Land use change is the most prominent feature of Chinese urbanisation. In China, the expansion of land consumed for urban development is inevitable given the rapid increases in the urban economy and urban population, but also in meeting the population’s increasing demand for better quality of life. This paper is based on a research study of Wujiang district in Suzhou, which is considered representative of many of the rapid urbanisation areas within the nation. The objective is to develop an in-depth understanding of the characteristics of land use change and how this change contributes to environmental deterioration, as assessed by changes in the ecosystem service value (ESV). In this study, ESV is defined as the environmental products and functions provided for human well-being. Based on local planning documents, Landsat TM remote-sensing images and field surveys, the research analyses the cost to the environment when traditional land uses are transformed into urbanisation. The research demonstrates that conversion to urban land use which ignores the limit and capacity of the environment can generate significant environmental costs, as assessed by ESV, which in turn, can lead to a deterioration of quality of life for inhabitants, the exact opposite of the original intention. The research demonstrates that by mapping the spatial distribution of ecological service values, ESV can be used as a guide to urban sustainable development.

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.

One of the focal points in Geographic Information Science (GIS) is to uncover the spatial distribution patterns of geographical phenomena. In response to the insufficient spatial feature learning concerning neighborhoods in traditional machine learning-based Cellular Automata (CA) models for land use change, this study couples the Random Forest (RF) model and the Spatially Non-Stationary Convolutional Neural Network (SNSCNN) model to the CA model. The resulting RF-SNSCNN-CA model considers the issue of spatial non-stationarity by incorporating attention mechanisms. Using observed urban land change data from 2010 to 2017 in the 21 districts of Chongqing’s main city as an example, two sets of experiments comprising eight scenarios were designed to verify the neighborhood effects. The results demonstrate that the proposed RF-SNSCNN-CA model achieves an Overall Accuracy (OA) of 97.82%, Kappa of 0.7683, and Figure of Merit (FoM) of 0.3836. The study reveals the following findings. Firstly, the RF-SNSCNN-CA model integrates the dual advantages of traditional machine learning and deep learning models, in which SNSCNN improves by the combined effect of channel and spatial attention mechanisms improves the learning of neighborhood features; secondly, the machine learning-like urban sprawl CA modeling process, regardless of the approach taken to obtain development suitability, cannot completely replace the learning of the neighborhood part; lastly, the use of traditional neighborhood modeling methods may produce suppression of simulation results and make the model inadequately learn spatial features.