Forest Canopy Closure Estimation in Mountainous Southwest China Using Multi-source Remote Sensing Data

Wenwu Zhou¹Qingtai Shu^2*Cuifen Xia²Li Xu²Qin Xiang²Lianjin Fu³Yang Zhengdao Yang²Shuwei Wang²

• ¹Guangyuan Forestry Workstation, Guang yuan, China
• ²College of Forestry, Southwest Forestry University, Kunming, China
• ³Faculty of College of Soil and Water Conservation, Southwest Forestry University, Kunming, China

Forest canopy closure (FCC) is an important biological parameter to evaluate forest resources and biodiversity, and the use of multi-source remote sensing synergy to achieve high-accuracy estimate regional FCC at low-cost is a current research hotspot. In this study, Shangri-La City, a mountainous area in southwest China, was taken as the research area. The satellite-borne LiDAR ICESat-2/ATLAS data was used as the main information source. Combined with 54 measured plot data, the improved machine learning model of Bayesian optimization (BO) algorithm was used to obtain the FCC in the footprintspot-scale ATLAS footprintspot. Then, the multi-source remote sensing image Sentinel-1/2 and terrain factors were combined to perform regional-scale FCC remote sensing estimation based on the geographically weighted regression (GWR) model. The research results showed that: (1) Among the 50 extracted ATLAS LiDAR feature indexes, the best spot footprint-scale modeling factors are Landsat_perc, h_dif_canopy, asr, h_min_canopy, toc_roughness and n_touc_photons after random forest (RF) RF feature variable optimization. (2) Among the BO-RFR, BO-KNN and BO-GBRT models developed at the footprint-spot scale, the FCC results estimated by the BO-GBRT model were the best (R 2 = 0.65, RMSE = 0.10, RS = 0.079, P = 79.2%), which was used as the FCC estimation model for 74808 spots footprints in the study area. (3) Taking the FCC value of ATLAS spot footprintscale in forest land as the training sample data of regional-scale GWR model, the model accuracy was R 2 = 0.70, RMSE = 0.06, P = 88.27%. (4) The R² between the FCC estimates from regional-scale remote sensing and the measured values is 0.70, with a correlation coefficient of 0.784, indicating strong agreement. Additionally, the average FCC is 0.50, predominantly distributed between 0.3 and 0.6, comprising 68.43%. These findings highlight the advantages of mountain FCC estimation using ICESat-2/ATLAS high-density, high-precision footprintlight spots, and that small-sample estimation results at the footprint-light spot scale can serve as training data for the regional-scale GWR model, offering a reference for low-cost, high-precision FCC estimation from footprint-scale light spot to regional-scale.