مدل‌سازی میدان سرعت پوسته زمین با استفاده از شبکه‌‌های عصبی مصنوعی ANNsبررسی موردی: شبکه ژئودینامیک ایران)

نویسندگان

دانشکده مهندسی نقشه برداری، دانشگاه صنعتی خواجه نصیرالدین طوسی

چکیده

در این مقاله از یک شبکه عصبی مصنوعی پرسپترون 3 لایه با 28 نورون در لایه مخفی به‌منظور مدل‌سازی مولفه شرقی (VE) و 27 نورون در لایه مخفی برای مدل‌سازی مولفه شمالی (VN) میدان سرعت پوسته زمین در منطقه ایران استفاده شده است. ارزیابی نتایج به‌دست آمده از شبکه عصبی مدل‌سازی شده در 11 ایستگاه آزمون GPSکه بردارهای سرعت آنها نسبت به صفحه اوراسیا مشخص بوده،صورت گرفته است. کمینه‌‌ خطای نسبی به‌دست آمده از این ارزیابی 57/3- درصد برای مولفه شرقی و 16/0+ درصد برای مولفه شمالی و بیشینه خطای نسبی برای مولفه شرقی 1/38+ درصد و برای مولفه شمالی 3/95+ درصد است. همچنین به‌منظور ارزیابی کارایی شبکه‌‌های عصبی مصنوعی در برآورد سرعت نقاط ژئودتیکی، در این مقاله از یک چندجمله‌ای مرتبه 5 با 18 ضریب برای مدل‌سازی مولفه شرقی و شمالی استفاده شده است. مقایسه مقادیر خطای نسبی محاسبه شده برای مدل چندجمله‌ای با مقادیر خطای نسبی به‌دست آمده برای شبکه عصبی، حاکی از برتری این روش نسبت به مدل چندجمله‌ای در برآورد سرعت نقاط ژئودتیکی در این منطقه است.

کلیدواژه‌ها


عنوان مقاله [English]

مدل‌سازی میدان سرعت پوسته زمین با استفاده از شبکه‌‌های عصبی مصنوعی ANNsبررسي موردی: شبکه ژئودینامیک ایران)

نویسندگان [English]

  • Mir Reza Ghaffari Razin
  • Ali Mohammadzadeh
چکیده [English]

Artifitial neural network (ANN) is an information processing system that is formed by a large number of simple processing elements, known as artificial nerves. It is formed by a number of nodes and weights connecting the nodes. The input data are multiplied by the corresponding weights, and the summation are entered into neurons. Each neuron has an activation function. Inputs are passed to the activation function, and the output of the neurons is determined. The number of neurons and layers could be obtained through trial and error according to a specific problem. The behavior of a neural network depends on the communication between nodes. Using the trained data, the designed ANN can be adjusted in an iterative procedure to determine optimal parameters of ANN. Then for an unknown input, we can compute corresponding output using the trained ANN.     One of the simplest and effective methods to use in the modeling of real neurons is the multi-layer perceptron neural network. This model consists of one input layer, one or more hidden layers, and one output layer. In this structure, all the neurons in one layer are connected to all neurons in the next layer. An important issue in multi-layer artificial neural networks is the number of neurons. The neurons of input and output layers are determined according to the number of input and output parameters. The number of neurons in the hidden layer can be determined by trial and error through minimizing the total error of the ANN. For this minimization, each ANN parameter’s share in the total error should be computed which can be achieved by a back-propagating algorithm.     There are many methods for training the network and modifications of the weights. One of the most famous and simplest methods is a back-propagation algorithm that trains the network in two stages: feed-forward and feed-backward. In the feed-forward process, the input parameters are moved to the output layer. In this stage, the output parameters are compared with known parameters and the errors are identified. The next stage is done feed-backward. In this stage, the errors are moved from the output layer to the input layer. Again, the input weights are calculated. These two stages are repeated until the errors reach a threshold expected for the output parameters.     In this study, a 3-layer perceptron neural network was used with 28 neurons in a hidden layer for modeling the eastern component (VE) and 27 neurons in a hidden layer for modeling the northern component (VN) velocity field of the earth's crust in Iran. Evaluation of the neural network model has been applied using 11 stations of GPS, and the velocity fields are defined with respect to the Eurasian plate.  The minimum relative error obtained from this evaluation for the eastern component was -3.57% and for the northern component was +0.16%: also the maximum relative error for the eastern component was +38.1% and for the northern component was +95.3%. In this study, a polynomial of degree 5 with 18 coefficients was used to model the east and north components for the evaluation of artificial neural networks in estimating the velocity rate of geodetic points. A comparison of the relative error from the polynomial model and the relative error from the neural network illustrated the superiority of the neural model with respect to the polynomial model in this region.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Crustal velocity
  • back-propagation algorithm
  • polynomial modeling

احمدی، م.، موسوی، س.، م.، 1391، حل دقیق معادلات موقعیت در گیرنده های GPS با استفاده از شبکه های عصبی: مجله علمی و پژوهشی رایانش نرم و فناوری اطلاعات، جلد 1 شماره 1

Beale, M. H. , Hagan, M. T. , Demuth, H. B., 2010, Neural Network Toolbox 7 User’s Guide: The MathWorks Inc., Natick, MA, 951 pp.,

Gullu, M., Yilmaz, I., Yilmaz, M., Turgut, B., 2011a, an alternative method for estimating densification point velocity based on back propagation artificial neural networks: Studia Geophysica et Geodaetica, 55 (1), 73-86

Ghaffari, M. R., Vosooghi, B., 2014, 2Dimentinal Crustal Deformation Analysis with Using IPGN Data:  International Geosciences Congress

Hossainali, M. M., 2006, a Comprehensive Approach to the Analysis of the 3Dkinematics of Deformation: Geodesy. Darmstadt, University of Darmstadt

Moghtased-Azar, K., Zaletnyik, P., 2009, Crustal velocity field modeling with neural network and polynomials: In: SIDERIS, M.G. (Ed.), Observing our changing Earth, International Association of Geodesy Symposia, 133, pp. 809-816

Voosoghi, B. , 2000, Intrinsic deformation analysis of the earth surface based on 3-D displacement fields derived from space geodetic measurements: PhD Thesis, Department of Geodesy and Geoinformatics, Stuttgart University

Yilmaz, M., 2013, Artificial Neural Networks Pruning Apprpach for Geodetic Velocity Field Determination: BCG - Boletim de Ciências Geodésicas