William sees landscapes through data. His background in geography, remote sensing, and environmental indicators has led him from academic research on ecosystem vulnerability to applied work helping Nature-based Solutions teams understand vegetation and land-cover change at scale. He uses Python, deep learning, satellite imagery, and machine learning to support carbon credit frameworks and REDD+ projects, including workflows that combine Sentinel-1 SAR and optical imagery to validate vegetation conditions. William holds a PhD in Geography focused on remote sensing and land-cover mapping. His work brings the rigor of academic spatial research into the practical decisions project teams need to make.

‍