Congratulations to Jean de Dieu Tuyizere on the successful defense of his MSc thesis, entitled “Utilizing deep learning and Earth Observation data to predict land cover changes in Volcanoes National Park, Rwanda”.
His study analyzed and projected land cover change (LCC) in Rwanda’s Volcanoes National Park (VNP) from 2019 to 2049 using remote sensing, random forest classification, and a hybrid convolutional neural network (Hybrid-CNN).
The key findings were:
- Between 2019–2024, alpine, subalpine, bamboo, mixed forest, Hagenia-Hypericum, and water areas decreased, while herbaceous and bare land expanded significantly.
- The Hybrid-CNN model (97.9% accuracy) projected continued declines in alpine, bamboo, mixed forest, Hagenia-Hypericum, subalpine, and water cover through 2049, with herbaceous and bare areas expanding further.
- Regression analysis showed that bioclimatic variables influenced LCC patterns differently across land cover types.
This research fills a gap in temporal LCC analysis for VNP, offering high-resolution forecasts crucial for conservation and park management. It recommends ongoing remote sensing monitoring to guide adaptive strategies in response to environmental and climatic changes.
He was supervised by Dr. Insa Otte and Dr. Martin Wegmann (EORC). We wish him all the best for the future!
