The rapid assessment of building damage in earthquake-stricken areas is of paramount importance for emergency response. The development of remote sensing technology has aided in deriving reliable and precise building damage assessments of extensive areas following disasters. It is well documented that convolutional neural network methods have superior performance in earthquake building damage assessment compared with traditional machine learning methods. However, deep learning models require a large number of samples, and sufficient numbers of samples are usually not available in the newly earthquake-stricken areas rapidly enough. At the same time, the historical samples inevitably differ from the new earthquake-affected areas due to the discrepancy of regional building characteristics. For this purpose, this study proposes a data transfer algorithm for evaluating the impact of a single historical training sample on the model performance. Then, beneficial samples are selected to transfer knowledge from the historical data for facilitating the calibration of the new model. Four models are designed with two earthquake damage building datasets and the performance of the models is compared and evaluated. The results show that the data transfer algorithm proposed in this work improves the reliability of the building damage assessment model significantly by filtering samples from the historical data that are suitable for the new task. The performance of the model built based on the data transfer method on the test set of new earthquakes task is approximately 8% higher in overall accuracy compared with the model trained directly with the new earthquake samples when the training data for the new task is only 10% of the historical data and is operating under the objective of four classes of building damage. The proposed data transfer algorithm has effectively enhanced the precision of the seismic building damage assessment in a data-limited context. Thus, it could be applicable to the building damage assessment of new disasters.

China has experienced a huge socioeconomic advancement over the past few decades, resulting in great change in land use and land cover. To date, negligible attention has been given to examining the socioeconomic changes in the context of land-use change, especially from a futuristic standpoint. However, motivated by China’s latest carbon neutrality target, this study analyzes the prospective changes in socioeconomic status, and carbon dioxide emission in the context of future land-use change, focusing on three future periods: 2026–2030 (carbon dioxide peak phase), 2056–2060 (carbon-neutral phase), and 2080–2099 (long-term period). In this regard, recently published land-use products under seven Shared Socioeconomic Pathways-based scenarios (SSP1-1.9, SSP1-2.6, SSP4-3.4, SSP2-4.5, SSP4-6.0, SSP3-7.0, and SSP5-8.5) as part of the CMIP6, as well as the projected GDP and population under five socioeconomic scenarios are used. To estimate socioeconomic change over prominent land-use types (urban), we combined five socioeconomic scenarios with seven corresponding SSPs-based land-use change scenarios (SSP1 with SSP1-1.9 and SSP1-2.6; SSP2 with SSP2-4.5; SSP3 with SSP3-7.0; SSP4 with SSP4-3.4 and SSP4-6.0; and SSP5 with SSP5-8.5 scenarios). Our results reveal that rapid urban land expansion in the future is the most dominant aspect in China. In the carbon neutrality phase (2056–2060), urban land is expected to expand ~80% more than that of the reference period (1995–2014). In the spatial aspect, the expansion of urban land is mainly prominent in the eastern and central parts of China. For socioeconomic changes, the most prominent increase in the urban population is estimated at 630.8% under SSP5-8.5 for the 2056–2060 period compared to the reference period. Regarding GDP for the urban area, industrial GDP will be higher than service GDP in the carbon emission peak phase (2026–2030), but it is projected to be overtaken by service GDP for the carbon-neutral target (2056–2060) and long-term periods (2080–2099). Further, the CO₂ emission in China was found to increase with intensified urban land for the historical period (1995–2019). In the future, the largest increase in CO₂ emission from the urban area is anticipated under SSP5-8.5 in the carbon-neutral target (2056–2060) phase, while CO₂ emission will largely decline after (2056–2060) under SSP1-1.9, SSP1-2.6, and SSP4-3.4. Importantly, population change is expected to be the most predominant factor in future urban land expansion in China. These findings highlight the importance of well-governed urban-land development as a key measure to achieve China’s carbon neutrality goal.