Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Studying Urban Growth Dynamics in Indo-Gangetic Plain
The spatio-temporal characteristics of urban growth in the Indian-Gangetic planes (IGP) using night-time light (NTL) data sets have been studied in the present chapter. The study proposes to use Mann–Kendall’s (MK) test and Principal Component Analysis (PCA) (S-Mode) for urban area extraction from NTL data sets in place of traditional thresholding techniques. The urban areas extracted using MK test and PCA (S-Mode) had 0.92 accuracy when evaluated using area under curve (AUC–ROC) method. Subsequently, urban areas of year 2000 and 2018 were extracted using the MK test and PCA (S-Mode). Using NTL extracted urban areas of year 2000 and 2018 and other thematic layers as input variables, three machine learning algorithms (i.e. artificial neural network, decision tree, and logistic regression)-based cellular automata models were executed for predicting the urban growth in year 2028. The model calibration results were evaluated using spatial metrics and it was found that artificial neural networks-based CA model gave the best simulation result. Thus, the present study provides a methodology for understanding spatio-temporal characteristics of urban areas at the regional scale using of NTL data (which is freely available in public domain).
Studying Urban Growth Dynamics in Indo-Gangetic Plain
The spatio-temporal characteristics of urban growth in the Indian-Gangetic planes (IGP) using night-time light (NTL) data sets have been studied in the present chapter. The study proposes to use Mann–Kendall’s (MK) test and Principal Component Analysis (PCA) (S-Mode) for urban area extraction from NTL data sets in place of traditional thresholding techniques. The urban areas extracted using MK test and PCA (S-Mode) had 0.92 accuracy when evaluated using area under curve (AUC–ROC) method. Subsequently, urban areas of year 2000 and 2018 were extracted using the MK test and PCA (S-Mode). Using NTL extracted urban areas of year 2000 and 2018 and other thematic layers as input variables, three machine learning algorithms (i.e. artificial neural network, decision tree, and logistic regression)-based cellular automata models were executed for predicting the urban growth in year 2028. The model calibration results were evaluated using spatial metrics and it was found that artificial neural networks-based CA model gave the best simulation result. Thus, the present study provides a methodology for understanding spatio-temporal characteristics of urban areas at the regional scale using of NTL data (which is freely available in public domain).
Studying Urban Growth Dynamics in Indo-Gangetic Plain
GIScience & Geo-environmental Modelling
Rahman, Atiqur (Herausgeber:in) / Sen Roy, Shouraseni (Herausgeber:in) / Talukdar, Swapan (Herausgeber:in) / Shahfahad (Herausgeber:in) / Maithani, Sandeep (Autor:in) / Shankar, Hamde Narayan (Autor:in)
04.03.2023
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Night-time light , Principal component analysis , Indian-Gangetic plane , Mann–Kendall’s test , Cellular automata , Artificial neural networks , Decision tree Environment , Environment, general , Computer Applications , Geography, general , Urban Ecology , Ecology , Climate, general , Earth and Environmental Science
Aerosol indirect effect over Indo-Gangetic plain
| Elsevier | 2007
Modelling urban growth in the Indo-Gangetic plain using nighttime OLS data and cellular automata
| Online Contents | 2014
Seismic Response of the Central Part of Indo-Gangetic Plain
| Taylor & Francis Verlag | 2019
The Seismotectonic Setting of Indo-Gangetic Plain and Its Importance
| Springer Verlag | 2021