ارزيابي حساسيت زمين‌لغزش با استفاده از مدل جديد تركيبي الگوريتم مبنا (مطالعه موردي: شهرستان كامياران، استان كردستان)

Landslide susceptibility assessment using a novel ensemble algorithm based model (Case Study: Kamyaran city, Kurdistan province)

زمين­ لغزش­ها به عنوان يكي از مخرب­ترين پديده­ هاي طبيعي محسوب مي­شوند. به دليل تهديد آن­ها، بايد يك نقشه جامع حساسيت زمين­لغزش براي كاهش آسيب­هاي احتمالي به افراد و زيرساخت­ها تهيه شود. كيفيت نقشه­هاي حساسيت زمين­لغزش تحت تأثير بسياري از عوامل، از جمله كيفيت داده ­هاي ورودي و انتخاب مدل­هاي رياضي است. هدف اصلي اين پژوهش ارائه يك مدل تركيبي جديد داده­كاوي به نام Rotation Forest - Functional Trees (RF-FT) كه يك رويكرد هوشمند تركيبي از دو تكنيك يادگيري ماشين مدل Functional Trees (FT) و تكنيك طبقه ­بندي مدل Rotation Forest (RF) براي ارزيابي حساسيت زمين لغزش­هاي اطراف شهر كامياران واقع در استان كردستان مي­باشد. در ابتدا، بيست و يك عامل مؤثر بر وقوع زمين­لغزش­هاي منطقه مورد مطالعه شامل درجه شيب، جهت شيب، ارتفاع، انحناي شيب، انحناي عرضي شيب، انحناي طولي شيب، تابش خورشيد، عمق دره، شاخص قدرت جريان، شاخص نمناكي توپوگرافي، شاخص طول دامنه، كاربري اراضي، تراكم پوشش گياهي، فاصله از گسل، تراكم گسل، فاصله از جاده، تراكم جاده، فاصله از آبراهه، تراكم آبراهه، همباران و ليتولوژي به همراه نقشه پراكنش زمين­لغزش با 60 نقطه لغزشي براي جمع­آوري داده­هاي آموزشي و آزمون جمع ­آوري شدند. سپس، بر اساس شاخص Information Gain Ratio هفده عامل مؤثر از بين آن­ها انتخاب و جهت مدل­سازي به كار گرفته شدند. در مرحله بعد مدل هيبريدي RFFT براي ارزيابي حساسيت زمين­لغزش با استفاده از مجموعه داده­هاي آموزشي ساخته شد. عملكرد مدل پيشنهادي RFFT با استفاده از چندين پارامتر آماري از جمله حساسيت، شفافيت، صحت، مجذور مربعات خطا، منحني نرخ موفقيت و سطح زير اين منحني مورد ارزيابي قرار گرفت.

Landslides are considered one of the most destructive natural phenomena. Landslides are dangerous natural hazards. Because of their threat, a comprehensive landslide susceptibility map should be produced to reduce the possible damages to people and infrastructure. The quality of landslide susceptibility maps is influenced by many factors, such as the quality of input data and the selection of mathematical models. The main purpose of this study is to presentation, a novel hybrid model namely Rotation Forest based Functional Trees (RFFT), which is a hybrid intelligent approach of two state of the art machine learning techniques of Functional Trees (FT) classifier and Rotation Forest (RF) ensemble, for landslide susceptibility Assessment prediction in Kamyaran city located in Kurdistan Province, Iran. At first, twenty-one factors affecting the occurrence of landslide in the study area including Slope angle, Aspect, Elevation, Curvature, Plan curvature, Profile curvature, Radiation, Valle depth(VD), stream power index (SPI), topographic wetness index (TWI), combination of length-angle of slope (LS), Land use, NDVI (normalized vegetation index), Distance to Faults, Faults density, Distance to Road, Road density, Distance to River, River density Lithology and Rainfall with total of 60 landslide locations have been collected for generating training and testing datasets. Then, based on the Information Gain Ratio Index, eight effective factors were chosen and used for modeling. Performance of the proposed RFFT model was evaluated using some statistical-based measures such as sensitivity, specificity, accuracy, RMSE and area under the ROC curve (AUROC). The results showed that the proposed model performed well in this study (AUC = 0.891), and it improved significantly the performance of the FT base classifier (AUC = 0.819). Therefore, it can be concluded that the proposed RFFT model should be used as a great alternative method for better landslide susceptibility assessment in landslide prone area.Landslides are considered one of the most destructive natural phenomena. Landslides are dangerous natural hazards. Because of their threat, a comprehensive landslide susceptibility map should be produced to reduce the possible damages to people and infrastructure. The quality of landslide susceptibility maps is influenced by many factors, such as the quality of input data and the selection of mathematical models. The main purpose of this study is to presentation, a novel hybrid model namely Rotation Forest based Functional Trees (RFFT), which is a hybrid intelligent approach of two state of the art machine learning techniques of Functional Trees (FT) classifier and Rotation Forest (RF) ensemble, for landslide susceptibility Assessment prediction in Kamyaran city located in Kurdistan Province, Iran. At first, twenty-one factors affecting the occurrence of landslide in the study area including Slope angle, Aspect, Elevation, Curvature, Plan curvature, Profile curvature, Radiation, Valle depth(VD), stream power index (SPI), topographic wetness index (TWI), combination of length-angle of slope (LS), Land use, NDVI (normalized vegetation index), Distance to Faults, Faults density, Distance to Road, Road density, Distance to River, River density Lithology and Rainfall with total of 60 landslide locations have been collected for generating training and testing datasets. Then, based on the Information Gain Ratio Index, eight effective factors were chosen and used for modeling. Performance of the proposed RFFT model was evaluated using some statistical-based measures such as sensitivity, specificity, accuracy, RMSE and area under the ROC curve (AUROC). The results showed that the proposed model performed well in this study (AUC = 0.891), and it improved significantly the performance of the FT base classifier (AUC = 0.819). Therefore, it can be concluded that the proposed RFFT model should be used as a great alternative method for better landslide susceptibility assessment in landslide prone area.Landslides are considered one of the most destructive natural phenomena. Landslides are dangerous natural hazards. Because of their threat, a comprehensive landslide susceptibility map should be produced to reduce the possible damages to people and infrastructure. The quality of landslide susceptibility maps is influenced by many factors, such as the quality of input data and the selection of mathematical models. The main purpose of this study is to presentation, a novel hybrid model namely Rotation Forest based Functional Trees (RFFT), which is a hybrid intelligent approach of two state of the art machine learning techniques of Functional Trees (FT) classifier and Rotation Forest (RF) ensemble, for landslide susceptibility Assessment prediction in Kamyaran city located in Kurdistan Province, Iran. At first, twenty-one factors affecting the occurrence of landslide in the study area including Slope angle, Aspect, Elevation, Curvature, Plan curvature, Profile curvature, Radiation, Valle depth(VD), stream power index (SPI), topographic wetness index (TWI), combination of length-angle of slope (LS), Land use, NDVI (normalized vegetation index), Distance to Faults, Faults density, Distance to Road, Road density, Distance to River, River density Lithology and Rainfall with total of 60 landslide locations have been collected for generating training and testing datasets. Then, based on the Information Gain Ratio Index, eight effective factors were chosen and used for modeling. Performance of the proposed RFFT model was evaluated using some statistical-based measures such as sensitivity, specificity, accuracy, RMSE and area under the ROC curve (AUROC). The results showed that the proposed model performed well in this study (AUC = 0.891), and it improved significantly the performance of the FT base classifier (AUC = 0.819). Therefore, it can be concluded that the proposed RFFT model should be used as a great alternative method for better landslide susceptibility assessment in landslide prone area.