A neural network and landscape metrics to propose a flexible urban growth boundary: A case study. (October 2018)

• Record Type: Journal Article
• Authors: Chakraborti, Suman; Das, Dipendra Nath; Mondal, Biswajit; Shafizadeh-Moghadam, Hossein; Feng, Yongjiu
• Is Part Of: Ecological indicators. Volume 93(2018)
• Page Start: 952
• Page End: 965
• Publication Date: 2018-10
• Subjects: Urban hard boundary -- Urban soft boundary -- Artificial neural network -- Boundary demarcation -- Landscape metrics; Environmental monitoring -- Periodicals; Environmental management -- Periodicals; Environmental impact analysis -- Periodicals; Environmental risk assessment -- Periodicals; Sustainable development -- Periodicals; 333.71405
• DOI: 10.1016/j.ecolind.2018.05.036
• Languages: English
• ISSNs: 1470-160X

Abstract

Highlights: Landscape metrics were integrated with neural network to delineate urban growth. We proposed an Urban Hard Boundary (UHB) and an Urban Soft Boundary (USB). The results showed that land resource management without any master planning is a paradox. Abstract: Urban sprawl is a major barrier for the precise demarcation of administrative boundary in the world. In India, medium and small towns have so far developed outside the envisaged planning, resulting in a leapfrog and haphazard growth. This paper has attempted to simulate the spatial extent of urban expansion and boundary demarcation for the purpose of efficient urban planning and land resource management. An Artificial Neural Network (ANN) model and a set of landscape metrics were used to delineate the Urban Growth Boundary (UGB) and characterize the future patterns of growth in Siliguri Municipal Corporation (SMC, India). In particular, two urban boundaries – namely, Urban Hard Boundary (UHB) and Urban Soft Boundary (USB) – were simulated. The results suggest a USB with the area of 123 km 2 to address the basic service delivery and a UHB with the area of 211.88 km 2 to manage the ecological fragmentation.