An urban agglomeration is a growth pole of regional development. However, the land uses have changed significantly due to the impacts of intense human activities. Analyzing the overall change characteristics of land use and hotspots has direct reference value for the formulation and implementation of land use management measures. This study used a complex network of analysis methods and a cluster and outlier analysis to study the land use changes and hotspots in the Harbin–Changchun urban agglomeration (HCUA). The results showed that farmland exhibited a high weighted degree of centrality, indicating that it is the key land type in the HCUA land use change network. From 1990 to 2000, the land use change in each city mainly manifested as the loss of ecological land, whereas from 2000 to 2010 it manifested as the restoration of ecological land. From 1990 to 2020, the average path length of the network in 11 cities was less than 1.4, which was reduced in 10 cities, indicating that the stability weakened and land use change more likely occurred. Specifically, the area of ecological land reduction hotspots gradually decreased from 15,237.81 km² to 11,533.95 km². In the ecological land concentration area, the change hotspots for ecological land use and ecological function had strong consistency. The distribution and changes of hotspots were affected by policies and the terrain. The increase in ecological land around urban built-up areas, however, did not improve the landscape connectivity. Therefore, in the planning of ecological land use, attention should be paid to the landscape pattern.

Understanding intra-urban spatial interaction is essential for context-sensitive urban planning. While classical spatial interaction theories provide strong conceptual foundations, systematically translating these theoretical concepts into quantifiable indicators remains a significant methodological challenge. Furthermore, capturing the complex, non-linear dynamics driving urban mobility requires analytical approaches that balance predictive power with interpretability. To address this gap, this study develops a feasible, theory-informed analytical framework that bridges classical spatial interaction theory with interpretable machine learning to quantify the predictive patterns underlying intra-urban mobility. In a case study of Changchun, China, Ullman’s three core concepts, together with fundamental measures of urban scale, were systematically operationalized as a set of quantitative proxy variables based on multi-source geospatial big data. XGBoost was then used to model grid-level origin-destination flows at multiple spatial resolutions, and the SHapley Additive exPlanations (SHAP) was used to assess the contributions and dependence patterns of the theory-driven indicators. The results demonstrate the framework’s predictive robustness, with the XGBoost model consistently outperforms the traditional parametric benchmark across all evaluated spatial resolutions. The 1000 m resolution provided the best balance between predictive performance and spatial detail, yielding an R² of 0.696, compared with 0.611 for the benchmark. The explanatory analysis indicates that functional complementarity is the most critical predictive dimension overall. It also identifies distinct nonlinear patterns, including negative associations between transfer impedance and predicted mobility flows beyond critical thresholds, positive associations between built-environment scale indicators and predicted flows only above minimum intensity thresholds, and diminishing marginal associations between intervening opportunities and predicted flows. This study provides a scalable and transferable approach for diagnosing spatial interactions in data-rich urban contexts, providing an empirical basis for calibrating future micro-level urban simulations.