City energy and satellite images generate monthly dynamic energy maps
DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
City energy use is a major part of global carbon emissions, but data showing how energy changes month to month and place to place in cities are hard to get. The authors created DySENSE, a tool that uses satellite images of cities and some real energy data to create detailed, month-by-month maps of building energy use. DySENSE can imagine new city layouts and predict how energy use would look over time, helping plan for energy efficiency. It works well even with limited real data and is useful for understanding energy patterns.
What this means in practice
- •For urban planners: Generate detailed month-by-month energy use maps for city planning and energy optimization using limited real data and satellite images.
- •For energy management teams: Improve building energy demand forecasting and dynamic load management using synthetic, high-fidelity monthly energy consumption maps.
Authors
Kailai Sun, Zijie Gao, Mingyi He, Can Rong, Alok Prakash, Baoshen Guo, Shenhao Wang, Jinhua Zhao
Abstract
Cities account for over two-thirds of the world's energy and more than 70% of global carbon dioxide emissions. City energy is essential for achieving the 2050 net-zero target and the UN's Sustainable Development Goals 7 and 11. Although existing studies have made progress, they are limited by data and methodological gaps. Existing studies are largely predictive for existing cities rather than generative for future cities; fine-grained, aligned monthly dynamic energy data are scarce; and existing GenAI models struggle to generate dynamic urban functional monthly energy. We present DySENSE, a joint multimodal GenAI framework that synthesizes static urban satellite imagery together with spatially aligned, dynamic monthly building energy consumption maps. We decouple long-term static urban morphology from short-term dynamic energy consumption. By conditioning on static urban land use, DySENSE can generate realistic, diverse and new static urban imagery with aligned energy maps. By conditioning on dynamic monthly and climate prompts, DySENSE can jointly generate dynamic, monthly energy consumption maps while keeping the urban morphology static. Experiments across four cities (New York, Washington, Norfolk, Busan) demonstrated that DySENSE can generate annotated high-fidelity synthetic energy data using less than 25% labelled data, boosting downstream prediction performance by 8% mIoU, and achieving strong energy dynamic consistency. Compared to existing methods, DySENSE significantly improved prediction performance (8.7% accuracy) and reduced prediction error (9%-18% CVRMSE, ASHRAE). DySENSE offers an effective foundation for energy-efficient cities, peak-load analysis, building performance simulation and dynamic demand response for city, energy, and building science. The data and code: https://huggingface.co/datasets/skl24/MUSE2 and https://github.com/kailaisun/DySENSE