Leveraging Deep Learning and IoT Big Data Analytics for The Determination of Development Priorities Utilizing GeoAI in The National Project for The Development of the Egyptian Rural Villages - Decent Life "Hayah Karima"

The problem of rural villages and slums of the countryside is one of the most critical matters faced by many developing countries as well as some developed countries. In 2021 The Egyptian government launched the National Initiative for the Development of the Egyptian Rural Villages – Decent Life (Hayah Karima). This initiative is the result of a humane responsibility and a social dimension since it has a greater purpose than simply enhancing the daily lives and living situations of Egyptian residents. This paper focuses on developing a model for the determination of the development priorities utilizing GeoAI in the villages of Asuit as it was considered as one of the governorates with the greatest need for development. GeoAI can be construed as an analysis environment to build intelligent computer programs that mimic human perception, spatial reasoning, and discovery of geographic phenomena and dynamics, for advanced knowledge about the determination of development priorities in the study area. Shamya village, which located in Sahel Selim center, Asuit, Egypt; was selected as a study area as it was considered one of the poorest villages according to the development priorities in the Egyptian Rural Villages Development Project, where the poverty rate exceeds more than 70%. This is consistent with the Egyptian government strategy of giving Upper Egypt villages more consideration. GeoAI was utilized for buildings and streets footprint automatic detection and digitizing employing deep learning algorithms. Evaluating the use of classic techniques to create spatial maps, which required 40 working hours, utilizing GeoAI, which produced spatial maps for the same area in 30 minutes with higher precision and with less working and quality control time. It was proven that GeoAI presents a unique and promising approach for automatically detecting objects and mapping them to determine development trajectories.