Land use/cover change (LUCC) models are essential for studying the profound impact of land use/cover dynamics on various aspects of the natural and social environment. Cellular Automata (CA) is widely used in the dynamic modeling of complex LUCC systems. In the traditional machine learning CA model, when using statistical methods to obtain neighborhood features, there is usually the problem that the spatio-temporal feature learning of neighborhood factors is insufficient. At the same time, the CA dynamic iteration module using the random seed selection mechanism often has the problem that the seed selection efficiency is very low. In this paper, taking the Chongqing Metropolitan Area as an example, convolutional neural networks (CNN)-Long Short-Term Memory Network (LSTM) is introduced to improve the learning effect of the traditional random forest (RF)-CA model in the spatial and temporal characteristics of neighborhood factors. CNN is used to extract the spatial dimension features of LUCC in the neighborhood, and the LSTM model is used to extract the time dimension features and long-term dependencies. At the same time, a high-quality seed selection iterative algorithm (HQSSIA) is used to improve the accuracy of the multi-land-use dynamic change model and the efficiency of the iterative algorithm. The results show that, the proposed model performs better than other models in simulating the LUCC from 2015 to 2020 (Kappa = 0.9684, FOM = 0.1744, Accuracy = 0.9829, F1 = 0.9641, Hamming = 0.0171) and from 2010 to 2020 (Kappa = 0.9599, FOM = 0.4662, Accuracy = 0.9785, F1 = 0.8113, Hamming = 0.0214). After introducing the CNN-LSTM model, the Figure of Merit (FOM) increased by 1.56% and 18.88% for 2015–2020 and 2010–2020. Compared with the CA model-based random seed selection algorithm, the FOM of the model using HQSSIA in the dynamic iteration module are improved by 11.60% and 24.79% for 2015–2020 and 2010–2020, and the operation efficiency of the dynamic iteration module is improved by about 19 times. Compared with the current mainstream LUCC models PLUS and FLUS, the proposed model has improved 14.38%, 37.55%, and 14.93%, 37.74% in FOM, respectively, for 2015–2020 and 2010–2020. The research shows that: (1) RF-CNN-LSTM-CA model not only retains the interpretability advantage of the traditional RF-CA model, but also improves the accuracy of the whole model by improving the spatio-temporal characteristics of neighborhood factors through in-depth learning; (2) the HQSSIA can quickly and accurately search for cells to be converted with higher conversion probability in the observed data, which can not only significantly reduce the time complexity of the model, but also improve the accuracy of LUCC simulation.

Natural environmental factors and human activity intensity factors, the two main factors that affect the spatial and temporal distribution of PM_2.5 concentration near the surface, have different mechanisms of action on PM_2.5 concentration. In this paper, a GTWR-XGBoost two-stage sequential hybrid model is proposed aiming at detecting the expression of spatiotemporal heterogeneity in the traditional machine learning retrieval model of PM_2.5 concentration and the difficulty of expressing the complex nonlinear relationship in the statistical regression model. In the first stage, the natural environmental factors are used to predict PM_2.5 concentration with spatiotemporal characteristics by collinearity diagnosis method and Geographically and Temporally Weighted Regression method (GTWR). In the second stage, the simulation results in the first stage and the natural factors eliminated through LUR stepwise regression in the first stage are into the XGBoost model together with the human activity intensity factors in the buffer zone with the best correlation coefficient of PM_2.5, and finally the temporal and spatial distribution of PM_2.5 concentration. Taking the Chengdu Chongqing Economic Circle as an example, the proposed model is used to retrieve PM_2.5 concentration and compared with the single GTWR, XGBoost, and coupling model published recently. The experimental results show that the R², RMSE, and MAE of the GTWR-XGBoost two-stage model cross-validation are 0.92, 5.44 ug·m⁻³, and 4.12 ug·m⁻³, respectively. Compared with the above single models, R² increased by 0.01 and 0.12, and MAE decreased by more than 0.11 and 3.1, respectively. Compared with the coupling model published recently, R² is increased by 0.02, and MAE is reduced by more than 0.4. In addition, the PM_2.5 concentration in Chengdu Chongqing showed obvious seasonal temporal and spatial changes, and the influence ratios of natural environmental factors and human activity intensity activities factors on PM_2.5 were 0.66 and 0.34. The results show that the GTWR-XGBoost two-stage Model can not only describe the heterogeneity and objectively reflect the complex nonlinear relationship between the phenomenon and the influencing factors, but also enhance the interpretability of the phenomenon when simulating the spatiotemporal distribution characteristics of PM_2.5 concentration.

The identification of roads from satellite imagery plays an important role in urban design, geographic referencing, vehicle navigation, geospatial data integration, and intelligent transportation systems. The use of deep learning methods has demonstrated significant advantages in the extraction of roads from remote sensing data. However, many previous deep learning-based road extraction studies overlook the connectivity and completeness of roads. To address this issue, this paper proposes a new high-resolution satellite road extraction network called FERDNet. In this paper, to effectively distinguish between road features and background features, we design a Multi-angle Feature Enhancement module based on the characteristics of remote sensing road data. Additionally, to enhance the extraction capability for narrow roads, we develop a High–Low-Level Feature Enhancement module within the directional feature extraction branch. Furthermore, experimental results on three public datasets validate the effectiveness of FERDNet in the task of road extraction from satellite imagery.

Exploring spatial anisotropy features and capturing spatial interactions during urban change simulation is of great significance to enhance the effectiveness of dynamic urban modeling and improve simulation accuracy. Addressing the inadequacies of current cellular automaton-based urban expansion models in exploring spatial anisotropy features, overlooking spatial interaction forces, and the ineffective expansion of cells due to traditional neighborhood computation methods, this study builds upon the machine learning-based urban expansion model. It introduces a spatial anisotropy index into the comprehensive probability module and incorporates a gravity-guided expansion neighborhood operator into the iterative module. Consequently, the RF-CNN-SAI-CA model is developed. Focusing on the 21 districts of the main urban area in Chongqing, the study conducts comparative analysis and ablation experiments using different models to simulate the land use changes between 2010 and 2020. Different model comparison results show that the recommended model in this study has a Kappa value of 0.8561 and an FOM value of 0.4596. Compared with the RF-CA model and the FA-MLP-CA model, the Kappa values are higher by 0.0407 and 0.1577, respectively, while the FOM values are improved by 0.0529 and 0.0654, respectively. Ablation experiment results indicate that removing gravity, SAI, and expansion neighborhood operators leads to a decrease in both Kappa and FOM values. These findings demonstrate that the RF-CNN-SAI-CA model, based on the expanded neighborhood iteration algorithm, effectively integrates spatial anisotropy features, captures spatial interaction forces, and resolves neighborhood cell failure issues, thereby significantly improving simulation effectiveness.

Aiming at the problem that demographic data cannot visually and clearly show the true distribution of population and cannot be combined with other environmental resource spatial data for analysis. This paper takes Chongqing as an example, selects nighttime light data etc. as variable factors affecting population distribution. Using the Xgboost model to build a regression model on the county level, and generates the population data of 100m in Chongqing in 2010. The accuracy of the population spatialization results and three public data sets were compared on the township scale. Finally, based on the importance of the variable factors of the Xgboost model, the influencing factors of the spatial distribution of Chongqing’s population were explored. The results show that the root mean square error in this paper is significantly better than the other three population data sets, the absolute value error is significantly better than the GPW data set and the Chinese kilometer grid data set, and slightly better than the World Pop data set. Through the analysis of the importance of variable factors, it is found that the distance from construction land is the most important indicator, and the nighttime light data, residential area and POI data all play an important role in population distribution of Chongqing.

Semantic segmentation for high-resolution remote-sensing imagery (HRRSI) has become increasingly popular in machine vision in recent years. Most of the state-of-the-art methods for semantic segmentation of HRRSI usually emphasize the strong learning ability of deep convolutional neural network to model the contextual relationship in the image, which takes too much consideration on every pixel in images and subsequently causes the problem of overlearning. Annotation errors and easily confused features can also lead to the confusion problem while using the pixel-based methods. Therefore, we propose a new semantic segmentation network—the region-enhancing network (RE-Net)—to emphasize the regional information instead of pixels to solve the above problems. RE-Net introduces the regional information into the base network, to enhance the regional integrity of images and thus reduce misclassification. Specifically, the regional context learning procedure (RCLP) can learn the context relationship from the perspective of regions. The region correcting procedure (RCP) uses the pixel aggregation feature to recalibrate the pixel features in each region. In addition, another simple intra-network multi-scale attention module is introduced to select features at different scales by the size of the region. A large number of comparative experiments on four different public datasets demonstrate that the proposed RE-Net performs better than most of the state-of-the-art ones.