Journal of Engineering Geology
نشریه زمین شناسی مهندسی
Journal of Engineering Geology
Basic Sciences
http://jeg.khu.ac.ir
1
admin
2228-6837
2981-1600
doi
fa
jalali
1397
5
1
gregorian
2018
8
1
12
1
online
1
fulltext
fa
تلفیق مدل فرایند تحلیل سلسله مراتبی و شبکههای عصبی بهمنظور پهنهبندی خطر وقوع زمینلغزش (مطالعۀ موردی شهرستان بیجار)
Combination AHP and Neural Network Model to landslide Hazard Zonation (Case Study city of Bijar)
زمین شناسی مهندسی
En. Geology
مقاله پژوهشی
Original Research
<span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">شناسایی</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">محدودههای</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">مستعد</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">زمینلغزش</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">در</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">عمران</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">شهری</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">و</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">منطقه</span></span></span><span dir="LTR"><span style="color:black;"><span style="font-size:10.0pt;">­</span></span></span><span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">ای</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">دارای اهمیت ویژهای است.</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">در</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">این</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">مقاله</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">به</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">پهنه­بندی</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">میزان</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">حساسیت</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">به</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">زمینلغزش</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">با</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">استفاده</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">از</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">شبکه</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">عصبی</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">مصنوعی و تحلیل سلسله مراتبی اقدام شده است. این پهنهبندی و تحلیل با استفاده از شبکههای عصبی مصنوعی</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">که</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">قادر</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">به</span></span></span><span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:5.0pt;"> </span></span></span><span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">شناسایی</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">روابط</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">پیچیده</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">بین</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">حرکات</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">توده­ای</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">و</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">هدف</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">یعنی</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">عوامل</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">پهنۀ</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">حساسیت، بهمنظور شناسایی مناطق ناپایدار صورت گرفته است. روش</span></span></span> <span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">تحلیل سلسله مراتبی برای بهبود نمونه آموزش، در سیستم اطلاعات جغرافیایی انجامشده است. پیشپردازش با استفاده از روش تحلیل سلسله مراتبی داده­ها برای انتخاب پیکسلهای مناطق بدون لغزش و کمک به بهبود قابلیت پیش­بینی روش شبکۀ عصبی که یک مدل جعبه سیاه است انجام شده است.</span></span></span><span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;"> این روش در </span></span></span><span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">شهرستان بیجار در شمال شرق استان کردستان که پتانسیل زیادی برای حرکات دامنهای دارد، باهدف پهنه­بندی زمینلغزش بهعنوان یکی از حرکات دامنهای اعمال شد. بدینمنظور ابتدا بررسیهای کتابخانهای برای شناسایی معیارهای تأثیرگذار در این فرایند انجام گرفت بر اساس پژوهشها، متغیرهای لیتولوژی، فاصله از گسل، جهت شیب، کاربری اراضی، فاصله از رودخانه، فاصله از خطوط ارتباطی، شیب، ارتفاع و شبکه زهکش مهمترین فاکتورهای مؤثر بر زمینلغزش محسوب می­شوند که در این تحقیق ارزیابی شدند. برای ارزیابی این متغیرها در شبکۀ عصبی پرسپترون با ساختار نه لایه ورودی، دولایه پنهان و نه گره </span></span></span><span style="color:black;"><span style="font-family:b lotus;"><span style="font-size:10.0pt;">در هر دولایه با میزان یادگیری01/ با دو تابع سیگموئید و خطی بهعنوان ساختار بهینه با آزمون و خطا پذیرفته شد برسی این متغیرها با استفاده از شبکه عصبی نشاندهندۀ آن است که بیش از 60 درصد از منطقه بررسی شده جزء مناطق با قابلیت زمینلغزش زیاد است. بهمنظور صحت­سنجی این مدلها از داده­های مشاهده­ای موجود استفادهشده که حاکی از موفقیت و کارایی هر دو تابع با اولویت اندک تابع سیگموئید است.</span></span></span>
<strong>Introduction</strong><br>
The prediction of landslide occurrence in a region is very important in reducing the risks and damages caused by this<span dir="RTL">.</span>landslide as a natural disaster in Iran caused a lot of life and financial losses to Iran annually. According to the National Committee on Natural Disaster Reduction of the Ministry of the Interior in 1994, the share of annual damage caused by mass movements in Iran is estimated at 500 billion rials<span dir="RTL">.</span> In the meantime Kurdistan province is the third province in terms of landslide phenomenon after Mazandaran and Golestan. If considering the area is at a higher level. The city of Bijar in this province has a high potential for a wide range of landslides with a combination of mainly mountain topographical factors, lithologic conditions and positioning between two major faults in the region. In this research, using quantitative methods and models on the quantitative factors of this phenomenon based on the level of information given by past mass movements and influential factors, focusing on artificial neural network method, susceptibility zones were determined by determining the possible risk level<span dir="RTL">.</span><br>
Knowing such natural events requires proper management of the risks posed by them. On the other hand, artificial neural network as a quantitative model is capable of learning, generalization and decision making, and less need to analyze the accuracy of data in comparison to statistical methods<span dir="RTL">.</span> Map of the susceptibility of the areas to the landslide is an important tool for landuse planning. However, there are many issues in the formation of this phenomenon, which, due to the complexity of the natural processes arising from the relationship between the outcome (dependent variable) and the factors (independent variables), puts into question the general zoning of such areas<span dir="RTL">. </span><br>
<strong>Methodology<span dir="RTL"></span></strong><br>
Bijar is located in the northeastern part of Kurdistan province, along the longitude of 47 ' 29° to 47 ° 47' east, in latitude 35 ° 35 'to 35' 59 °north<span dir="RTL">.</span> In recent years, the development of the Geographic Information System (GIS) and spatial analysis techniques have improved the risk of indirect zoning. In this regard, artificial neural networks can cover a significant part of these needs<span dir="RTL">.</span>Implementing the neural network model requires learning data. Without learning data, it's virtually impossible to make neural networks<span dir="RTL">.</span> In this paper, learning data shows the occurrence of landslides which have geographical coordinates and were obtained from the Kurdistan Province Natural Resources Organization<span dir="RTL">.</span> In general, learning data in GIS and remote sensing can include data or raster, which in this paper is a point phenomenon and has 144 cases<span dir="RTL">. </span> However, because of the large extent of the study area and the low number of them, as well as the lack of risk of any landslide zone (from low to very high), the points should be classified as well, and, in terms of numbers, Acceptance. Also, the number of points of relative value In terms of numbers, the conditions are the Normal and the same (that is, the appropriate geographical distribution and distribution in each class) would be more accurate; thus, to create a classifiable spectrum of the AHP Was used<span dir="RTL">.</span> It should be noted that all the maps were standardized in the format and format of the Raster in a matrix (698 rows in 897 columns) identical with a size of 30 * 30 meters. This means that each map has 626,106 pixels of varying value and somewhat similar. In addition, the AHP model was used to categorize the studied area from very desirable (hazardous) to very undesirable (very dangerous) areas<span dir="RTL">.</span> Also, 33 points were added to the learning data on different levels of the map derived from the AHP model. But in order to verify accurately the model, only landslide occurrences were considered<span dir="RTL">.</span><br>
In order to find out the factors of landslide in Bijar, a map of slope, Aspect, elevation, distance from the fault, distance from the road, distance from the river, Drainage density, lithology and land use using ArcGIS software were prepared and digitized<span dir="RTL">.</span><br>
After compiling and categorizing these variables, at first, each of the effective criteria in the field was divided into six sub-criteria (land suitability for landslide) from very desirable to very undesirable conditions<span dir="RTL">.</span> The present study utilizes the technique of multi-layer propspert neural networks using post-propagation algorithm (BP). In addition to correcting and editing the layers, the neural network model was implemented using the classification method and applying two types of functions (linear and sigmoid)<span dir="RTL">.</span> Then, using the test-error method, the study of the magnitude of the error and the period of the repetition and the change in the number of hidden layers and weights, both functions were performed. Finally, the sigmoid function, which yielded a better result, was selected as the proposed and final function<span dir="RTL">.</span>Order to verify the (accuracy) of the map taken with the existing landslide zones, the final map of the neural network model was again transferred to the ArcGIS software. Finally, the available landscapes on the map resulted from the adaptive neural network model, which, by comparison, gave a percentage and amount Accuracy of each class was achieved<span dir="RTL">.</span><br>
<strong>Result<span dir="RTL"></span></strong><br>
The input layer were calculated to six classes based on the desirability of mass movements. This decision approach reduces the complexity of the network and improves its performance<span dir="RTL">.</span><br>
For this purpose. The AHP method was used to define non-slip pixels and range classification<span dir="RTL">.</span><br>
To implement this method, 9 variables discussed, were scaled up to the most suitable and un suitable range. The final weight of these variables was obtained by using the Thomas saati pair comparison (Table 4), the study area was divided into five categories according to the map for land suitability for landslide hazard<span dir="RTL">.</span> From each class, the 20-pixel from AHP model was selected for network learning in a completely randomized manner<span dir="RTL">.</span> The proposed model is an artificial neural network of MLP multi-layered perceptron with levenberg-marquardt learning algorithm<span dir="RTL">.</span> An early stopping method was used to improve network optimization. Several hidden layers were tested to find the best results<span dir="RTL">.</span> It should be noted that in the structure of all networks, at least the optimal design with the middle one is used, but in their structural composition they are also used with mid-duplex networks. In this paper, the use of tow mid-layers showed better results<span dir="RTL">. </span> In all Simulations have been made, the mean square error index, as a guide, indicates the network performance in learning the existing model<span dir="RTL">.</span> By changing the number of intermediate neurons and changing the weights as try and error, the most appropriate network model was obtained for the purpose. In this study, the structure of the network with 9 input layers, 2 hidden layers, 1500 repetitions in both functions was accepted as the final structure. The main structure of the neural network with two linear and sigmoid functions was prepared with acceptable error, and the study area was analyzed with a total area of 564 km2 with 9 input variables converted into raster data to 30 × 30 pixels<span dir="RTL">.</span> From 564 km2 based on the sigmoid function 61.17% and based on the linear function, 72.76% of the area is unsuitable and very unsuitable in the area where expose to high risk. In both networks, there were very few areas in both optimal and moderate classes (Figures 16 and 17), which indicate the high talent of the area for landslide as a threat<span dir="RTL">.</span> Then, ArcGIS software was used to evaluate the efficiency and accuracy of the model<span dir="RTL">. </span>For this purpose, the point of landslide and zoning maps were combined, compared and anlayzed. The results showed in the sigmoid function 75 items of Landslides were in a very unsuitable range, which included 61% of the total of region.<br>
<strong>Conclusion<span dir="RTL"></span></strong><br>
In the linear function, approximately 69% of the landslides are in a very unsuitable range and the unsuitable results are about 57%, which results in the success of the model designed in the neural networks (MLP). In the end, the network with sigmoid function is negligibly better than the linear function network.The results show that Bijar and its functions are relatively prone to occurrence of landslides, so that nearly 60% of the city's area is a high risk area with a high risk and only 2% is a low-risk region<span dir="RTL">. </span>The hazardous areas are mainly located around the city of Bijar especially southern and southeast. These areas correspond to high altitudes and maximum fault density and lime lithology with marl (Qom Formation)<span dir="RTL">.</span> The model can be very challenging, because of innovative nature of the research, that means need more detailed and comprehensive studies.<a href="./files/site1/files/121/neiri_Abstract.pdf">./files/site1/files/121/neiri_Abstract.pdf</a>
حرکات دامنهای, سیستم اطلاعات جغرافیایی, مخاطره
153
182
http://jeg.khu.ac.ir/browse.php?a_code=A-10-1270-1&slc_lang=fa&sid=1
Hadi
nayyeri
هادی
نیری
10031947532846004620
10031947532846004620
Yes
University of Kurdistan
دانشگاه کردستان، دانشکدۀ منابع طبیعی، گروه ژئومورفولوژی
Mohammadreza
Karami
محمدرضا
کرمی
10031947532846004621
10031947532846004621
No
دانشگاه پیام نور، گروه جغرافیا و برنامهریزی شهری