش زمینآمار شوری خاک را بهتر برآورد میکنند. بین روشهای هوش مصنوعی روش درخت تصمیم با توجه به ضریب تبیین 99/0 و آمارههای RMSE و MAE بهترتیب برابر 26/0 و 18/0 بهعنوان روش برتر انتخاب شد. نتایج روند شوری نشان داد شوری خاک منطقه از غرب به شرق ابتدا کاهش و سپس افزایش و از شمال به جنوب کاهش مییابد. بنابراین با توجه به نتایج برای حفظ محیطزیست منطقه، باید زمینه کاشت گونههای گیاهی سازگار با منطقه، منطبق با شوری خاک فراهم شود.

کلیدواژه‌ها

موضوعات

فیزیک و حفاظت خاک

عنوان مقاله [English]

Comparison of Artificial Intelligence and Geostatistical Methods in Soil Surface Salinity Prediction in Ghorghori, Hirmand

نویسندگان [English]

Halimeh Piri ¹
Mojtaba Mobaraki ²

¹ Assist. Professor, Department of Water Engineering, College of Water and Soil, University of Zabol, Zabol, Iran

² M. Sc. Alumni, Department of Water Engineering, College of Water and Soil, University of Zabol, Zabol, Iran

چکیده [English]

In this study, geostatistical methods and artificial intelligence models (artificial neural network, decision tree, and support vector machine) were used to simulate the soil salinity of Ghorghori lands in Hirmand city. A total of 130 soil samples were collected from 0-30 cm layers of the soil. The electrical conductivity of each sample was measured using an electrical conductivity device. Soil salinity values were estimated using Geostatistical methods and artificial intelligence methods. Geostatistical and artificial intelligence models were applied and the best model was selected; the accuracy of the methods was compared using independent validation. The results showed that the artificial intelligence methods outperformed the geostatistical method in estimating the soil salinity of the artificial intelligence methods, the decision tree model was the superior model due to its coefficient of determination of 0.99 and RMSE and MAE statistics of 0.26 and 0.18 respectively. The salinity trend showed that the salinity of the soil of the region decreases from west to east first and then increases and decreases from north to south. In order to preserve the environment of the region, the field of planting plant species compatible with the region should be provided in accordance with soil salinity.

کلیدواژه‌ها [English]

Decision Tree
Neural Network
Support Vector Machine
Zoning

مراجع

Ahmadi, A., Taranjozar, H. and Kazemi, A. (2019). Surface salinity zonation in saline lands of Bolagh Saveh using geostatistical methods. Nat. Environ. Hazard., 8(19), 1-14. [In Persian]

Ahmadi, Z., Abbasi Kloo, A., Shahabi, M. and Bouali, A. (2020). Comparison of decision tree methods and artificial neural network in predicting soil salinity in the west of Lake Urmia. Destruct. Rehabilit. Nat. Land., 1(1), 82-91 [In Persian].

Akramkhanov, A., Brus, D. J. and Walvoort, D. J. J. (2014). Geostatistical monitoring of soil salinity in Uzbekistan by repeated EMI surveys. Geoderm., 213, 600–607.

Amini, A., Kolahchi, A. A., Al-Ansari, N., Moghadam, M. K., and Mohammad, T. (2019). Application of TRMM precipitation data to evaluate drought and its effects onwater resources instability. Applied Sciences (Switzerland), 9(24) doi:10.3390/app9245377

Azhirabi, R., Kamkar, B. and Abdi, O. (2015). Comparison of different indices adopted from Landsat images to map soil salinity in the army field of Gorgan. J. Soil Manage. Sust. Prod., 5(1), 173-176 [In Persian].

Behnam, V., Gholamalizadeh, A., Rahmanian, M. and Bameri, A. (2019). Investigation of spatial distribution of some physical and chemical properties of soil using Geostatistical methods (Case study: Zabol to Zahedan route). Environ. Water Eng., 5(3), 251-263 [In Persian].

Debeljak, M. and Džeroski, S. (2011). Decision trees in ecological modelling. In: Jopp, F., Reuter, H., Breckling, B. (eds), Modelling complex ecological dynamics. (197-209). Springer, Berlin, Heidelberg.

Foroughifar H., Jafarzadah A. A., Torabi Gelsefidi H., Aliasgharzadah N., Toomanian N. and Davatgar, N. (2010). Spatial variations of surface soil physical and chemical properties on different landforms of Tabriz plain. J. Soil Water Sci., 21(3), 1-21 [In Persian]

Gholami, S., Hosseini, S. M., Mohammadi, J. and Mahini, A. S. (2011). Spatial variability of soil macrofauna biomass and soil properties in riparian forest of Karkhe River. J. Water Soil, 25, 248-257 [In Persian].

Hassani Pak, A. (2010). Geostatistics. University of Tehran Press, 3^rd Ed., p 325, Tehran [In Persian].

Hossein Abadi, S., Khozeime Nezhad, H. and Khashei Sioki., A. (2021). Evaluation of gene expression model in spatial prediction of groundwater salinity and comparison with geostatistical models Case Study: Mashhad Plain. Echo. Hydrol., 8(3), 855-866.

Haykin, S. (1994). Neural network: A comprehensive foundation. 2^nd Ed. Macmillan. New York.

Isaaks, E. H. and Srivastava, R. M. (1989). An introduction to applied geostatistics: Oxford University Press, 561.

Jahantigh, M. and Jahantigh M. (2019). Study effect of flood productivity on vegetation changes using field work and Landsat satellite images (Case study: Shandak of Sistan region). J. RS GIS Nat. Resour., 10(4), 57-73 [In Persian].

Juan P., Mateu, J. Jordan, M. M, Mataix-Solera, J., Meléndez-Pastor, I. and Navarro-Pedreño. J. (2011). Geostatistical methods to identify and map spatial variations of soil salinity. J. Geochem. Explor., 108, 66-72.

Moonjun, R., Farshad A., Shrestha, D. P. and Vaiphasa, C. (2010). Artificial neural network and decision tree in predictive soil mapping of Hoi NumRin Sub-Watershed, Thailand, Digital Soil Mapping. Prog. Soil Sci., 2(23), 151-164.

Moradian, S., Nabiollahi, K. and Taghizadeh Mehrjerdi, R. (2017). Prediction of soil salinity using tree regression and artificial neural network in Qorveh region of Kurdistan province. Soil Manage. Sustain. Product., 7(4), 115-129 [In Persian].

Nawar, S., Reda, M., Farag, F. and El-Nahry, A. (2011). Mapping soil salinity in El-Tina plain in Egypt using geostatistical approach. Geoinformatics Forum, Salzburg, Austria. 211-216.

Nikbakht Shahbazi, A., Zahraei, B. and Naseri, M. (2012). Seasonal forecast of meteorological drought using support vector machines. Water Wastewater, 2(23), 73-85 [In Persian].

Nikpour, M. R., Thanikhani, H., Mahmoudi Babalan, S. and Mohammadi, A. (2017). Application of SVM, ANN, WNN and GEP models in rainfall-runoff simulation of Khiavachai river. Echo. Hydrol., 4(2), 627-639 [In Persian].

Ranjbar, F. and Jalali, M. (2016). The combination of geostatistics and geochemical simulation for the site-specific management of soil salinity and sodicity. Comput. Electron. Agri., 121, 301-322.

Sharma, V., Negi, S. C., Rudra, R. P. and Yang, S. (2003). Neural networks for predicting nitrate-nitrogen in drainage. Agri. Water Manage., 63, 169–183.

Siasar, H. and Honar, T. (2019). Application of support vector machine models, chad and random forest in estimating daily reference transpiration evaporation in northern Sistan and Baluchestan province. Irrig. Drain. Iran., 2(13), 378-388 [In Persian].

Sitharam, T. G., Samui, P. and Anbazhagan, P. (2008). Spatial variability of rock depth in temperate forests. Geotech. Geol. Eng., 26(5), 503-517.

Sokouti Scoei, R., Mahdian, R. and Mahmoodi, S. H. (2007). Comparing the applicability of semigeostatistc methods to predict the variability of soil salinity, a case study of Uromia plain. Pajuhesh Sajandegi, 74, 90-98 [In Persian].

Soleimani, K., Habibnejad, M., Abkar, A. and Bani Asadi, M. (2006). Analysis of depth, surface and continuity curves using geostatistical methods in arid and semi-arid rainfall areas (D.A.D) Case study: Sirizjan salt pan). J. Desert, 11(1), 32-41 [In Persian].

Taghizadeh, R., Minasny. B., Sarmadian, F. and Malone, P. B. (2016). Digital mapping of soil salinity in Ardakan region, central Iran. Geoderm., 213(56), 15-28.

Wang, Y. and Witten, I. H. (1997). Inducing model trees for continuous classes. In Proceedings of the Ninth European Conference on Machine Learning. 128-137.

Watt, M. and Palmer, S. (2010). Use of regression kriging to develop a Carbon: Nitrogen ratio surface for New Zealand. Geoderm, 183,49-57.

Yu, H., Liu, M, Du, B., Wang, Z., Hu, L. and Zhang, B. (2018). Mapping Soil Salinity/Sodicity by using Landsat OLI Imagery and PLSR Algorithm over Semiarid West Jilin Province, China. Sensor., 18(4), 1043-1017.

محیط زیست و مهندسی آب

مقایسه روش‌های هوش مصنوعی و زمین آمار در پیش‌بینی شوری سطحی خاک در قرقری، هیرمند

مراجع

مراجع

دوره 8، شماره 3
مهر 1401
صفحه 622-635

مقایسه روش‌های هوش مصنوعی و زمین آمار در پیش‌بینی شوری سطحی خاک در قرقری، هیرمند

مراجع

مراجع

دوره 8، شماره 3مهر 1401صفحه 622-635

دوره 8، شماره 3
مهر 1401
صفحه 622-635