The land use dynamics of urban, agricultural, and ecological spaces are critical factors influencing land surface temperature (LST); however, the existing methods for describing the spatial carriers of land surface temperature evolution face issues such as granularity effects and projection sensitivity, which hinder effective comparisons across different regions and categories, thus limiting the progress of current research. This study introduces a quadtree-based spatial framework to achieve unified measurements of scale and fragmentation across Urban–Agricultural–Ecological spaces, with an empirical analysis of the Middle Yangtze River Region. Results show that between 2000 and 2020, urban and agricultural spaces expanded while ecological spaces declined, with all three types becoming increasingly fragmented. Urban agglomeration and expansion significantly elevated LST; agricultural spaces exerted relatively limited effects; and ecological fragmentation generated localized cooling but weakened core regulatory functions, ultimately leading to warming within ecological spaces themselves. This study proposes a robust method for spatial identification and fragmentation quantification, revealing the dual role of scale and morphology in regulating regional thermal environments and underscoring the importance of balanced Urban–Agricultural–Ecological configurations for climate-adaptive land use planning.

Exploring the evolutionary dynamics of urban, agricultural, and ecological spaces is critical for regional sustainable development and spatial governance. However, traditional spatial simulation methods based on Cellular Automata often struggle to accommodate top-down spatial regulation, non-linear development patterns, and coordinated regional growth. The objective of this scientific research is to address these limitations by proposing a deep learning-based framework for simulating the future distribution of these three spaces. Utilizing the Unet++ model and integrating empirical data sources including multi-period remote sensing land-use mapping and prefecture-level socioeconomic statistical data, the framework predicts regional spatial patterns for the year 2030. Empirical results from the Yangtze River Economic Belt demonstrate that the model achieves high precision in large-scale spatial forecasting (with an average test accuracy of 99.32%) and effectively captures non-linear evolutionary characteristics. Predictions across various growth scenarios reveal that a moderate socioeconomic growth rate facilitates ecological preservation; controlling the expansion of urban space to approximately 20% by 2030 can prevent excessive resource depletion and regional imbalances. Consequently, it is recommended to implement the construction land increment targets outlined in current spatial planning to achieve a balance between economic growth and ecological protection.