ارزیابی مدل‌های مختلف داده‌کاوی برای پیش‌بینی نقشه حساسیت فرسایش آبکندی در حوزه آبخیز رباط ترک استان مرکزی

فرسایش آبکندی یکی از اشکال فرسایشی است که موجب هدر رفت مقدار زیادی خاک می گردد. بنابرین از این فرسایش می توان به عنوان یکی از علل اصلی تخریب زمین و محیط زیست نام برد. این تحقیق با هدف پهنه بندی حساسیت فرسایش آبکندی با استفاده از مدل های داده کاوی، مدل خطی تعمیم یافته (glm) و شبکه عصبی مصنوعی (ann) در حوزه آبخیز رباط ترک انجام شد. مناطق دارای فرسایش آبکندی طی بازدیدهای میدانی شناسایی و تعداد 242 نقطه فرسایشی انتخاب گردید. 12 متغیر محیطی موثر در فرسایش آبکندی، نقشه رقومی ارتفاع، درجه شیب، جهت شیب، شکل شیب، شاخص همگرایی، فاصله از رودخانه، تراکم زهکشی، فاصله از جاده، سنگ شناسی، کاربری اراضی، شاخص اختلاف پوشش گیاهی نرمال شده (ndvi) و نقشه هم باران به منظور مدل سازی حساسیت فرسایش آبکندی مورد استفاده قرار گرفتند. به منظور ارزیابی و اعتبارسنجی مدل های مورد استفاده از معیارهای roc، tss و kappa استفاده شد. نتایج حاصل از ارزیابی مدل نشان داد که مدل glm با مقدار roc، kappa و tss به ترتیب 0.89، 0.7 و 0.7 و مدل ann با roc، kappa و tss به ترتیب 0.88، 0.7 و 0.7 کارایی خیلی خوبی در مدل سازی مناطق حساس به فرسایش آبکندی دارند. همچنین بررسی کلی مدل های مورد استفاده براساس شاخص های ذکر شده نشان داد که مدل glm دارای کارایی مناسب تری نسبت به مدل ann در منطقه مورد مطالعه دارد. نتایج حاصل از پهنه بندی حساسیت فرسایش آبکندی در منطقه مورد مطالعه نشان داد که مناطق مرکزی حوزه دارای حساسیت خیلی زیاد و زیاد نسبت به فرسایش آبکندی می باشد.

Evaluating the Capability of Various Types of Geomorphological facies in supplying dust sources in the west of Khozestan province- Iran

Soil erosion is a problem for agriculture in arid and semiarid regions and is of great importance due to its longterm effects on soil fertility and sustainable agriculture. Among the types of water erosion, gully erosion is one of the most important events in soil erosion and land reclamation. Given that the Markazi province is located in a region with arid and semiarid climate, the intensity of rainfall is high in some months of the year. Also because of the abandoned agricultural land in the study area, there is much vegetation exposed to severe erosion which is conducive to erosion such as gutter erosion, so serious attention is needed for this area. The data mining method extracts useful information from a large volume of data and has shown good performance based on the literature review. Therefore, the aim of the present study was to prioritize environmental factors affecting the occurrence of gully erosion with data mining and statistical methods.Material and MethodsIn order to conduct the present study and to map the distribution of gully erosion zones in the Robat Turk watershed, 242 gully data were identified in the study area and used. A total of 242 points were identified as nonflooded areas. In order to model the data, it was divided into two categories of training and validation, with 70% of data used as training and 30% of data used as validation. Based on the research background, hydrological, geological and physiographic factors including elevation, slope, aspect, curvature, slope shape, distance from river, distance from road, lithology, land use, annual precipitation and NDVI, variables were selected for modeling. In order to model the gully erosion, artificial neural network (ANN) and generalize linear model (GLM) models were used, and the ROC and Kappa, TSS coefficient were used to determine the accuracy of the gully erosion susceptibility map.Result and discussion The results of gully erosion susceptibility showed that the central areas of the watershed are highly sensitive to erosion. Considering that most of the lands in the central part of the watershed are bare land and agricultural, the study of the gully erosion susceptibility map showed that the most sensitive and highly sensitive erosion susceptibility area was formed in the bare land. In relation to the influence of different elevation and slope classes in the study area on susceptibility to erosion, it should be stated that altitude class of 18002000 meters and slope class of 012% had the highest contribution to erosion susceptibility in the study area. This may be due to the higher soil compactness of these classes than other classes, which increases the likelihood of water infiltration into the soil and the possibility of material dissolution and piping. Validation results showed that GLM and ANN with ROC of 0.89 and 0.88 have very good performance regarding gully erosion susceptibility in the study area.ConclusionGully erosion is one of the erosion processes that widely affects the appearance of the earth. In this study, GLM and ANN were used to evaluate the impact of environmental variables on gully erosion as well as to identify potential areas for gully erosion. For this purpose, 12 variables and 242 gully erosion points were used. ROC, TSS and KAPPA statistics were used to evaluate the models. The results of evaluation and validation of the models used showed that both models have good performance in zoning susceptibility to gully erosion. Identification and prediction of gully erosion susceptible areas can reduce the damaging effects of this type of erosion and prevent its further development and can be of considerable help to the people of the study area. Given that most of the gutters were created in the central part of the study area near the village of Robat Turk, protective measures should be increased in these areas to prevent the spread of agriculture and residential areas to erosive areas.