Identifying direct deforestation drivers in Cameroon using deep learning and optical satellite data

Deforestation rates have been increasing in the Congo Basin in recent years, especially in Cameroon. To support actions to slow deforestation, Earth Observation (EO) has been used extensively to detect forest loss, but approaches to automatically identify specific drivers of deforestation in a level of detail that allows for intervention prioritisation have been rare. In this paper, we use deep learning to classify direct deforestation drivers in Cameroon and create a country-specific dataset for this task. We also compare the effectiveness of two types of freely available optical satellite imagery: Landsat-8 (pan-sharpened to a 15 m spatial resolution) and NCIFI PlanetScope (4.77 m spatial resolution). Our detailed classification strategy includes 15 direct deforestation drivers for forest loss events taking place between 2015 and 2020. We obtain an overall accuracy of 82% (F1-score: 0.82) with Landsat-8 data and an overall accuracy of 76% (F1-score: 0.76) for NICFI PlanetScope. Despite a coarser spatial resolution, Landsat-8 performs better than NICFI PlanetScope overall, including for small-scale drivers, although results vary by class. With Landsat-8, using only a single-image approach, we achieve an accuracy of at least 70% for all classes except for ‘Hunting’, ‘Oil palm plantation’, and ‘Fruit plantation’. These results show the potential of using this approach to monitor or analyse land-use changes leading to deforestation with more refined classes than before. In addition, our study demonstrates the potential of leveraging existing available datasets and straightforwardly adapting a generalised framework for other tropical locations with a relatively small amount of location-specific data.