Applications of Artificial Neural Networks in Aerial and Satellite Imagery Analysis: A Case Study on the Natural Terrain of South Sinai | ||||
| مجلة الدراسات الإنسانية والأدبية | ||||
| Volume 31, Issue 2, June 2024, Page 1414-1495 PDF (2.63 MB) | ||||
| Document Type: المقالة الأصلية | ||||
| DOI: 10.21608/shak.2024.307420.1668 | ||||
 View on SCiNiTO | ||||
| Author | ||||
وليد محمد على محمود عجوة عجوة 
| ||||
| مدرس الجغرافيا الطبيعيه- المعهد العالي للدراسات الأدبية – كينج مريوط | ||||
| Abstract | ||||
| Neural networks are considered powerful and effective tools in geographic studies, with numerous applications in image classification, phenomenon modeling, spatial prediction, and change detection. A study has demonstrated successful use of neural networks in analyzing aerial and satellite images in studying the southern Sinai Peninsula. This study addresses geomorphological and geological analysis of southern Sinai's terrain using artificial intelligence and artificial neural networks. The research aims to explore the role of neural networks in classifying and analyzing aerial and satellite images to determine geomorphological phenomena such as land elevations and natural terrain changes. The study focuses on applying Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) in analyzing geographical and geological data, as well as classifying unstructured geomorphological data and using machine learning to extract patterns and relationships. Additionally, it analyzes natural terrains to identify areas of high elevations and rugged terrains. The study utilizes neural networks to predict future changes in natural terrains, such as coastline shifts, rock mass movements, and the formation of new valleys due to climatic or geological factors. It includes gathering and analyzing historical and current data on natural changes in the southern Sinai region using remote sensing techniques and Geographic Information Systems. The study aims to provide information to aid in urban planning, environmental protection, and natural resource exploration based on geomorphological data analysis and predictions of natural changes. | ||||
| Keywords | ||||
| Artificial؛ Neural؛ Networks; Deep؛ Learning | ||||
|
Statistics Article View: 20 PDF Download: 12 |
||||
