Urban expansion prediction and land cover dynamics in Greater Imphal, India, using cellular automata-multilayer perceptron neural network model

Urban expansion in medium-sized cities of ecologically sensitive regions remains under-examined relative to metropolitan centres, despite comparable pressures on agricultural land and infrastructure. This study develops an integrated geospatial framework that couples multi-temporal land-cover classification (1992–2022), distance- and direction-based growth diagnostics, the Urban Expansion Intensity Index (UEII), driving-factor evaluation and Cellular Automata–Multilayer Perceptron (CA-MLP) simulation to analyse and project urban change in Greater Imphal, Manipur, North-Eastern India. Unlike most previous CA-MLP applications that focus on large metropolitan or southern/western Indian cities and emphasise predictive accuracy alone, the present framework is tailored to a valley-constrained, data-moderate setting and explicitly links spatial results to planning instruments. Landsat-derived land-cover maps show built-up area rising from 35.81% in 1992 to 51.65% in 2022, accompanied by a marked decline in agricultural land. Expansion has been predominantly outward and corridor-oriented, with higher intensity in eastern and north-eastern sectors. Proximity to roads, markets, higher-education institutions and the city centre emerge as the dominant drivers. The CA-MLP model yields an AUC of 0.759, indicating acceptable discriminative ability rather than definitive predictive strength; the 2032 projection nonetheless signals continued conversion of agricultural and wetland areas under current trends. The study demonstrates that a carefully calibrated CA-MLP approach, when combined with multi-metric spatial diagnostics, can generate policy-relevant evidence for green-belt designation, zoning, controlled corridor development and agricultural-land protection in medium-sized cities of environmentally sensitive regions.

Authors

Institutions

Publication Details

Journal
Discover Sustainability
Published
2026-11-18
DOI
https://doi.org/10.1007/s43621-026-04556-0
Primary Topic
Land Use and Ecosystem Services
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Urban expansion prediction and land cover dynamics in Greater Imphal, India, using cellular automata-multilayer perceptron neural network model

Abujam Manglem Singh, Paonam Robinson Singh, Kshetrimayum Zeba Devi
3 links
Discover Sustainability
Land Use and Ecosystem Services
article

Urban expansion prediction and land cover dynamics in Greater Imphal, India, using cellular automata-multilayer perceptron neural network model

Abujam Manglem Singh, Paonam Robinson Singh, Kshetrimayum Zeba Devi
article en

Abstract

Urban expansion in medium-sized cities of ecologically sensitive regions remains under-examined relative to metropolitan centres, despite comparable pressures on agricultural land and infrastructure. This study develops an integrated geospatial framework that couples multi-temporal land-cover classification (1992–2022), distance- and direction-based growth diagnostics, the Urban Expansion Intensity Index (UEII), driving-factor evaluation and Cellular Automata–Multilayer Perceptron (CA-MLP) simulation to analyse and project urban change in Greater Imphal, Manipur, North-Eastern India. Unlike most previous CA-MLP applications that focus on large metropolitan or southern/western Indian cities and emphasise predictive accuracy alone, the present framework is tailored to a valley-constrained, data-moderate setting and explicitly links spatial results to planning instruments. Landsat-derived land-cover maps show built-up area rising from 35.81% in 1992 to 51.65% in 2022, accompanied by a marked decline in agricultural land. Expansion has been predominantly outward and corridor-oriented, with higher intensity in eastern and north-eastern sectors. Proximity to roads, markets, higher-education institutions and the city centre emerge as the dominant drivers. The CA-MLP model yields an AUC of 0.759, indicating acceptable discriminative ability rather than definitive predictive strength; the 2032 projection nonetheless signals continued conversion of agricultural and wetland areas under current trends. The study demonstrates that a carefully calibrated CA-MLP approach, when combined with multi-metric spatial diagnostics, can generate policy-relevant evidence for green-belt designation, zoning, controlled corridor development and agricultural-land protection in medium-sized cities of environmentally sensitive regions.

Discover Sustainability
Manipur University (IN), Seva Mandir (IN)
Sustainable cities and communities
Land Use and Ecosystem Services
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon