Developing countries such as China are undergoing rapid urban expansion and land use change. Urban expansion regulation has been a significant research topic recently, especially in Eastern China, with a high urbanization level. Among others, roads are an important spatial determinant of urban expansion and have significant influences on human activities, the environment, and socioeconomic development. Understanding the urban road network expansion pattern and its corresponding social and environmental effects is a reasonable way to optimize comprehensive urban planning and keep the city sustainable. This paper analyzes the spatiotemporal dynamics of urban road growth and uses spatial statistic models to describe its spatial patterns in rapid developing cities through a case study of Nanjing, China. A kernel density estimation model is used to describe the spatiotemporal distribution patterns of the road network. A geographically weighted regression (GWR) is applied to generate the social and environmental variance influenced by the urban road network expansion. The results reveal that the distribution of the road network shows a morphological character of two horizontal and one vertical concentration lines. From 2012 to 2016, the density of the urban road network increased significantly and developed some obvious focus centers. The development of the urban road network had a strong correlation with socioeconomic and environmental factors, which however, influenced it at different degrees in different districts. This study enhances the understanding of the effects of socio-economic and environmental factors on urban road network expansion, a significant indicator of urban expansion, in different circumstances. The study will provide useful understanding and knowledge to planning departments and other decision makers to maintain sustainable development.
Land use and cover change (LUCC) is one of the most significant parts of global environmental changes, which reflects the interaction between human society and natural resources. In China, the urbanization process is experiencing a rapid sprawl since the reform and open program in 1978, and there has been a serious change in situation in the human–land relationship. In this paper, taking Jiangsu province located in the eastern coastal developed region as an example, the historic evolution process of the land use situation from 1990 to 2010 was explored. Landsat images from three periods were analyzed, using the land use transition matrix model, the land use dynamic degree model, and the land use degree model to evaluate the LUCC of Jiangsu during two research periods from 1990 to 2000 and from 2000 to 2010. Additionally, logistic regression models and some quantitative analysis were applied to identify the major potential driving factors behind the LUCC during the research period based on different dimensions. The results showed the following: (1) the most obvious change was the continuous increase of built-up area and the decrease of arable land, which reflected the deterioration of the ecological environment and the accelerate of the urbanization trend. (2) The land use change dynamic degree from 2000 to 2010 was much greater than that from 1990 to 2000. (3) Socio-economic elements and human activities were the major driving forces of LUCC in Jiangsu province. Amongst these forces, the driving factors of the population change, GDP, per capita household income, and per capita housing area have an obvious effect on the arable land loss and the built-up area expansion.
Big data-driven technologies, especially machine learning and deep learning technologies, have been extensively employed in mineral prospectivity prediction. Several approaches have been proposed to learn the deep characteristics of geoscience data, enhance the accuracy of prediction and reduce uncertainty. Nevertheless, the approaches always contain the following two limitations. Firstly, the formation of mineral resources often involves the coupling of multiple factors on a certain spatio-temporal scale, resulting in rare labelled deposits and insufficient number of training samples. Secondly, training Deep Neural Network (DNN) is very challenging. Many approaches are subject to weak interpretability and lack of organic combination with geoscience knowledge. To address these two problems, we propose Geo-Rnet and GCAE (Geological Convolutional Autoencoder). Geo-Rnet is a multi-class mineral prospectivity prediction approach based on improved DNN. GCAE is able to effectively augment multi-disciplinary geoscience data by constructing upon an optimized Convolutional Autoencoder. The experimental results show that most of prospective areas predicted by Geo-Rnet overlap with the labelled mineralization locations, with an average accuracy of 91.1%. In addition, 89.98% of the ore deposits are located in the predicted areas. The results indicate the effectiveness of Geo-Rnet and GCAE for multi-class prediction of mineral resources. Finally, we classify the target area into several mineral prospectiviy areas according to their different mineral types. The research provides an innovative approach for mineral prospectivity prediction in the target area.INDEX TERMS Deep neural network, Geo-Rnet, multi-class, mineral prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.