Mapping and Forecasting the Land Surface Temperature in Response to the Land Use and Land Cover Changes using Machine Learning Over the Southernmost Municipal Corporation of Tamilnadu, India

Aran Castro A. J.*, Ajith Chandran**, Harishma S.***, Raj Kumar P.****, Justine K. Antony*****, Praveen Raj******
*-** Sysglob Software Solutions Pvt. Ltd., Kochi, Kerala, India.
*** Department of Geology, Sree Narayana Guru College of Advanced Studies, Sivagiri, Varkala, Kerala, India.
**** Advanced Facility for Microscopy and Microanalysis, Indian Institute of Science, Bangalore, India.
***** Petrology Lab, Earth and Environmental Sciences, Undergraduate Programme, Indian Institute of Science, Bangalore, India.
****** Department of Earth Sciences, Annamalai University, Tamil Nadu, India.
Periodicity:January - April'2023

Abstract

In this decade, global warming and urbanization have become fundamental problems. Numerous locations have experienced a temperature increase that has negatively affected the ecosystem. Land Surface Temperature (LST) is a valuable parameter for studying temperature variation because it is closely correlated with Land Use and Land Cover (LULC). This study combines Machine Learning, Remote Sensing, and Geographic Information System (GIS) techniques to detect the spatial variation of LST and quantify its relationship with LULC. The Nagercoil Municipal Corporation (the Southernmost Municipal Corporation of Tamil Nadu, India) was chosen as the study area to explore the relationship between LST and LULC. From 2014 to 2022, three scenes of Landsat 8 OLI, 9 OLI-2 LULC, and LST data were extracted. Markov Chain Analysis (MCA) is adopted to predict the future LULC and LST of the study. Pearson's correlation method is used in the study to determine the correlation of the LULC and LST. The correlation between LULC and LST is an essential metric for identifying and quantifying higher-temperature areas with urban development. These metrics can be incorporated into advanced UHI detection models and machine learning algorithms for more precise and accurate identification and quantification of Urban Heat Island zones. The proposed urban land use measures and urban land planning should be informed by continuous and detailed Remote Sensing and GIS combined with statistical modeling and analysis of LULC and LST. Possible actions include the conservation of agricultural and vegetated lands and the management of the reclamation of barren lands into croplands toprevent surface impermeability loss and ecosystem fragmentation.

Keywords

Land Use, Land Cover, Land Surface Temperature, Urbanization, Machine learning, Mapping, Forecasting.

How to Cite this Article?

Castro, A. J. A., Chandran, A., Harishma, S., Kumar, P. R., Antony, J. K., and Raj, P. (2023). Mapping and Forecasting the Land Surface Temperature in Response to the Land Use and Land Cover Changes using Machine Learning Over the Southernmost Municipal Corporation of Tamilnadu, India. i-manager’s Journal on Physical Sciences, 2(1), 1-11.

References

[20]. Obilor, E. I., & Amadi, E. C. (2018). Test for significance of Pearson's correlation coefficient. International Journal of Innovative Mathematics, Statistics & Energy Policies, 6(1), 11-23.
[27]. Story, M., & Congalton, R. G. (1986). Accuracy assessment: a user's perspective. Photogrammetric Engineering and Remote Sensing, 52(3), 397-399.
[29]. Zanter, K. (2016). Landsat 8 (L8) Data Users Handbook (Version 2.0). USGS: Reston, VA, USA, 1-98.
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Online 15 15

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.