DySENSE:用卫星影像合成城市逐月建筑能耗地图的多模态生成框架
DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery
做城市能耗或建筑模拟的团队可以看看这个开源框架,四城市实验里用不到 25% 标注数据就把下游预测 mIoU 拉高 8%,误差按 ASHRAE 标准降了 9%–18%。和只做预测的已有方法不同,它能生成带能耗对齐的新城市影像,MUSE2 数据集也一起放出了。
一个来自学界的新研究在 arXiv 上发布了 DySENSE,这是一个将城市卫星影像与空间对齐的逐月建筑能耗地图联合合成的多模态生成框架。该框架把长期静态城市形态与短期动态能耗解耦:以静态城市土地利用为条件可生成带对齐能耗图的新城市影像;以逐月气候提示为条件则可在保持城市形态不变的情况下生成动态逐月能耗图。
实验覆盖 New York、Washington、Norfolk、Busan 四个城市,结果显示 DySENSE 用不到 25% 的标注数据即可生成高保真合成能耗数据,使下游预测的 mIoU 提升 8%,准确率提升 8.7%,并按 ASHRAE 标准将 CVRMSE 预测误差降低 9%–18%。论文针对的是城市能耗数据稀缺的痛点:城市消耗全球三分之二以上的能源、产生超过 70% 的二氧化碳排放,而现有研究多是对已有城市的预测而非对未来城市的生成。数据集 MUSE2 和代码已在 Hugging Face 与 GitHub 开源,可服务于峰值负荷分析、建筑性能模拟和动态需求响应场景。
DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery
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
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DySENSE, satellite imagery, generative AI.
Source attribution: curated from arXiv cs.AI (@Kailai Sun, Zijie Gao, Mingyi He, Can Rong, Alok Prakash, Baoshen Guo, Shenhao Wang, Jinhua Zhao).