Impacts of future urban expansion on natural habitats will intensify in China: scenario analysis with the improved LUSD-urban model

Context Evaluating the impacts of future urban expansion on natural habitats in China is important for achieving sustainable development goals. However, existing models cannot reliably and effectively simulate future urban expansion in China, which causes great uncertainties in evaluating the impacts of future urban expansion on natural habitats. Objectives The objective of this study was to simulate future urban expansion and evaluate its impacts on natural habitats in China. Methods First, the Land Use Scenario Dynamics-urban (LUSD-urban) model was improved by coupling localized Shared Socioeconomic Pathways (SSPs) and a convolutional neural network (CNN). Then, urban expansion in China was simulated from 2020 to 2050 by using the improved LUSD-urban model. Finally, we evaluated the potential impacts of future urban expansion on natural habitats. Results The localized SSPs could more reliably represent future socioeconomic development trends in China, and the CNN could fully extract the multiscale neighborhood information of nonurban pixels. By combining the advantages of the localized SSPs and the CNN, the simulation accuracy of the improved LUSD-urban model increased by 15–32% compared with that of other models. From 2020 to 2050, urban land is projected to increase by 6.84 (3.94–9.03) × 10 4 km 2 and cause a 2.21 (1.23–2.95) × 10 4 km 2 loss of natural habitat. Compared with the 1990–2020 period, the impacts of future urban expansion on natural habitats will intensify. Natural habitat loss during 2020–2050 will be 1.23 (1.22 to 1.64) times greater than that during 1990–2020. In addition, grasslands will experience the most serious losses under the influence of future urban expansion. Conclusions We suggest that relevant policies be issued to protect important natural habitats during urbanization to achieve Sustainable Development Goals and biodiversity conservation targets in China.