Researchers have developed deep neural networks to improve the resolution of land surface temperature (LST) data for urban areas. By combining data from geostationary and polar-orbiting satellites, they created LST fields with a 1 km resolution at 15-minute intervals. A U-Net model was trained to downscale SEVIRI/MSG data to MODIS resolution, achieving an RMSE of 1.92°C. Additionally, a ConvLSTM model was used for nowcasting LSTs up to 75 minutes ahead, outperforming benchmark models with RMSEs between 0.57°C and 1.15°C. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Enhances urban climate modeling and satellite monitoring capabilities with higher-resolution temperature data.
RANK_REASON The cluster contains an academic paper detailing a new methodology and results in the field of machine learning applied to environmental science. [lever_c_demoted from research: ic=1 ai=1.0]