Mohammad, Pir and Goswami, Ajanta and Chauhan, Sarthak and Nayak, Shailesh
(2022)
Machine learning algorithm based prediction of land use land cover and land surface temperature changes to characterize the surface urban heat island phenomena over Ahmedabad city, India.
Urban Climate, 42 (101116).
Full text not available from this repository.
| Abstract: |
Rapid urbanization over the world's dense urban centers cause an enormous change in the land use land cover (LULC) over a metropolitan area, which adversely affects the land surface temperature (LST) and intensify the urban heat island phenomena. The present study emphasizes the prediction of LULC, seasonal LST, and urban thermal field variance (UTFVI) over Ahmedabad city, India using multi date Landsat data. Artificial Neural Network (ANN) based Cellular Automata (CA) model is use to predict the LULC, while the XGB Regression model is used to predict seasonal LST with input data from 2010, 2015, and 2020 to predict future scenarios of 2025 and 2030. The result suggests an addition in the built-up area of about 5.77% and 13.08%, while a deduction in cropland area of about 4.15% and 12.54% is manifest in the year 2025 and 2030, respectively. This excessive urban growth in the study area will cause to face higher LST ranges of greater than 45 °C (24.9 km2 in 2025 and 24.2 km2 in 2030) in summer and 35 °C (19.9 km2 in 2025 and 43.6 km2 in 2030) in winter. The concentration of higher LST zones is evident in the rural areas than urban areas, witnessing cool urban islands. The predicted LST analysis suggests a dominant occurrence of none UTFVI zone in the city area and the strongest UTFVI zone in the surrounding rural area during both the seasons. An increase in green space area and avoidance of non-impermeable surfaces is suggest in future scenarios to mitigate UHI. Furthermore, the outcome of the research can help urban planners and policymakers while formulating urban heat island related mitigation strategies in the near-future scenario. |
| Item Type: |
Journal Paper
|
| Additional Information: |
The authors acknowledge the Department of Earth Sciences, Indian Institute of Technology Roorkee, India, for providing necessary infrastructure facilities. The authors should also like to acknowledge the United States Geological Survey (USGS) for providing satellite imagery, which made the foundation of this research. |
| Keywords: |
LULC, LST, Urban growth, Machine learning, Prediction, UTFVI |
| Subjects: |
General > Directors > Shailesh Nayak > Publications |
| Date Deposited: |
29 Jul 2022 06:39 |
| Last Modified: |
29 Jul 2022 06:39 |
| Official URL: |
https://www.sciencedirect.com/science/article/pii/... |
| Related URLs: |
|
| Funders: |
MHRD and DST NRDMS (Grant number- NRDMS/01/179/2015(C)), New Delhi |
| Projects: |
UNSPECIFIED |
| DOI: |
https://doi.org/10.1016/j.uclim.2022.101116 |
| URI: |
http://eprints.nias.res.in/id/eprint/2336 |
Actions (login required)
 |
View Item |
