This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1016/j.envsoft.2019.05.006. This is version 1 of this Preprint.
This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1016/j.envsoft.2019.05.006. This is version 1 of this Preprint.
Studies evaluating potential of Green Infrastructure (GI) development using traditional Boolean logic-based multi-criteria analysis methods are not capable of predicting future GI development under dynamic urban scape. This study evaluated robust soft-computing-based methods of artificial intelligence (Artificial Neural Network, Adaptive Neuro-Fuzzy Interface-System) and used statistical modelling (logistic regression) to predict GI or grey transformation likelihoods for vacant sites along waterway corridors (WWC) and derelict sites (DS) based on ecological, environmental, and social criteria. The study found that the ANN and ANFIS models had better predictive capacity and more accuracy (72% accurate) than logistic models (65% accurate). Site sizes, population coverage, and air pollution were identified as the main influencing factors regarding GI/GY transformation. Finally, for Manchester, the likelihood of GI transformation was higher for WWCs (80%) than for DS (60%), and DS were more likely to transform into GY based on current trends.
https://doi.org/10.31223/osf.io/p96g7
Artificial Intelligence and Robotics, Computer Sciences, Environmental Monitoring, Environmental Sciences, Geographic Information Sciences, Geography, Physical Sciences and Mathematics, Social and Behavioral Sciences, Spatial Science
machine learning, Artificial Neural Network, Green Infrastructure, Green Space, Urban Land Use
Published: 2019-05-08 07:13
There are no comments or no comments have been made public for this article.