Prediction of Ecological Pressure on Resource-Based Cities Based on an RBF Neural Network Optimized by an Improved ABC Algorithm

• Published in: IEEE access 2019, Vol.7, p.47423-47436
• Main Authors: Jiang, Song, Lu, Caiwu, Zhang, Sai, Lu, Xiang, Tsai, Sang-Bing, Wang, Cheng-Kuang, Gao, Yuan, Shi, Yufei, Lee, Chien-Hung
• Format: Article
• Language: English
• Subjects: ABC algorithm; Biological system modeling; Carrying capacity; Decision making; Ecological effects; ecological footprint theory; ecological pressure prediction; Economics; Ecosystems; Energy consumption; Environmental impact; Footprint analysis; Local government; Neural networks; Per capita; Prediction models; Predictive models; Pressure dependence; Radial basis function; RBF neural network; Resource-based city; Search algorithms; Sustainable development; Swarm intelligence; Urban areas
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2908662

Resource-based cities are those where resource-based industries comprise a large proportion of all industries. Sustainable development implies that cities make full use of their own resources to support current development initiatives and take sustainability into account both during and after resource consumption. To promote investment in the sustainable development of resource-based cities and to a provide a decision system for these cities, this paper uses an ecological footprint model to evaluate and analyze the per capita ecological footprint, per capita ecological carrying capacity and per capita ecological deficit of a representative resource-based city, Yulin. The data are collected from 2001 to 2015. In addition, due to the complexity of the influencing factors for ecological carrying capacity and the variety of situations that are difficult to accurately predict, this paper proposes a new urban ecological carrying capacity prediction model, which consists of a radial basis function (RBF) neural network that is optimized by an improved artificial bee colony algorithm. The prediction results show that energy consumption is the major factor affecting the urban ecosystem; moreover, the model precision of the training results and the simulation accuracy of the test results achieved by the RBF neural network model are 97.91% and 94.16%, respectively, and in 2020, the per capita ecological footprint, biocapacity, and ecological deficit of Yulin are predicted to reach 4.892 hm 2 , 3.317 hm 2 , and 1.575 hm 2 , respectively. Accordingly, effective proactive measures should be taken in advance to maintain or reduce the ecological pressure on this resource-dependent city. This paper strives to provide a scientific basis for local government decision-making to realize the healthy, stable, and rapid sustainable development of resource-based cities.