Abstract

Yellowwood or Podocarpus (spp.) holds the esteemed biodiversity status, as key forest species in the mist-belt Afromontane forests of southern Africa. The podocarps are listed as endangered species owing to extensive logging. The forest species support large communities of plants and birds, attributing to the maintenance of biodiversity. Therefore, there is a need to understand the condition of such keystone species if effective and comprehensive biodiversity conservation measures are to be drawn for these dwindling forests. Leaf area index is a crucial eco-physiological parameter applied in the evaluation of the growth and productivity of forest trees, hence it is a suitable proxy for understanding the condition of Yellowwood trees. This study, therefore, sought to estimate the leaf area index of the Yellowwood spp. using Sentinel 2 Multispectral instrument (S2 MSI) data in concert with the Random Forest regression ensemble. Specifically, individual wavebands and vegetation indices were used in developing leaf area index prediction models based on two approaches. The multistage approach, categorised the predictors according to the generalised order of progression, from standard spectral bands to vegetation indices. The second approach involved using a pooled set of predictors, with the backward elimination of poorly performing wavebands and vegetation indices. Results showed that the backward elimination method produced a better model (R² = 0.59; RMSE =0.48) when compared to the multistage approach (R² = 0.50; RMSE =0.48). The most influential predictor variables in both models were Band 5 and NDVI Red Edge 2. Results of this study underscore the prospects of Sentinel 2 MSI data in characterising the productivity of critical forest species such as the Yellowwoods of the Afromontane forest in southern Africa. The findings of this study are a fundamental step towards understanding forest health and productivity, required in deriving comprehensive monitoring and management strategies in biodiversity conservation.

摘要

黄木或罗汉松(spp.) 拥有备受推崇的生物多样性地位，是南部非洲雾带非洲山地森林中的主要森林物种。由于大量采伐，罗汉果被列为濒危物种。森林物种支持大型植物和鸟类群落，有助于维护生物多样性。因此，如果要为这些逐渐减少的森林制定有效和全面的生物多样性保护措施，就需要了解这些关键物种的状况。叶面积指数是评估林木生长和生产力的重要生态生理参数，因此它是了解黄木树状况的合适代表。因此，本研究试图估计黄木属植物的叶面积指数。使用 Sentinel 2 多光谱仪器 (S2 MSI) 数据与随机森林回归集成。具体而言，单个波段和植被指数用于基于两种方法开发叶面积指数预测模型。多阶段方法根据从标准光谱带到植被指数的一般进展顺序对预测因子进行分类。第二种方法涉及使用一组汇集的预测变量，向后消除表现不佳的波段和植被指数。结果表明，后向消除法产生了更好的模型（R 根据从标准光谱带到植被指数的一般进展顺序对预测因子进行分类。第二种方法涉及使用一组汇集的预测变量，向后消除表现不佳的波段和植被指数。结果表明，后向消除法产生了更好的模型（R 根据从标准光谱带到植被指数的一般进展顺序对预测因子进行分类。第二种方法涉及使用一组汇集的预测变量，向后消除表现不佳的波段和植被指数。结果表明，后向消除法产生了更好的模型（R² = 0.59；与多级方法（R ² = 0.50；RMSE = 0.48）相比，RMSE = 0.48）。两个模型中最具影响力的预测变量是 Band 5 和 NDVI Red Edge 2。这项研究的结果强调了 Sentinel 2 MSI 数据在表征关键森林物种（例如南部非洲非洲山地森林的黄树林）生产力方面的前景。这项研究的结果是了解森林健康和生产力的基本步骤，这是制定生物多样性保护的综合监测和管理战略所必需的。