Beyond built-up land: Mapping complete settlement footprint in China from 1990 to 2020 with Landsat imagery

Introduction Accurate mapping of human settlements is vital for understanding urbanization, human-environment interactions, and sustainable development. Existing medium-resolution products often underestimate the real spatial extent of settlements by focusing solely on built-up cores. Here, we present the China Settlement Footprint 1990-2020 (CSF30) dataset, a nationwide product depicting complete human settlement footprints from Landsat imagery at five-year intervals. CSF30 was generated using an Entity-Based Image Analysis framework integrated with a deep learning architecture. To ensure spatio-temporal generalizability and boundary accuracy, the model was trained via a two-stage strategy utilizing existing built-up area datasets and a newly created settlement footprint dataset. Comprehensive validation demonstrates that CSF30 achieves a mean F1-score of 0.91 across the 30-year period, showing distinct advantages in representing rural and peri-urban areas compared to existing products. CSF30 provides a critical, high-quality baseline for diverse applications, including investigating settlement trajectories, assessing ecological and environmental impacts, and monitoring progress toward the Sustainable Development Goals (SDGs). Data description This product is generated using Landsat collection 2 surface reflectance images. The data contains seven GeoTIFF files representing the China's settlement footprints in seven mapping years from 1990 to 2020 at five-year intervals. In each CSF30 layer, settlement pixels are labeled as 1, while background values are set to NoData (0). CSF 30 dataset employs the EPSG:4326(GCS_WGS_1984) spatial reference system. Acknowledgments This study was supported by the National Natural Science Foundation of China (no. 42401474), the Otto Poon Research Institute for Climate-Resilient Infrastructure (no. N-ZH8Q) and the Hong Kong Polytechnic University (nos. 4-ZZVP and 1-WZC2).