Monitoring and analysis of leaf area index of vegetation along expressway based on satellite remote sensing images

Leaf area index (LAI) constitutes a crucial indicator in the monitoring of ecological environment protection for vegetation in expressway road areas. To fulfill the demands for efficient, rapid, and long-term cyclical monitoring of large-scale LAI in expressway road areas, this study presents a monitoring approach for LAI in expressway road areas based on high-resolution remote sensing images. Firstly, multiple LAI remote sensing inversion models are constructed by utilizing typical vegetation indices and machine learning algorithms with the aid of high-resolution remote sensing images. Subsequently, the optimal inversion model is determined through comparative analysis. Finally, this model is employed to analyze the spatiotemporal variations of LAI in road areas, realizing high-precision inversion of large-scale LAI in road areas and dynamic monitoring of growth conditions. The experimental results demonstrate that high-resolution remote sensing images can rapidly invert large-scale LAI in road areas and obtain the growth and change status of vegetation in road areas, providing scientific data support for the green and low-carbon construction and operation management of expressways.