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.
More from Research
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- U-M's CrowdBark crowdsources dog videos to study canine communication with AI — radamihalcea · 2026-11-16
- Top 10 Eval Papers of 2026: verifiers, agent-as-a-judge, and audit of self-improvement — omarsar0 · 2026-11-16
- Koshien robot team shares control stack: nonlinear-opt trajectories hit ±1.2cm average error — 4310sy · 2026-11-16
- A diffusion model trained on CIFAR-10 re-images black hole M87* — and the ring persists — bravo_abad · 2026-11-16
- SPU benchmark tests whether AI can predict real wet-lab outcomes in 116 tasks — liangchen5518 · 2026-11-16