Search

Kunming is the capital city of Yunnan Province and a bridgehead city facing South Asia and Southeast Asia. With the rapid development of Kunming's economy and society, the urbanization rate continues to increase, and the quality of the ecological environment in this area is also changing rapidly. How to quickly and accurately obtain the temporal and spatial pattern evolution of Kunming's ecological environment quality and explore the driving factors is of great significance to the realization of ecological environmental protection and sustainable development of Kunming. In this paper, the Google Earth Engine (GEE) platform is used to use the long-term Landsat remote sensing image data to mask the water body, extract greenness, dryness, humidity and heat, and construct the remote sensing ecological index RSEI through PCA. Using spatial analysis methods such as cold and hot spot analysis and center of gravity migration to explore the evolution of the spatio-temporal pattern of ecological environment quality in Kunming from 2000 to 2019, and use single-factor analysis and interactive detection in geographic detectors to analyze its internal driving forces. The results show, (1) From 1995 to 2019, the quality of the ecological environment in Kunming showed a trend of first increasing-then decreasing-then increasing. The overall ecological environment quality was in a general state in the past 25 years, but the ecological environment continued to improve. (2) In the past 25 years, the ecological environment quality grade area of Kunming City is, medium ecological environment area > good ecological environment area > poor ecological environment area > poor ecological environment area > excellent ecological environment area. From the perspective of spatial distribution, the ecological environment quality presents The spatial distribution pattern of high in the southwest and poor in the northeast. (3) From 1995 to 2019, the centers of the standard deviation ellipse of Kunming's ecological environment were relatively close to each other, and the major axes all showed a south-north direction. (4) In Kunming, the ecological environment quality is poor in areas with concentrated rocky desertification, concentrated water and soil erosion, concentrated population and rapid urban expansion, while areas with better ecological environment mostly have higher vegetation coverage. Population and slope are the human activity factors and natural factors that dominate the spatial distribution of ecological environment in Kunming, respectively. Slope, population and GDP, together with other factors, have a significant impact on the quality of ecological environment in Kunming. (5) In the future, Kunming City should rigorously prioritize the protection of key ecological areas, enhance ecological conservation and restoration efforts, optimize land use and development, continuously enhance the quality of the ecological environment, and achieve synchronous and sustainable development of the ecological environment and the economy. [ABSTRACT FROM AUTHOR]

Traffic congestion prediction has become an indispensable component of an intelligent transport system. However, one limitation of the existing methods is that they treat the effects of spatio-temporal correlations on traffic prediction as invariable during modeling spatio-temporal features, which results in inadequate modeling. In this paper, we propose an attention-based spatio-temporal 3D residual neural network, named AST3DRNet, to directly forecast the congestion levels of road networks in a city. AST3DRNet combines a 3D residual network and a self-attention mechanism together to efficiently model the spatial and temporal information of traffic congestion data. Specifically, by stacking 3D residual units and 3D convolution, we proposed a 3D convolution module that can simultaneously capture various spatio-temporal correlations. Furthermore, a novel spatio-temporal attention module is proposed to explicitly model the different contributions of spatio-temporal correlations in both spatial and temporal dimensions through the self-attention mechanism. Extensive experiments are conducted on a real-world traffic congestion dataset in Kunming, and the results demonstrate that AST3DRNet outperforms the baselines in short-term (5/10/15 min) traffic congestion predictions with an average accuracy improvement of 59.05%, 64.69%, and 48.22%, respectively. [ABSTRACT FROM AUTHOR]

Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data's positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area's road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods. [ABSTRACT FROM AUTHOR]

This paper examines the morphologies of Villages-in-the-City (ViCs) in Kunming in China and Hanoi in Vietnam, that are undergoing rapid urbanisation and urban transformation. In China, the term Chengzhongcun refers to development of rural settlements that have been included in the urban districts arising from city expansion. Meanwhile, in Vietnam, the phrase Làng trong phố is used to describe settlements in urban areas that used to be rural villages. Both types of settlements share many common characteristics linked to rural background, and to social and economic policies in these two countries. The findings illustrate that spatial transformations are generated by fundamental economic and social changes, and that the influences of land policies and roles played by local government in each country have significant impacts on the formation of the ViCs. Although the planning processes are managed though top-down systems, the diverse practices and small scale and cost-effective tactics contribute to the transitions of the ViCs. The morphological differences between ViCs development in two countries are due to differences in management modes and land use rights. The outcome of this paper contributes to the deeper understanding about similarities and differences of ViCs in the Global South. • This paper examines and compare the morphologies of Villages-in-the-City in Kunming in China and Hanoi in Vietnam. • The diverse practices and small scale tactics contribute to the transition from rural to urban live styles in both places. • The differences between ViCs developments are due to different modes of management and land use rights. [ABSTRACT FROM AUTHOR]