Global land use / land cover with Sentinel 2 and deep learning

• Main Authors: Karra, Krishna, Kontgis, Caitlin, Statman-Weil, Zoe, Mazzariello, Joseph C., Mathis, Mark, Brumby, Steven P.
• Format: Conference Proceeding
• Language: English
• Subjects: Deep learning; Geoscience and remote sensing; Government; Image segmentation; Industries; land use land cover; Satellites; segmentation; Sentinel 2; Time series analysis
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS47720.2021.9553499

Land use/land cover (LULC) maps are foundational geospatial data products needed by analysts and decision makers across governments, civil society, industry, and finance to monitor global environmental change and measure risk to sustainable livelihoods and development. There is a strong need for high-level, automated geospatial analysis products that turn these pixels into actionable insights for non-geospatial experts. The Sentinel 2 satellites, first launched in mid-2015, are excellent candidates for LULC mapping due to their high spatial, spectral, and temporal resolution. Advances in deep learning and scalable cloud-based compute now provide the analysis capability required to unlock the value in global satellite imagery observations. Based on a novel, very large dataset of over 5 billion human-labeled Sentinel-2 pixels, we developed and deployed a deep learning segmentation model on Sentinel-2 data to create a global LULC map at 10m resolution that achieves state-of-the-art accuracy and enables automated LULC mapping from time series observations.