Vegetation indices can be used to perform quantitative and qualitative assessment of vegetation cover. These indices exploit the reflectance features of leaves to predict their biophysical properties. In general, there are different vegetation indices capable of describing the same biophysical parameter. For instance, vegetation water content can be inferred from at least sixteen vegetation indices, where each one uses the reflectance of leaves in different spectral bands. Therefore, if the leaf moisture content, a vegetation index and the reflectance at the wavelengths to compute the vegetation index are known, then the reflectance in other spectral bands can be computed with a bounded error. The current work proposes a method to predict, by a machine learning regressor, the leaf reflectance (spectral signature) at specific spectral bands using the information of leaf moisture content and a single vegetation index of two tree species (Pinus radiata, and Eucalyptus globulus), which constitute 97.5% of the Valparaíso forests in Chile. Results suggest that the most suitable vegetation index to predict the spectral signature is the Leaf Water Index, which using a Kernel Ridge Regressor achieved the best prediction results, with a RMSE lower than 0.022, and a average R² greater than 0.95 for Pinus radiata and 0.81 for Eucalyptus globulus, respectively.

植被指数可用于对植被覆盖度进行定量和定性评估。这些指数利用叶片的反射特征预测其生物物理特性。通常，有不同的植被指数能够描述相同的生物物理参数。例如，可以从至少十六个植被指数中推断出植被含水量，其中每个指数都使用不同光谱带中叶片的反射率。因此，如果已知叶片的水分含量，植被指数和在计算植被指数的波长下的反射率，则可以计算出其他光谱带中的反射率，但有一定的误差。当前的工作提出了一种通过机器学习回归器预测的方法辐射松和桉树（Eucalyptus globulus），占智利瓦尔帕莱索森林的97.5％。结果表明，最适合预测光谱特征的植被指数是叶水指数，它使用内核岭回归器获得了最佳的预测结果，RMSE小于0.022，辐射松和R的平均R ²大于0.95。桉树球分别为0.81 。