Integration of ChatGPT and GeoAI in Change Detection of Landcover on Landsat Images 2000-2020: A Critical & Empirical Review | ||||
Bulletin de la Société de Géographie d'Egypte | ||||
Articles in Press, Accepted Manuscript, Available Online from 23 November 2024 | ||||
Document Type: Original Article | ||||
DOI: 10.21608/bsge.2024.318561.1039 | ||||
![]() | ||||
Authors | ||||
Mohamed Alkhuzamy Aziz ![]() ![]() | ||||
1Fayoum University | ||||
2Ain Shams University | ||||
3University of Mumbai | ||||
Abstract | ||||
Abstract: Geographical research can be time-consuming and complex due to the need for extensive spatial data analysis. However, the emergence of Geographic Artificial Intelligence (GeoAI) and Chat Generative Pre-Trained Transformer (ChatGPT) offers a promising solution. GeoAI automates spatial data processing and analysis, while ChatGPT generates human-like text based on prompts. By combining these technologies, researchers can streamline their work. This paper introduces an innovative approach combining GeoAI and ChatGPT, referred to as geospatial artificial intelligence and chat-based generative pre-trained transformers. This integration has the potential to revolutionize geographical research by enabling interactive and dynamic interactions between researchers and geospatial data. The methodology involves using GeoAI to prepare specific spatial data for research topics. Advanced algorithms and techniques are employed to process raw geospatial data and extract relevant features. Subsequently, ChatGPT generates Python code for the remaining spatial analysis tasks. The generated code seamlessly integrates into the Python Integrated Development and Learning Environment (Python IDLE) within the ArcGIS environment, allowing researchers to execute the code and obtain optimal outcomes. The paper provides an overview of the integrated methodology's key components and explores its potential applications in various geographical research domains. To demonstrate its practical application, a case study on land cover change detection in the coastal areas of Halayeb and Shalateen in the Red Sea, Egypt, is presented. Landsat images from 2000 to 2020 were analyzed using GeoAI and ChatGPT, showcasing the effectiveness of the proposed methodology. | ||||
Keywords | ||||
Python code generation; geospatial data analysis; landcover; change detection | ||||
Statistics Article View: 366 |
||||