Policies, measures, and models geared towards flood prevention and managing surface waters benefit from high quality data on the presence and characteristics of drainage ditches. As a cost and labour effective alternative for acquiring such data through field surveys, we propose a method (a) to extract vector data representing ditch drainage networks based on local morphologic features derived from high resolution digital elevation models (DEM) and (b) to identify possible connections in the ditch network by calculating a probability of the connectivity using a logistic regression where the predictor variables are characteristics of the ditch centre lines or derived from the DEM. Using Light Detection and Ranging (LiDAR) derived DEMs with a 1 m resolution, the method was developed and tested for a mixed agricultural residential area in north-eastern Belgium. The derived ditch segments had an error of omission of 8% and an error of commission of 5%. The original positional accuracy of the centre lines of the extracted ditches was 0.6 m and could be improved to 0.4 m by shifting each vertex to the position of the lowest LiDAR point located within a radius equal to the spatial resolution of the used DEM. About 69% of the false disconnections in the network were identified and corrected leading to a reduction of the unconnected parts of the ditch network by 71%. The extracted and connected network approximated the reference ditch network fairly well.

No abstract

Rural European landscapes are characterized by a variety of vegetated landscape elements. Although it is often not their main function, they have the potential to affect river discharge and the frequency, extent, depth and duration of floods downstream by creating both hydrological discontinuities and connections across the landscape. Information about the extent to which individual landscape elements and their spatial location affect peak river discharge and flood frequency and severity in agricultural catchments under specific meteorological conditions is limited. This knowledge gap can partly be explained by the lack of exhaustive inventories of the presence, geometry, and hydrological traits of vegetated landscape elements (vLEs), which in turn is due to the lack of appropriate techniques and source data to produce such inventories and keep them up to date. In this paper, a multi-step methodology is proposed to delineate and classify vLEs based on LiDAR point cloud data in three study areas in Flanders, Belgium. We classified the LiDAR point cloud data into the classes ‘vegetated landscape element point’ and ‘other’ using a Random Forest model with an accuracy classification score ranging between 0.92 and 0.97. The landscape element objects were further classified into the classes ‘tree object’ and ‘shrub object’ using a Logistic Regression model with an area-based accuracy ranging between 0.34 and 0.95.

No abstract

<p>Extensive areas throughout Europe are affected by river flooding. The frequency of these floods has considerably augmented in the past decades, resulting in substantial economic damage. In the strongly urbanized Flanders region of Belgium, insured losses due to floods are estimated at €40-75 million per year. So far little attention has been paid to off-site source areas of which hydrological behaviour influences the flood risk downstream in the catchment. These off-site areas have however the ability to either increase or reduce the exposure of downstream properties and infrastructures to floods. In rural European landscapes, these off-site areas are characterized by a variety of landscape elements (LSEs) such as hedgerows, trees, drainage ditches and terrace slopes. They affect river discharge and the frequency, extent, depth and duration of floods downstream by creating hydrological discontinuities and connections across the landscape but the magnitude of these effects is very much landscape specific.</p><p>We propose a hierarchical workflow to extract vegetated LSEs from LiDAR point data consisting of six steps: (1) selection of non-ground LiDAR points from an airborne LiDAR dataset with an average point density of at least 16 points per square meter, (2) extraction of geometry and eigenvalue based features for each point in the LiDAR point clouds, (3) supervised classification of the points into the classes ‘vegetated LSE’ and ‘other non-ground LiDAR points’ using a Random Forest classifier, (4) clustering of the classified vegetated LSE points by using the density-based clustering algorithm DBSCAN, (5) segmentation of the clustered points by calculating the concave hull per cluster, and (6) classification of the 2D objects into the vegetated LSE classes ‘tree objects’ (individual trees, tree groups and tree rows) and ‘shrub objects’ (bushes, hedgerows and woody edges) by using a Random Forest Classifier and a rule-based approach.</p><p>Our workflow was calibrated and tested on two undulating study areas in which the position and geometric characteristics of all vegetated LSEs were recorded in the summer of 2019 using a real-time kinematic GNSS device. The land use in both study areas is dominated by agricultural land. Step 3 of our workflow was validated by using a stratified ten-fold cross-validation method and resulted in a producer’s accuracy of 99% in distinguishing between vegetated LSE and other non-ground LiDAR point. Step 6 resulted in producer’s accuracies between 42% and 64% when distinguishing tree and shrub objects.</p><p>Further fine-tuning of the workflow by incorporating features based on point density distributions within LSE segments is expected to increase the classification accuracy. Our aim is to incorporate the classified 2D objects in spatially explicit hydrological models which will allow estimating their effect on river discharge and the frequency, extent, depth and duration of floods downstream.</p>