Remote Sensing-Based Quantification of the Relationships between Land Use Land Cover Changes and Surface Temperature over the Lower Himalayan Region

Siddique Ullah, Adnan Ahmad Tahir, Tahir Ali Akbar, Quazi K. Hassan, Ashraf Dewan, Asim Jahangir Khan and Mudassir Khan
Additional contact information
Siddique Ullah: Department of Environmental Sciences, COMSATS University Islamabad (CUI), Abbottabad Campus, Abbottabad 22060, Pakistan
Adnan Ahmad Tahir: Department of Environmental Sciences, COMSATS University Islamabad (CUI), Abbottabad Campus, Abbottabad 22060, Pakistan
Tahir Ali Akbar: Department of Civil Engineering, COMSATS University Islamabad (CUI), Abbottabad Campus, Abbottabad 22060, Pakistan
Quazi K. Hassan: Department of Geomatics Engineering, Schulich School of Engineering, University of Calgary, 2500 University Dr. NW, Calgary, AB T2N 1N4, Canada
Ashraf Dewan: Spatial Sciences Discipline, School of Earth and Planetary Sciences, Curtin University, Kent St, Bentley WA 6102, Australia
Asim Jahangir Khan: Department of Environmental Sciences, COMSATS University Islamabad (CUI), Abbottabad Campus, Abbottabad 22060, Pakistan
Mudassir Khan: Department of Environmental Sciences, COMSATS University Islamabad (CUI), Abbottabad Campus, Abbottabad 22060, Pakistan

Sustainability, 2019, vol. 11, issue 19, 1-16

Abstract: Population growth and population inflow from other regions has caused urbanization which altered land use land cover (LULC) in the lower Himalayan regions of Pakistan. This LULC change increased the land surface temperature (LST) in the region. LULC and LST changes were assessed for the period of 1990–2017 using Landsat data and the support vector machine (SVM) method. A combined cellular automata and artificial neural network (CA-ANN) prediction model was used for simulation of LULC changes for the period of 2032 and 2047 using transition potential matrix obtained from the data years of 2002 and 2017. The accuracy of the CA-ANN model was validated using simulated and classified images of 2017 with correctness value of 70% using validation modules in QGIS. The thermal bands of Landsat images from the years 1990, 2002 and 2017 were used for LST derivation. LST acquired for this period was then modeled for 2032 and 2047 using urban indices (UI) and linear regression analysis. The SVM land cover classification results showed a 5.75% and 4.22% increase in built-up area and bare soil respectively, while vegetation declined by 9.88% during 1990–2017. The results of LST for LULC classes showed that the built-up area had the highest mean LST as compared to other classes. The future projection of LULC and LST showed that the built-up area may increase by 12.48% and 14.65% in 2032 and 2047, respectively, of the total LULC area which was ~11% in 2017. Similarly, the area with temperature above 30 °C could be 44.01% and 58.02% in 2032 and 2047, respectively, of the total study area which was 18.64% in 2017. This study identified major challenges for urban planners to mitigate the urban heat island (UHI) phenomenon. In order to address the UHI in the study area, an urban planner might focus on urban plantation and decentralization of urban areas.

Keywords: artificial neural network; cellular automata; support vector machine; urban heat island; urban indices (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
https://www.mdpi.com/2071-1050/11/19/5492/pdf (application/pdf)
https://www.mdpi.com/2071-1050/11/19/5492/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:11:y:2019:i:19:p:5492-:d:273420

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().