Urban growth modeling and prediction of land use land cover change over Nagpur City, India using cellular automata approach

F Khan, B Das, P Mohammad - Geospatial technology for landscape and …, 2022 - Springer
Geospatial technology for landscape and environmental management: sustainable …, 2022Springer
The monitoring of land use land cover (LULC) change is essential to estimate the urban
sprawl as the rapid growth of urban areas affects the ecology and eminence of city life.
LULC forms a reference line of the spatial map for observing, managing, and planning
activities for urban development. The LULC change dynamics is self-explanatory using GIS
and remote sensing techniques. Thus, the present study uses these techniques to
understand the spatial–temporal variability of LULC of Nagpur city, Maharashtra, from 2000 …
Abstract
The monitoring of land use land cover (LULC) change is essential to estimate the urban sprawl as the rapid growth of urban areas affects the ecology and eminence of city life. LULC forms a reference line of the spatial map for observing, managing, and planning activities for urban development. The LULC change dynamics is self-explanatory using GIS and remote sensing techniques. Thus, the present study uses these techniques to understand the spatial–temporal variability of LULC of Nagpur city, Maharashtra, from 2000 to 2020. The study area is a center for economic, education, and medical activities; therefore, changes should be analyzed to understand urban growth trends. The LULC classification is performed considering four different classes, i.e., barren land, built up, agriculture (include shrubs, urban forest, small plantation, vegetation area), and water bodies. The LULC results show that the built-up area is increased by 26.62% from 2000 (41.24%) to 2020 (67.86%), with a slight increase in water bodies 0.19% is also evident. On the other hand, the area covered with vegetation is decreased by 15.93% from 2000 (30.17%) to 2020 (14.24%), and barren land is reduced by 10.88%. The present study also includes predicting the LULC map using the artificial neural network-based (ANN) cellular automata (CA) model, using seven different driving parameters, like elevation, slope, aspect, distance to major roads, distance to water bodies, central building distance, and population. The prediction model showed an overall accuracy of 81.23% in predicting the 2025 LULC maps with the help of 2015 and 2020 LULC data. The result of the prediction model evidents a maximum growth of 30.88% in the built-up area as compared to year 2020. Therefore, the study results show that the use of LULC and CA-ANN model will be suitable to understand the future trend, and it will help the administration and planner for the development of the sustainable city.
Springer
以上显示的是最相近的搜索结果。 查看全部搜索结果

Google学术搜索按钮

example.edu/paper.pdf
搜索
获取 PDF 文件
引用
References