Abstract:
Over the past two and a half decades, rapid urbanization has led to significant land use and land cover (LULC) changes in Kabul province, Afghanistan. To assess the impact of LULC changes on land surface temperature (LST), Kabul province was divided into four LULC classes applying the Support Vector Machine (SVM) algorithm using the Landsat satellite images from 1998 to 2022. The LST was assessed using Landsat data from the thermal band. The Cellular Automata-Logistic Regression (CA-LR) model was applied to predict the future patterns of LULC and LST for 2034 and 2046. Results showed significant changes in LULC classes, as the built-up areas increased about 9.37%, while the bare soil and vegetation cover decreased 7.20% and 2.35%, respectively, from 1998 to 2022. The analysis of annual LST revealed that built-up areas showed the highest mean LST, followed by bare soil and vegetation. The future simulation results indicate an expected increase in built-up areas to 17.08% and 23.10% by 2034 and 2046, respectively, compared to 11.23% in 2022. Similarly, the simulation results for LST indicated that the area experiencing the highest LST class (≥ 32 °C) is expected to increase to 27.01% and 43.05% by 2034 and 2046, respectively, compared to 11.21% in 2022. The results indicate that LST increases considerably as built-up areas increase and vegetation cover decreases, revealing a direct link between urbanization and rising temperatures.
摘要:
在过去的25年里,快速的城市化导致喀布尔省的土地利用和土地覆盖(LULC)发生了重大变化,阿富汗。为了评估LULC变化对地表温度(LST)的影响,喀布尔省使用1998年至2022年的Landsat卫星图像应用支持向量机(SVM)算法分为四个LULC类。使用来自热带的Landsat数据评估LST。应用细胞自动机-逻辑回归(CA-LR)模型预测了2034年和2046年LULC和LST的未来模式。结果显示LULC类的显著变化,随着建成区面积增加约9.37%,而裸露的土壤和植被覆盖率下降了7.20%和2.35%,分别,从1998年到2022年。对年度LST的分析表明,建成区的平均LST最高,其次是裸露的土壤和植被。未来的模拟结果表明,预计到2034年和2046年,建成区面积将分别增加到17.08%和23.10%,比2022年的11.23%。同样,LST的模拟结果表明,到2034年和2046年,经历最高LST等级(≥32°C)的区域预计将分别增加到27.01%和43.05%,比2022年的11.21%。结果表明,随着建成区面积的增加和植被覆盖的减少,LST显著增加,揭示了城市化和气温上升之间的直接联系。