Investigating the Potential of Erosion-Prone Areas with ICONA Models, Support Vector Machine, Chaid and Random Forest (Case Study: Gonabad Basin)

جغرافیا و مخاطرات محیطی

Article 5, Volume 10, Issue 4 - Serial Number 40, February 2022, Pages 93-112   

Document Type: Research Article

DOI: 10.22067/geoeh.2021.71162.1080

Authors

Mohammad Ali Zangeneh Asadi¹; Mahnaz Naemi Tabar^{* 2}; Rahman Zandi³

¹Associate Professor in Geomorphology, Hakim Sabzevari University, Faculty of Geography and Environmental Sciences, Sabzevar, Iran

²PhD Student in Geomorphology, Hakim Sabzevari University, Faculty of Geography and Environmental Sciences, Sabzevar, Iran

³c Assistant Professor, Department of Remote Sensing and Geographic Information System, Faculty of Geography and Environmental Sciences, Hakim Sabzevari University, Sabzevar, Iran

Abstract

Experimental models for estimating erosion have been developed for a specific area and their calibration is necessary for use in conditions other than their own location. Examining the accuracy of experimental models for estimating erosion can lead to better estimates of sediment load and thus better design of soil and water protection operations. Therefore, it is necessary to identify high-risk areas of erosion to control and reduce erosion and sediment production. The study aimed to investigate the accuracy and capability of ICONA, support vector machine, Chaid and random forest models in estimating erosion. First, digital layers of variables affecting erosion including slope, geological formation, land use, soil, height, slope direction, surface curvature, waterway network density, distance from the waterway, fault density, distance from the fault, and topographic moisture index (Twi) were prepared. To compare different models, statistical indices of correlation coefficient (R) and absolute magnitude of error (MAE) were used. The results showed that among the mentioned models, the support vector machine model, ICONA and random forest with M7, M9 and M12 pattern had the highest accuracy with correlation coefficient of 0.899, 0.845, and 0.921 and the lowest mean absolute value. It has error MAE = 0.711, MAE = 0.721, and MAE = 0.628. According to the study of effective factors in soil erosion model, it is concluded that the parameters of the slope, geological formation, land use, soil, distance from the waterway, and topographic moisture index (Twi) are more sensitive to erosion and the factors affecting erosion in these areas are more active. Most of the study area is part of a very high to high erosion class that these classes are mainly located in the center of the area. Most areas at high to severe erosion risk are located in the sloping topographic unit.

Keywords

Soil Erosion; Gonabad Basin; Experimental Models; Statistical Indicators; Correlation Coefficient

References

خالقی، سمیه؛ نصرتی، کاظم؛ عباسپور، رحیم؛ 1399. برآورد فرسایش خاک و انتقال رسوب در حوضه آبخیز بادآور لرستان با استفاده از مدلSWAT. پژوهش‌های ژئومورفولوژی کمّی. شماره 3. 186-202.

خسروی اقدم، کمال؛ ممتاز، حمیدرضا­؛ اسدزاده، فرخ؛ 1398. برآورد عامل فرسایش‌پذیری خاک مدل USLE و ارتباط آن با برخی از ویژگی­های زمین منظر در بخشی از حوزه آبخیز نازلو چای ارومیه. مجله تحقیقات کاربردی خاک. شماره 7. 43-31.

رضازاده، محمد سهیل؛ بختیاری، بهرام؛ عباس پور، کریم؛ احمدی، محمد؛ 1397. شبیه‌سازی رواناب، رسوب و تبخیر تعرق با استفاده از سناریوهای مدیریتی برای کاهش  بار رسوب با استفاده از مدل SWAT. نشریه علوم و مهندسی آبخیزداری ایران. شماره 41. 51-40.

سیاسر، هادی؛ هنر، تورج؛ 1398. کاربرد مدل‌های ماشین بردار پشتیبان، چاید و جنگل تصادفی در برآورد تبخیر تعرق مرجع روزانه در شمال استان سیستان و بلوچستان. نشریه آبیاری و زهکشی ایران. شماره 2. 388-378.

قربانی نژاد­، سمیرا؛ زینی وند، حسین؛ حقی زاده،­ علی­؛ طهماسبی، ناصر؛ 1398. بررسی کارایی مدل دمپستر- شافر در پتانسیل‌یابی مناطق مستعد فرسایش خاک حوزه آبخیز کاکا رضا در استان لرستان. سنجش‌ازدور و سامانه اطلاعات جغرافیایی در منابع طبیعی. شماره 9. 114-100.

کرمی، فریبا؛ بیاتی خطیبی، مریم؛ 1398. مدل‌سازی فرسایش خاک و اولویت‌بندی تولید رسوب در حوضه سد ستارخان اهر با استفاده از مدل‌های MUSLE و SWAT. هیدروژئومورفولوژی. شماره 18. 115-137.

مزبانی، مهدی؛ رضایی مقدم، محمدحسین؛ حجازی، اسدالله؛ 1400.  ارزیابی خطر فرسایش خاک در کاربری‌های اراضی با استفاده از معادله اصلاح‌شده جهانی فرسایش خاک (مطالعه موردی: حوضه آبریز سیکان). جغرافیا و مخاطرات محیطی. شماره 37. 41-63.

یمانی، مجتبی؛ عرب عامری، علیرضا؛ 1397. کارایی آنالیز کمی پارامترهای ژئومورفومتریک در تهیه نقشه حساسیت فرسایش خاک (مطالعه موردی: حوضه منج). جغرافیا و مخاطرات محیطی. شماره 26. 21-1.

Ashraf  A., 2020. Risk modeling of soil erosion under different land use and rainfall conditions in Soan river basin. Sub -Himalayan region and mitigation options. Modeling Earth Systems and Environment, 6:  417–428.

Ayele G.T, Teshale E.Z, Yu B, Rutherfurd I.D, Jeong J., 2017. Streamflow and Sediment Yield Prediction for Watershed Prioritization in the Upper Blue Nile River Basin. Ethiopia. Water 9: 1-29.

Borrelli P,  Alewell Ch, Alvarez P, Jamil Alexandre A.A, Jantiene B, Cristiano B, Nejc B,  Marcella B,  Artemi C, Devraj Ch, Songchao Ch, Walter Ch, Anna M, Gizaw Desta G, Detlef D, Nazzareno D, Nikolaos E, Gunay E, Peter F, Michele F, Francesco G, Andreas G, Nigussie H, Bifeng H, Amelie J, Konstantinos K, Kiani-Harchegani M, Ivan Lizaga V, Changjia L, Luigi L, Manuel L, Manuel Esteban L, Michael M, Francis M, Chiyuan M, Matjaž M, Sirio M, Markus M, Victoria N, Laura P, Raquel P, Laura Q, Rahdari M, Renima M, Giovanni F, Jesús R, Sergio S, Samani A, Calogero S, Vasileios S, Hyuck Soo K, Diogo Noses S, Paulo Tarso O, Hongfen T, Resham T, Konstantinos V, Diana V, Jae E, ShuiqingY, Demetrio Antonio Z, Guangju Z, Panos P., 2021. Soil erosion modelling: A global review and statistical analysis. Science of the Total Environment 780 : 3-16.

Briak H, Moussadek R, Aboumaria  KH, Mrabet R., 2016. Assessing sediment yield in Kalaya gauge dwatershed (Northern Morocco) using GIS and SWAT model. International Soil and Water Conservation Research 4: 177- 185.

Christos G, Panagos P, Ioannis Z, Gitas., 2014. A classification of water erosion models according to their geospatial characteristics. International Journal of Digital Earth 7: 229-250.

Duru U, Arabi M, Whol E., 2018. Modeling stream flow and sediment yield using the SWAT model: a case study of Ankara River basin, Turkey. Journal Physical Geography 39: 264-289.

Gull S, MA A, Dar A.M., 2017. Prediction of Stream Flow and Sediment Yield of Lolab Watershed Using SWAT Model. HydrologyCurrent Research 8: 1-9.

ICONA. 1991. Plan National de Restauracion hidrologico-forest alpara el Control de la Erosion. Ministries deAgriculture, Pescay Alimentacion, Madrid.

Kisi O, Kilic Y. 2015. An investigation on generalization ability of artificial neural networks and M5 model tree in modeling reference evapotranspiration. TheorAppl Climatol, 1-13.

Kumar T,  jahria DC, Pandey H.K., 2019. Comparative study of different models for soil erosion and sediment yield in Pairi watershed, Chhattisgarh, India. Journal Geocarto internathinal 9: 112-124.         

Muche H, Temesgen M, Yimer F., 2013. Soil loss prediction using USLE and MUSLE under conservation tillage integrated with ‘fanya juus’ in Choke Mountain, Ethiopia. International Journal of Agricultural Sciences 3: 046-052.

Pahlavan Rad M.R, Toomanian N,  Khormali F, Brungard C, Komaki C.B,  Bogaert P., 2014. Updating soil survey maps using random forest and conditioned Latin hypercube sampling in the loessderived soils of northern Iran. Journal of Geoderma 32:  97–106.

Thi Phuong Y, Chau V, Trung T, Nguyen B N, Huynh CH., 2014. Modeling Soil Erosion within Small Moutainous Watershed in Central Vietnam Using GIS and SWAT. Resources and Environment 4: 139-147.