Inversion and analysis of leaf area index (LAI) of urban park based on unmanned aerial vehicle (UAV) multispectral remote sensing and random forest (RF)

Leaf Area Index (LAI) is a critical indicator of vegetation growth and ecological function. Unlike the relatively uniform crop types and planting methods typically found in agricultural fields, parks typically feature a diverse range of plant species, varied configurations, and complex vertical structures, making LAI estimation more complex and challenging. To improve the accuracy of LAI estimation in urban parks, this study, by combining unmanned aerial vehicle (UAV) multispectral remote sensing technology with Random Forest (RF) to conduct the inversion and analysis of LAI in Xinxiang People's Park. High-resolution images are obtained using multispectral sensors carried by a UAV, which are then used to calculate the Normalized Difference Vegetation Index (NDVI). Combined with ground-measured vegetation LAI data, this study applies RF to estimate the park LAI. The results indicate that the average LAI of Xinxiang People's Park is 2.30 (for the entire park). excluding the hard surfaces (which account for 36.05%), the average LAI increases to 3.59, indicating good vegetation conditions. The LAI of the park and its distribution are influenced by factors such as plant species, configuration patterns, planting density, aesthetic design, and site function. Accurate LAI inversion is crucial for effective management and optimization of these green spaces. RF can effectively capture the complex nonlinear relationship between NDVI and LAI, with a coefficient of determination (R-2) of 0.54 and a root mean square error (RMSE) of 0.91. Although the accuracy is still insufficient, RF's ability to handle nonlinear relationships makes it an effective tool for LAI inversion in complex vegetation environments. LAI inversion of park vegetation based on UAV multispectral imagery can provide valuable insights for the management and optimization of park vegetation.