This study builds a situation awareness and decision support framework for the rural economy using spatio-temporal big data, collecting data from 2013 to 2023 on macroeconomics, population, land environment, and traffic flow.After data cleaning and processing, reliable samples are formed.The study uses clustering methods to reveal the spatio-temporal distribution of rural economy and identifies development rhythm differences with slow and fast variable models.A decision-making model is developed with input variables and strategy simulations for different scenarios.A multi-dimensional evaluation system, incorporating comprehensive weighting and grade classification, is used for dynamic early warning and feedback.The results show increasing economic activity in the eastern region, fluctuating activity in the central region, and slow growth in the western region, with the model predictions fitting actual values well.The study highlights current bottlenecks in rural economic development and offers policy suggestions for regional coordination, labour support, resource optimisation, and data governance.
Chen et al. (Thu,) studied this question.