Application of CNN model for ozone layer depletion prediction using satellite data
- Author
- Changamire, Clayton T.
- Title
- Application of CNN model for ozone layer depletion prediction using satellite data
- Abstract
- Ozone layer depletion poses a significant threat to environmental stability and human health, primarily due to increased ultraviolet (UV) radiation exposure. Traditional methods of monitoring ozone concentration rely heavily on ground-based and atmospheric instruments, which are often limited by spatial and temporal constraints. This study proposes the application of a Convolutional Neural Network (CNN) model to predict and analyze ozone layer depletion patterns using satellite imagery and atmospheric data. By leveraging the feature extraction capabilities of CNNs, the model is trained on satellite datasets—such as those from NASA’s OMI (Ozone Monitoring Instrument) and TOMS (Total Ozone Mapping Spectrometer)—to identify anomalies and thinning regions in the stratospheric ozone layer. The model demonstrates high accuracy in classifying ozone-depleted zones and provides a scalable, automated solution for continuous global monitoring. The results underscore the potential of deep learning approaches in enhancing climate surveillance systems and supporting policy-driven environmental protection efforts.
- Date
- June 2025
- Publisher
- BUSE
- Keywords
- CNN Model
- Ozone Layer Depletion
- Supervisor
- Mr. H. Chikwiriro
- Item sets
- Department of Computer Science
Part of Application of CNN model for ozone layer depletion prediction using satellite data