Future land use land cover changes in El-Fayoum governorate: a simulation study using satellite data and CA-Markov model

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT(2023)

引用 0|浏览0
暂无评分
摘要
This study aims to monitor the changes in land use land cover (LULC) in El-Fayoum governorate over time (past, present, and future) to provide current information for stakeholders involved in land use planning. The study utilized Landsat satellite images and applied the Support Vector Machine algorithm using ArcGIS Pro 2.8.3 to classify the images into four major LULC classes: water, desert, built-up, and agricultural. To evaluate the accuracy of the LULC maps, the study used kappa statistical parameters, which ranged from 0.91 to 0.94, indicating acceptable results for further analysis. To predict spatio-temporal LULC changes, the study considered biophysical and socioeconomic factors such as distance to canals, distance to roads, distance to urban areas, a digital elevation model, and slope. A combination of Multi-Criteria Evaluation, a Fuzzy Membership Function, and the Analytic Hierarchy Process were employed to develop a land cover suitability map. The Hybrid CA-Markov model of the IDRISI-TerrSet software was used to simulate LULC changes, and the accuracy of the simulation was validated using 2020 imagery data. The values gained from the kappa indices for agreement (standard) = 0.9006, kappa for lack of information (no) = 0.916, and kappa for location at grid cell level (location) = 0.9572 demonstrate that the results of the simulation of the LULC changes were deemed satisfactory. The future scenarios modeled in LULC indicate a significant change in the LULC classes over time, specifically for 2030. The change rates of agriculture, desert, built-up, and water areas in El-Fayoum in 2030 compared to 2020 are estimated to be 9.68%, - 17.58%, 133.62%, and 6.06%, respectively. These findings establish both past and future LULC trends and provide crucial data useful for planning and sustainable land use management.
更多
查看译文
关键词
GIS,CA-Markov,Remote sensing,SVM
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要