A big data approach to assess progress towards Sustainable Development Goals for cities of varying sizes

Cities are the engines for implementing the Sustainable Development Goals (SDGs), which provide a blueprint for achieving global sustainability. However, knowledge gaps exist in quantitatively assessing progress towards SDGs for different-sized cities. There is a shortage of relevant statistical data for many cities, especially small cities, in developing/underdeveloped countries. Here we devise and test a systematic method for assessing SDG progress using open-source big data for 254 Chinese cities and compare the results with those obtained using statistical data. We find that big data is a promising alternative for tracking the overall SDG progress of cities, including those lacking relevant statistical data (83 Chinese cities). Our analysis reveals decreasing SDG Index scores (representing the overall SDG performance) with the decrease in the size of Chinese cities, suggesting the need to improve SDG progress in small and medium cities to achieve more balanced sustainability at the (sub)national level. A neural network approach, which utilises open-source big data, can help assess sustainable development in smaller cities across China which have limited data availability and may be further behind in reaching Sustainable Development Goals than their larger counterparts

Automated summary

This study uses open-source big data to assess the progress of Sustainable Development Goals (SDGs) in 254 Chinese cities and compares the results with those obtained using statistical data. The findings suggest that big data is a promising alternative for tracking the overall SDG progress of cities, including those lacking relevant statistical data. The analysis reveals that smaller Chinese cities have lower SDG Index scores, indicating the need to improve SDG progress in small and medium cities for more balanced sustainability.