In recent decades, land use/cover change (LUCC) due to urbanization, deforestation, and desertification has dramatically increased, which changes the global landscape and increases the pressure on the environment. LUCC not only accelerates global warming but also causes widespread and irreversible loss of biodiversity. Therefore, LUCC reconstruction has important scientific and practical value for studying environmental and ecological changes. The commonly used LUCC reconstruction models can no longer meet the growing demand for uniform and high-resolution LUCC reconstructions. In view of this circumstance, a deep learning-integrated LUCC reconstruction model (DLURM) was developed in this study. Zhenlai County of Jilin Province (1986–2013) was taken as an example to verify the proposed DLURM. The average accuracy of the DLURM reached 92.87% (compared with the results of manual interpretation). Compared with the results of traditional models, the DLURM had significantly better accuracy and robustness. In addition, the simulation results generated by the DLURM could match the actual land use (LU) map better than those generated by other models.

Land use and land cover change (LUCC) modeling has continuously been a major research theme in the field of land system science, which interprets the causes and consequences of land use dynamics. In particular, models that can obtain long-term land use data with high precision are of great value in research on global environmental change and climate impact, as land use data are important model input parameters for evaluating the effect of human activity on nature. However, the accuracy of existing reconstruction and prediction models is inadequate. In this context, this study proposes an integrated convolutional neural network (CNN) LUCC reconstruction and prediction model (CLRPM), which meets the demand for fine-scale LUCC reconstruction and prediction. This model applies the deep learning method, which far exceeds the performance of traditional machine learning methods, and uses CNN to extract spatial features and provide greater proximity information. Taking Baicheng city in Northeast China as an example, we verify that CLRPM achieved high-precision annual LUCC reconstruction and prediction, with an overall accuracy rate 9.38% higher than that of the existing models. Additionally, the error rate was reduced by 49.5%. Moreover, this model can perform multilevel LUCC classification category reconstructions and predictions. This study casts light on LUCC models within the high-precision and fine-grained LUCC categories, which will aid LUCC analyses and help decision-makers better understand complex land-use systems and develop better land management strategies.

Crop potential yields in cropland are the essential reflection of the utilization of cropland resources. The changes of the quantity, quality, and spatial distribution of cropland will directly affect the crop potential yields, so it is very crucial to simulate future cropland distribution and predict crop potential yields to ensure the future food security. In the present study, the Cellular Automata (CA)-Markov model was employed to simulate land-use changes in Northeast China during 2015–2050. Then, the Global Agro-ecological Zones (GAEZ) model was used to predict maize potential yields in Northeast China in 2050, and the spatio-temporal changes of maize potential yields during 2015–2050 were explored. The results were the following. (1) The woodland and grassland decreased by 5.13 million ha and 1.74 million ha respectively in Northeast China from 2015 to 2050, which were mainly converted into unused land. Most of the dryland was converted to paddy field and built-up land. (2) In 2050, the total maize potential production and average potential yield in Northeast China were 218.09 million tonnes and 6880.59 kg/ha. Thirteen prefecture-level cities had maize potential production of more than 7 million tonnes, and 11 cities had maize potential yields of more than 8000 kg/ha. (3) During 2015–2050, the total maize potential production and average yield decreased by around 23 million tonnes and 700 kg/ha in Northeast China, respectively. (4) The maize potential production increased in 15 cities located in the plain areas over the 35 years. The potential yields increased in only nine cities, which were mainly located in the Sanjiang Plain and the southeastern regions. The results highlight the importance of coping with the future land-use changes actively, maintaining the balance of farmland occupation and compensation, improving the cropland quality, and ensuring food security in Northeast China.

Evaluating the impacts of land-use change (LUC) on ecosystem services (ESs) is necessary for regional sustainable development, especially for the farming–pastoral ecotone of northern China (FPENC), an ecologically sensitive and fragile region. This study aimed to assess the impacts of LUC on the ESs and provide valuable information for regional planning and management in the FPENC. To accomplish this, we assessed LUC in the FPENC from 2010 to 2020 and simulated land-use patterns in 2030 under three plausible scenarios: the business as usual scenario (BAUS), economic development scenario (EDS), and ecological protection scenario (EPS). Then, we quantified five ESs (including crop production, water yield, soil retention, water purification, and carbon storage) for 2020–2030 and analyzed the trade-offs and synergies among ESs in all scenarios. The results show that FPENC experienced expanding farming land and built-up land throughout 2010–2020. Under the BAUS and EDS from 2000 to 2030, especially EDS, the increase in farming land and built-up land will continue. As a result, crop production and water yield will increase, while soil retention, water purification, and carbon storage will decrease. In contrast, EPS will increase soil retention, water purification, and carbon storage at the cost of a decline in crop production and water yield. These results can provide effective reference information for future regional planning and management in the farming–pastoral ecotone.

Forest canopy cover is a crucial indicator for measuring ecological functions. However, traditional plot-based measurement methods suffer from low efficiency and insufficient spatial continuity. Addressing issues in UAV RGB imagery—such as tree crown boundary adhesion, shadow interference, and texture confusion—this paper proposes a lightweight and edge-sensitive tree crown segmentation network. The model employs MobileNetV3-Large to replace the traditional U-Net encoder, significantly reducing parameter count and computational load while satisfying the potential for edge device deployment. In the decoding phase, a Semantic-guided Channel Compression and Focus (SCCF) module is designed to enhance semantic-guided channel compression and feature focusing. Furthermore, a Gradient-guided Morphological Tree Crown Attention Module (G-MTCAM) is proposed. By utilizing Gradient-Induced Center Difference Convolution (GI-CDC) and a variance-based statistical gating mechanism, this module constructs a dual-stream architecture for morphology and texture interaction, achieving precise cutting of tree crown boundaries and effective filtering of background noise. Additionally, a boundary-enhanced composite loss function is introduced to improve the accuracy of crown edge identification. Experimental results indicate that the proposed model achieves an IoU, Acc, and F1 score of 88.59%, 88.62%, and 93.77%, respectively. Compared to the classic U-Net, these represent improvements of 2.77%, 1.71%, and 1.44%, while the parameter count and computational cost are only 5.98 M and 6.71 GFLOPs. The forest Canopy Cover (CC) estimated based on the segmentation results shows high consistency with ground-based near-zenith canopy hemispherical percentage ($CH{P}_{0–30}$, denoted as $C{C}_{obs}$), with a correlation coefficient ($R^2$) exceeding 0.90. This verifies the effectiveness of the method in forest canopy structure monitoring and provides technical support for the application of consumer-grade UAVs in forestry surveys.

Accurate semantic segmentation of high-resolution remote sensing imagery is crucial for applications such as land cover mapping, urban development monitoring, and disaster response. However, remote sensing data still present inherent challenges, including complex spatial structures, significant intra-class variability, and diverse object scales, which demand models capable of capturing rich contextual information from both local and global regions. To address these issues, we propose ArgusNet, a novel segmentation framework that enhances multi-scale representations through a series of carefully designed fusion mechanisms. At the core of ArgusNet lies the synergistic integration of Adaptive Windowed Additive Attention (AWAA) and 2D Selective Scan (SS2D). Specifically, our AWAA extends additive attention into a window-based structure with a dynamic routing mechanism, enabling multi-perspective local feature interaction via multiple global query vectors. Furthermore, we introduce a decoder optimization strategy incorporating three-stage feature fusion and a Macro Guidance Module (MGM) to improve spatial detail preservation and semantic consistency. Experiments on benchmark remote sensing datasets demonstrate that ArgusNet achieves competitive and improved segmentation performance compared to state-of-the-art methods, particularly in scenarios requiring fine-grained object delineation and robust multi-scale contextual understanding.