AI-Enhanced Remote Sensing Applications in Earth Science Processes for Enhancing Sanitation Workers’ Safety

Sanitation workers are pivotal in sustaining public health and environmental hygiene but face numerous challenges, such as exposure to hazardous environments, inefficient routing, and variable environmental conditions. Traditional approaches to these challenges lack the precision and flexibility needed to guarantee safety and improve operational efficiency. With rising urbanization and industrial activities, addressing these issues is increasingly urgent. This study proposes a novel methodology that harnesses AI and remote sensing technologies to enhance the safety and efficiency of sanitation workers. Utilizing a hybrid model that combines advanced feature extraction via Cascade ShuffleNet with a sophisticated Ensembled AlexNet and SVM classification strategy (EA-SVM), this approach leverages data from satellite imagery, drone sensors, and terrestrial sensors to form an exhaustive environmental overview. The EA-SVM model achieves a remarkable accuracy of 97.54%, substantially surpassing conventional deep learning models. This approach not only enhances risk prediction and mitigation for sanitation workers but also optimizes their routing and overall operational effectiveness.