نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشیار دانشکده عمران دانشگاه صنعتی شاهرود
2 دانشجوی دکتری تخصصی مهندسی عمران-مهندسی و مدیریت منابع آب دانشگاه صنعتی شاهرود
3 گروه ژئوتکنیک، آب، راه و نقشه برداری، دانشکده مهندسی عمران-دانشگاه صنعتی شاهرود
چکیده
کلیدواژه‌ها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Remote sensing and image processing techniques have brought about a great transformation in traditional measurements by providing spatial and temporal information and have the potential to increase our knowledge in technical and engineering fields, including computers, water resources engineering, hydraulic structures, and mapping such as snow, geology, and geography. The ability to measure the amount of precipitation and flow is one of the basic applications of remote sensing and image processing. Different image integration methods are used to simultaneously use satellite image's spectral and spatial information. In the integrated image, the ability to interpret increases, and it brings more acceptable results because data with different characteristics are combined with each other. In this research, the integrated image of two satellites (Landsat 8) and (Sentinel - 2) for the study area of Bastam Shahrood was processed with five methods of maximum likelihood, minimum distance, support vector machine (SVM), artificial neural network and random forest. The artificial neural network method with a Kappa coefficient of 0.93 and the minimum distance method with a Kappa coefficient of 0.34 had the best and worst results, respectively. Then, four classification methods of maximum likelihood, support vector machine(SVM), artificial neural network, and random forest were combined with a fuzzy algebraic summation algorithm, and the Kappa coefficient was 0.94, which shows that combining the best classification results can bring better and more accurate classification results.
کلیدواژه‌ها [English]
)