Tar spot is a foliar disease of corn characterized by fungal fruiting bodies that resemble tar spots. The disease emerged in the U.S. in 2015, and severe outbreaks in 2018 caused an economic impact on corn yields throughout the Midwest. Adequate epidemiological surveillance and disease quantification are necessary to develop immediate and long-term management strategies. This study presents a measurement framework that evaluates the disease severity of tar spot using unmanned aircraft systems (UAS)-based plant phenotyping and regression techniques. UAS-based plant phenotypic information, such as canopy cover, canopy volume, and vegetation indices, were used as explanatory variables. Visual estimations of disease severity were performed by expert plant pathologists per experiment plot basis and used as response variables. Three regression methods, namely ordinary least squares (OLS), support vector regression (SVR), and multilayer perceptron (MLP), were used to determine an optimal regression method for UAS-based tar spot measurement. The cross-validation results showed that the regression model based on MLP provides the highest accuracy of disease measurements. By training and testing the model with spatially separated datasets, the proposed regression model achieved a Lin’s concordance correlation coefficient (ρc) of 0.82 and a root mean square error (RMSE) of 6.42. This study demonstrated that we could use the proposed UAS-based method for the disease quantification of tar spot, which shows a gradual spectral response as the disease develops.

Terrestrial laser scanners, unmanned aerial LiDAR, and unmanned aerial photogrammetry are increasingly becoming the go-to methods for forest analysis and mapping. The three-dimensionality of the point clouds generated by these technologies is ideal for capturing the structural features of trees such as trunk diameter, canopy volume, and biomass. A prerequisite for extracting these features from point clouds is tree segmentation. This paper introduces an unsupervised method for segmenting individual trees from point clouds. Our novel, canopy-to-root, least-cost routing method segments trees in a single routine, accomplishing stem location and tree segmentation simultaneously without needing prior knowledge of tree stem locations. Testing on benchmark terrestrial-laser-scanned datasets shows that we achieve state-of-the-art performances in individual tree segmentation and stem-mapping accuracy on boreal and temperate hardwood forests regardless of forest complexity. To support mapping at scale, we test on unmanned aerial photogrammetric and LiDAR point clouds and achieve similar results. The proposed algorithm’s independence from a specific data modality, along with its robust performance in simple and complex forest environments and accurate segmentation results, make it a promising step towards achieving reliable stem-mapping capabilities and, ultimately, towards building automatic forest inventory procedures.

Field-based forest inventory plots are fundamental for many forest studies. These on-the-ground measurements of small samples of forested areas provide foresters with key information such as the size, abundance, health, and value of their forests. Recently, forest inventory plots have begun to be used as ground validation for tree features automatically extracted from remotely sensed data sets. Additionally, machine learning methods for feature extraction rely heavily on large quantities of training data and require these field forest inventory measurement datasets for algorithm training. Undermining the usefulness of forest inventory plot data as validation or training data is the positional uncertainty of plot location measurements. Because global navigation satellite systems (GNSS) cannot reliably measure plot center coordinates under thick tree canopy, plot center coordinates usually contain multiple meters of horizontal error. We present a method for reliably measuring plot center coordinates in which plot centers are individually marked with low-cost targets, allowing plot centers to be manually measured from orthoimagery captured during the leaf-off season. Our plot center measurements are shown to have less than 10 cm of horizontal error, an improvement of an order of magnitude over traditional GNSS methods. Study Implications: Recently, as unoccupied aerial systems (UASs) make high-resolution data easy to collect, researchers have begun to develop methods for measuring individual tree features automatically from remotely sensed data. The output from these methods must be compared to on-the-ground measurements, most commonly to forest inventories. Although forest inventories provide accurate per tree characteristics, there is no method for measuring the global position of these inventories accurately and reliably. This prevents the ground measurements from matching up with remotely sensed datasets. This study introduces a method for using UASs to reliably measure the coordinates of plot centers to within 10 cm of true position.

No abstract

No abstract