Qin Zhen, Yang Huanfen, Shu Qingtai, Yu Jinge, Yang Zhengdao, Ma Xu, Duan Dandan
College of Forestry, Southwest Forestry University, Kunming, Yunnan, China.
School of Ecology and Applied Meteorology, Nanjing University of Information Science & Technology, Nanjing, China.
Front Plant Sci. 2025 Jan 15;15:1505414. doi: 10.3389/fpls.2024.1505414. eCollection 2024.
The Leaf Area Index (LAI) is an essential parameter that affects the exchange of energy and materials between the vegetative canopy and the surrounding environment. Estimating LAI using machine learning models with remote sensing data has become a prevalent method for large-scale LAI estimation. However, existing machine learning models have exhibited various flaws, hindering the accurate estimation of LAI. Thus, a new method for large-scale estimation of LAI was proposed, which integrates ICESat-2/ATLAS, and Sentinel-1/-2 data, and refines machine learning models through the application of Bayesian Optimization (BO), Particle Swarm Optimization (PSO), Genetic Algorithms (GA), and Simulated Annealing (SA). First, spatial interpolation was performed using the Sequential Gaussian Conditional Simulation (SGCS) method. Then, multi-source remote sensing data were leveraged to optimize feature variables through the Pearson correlation coefficient approach. Subsequently, optimization algorithms were applied to Random Forest Regression (RFR), Gradient Boosting Regression Tree (GBRT), and Support Vector Machine Regression (SVR) models, leading to efficient large-scale LAI estimation. The results showed that the BO-GBRT model achieved high accuracy in LAI estimation, with a coefficient of determination ( ) of 0.922, a root mean square error () of 0.263, a mean absolute error () of 0.187, and an overall estimation accuracy ( ) of 92.38%. Compared to existing machine learning methods, the proposed approach demonstrated superior performance. This method holds significant potential for large-scale forest LAI inversion and can facilitate further research on other forest structure parameters.
叶面积指数（LAI）是影响植被冠层与周围环境之间能量和物质交换的重要参数。利用机器学习模型结合遥感数据估算LAI已成为大规模LAI估算的常用方法。然而，现有的机器学习模型存在各种缺陷，阻碍了LAI的准确估算。因此，提出了一种大规模估算LAI的新方法，该方法整合了ICESat-2/ATLAS和哨兵-1/-2数据，并通过应用贝叶斯优化（BO）、粒子群优化（PSO）、遗传算法（GA）和模拟退火（SA）对机器学习模型进行优化。首先，使用顺序高斯条件模拟（SGCS）方法进行空间插值。然后，利用多源遥感数据通过皮尔逊相关系数法优化特征变量。随后，将优化算法应用于随机森林回归（RFR）、梯度提升回归树（GBRT）和支持向量机回归（SVR）模型，实现了高效的大规模LAI估算。结果表明，BO-GBRT模型在LAI估算中取得了高精度，决定系数（ ）为0.922，均方根误差（ ）为0.263，平均绝对误差（ ）为0.187，总体估算精度（ ）为92.38%。与现有的机器学习方法相比，该方法表现出优越的性能。该方法在大规模森林LAI反演方面具有巨大潜力，可为其他森林结构参数的进一步研究提供便利。
