Storms can cause significant damage to forest areas, affecting biodiversity and infrastructure and leading to economic loss. Thus, rapid detection and mapping of windthrows are crucially important for forest management. Recent advances in computer vision have led to highly-accurate image classification algorithms such as Convolutional Neural Network (CNN) architectures. In this study, we tested and implemented an algorithm based on CNNs in an ArcGIS environment for automatic detection and mapping of damaged areas. The algorithm was trained and tested on a forest area in Bavaria, Germany. . It is a based on a modified U-Net architecture that was optimized for the pixelwise classification of multispectral aerial remote sensing data. The neural network was trained on labeled damaged areas from after-storm aerial orthophotos of a ca. $109k{m}^2$ forest area with RGB and NIR bands and 0.2-m spatial resolution. Around ${10}^7$ pixels of labeled data were used in the process. Once the network is trained, predictions on further datasets can be computed within seconds, depending on the size of the input raster and the computational power used. The overall accuracy on our test dataset was $92\%$ . During visual validation, labeling errors were found in the reference data that somewhat biased the results because the algorithm in some instance performed better than the human labeling procedure, while missing areas affected by shadows. Our results are very good in terms of precision, and the methods introduced in this paper have several additional advantages compared to traditional methods: CNNs automatically detect high- and low-level features in the data, leading to high classification accuracies, while only one after-storm image is needed in comparison to two images for approaches based on change detection. Furthermore, flight parameters do not affect the results in the same way as for approaches that require DSMs and DTMs as the classification is only based on the image data themselves, and errors occurring in the computation of DSMs and DTMs do not affect the results with respect to the z component. The integration into the ArcGIS Platform allows a streamlined workflow for forest management, as the results can be accessed by mobile devices in the field to allow for high-accuracy ground-truthing and additional mapping that can be synchronized back into the database. Our results and the provided automatic workflow highlight the potential of deep learning on high-resolution imagery and GIS for fast and efficient post-disaster damage assessment as a first step of disaster management.

Stereo satellites provide height information of the earth's surface with increasing accuracy. High temporal resolution and wide regional coverage are the great advantages of satellites compared with aerial surveys. There is currently little experience of how accurate forest attributes can be modelled using high-resolution stereo satellite data, especially for highly structured forests in Central Europe. Thus, the potential of Cartosat-1 and WorldView-2 was assessed for timber volume estimation in a complex forest in Germany. Digital surface models were generated using Semi-Global Matching. Canopy height models (CHMs) were computed by subtracting a Light detection and ranging (LiDAR) terrain model. The CHMs were co-registered with field plots of a forest inventory. Explanatory variables were derived from the CHMs for timber volume estimation using regressions. Accuracies were evaluated at plot and stand levels. Results were compared with estimations based on a LiDAR-CHM. At plot level the following root mean squared errors (RMSEs) for timber volume estimation were obtained: 50.26 per cent for Cartosat-1, 44.40 per cent for WorldView-2 and 38.02 per cent for LiDAR. The RMSEs were smaller than the standard deviation of the observed timber volume. The RMSEs at a stand level yielded 21.49 per cent for Cartosat-1, 19.59 per cent for WorldView-2 and 17.14 per cent for LiDAR. The study demonstrates the potential of satellite stereo images for regionalization of sample plot inventories.

Digital surface models (DSMs) derived from spaceborne and airborne sensors enable the monitoring of the vertical structures for forests in large areas. Nevertheless, due to the lack of an objective performance assessment for this task, it is difficult to select the most appropriate data source for DSM generation. In order to fill this gap, this paper performs change detection analysis including forest decrease and tree growth. The accuracy of the DSMs is evaluated by comparison with measured tree heights from inventory plots (field data). In addition, the DSMs are compared with LiDAR data to perform a pixel-wise quality assessment. DSMs from four different satellite stereo sensors (ALOS/PRISM, Cartosat-1, RapidEye and WorldView-2), one satellite InSAR sensor (TanDEM-X), two aerial stereo camera systems (HRSC and UltraCam) and two airborne laser scanning datasets with different point densities are adopted for the comparison. The case study is a complex central European temperate forest close to Traunstein in Bavaria, Germany. As a major experimental result, the quality of the DSM is found to be robust to variations in image resolution, especially when the forest density is high. The forest decrease results confirm that besides aerial photogrammetry data, very high resolution satellite data, such as WorldView-2, can deliver results with comparable quality as the ones derived from LiDAR, followed by TanDEM-X and Cartosat DSMs. The quality of the DSMs derived from ALOS and Rapid-Eye data is lower, but the main changes are still correctly highlighted. Moreover, the vertical tree growth and their relationship with tree height are analyzed. The major tree height in the study site is between 15 and 30 m and the periodic annual increments (PAIs) are in the range of 0.30–0.50 m.

So far, only a few studies have been carried out in central European forests to estimate individual tree stem volume of pine trees from high resolution remote sensing data. In this article information derived from airborne laser scanner and multispectral line scanner data were tested to predict the stem volume of 178 pines (Pinus sylvestris) in a study site in the south-west of Germany. First, tree crowns were automatically delineated using both multispectral and laser scanner data. Next, tree height, crown diameter and crown volume were derived for each crown segment. All combinations of the derived tree features were used as explanatory variables in allometric models to predict the stem volume. A model with tree height and crown diameter had the best performance with respect to the prediction accuracy determined by a leave-one-out cross-validation: Root Mean Square Error (RMSE) = 24.02% and Bias = 1.36%.

Forest damage due to storms causes economic loss and requires a fast response to prevent further damage such as bark beetle infestations. By using Convolutional Neural Networks (CNNs) in conjunction with a GIS, we aim at completely streamlining the detection and mapping process for forest agencies. We developed and tested different CNNs for rapid windthrow detection based on PlanetScope satellite data and high-resolution aerial image data. Depending on the meteorological situation after the storm, PlanetScope data might be rapidly available due to its high temporal resolution, while the acquisition of high-resolution airborne data often takes weeks to a month and is, therefore, used in a second step for more detailed mapping. The study area is located in Bavaria, Germany (ca. 165 km²), and labels for damaged areas were provided by the Bavarian State Institute of Forestry (LWF). Modifications of a U-Net architecture were compared to other approaches using transfer learning (e.g., VGG19) to find the most efficient architecture for the task on both datasets while keeping the computational time low. A custom implementation of U-Net proved to be more accurate than transfer learning, especially on medium (3 m) resolution PlanetScope imagery (intersection over union score (IoU) 0.55) where transfer learning completely failed. Results for transfer learning based on VGG19 on high-resolution aerial image data are comparable to results from the custom U-Net architecture (IoU 0.76 vs. 0.73). When using both architectures on a dataset from a different area (located in Hesse, Germany), however, we find that the custom implementations have problems generalizing on aerial image data while VGG19 still detects most damage in these images. For PlanetScope data, VGG19 again fails while U-Net achieves reasonable mappings. Results highlight the potential of Deep Learning algorithms to detect damaged areas with an IoU of 0.73 on airborne data and 0.55 on Planet Dove data. The proposed workflow with complete integration into ArcGIS is well-suited for rapid first assessments after a storm event that allows for better planning of the flight campaign followed by detailed mapping in a second stage.