Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability
Abstract The increasing trend in land surface temperature (LST) and the formation of urban heat islands (UHIs) has emerged as a persistent challenge for urban planners and decision-makers. The current research was carried out to study the land use and land cover (LULC) changes and associated LST pat...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87234-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585929047408640 |
|---|---|
| author | Sajid Ullah Xiuchen Qiao Aqil Tariq |
| author_facet | Sajid Ullah Xiuchen Qiao Aqil Tariq |
| author_sort | Sajid Ullah |
| collection | DOAJ |
| description | Abstract The increasing trend in land surface temperature (LST) and the formation of urban heat islands (UHIs) has emerged as a persistent challenge for urban planners and decision-makers. The current research was carried out to study the land use and land cover (LULC) changes and associated LST patterns in the planned city (Kabul) and the unplanned city (Jalalabad), Afghanistan, using Support Vector Machine (SVM) and Landsat data from 1998 to 2018. Future changes in LULC and LST were predicted for 2028 and 2038 using Cellular Automata-Markov (CA-Markov) and Artificial Neural Network (ANN) models. The results clearly emphasize different LULC changes and LST patterns between Kabul and Jalalabad. Between 1998 and 2018, the built-up areas in Kabul and Jalalabad increased by 16% and 30%, respectively, while bare soil and vegetation decreased by 15% and 1% in Kabul and 4% and 30% in Jalalabad. The built-up areas showed the highest seasonal and annual LST, followed by bare soil and vegetation. The maximum seasonal LST occurred during the summer for both cities from 1998 to 2018. Future predictions showed that the built-up areas (48% and 55% in 2018) will increase to approximately 59% and 68% by 2028 and to 68% and 79% by 2038 in Kabul and Jalalabad, respectively. Similarly, LST simulations showed that the percentage of areas with higher LST (> 35°C) would increase from (0% and 5% in 2018) to 4% and 5% and 22% and 43% in Kabul and Jalalabad by 2028 and 2038, respectively. Kabul’s planned city shows lower LST than Jalalabad’s unplanned city, primarily due to planned urbanization and greater vegetation cover in the city center. Urban planners should limit unplanned development and increase vegetation in Jalalabad to reduce the potential impacts of high temperatures. |
| format | Article |
| id | doaj-art-94782f58bd9f47e3a970c16a18f357e2 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-94782f58bd9f47e3a970c16a18f357e22025-01-26T12:24:22ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-025-87234-xImpact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainabilitySajid Ullah0Xiuchen Qiao1Aqil Tariq2School of Resources and Environmental Engineering, East China University of Science and TechnologySchool of Resources and Environmental Engineering, East China University of Science and TechnologyDepartment of Wildlife Fisheries and Aquaculture, College of Forest Resources, Mississippi State UniversityAbstract The increasing trend in land surface temperature (LST) and the formation of urban heat islands (UHIs) has emerged as a persistent challenge for urban planners and decision-makers. The current research was carried out to study the land use and land cover (LULC) changes and associated LST patterns in the planned city (Kabul) and the unplanned city (Jalalabad), Afghanistan, using Support Vector Machine (SVM) and Landsat data from 1998 to 2018. Future changes in LULC and LST were predicted for 2028 and 2038 using Cellular Automata-Markov (CA-Markov) and Artificial Neural Network (ANN) models. The results clearly emphasize different LULC changes and LST patterns between Kabul and Jalalabad. Between 1998 and 2018, the built-up areas in Kabul and Jalalabad increased by 16% and 30%, respectively, while bare soil and vegetation decreased by 15% and 1% in Kabul and 4% and 30% in Jalalabad. The built-up areas showed the highest seasonal and annual LST, followed by bare soil and vegetation. The maximum seasonal LST occurred during the summer for both cities from 1998 to 2018. Future predictions showed that the built-up areas (48% and 55% in 2018) will increase to approximately 59% and 68% by 2028 and to 68% and 79% by 2038 in Kabul and Jalalabad, respectively. Similarly, LST simulations showed that the percentage of areas with higher LST (> 35°C) would increase from (0% and 5% in 2018) to 4% and 5% and 22% and 43% in Kabul and Jalalabad by 2028 and 2038, respectively. Kabul’s planned city shows lower LST than Jalalabad’s unplanned city, primarily due to planned urbanization and greater vegetation cover in the city center. Urban planners should limit unplanned development and increase vegetation in Jalalabad to reduce the potential impacts of high temperatures.https://doi.org/10.1038/s41598-025-87234-xLand Use and Land Cover (LULC)Un-planned developmentArtificial Neural NetworkCA-MarkovUrban Heat Island(UHI)Remote Sensing (RS) and Geographic Information System (GIS) |
| spellingShingle | Sajid Ullah Xiuchen Qiao Aqil Tariq Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability Scientific Reports Land Use and Land Cover (LULC) Un-planned development Artificial Neural Network CA-Markov Urban Heat Island(UHI) Remote Sensing (RS) and Geographic Information System (GIS) |
| title | Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability |
| title_full | Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability |
| title_fullStr | Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability |
| title_full_unstemmed | Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability |
| title_short | Impact assessment of planned and unplanned urbanization on land surface temperature in Afghanistan using machine learning algorithms: a path toward sustainability |
| title_sort | impact assessment of planned and unplanned urbanization on land surface temperature in afghanistan using machine learning algorithms a path toward sustainability |
| topic | Land Use and Land Cover (LULC) Un-planned development Artificial Neural Network CA-Markov Urban Heat Island(UHI) Remote Sensing (RS) and Geographic Information System (GIS) |
| url | https://doi.org/10.1038/s41598-025-87234-x |
| work_keys_str_mv | AT sajidullah impactassessmentofplannedandunplannedurbanizationonlandsurfacetemperatureinafghanistanusingmachinelearningalgorithmsapathtowardsustainability AT xiuchenqiao impactassessmentofplannedandunplannedurbanizationonlandsurfacetemperatureinafghanistanusingmachinelearningalgorithmsapathtowardsustainability AT aqiltariq impactassessmentofplannedandunplannedurbanizationonlandsurfacetemperatureinafghanistanusingmachinelearningalgorithmsapathtowardsustainability |