The paper introduces Direct Rooftop Solar Prediction (DRSP), an end‑to‑end method that estimates rooftop solar potential directly from satellite images and regional sunlight data, bypassing explicit geometric reconstruction. DRSP does not predict roof orientation, slope, height, or DSMs, and therefore requires no geometric intermediate supervision. The authors built a large‑scale dataset from the Google Solar API, comprising about 60K rooftops in the U.S. Midwest and 87K in Texas, and evaluated how factors such as geographic training distribution, model depth, image resolution, and sunlight conditioning affect performance.
By Joshua Lee
arXiv:2609.13013v1 Announce Type: new
Abstract: Flat roofs are among the most influential components of the building envelope, governing both structural performance and thermal efficiency, and thereb...
By Samuel Dunthorne, Hashim A. Hashim
The paper introduces a deep‑learning framework that estimates building age using widely available multi‑source geospatial data, including satellite imagery, Digital Surface Models, and building footprints. It employs a pretrained backbone with fine‑tuning adapters, raster‑derived and property‑derived fusion modules, and a pyramid decoder with Cosine‑guided Mixture‑of‑Experts for pixel‑level predictions, while instance‑level predictions use attention pooling and Property‑Conditional Adaptive Instance Normalization. A Temporal Ordinal Constraint Loss enforces the natural ordering of building ages, and the authors provide a new Hong Kong building age benchmark along with open‑source code and datasets.
By Jialu Sui, Hongsheng Zhang, Rui Liu, Jing Ling, Ruisheng Wang, Hao Wu, Gang Chen
arXiv:2607. 07292v1 Announce Type: cross Abstract: Accurately estimating urban carbon emissions is critical for sustainable urban planning, yet many existing approaches remain difficult to apply consistently across cities due to data-source heterogeneity and the lack of fine-grained semantic-temporal context in remote sensing data.
By Zeru Yang, Fang-Ying Gong, Steve H. L. Yim, Chau Yuen
arXiv:2607. 23024v1 Announce Type: cross Abstract: High-resolution satellite imagery is the backbone of good land-cover classification, and without that, environmental monitoring, urban planning, and sustainable resource management all fall short.
By Atiq Ur Rehman, Joseph Michael Donovan
DeepC4 is a deep learning-based spatial disaggregation method that uses local census statistics as cluster-level constraints and incorporates multiple conditional label relationships in a multitask learning framework. Applied to Rwandan urban morphology, it achieves macro‑F1 scores of 0.63, 0.78, and 0.45 for roof, wall, and height prediction, respectively, and estimates national dwelling and occupant counts within about 1.1% error compared to census records. The approach outperforms existing GEM and METEOR methods and covers 32‑49% more 500‑meter grid pixels across provinces.
By Joshua Dimasaka, Christian Gei{\ss}, Emily So