Assessing a novel modelling approach with high resolution UAV imagery for monitoring health status in priority riparian forests

Background:Black alder(Alnus glutinosa)forests are in severe decline across their area of distribution due to a disease caused by the soil-borne pathogenic Phytophthora alni species complex(class Oomycetes),“alder Phytopththora”.Mapping of the different types of damages caused by the disease is challenging in high density ecosystems in which spectral variability is high due to canopy heterogeneity.Data obtained by unmanned aerial vehicles(UAVs)may be particularly useful for such tasks due to the high resolution,flexibility of acquisition and cost efficiency of this type of data.In this study,A.glutinosa decline was assessed by considering four categories of tree health status in the field:asymptomatic,dead and defoliation above and below a 50% threshold.A combination of multispectral Parrot Sequoia and UAV unmanned aerial vehicles-red green blue(RGB)data were analysed using classical random forest(RF)and a simple and robust three-step logistic modelling approaches to identify the most important forest health indicators while adhering to the principle of parsimony.A total of 34 remote sensing variables were considered,including a set of vegetation indices,texture features from the normalized difference vegetation index(NDVI)and a digital surface model(DSM),topographic and digital aerial photogrammetry-derived structural data from the DSM at crown level.Results:The four categories identified by the RF yielded an overall accuracy of 67%,while aggregation of the legend to three classes(asymptomatic,defoliated,dead)and to two classes(alive,dead)improved the overall accuracy to 72% and 91% respectively.On the other hand,the confusion matrix,computed from the three logistic models by using the leave-out cross-validation method yielded overall accuracies of 75%,80% and 94% for four-,three-and two-level classifications,respectively.Discussion:The study findings provide forest managers with an alternative robust classification method for the rapid,effective assessment of areas affected and non-affected by the disease,thus enabling them to identify hotspots for conservation and plan control and restoration measures aimed at preserving black alder forests.

Learning from the crowd:Road infrastructure monitoring system

The condition of the road infrastructure has severe impacts on the road safety, driving comfort, and on the rolling resistance. Therefore, the road infrastructure must be moni- tored comprehensively and in regular intervals to identify damaged road segments and road hazards. Methods have been developed to comprehensively and automatically digitize the road infrastructure and estimate the road quality, which are based on vehicle sensors and a supervised machine learning classification. Since different types of vehicles have various suspension systems with different response functions, one classifier cannot be taken over to other vehicles. Usually, a high amount of time is needed to acquire training data for each individual vehicle and classifier. To address this problem, the methods to collect training data automatically for new vehicles based on the comparison of trajectories of untrained and trained vehicles have been developed. The results show that the method based on a k-dimensional tree and Euclidean distance performs best and is robust in transferring the information of the road surface from one vehicle to another. Furthermore, this method offers the possibility to merge the output and road infrastructure information from multiple vehicles to enable a more robust and precise prediction of the ground truth.