Dynamic urban land surface monitoring in developing countries using remote sensing and machine learning: real-time investigational approach.

Land Surface Changes (LSC) are significantly impacted by dynamic environmental variations, particularly armed conflicts and associat-ed failures, according to a natural perspective. Regarding the current understanding of their relationship, on the other hand, human activi-ties on land usage or land covers may also increase the fluctuations. With a focus on the impacts of environmental restrictions like as land cover, temperature, air pollution, and sustainable water management, this study examines LSC in various metropolitan regions of developing nations. Recently, land cover has changed due to rapid urbanization and environmental pressures such socioeconomic and climatic shifts. We assess patterns of temporal LSC in the central urban regions of under-developing nations using Remote Sensing (RS) technologies, satellite data, and Geographic Information System (GIS). For example, Pakistan's urbanized land surface is Karachi. We measure and identify the major changes in urban landscapes, as well as the factors related environmental variables, by using Machine Learning-enabled Random Forest Classification (RFC) for image classification and Support Vector Machine for change detection patterns. Critical trends in urban sprawl and deforestation are revealed by the simulation results of the proposed model, underscoring the necessity of sustainable planning for industrialized cities. Furthermore, the outcomes highlight the uniqueness of combining RFC and SVM to categories patterns in terms of change detections from 2000 to 2023, reaching 26.91% and 19.73% higher than previously state-of-the-art techniques.