Rooftop photovoltaics (RPVs) are crucial in achieving energy transition and climate goals, especially in cities with high building density and substantial energy consumption. Estimating RPV carbon mitigation potential at the city level of an entire large country is challenging given difficulties in assessing rooftop area. Here, using multi-source heterogeneous geospatial data and machine learning regression, we identify a total of 65,962 km² rooftop area in 2020 for 354 Chinese cities, which represents 4 billion tons of carbon mitigation under ideal assumptions. Considering urban land expansion and power mix transformation, the potential remains at 3-4 billion tons in 2030, when China plans to reach its carbon peak. However, most cities have exploited less than 1% of their potential. We provide analysis of geographical endowment to better support future practice. Our study provides critical insights for targeted RPV development in China and can serve as a foundation for similar work in other countries.

Reliable information on building rooftops is crucial for utilizing limited urban space effectively. In recent decades, the demand for accurate and up-to-date data on the areas of rooftops on a large-scale is increasing. However, obtaining these data is challenging due to the limited capability of conventional computer vision methods and the high cost of 3D modeling involving aerial photogrammetry. In this study, a geospatial artificial intelligence framework is presented to obtain data for rooftops using high-resolution open-access remote sensing imagery. This framework is used to generate vectorized data for rooftops in 90 cities in China. The data was validated on test samples of 180 km²across different regions with spatial resolution, overall accuracy, and F1 score of 1 m, 97.95%, and 83.11%, respectively. In addition, the generated rooftop area conforms to the urban morphological characteristics and reflects urbanization level. These results demonstrate that the generated dataset can be used for data support and decision-making that can facilitate sustainable urban development effectively.

Rooftop photovoltaic (RPV) is often understood as a niche contribution to climate change mitigation. However, the global potential of RPVs to mitigate global warming is unknown. Here we map the global rooftop area at 1-km resolution, quantifying 286,393 km² of rooftops worldwide through geospatial data mining and artificial intelligence techniques. Using nine advanced Earth system models from the coupled model intercomparison project phase 6, we reveal that RPVs could substantially contribute to reducing global temperatures by 0.05–0.13 °C before 2050. Region-specific analysis underscores the variability in RPV potential and the necessity of tailored approaches to optimize RPV deployment, considering local solar resources, existing infrastructure and grid carbon intensity. Our findings reveal that leveraging RPV systems offers a viable and impactful strategy for reducing carbon footprints and combating climate change globally, while advocating targeted interventions to enhance the benefits of RPVs, particularly in areas with high solar radiation or rapid urbanization.

Urban functional area (UFA) recognition is one of the most important strategies for achieving sustainable city development. As remote-sensing and social-sensing data sources have increasingly become available, UFA recognition has received a significant amount of attention. Research on UFA recognition that uses a single dataset suffers from a low update frequency or low spatial resolution, while data fusion-based methods are limited in efficiency and accuracy. This paper proposes an integrated model to identify UFA using satellite images and taxi global positioning system (GPS) trajectories in four steps. First, blocks were generated as spatial units in the study area, and the spatiotemporal information entropy of the taxi GPS trajectory (STET) for each block was calculated. Second, a 24-hour time-frequency series was formed based on the pick-up and drop-off points extracted from taxi trajectories and used as the interpretation indicator of the blocks. The K-Means++ and k-Nearest Neighbor (kNN) algorithm were used to identify their social functions. Third, a multilabel classification method based on the residual neural network (MLC-ResNets) and “You Only Look Once” (YOLO) target detection algorithms were used to identify the features of the typical and atypical spatial textures, respectively, of the satellite images in the blocks. The confidence scores of the features of the blocks were categorized by the decision tree algorithm. Fourth, to find the best way to integrate the two sub-models for UFA identification, the 10-fold cross-validation method based on stratified random sampling was applied to determine the most optimal STET thresholds. The results showed that the average accuracy reached 82.0%, with an average kappa of 73.5%—significant improvements over most existing studies. This paper provides new insights into how the advantages of satellite images and taxi trajectories in UFA identification can be fully exploited to support sustainable city management.