DySENSE: MIT's GenAI framework synthesizes satellite imagery with dynamic city energy maps

MIT · hf · 2026-11-16

MIT, SMART, and collaborators present DySENSE, a joint multimodal GenAI framework that decouples long-term urban morphology from short-term building energy dynamics, generating realistic satellite imagery aligned with monthly energy maps. Across New York, Washington, Norfolk, and Busan, DySENSE produces high-fidelity synthetic energy data with under 25% labeled data, boosting downstream prediction by 8% mIoU and 8.7% accuracy while cutting error 9-18% CVRMSE (ASHRAE). Data (MUSE2) and code are open-sourced for peak-load analysis, building simulation, and demand response.

Original post →

More from Research

Research channel →