Predicting Tree Mortality Using Spectral Indices Derived from Multispectral UAV Imagery

Fire intensity impacts on physiological performance and mortality in Pinus monticola and Pseudotsuga menziesii saplings: a dose-response analysis

Fire is a major cause of tree injury and mortality worldwide, yet our current understanding of fire effects is largely based on ocular estimates of stem charring and foliage discoloration, which are error prone and provide little information on underlying tree function. Accurate quantification of physiological performance is a research and forest management need, given that declining performance could help identify mechanisms of-and serve as an early warning sign for-mortality. Many previous efforts have been hampered by the inability to quantify the heat flux that a tree experiences during a fire, given its highly variable nature in space and time. In this study, we used a dose-response approach to elucidate fire impacts by subjecting Pinus monticola var. minima Lemmon and Pseudotsuga menziesii (Mirb.) Franco var. glauca (Beissn.) Franco saplings to surface fires of varying intensity doses and measuring short-term post-fire physiological performance in photosynthetic rate and chlorophyll fluorescence. We also evaluated the ability of spectral reflectance indices to quantify change in physiological performance at the individual tree crown and stand scales. Although physiological performance in both P. monticola and P. menziesii declined with increasing fire intensity, P. monticola maintained a greater photosynthetic rate and higher chlorophyll fluorescence at higher doses, for longer after the fire. Pinus monticola also had complete survival at lower fire intensity doses, whereas P. menziesii had some mortality at all doses, implying higher fire resistance for P. monticola at this life stage. Generally, individual-scale spectral indices were more accurate at quantifying physiological performance than those acquired at the stand-scale. The Photochemical Reflectance Index outperformed other indices at quantifying photosynthesis and chlorophyll fluorescence, highlighting its potential use to quantify crown scale physiological performance. Spectral indices that incorporated near-infrared and shortwave infrared reflectance, such as the Normalized Burn Ratio, were accurate at characterizing stand-scale mortality. The results from this study were included in a conifer cross-comparison using physiology and mortality data from other dose-response studies. The comparison highlights the close evolutionary relationship between fire and species within the Pinus genus, assessed to date, given the high survivorship of Pinus species at lower fire intensities versus other conifers.

Combination of spectral index and transfer learning strategy for glyphosate-resistant cultivar identification

Glyphosate is one of the most widely used non-selective herbicides, and the creation of glyphosate-resistant cultivars solves the problem of limited spraying area. Therefore, it is of great significance to quickly identify resistant cultivars without destruction during the development of superior cultivars. This work took maize seedlings as the experimental object, and the spectral indices of leaves were calculated to construct a model with good robustness that could be used in different experiments. Compared with no transfer strategies, transferability of support vector machine learning model was improved by randomly selecting 14% of source domain from target domain to train and applying transfer component analysis algorithm, the accuracy on target domain reached 83% (increased by 71%), recall increased from 10 to 100%, and F1-score increased from 0.17 to 0.86. The overall results showed that both transfer component analysis algorithm and updating source domain could improve the transferability of model among experiments, and these two transfer strategies could complement each other's advantages to achieve the best classification performance. Therefore, this work is beneficial to timely understanding of the physiological status of plants, identifying glyphosate resistant cultivars, and ultimately provides theoretical basis and technical support for new cultivar creation and high-throughput selection.