Cuiping Wang

The accelerated global urbanization process has positioned land use/land cover change modeling as a critical component of contemporary geographic science and urban planning research. Traditional approaches face substantial challenges when addressing urban system complexity, multiscale spatial interactions, and high-dimensional data associations, creating urgent demand for sophisticated analytical frameworks. This review comprehensively evaluates machine learning applications in land use prediction through systematic analysis of 74 publications spanning 2020–2024, establishing a taxonomic framework distinguishing traditional machine learning, deep learning, and hybrid methodologies. The review contributes a comprehensive methodological assessment identifying algorithmic evolution patterns and performance benchmarks across diverse geographic contexts. Traditional methods demonstrate sustained reliability, while deep learning architectures excel in complex pattern recognition. Most significantly, hybrid methodologies have emerged as the dominant paradigm through algorithmic complementarity, consistently outperforming single-algorithm implementations. However, contemporary applications face critical constraints including computational complexity, scalability limitations, and interpretability issues impeding practical adoption. This review advances the field by synthesizing fragmented knowledge into a coherent framework and identifying research trajectories toward integrated intelligent systems with explainable artificial intelligence.

China has entered an era of population decline, yet urbanization continues as rural-to-urban migration persists. This demographic transition has prompted a strategic shift in urban development from extensive spatial expansion toward quality-oriented, intensive growth models. However, evolving human–land supply–demand dynamics in cities historically characterized by population inflows remain insufficiently understood. This study focuses on Xiamen, a prototypical coastal migrant-receiving city, to investigate land use simulation under demographic transition. By integrating the cohort-component method with the Patch-generating Land Use Simulation (PLUS) model, we project Xiamen’s population under three scenarios by 2030: Stable Continuation (SCS), Natural Development (NDS), and National 2030 Population Planning (NPP), with projected increases of 5.56%, 6.76%, and 24.69%, respectively. Results show continued but decelerating population growth, with adequate labor supply and persistent demographic dividend. Notably, the NPP scenario reveals a negative correlation between population growth and construction land expansion. In NPP-High, prioritizing compact development and ecological conservation, population grows by 1.27 million while construction land decreases by 2.85% and forest land increases by 4.09%. This framework provides empirical evidence for compact urban development under the dual constraints of land-use efficiency and ecological protection.

Different types of ecosystems form a complex community of life. Hence, ecosystem protection and restoration should not focus solely on a single ecosystem. Ecosystem health assessments should consider the integrity and systematicity of interrelated ecosystems to inform rational environmental planning and management. In this study, the key characteristic indicators of major ecosystems (mountain, water, forest, and cropland) and ecosystem service capacity indicators in Anxi County, China, were selected to construct an integrated assessment system of ecosystem health that led to integrated ecosystem restoration pathways that addressed the county’s ecological problems. The results revealed that ecosystem health was higher in the western and lower in the eastern parts of the county. Throughout the county, “medium” and “poor” ecosystem health levels predominated, revealing that overall ecosystem sustainability was weak. Ecosystem restoration programmes should be tailored to each health level. Where there was “excellent” and “good” ecosystem health ratings, those healthy ecosystem functions should be strengthened and maintained. In the “medium” health areas, the control and prevention of ecological problems should be strengthened. “Poor” health areas require immediate integrated ecological restoration projects that ensure the connectivity and coordination of restoration tasks in fragile ecosystems. This then will enhance holistic ecosystem stability and sustainability.

Accurate determination of the spatial distribution of coastal wetlands is crucial for the management and conservation of ecosystems. Feature selection methods based on the Jeffries-Matusita (J-M) method include J-M distance with simple average ranking (JM_ave), J-M distance based on weights and correlations (JM_improved), and heuristic J-M distance (JM_mc). However, as the impacts of these methods on wetland classification are different, their applicability has rarely been investigated. Based on the Google Earth Engine (GEE) and random forest (RF) classifier, this is a comparative analysis of the applicability of the JM_ave, JM_improved, and JM_mc methods. The results show that the three methods compress feature dimensions and retain all feature types as much as possible. JM_mc exhibits the most significant compression from a value of 35 to 15 (57.14%), which is 37.14% and 40% more compressed than JM_ave and JM_improved, respectively. Moreover, they produce comparable classification results, with an overall classification accuracy of 90.20 ± 0.19% and a Kappa coefficient of 88.80 ± 0.22%. However, different methods had their own advantages for the classification of different land classes. Specifically, JM_ave has a better classification only in cropland, while JM_mc is advantageous for recognizing water bodies, tidal flats, and aquaculture. While JM_improved failed to retain vegetation and mangrove features, it enables a better depiction of the mangroves, salt pans, and vegetation classes. Both JM_ave and JM_improved rearrange features based on J-M distance, while JM_mc places more emphasis on feature selection. As a result, there can be significant differences in feature subsets among these three methods. Therefore, the comparative analysis of these three methods further elucidates the importance of J-M distance in feature selection, demonstrating the significant potential of J-M distance-based feature selection methods in wetland classification.