Open borewells pose a significant threat, particularly in rural and semi-urban regions in India, leading to accidents and fatalities. Current manual inspection methods are inefficient and prone to delays. This paper presents an integrated solution that leverages deep learning and mobile technology to automate the identification, reporting, and management of open borewells. Using a convolutional neural network (CNN) (Alzubaidi et al. in J Big Data 8(1), (2004) [1]), our system classifies images of borewells. The CNN-based system demonstrated superior accuracy (99.5%), precision (99.07%), and recall (98.71%), outperforming state-of-the-art models such as YOLOv5 and ResNet. If the borewell is identified as open, it is reported. Once reported, the system emails the borewell location and uploads the data to Firebase Firestore for real-time monitoring. Authorized district officials can log in to a secure Android app, view borewells in their jurisdiction, and update the status when closed, with all changes reflected instantly in the database. While the system automates borewell detection and reporting, its effectiveness relies on the proactive participation of local authorities to close the borewells. Future work will explore advanced solutions, such as drone-based detection and autonomous navigation, to address geographic challenges and enhance scalability further.