1,720,970 research outputs found
Tree Species Maps Germany - Probabilities
No full textTree Species Maps for Germany from 2018 to 2024
These files provide the raw probabilities for a certain tree species and should be used when estimating the tree species composition / area in a given region.
Bands and their meaning:
1: Background
2: Alder
3: Ash
4: Beech
5: Birch
6: Douglas Fir
7: Fir
8: Larch
9: Maple
10: Oak
11: Other broadleaf
12: Pine
13: Spruc
Tree Species Maps Germany - Model Weights
No full textThese model weights were generated by training on 5-fold cross-validation on the S2GNFI dataset (https://www.openagrar.de/receive/openagrar_mods_00094435). The corresponding code can be found at https://github.com/maxfreu/Sen2-classification
Tree Species Maps Germany - Observation Counts
No full textThese maps depict how many valid satellite observations were used at each location and year. Pixels that did not contain snow, any form of cloud or cloud shadow were counted as valid. Lower counts can be related to worse performance
Tree Species Maps Germany - Categorical
No full textCategorical Tree Species Maps for Germany from 2018 to 2024
Classes:
0: Background
1: Alder
2: Ash
3: Beech
4: Birch
5: Douglas Fir
6: Fir
7: Larch
8: Maple
9: Oak
10: Other broadleaf
11: Pine
12: Spruc
Tree Species Maps Germany - Standard Deviation
No full textThese maps represent the standard deviation of the classification of five different models, trained on different cross-validation splits. The units are arbitrary. Higher values mean that the models did not agree well in a certain location, which can be a hint to degraded classification performance, high temporal dynamics (logging, dying trees) or to a species mix
Tree Species Maps Germany - Entropy
No full textThese maps represent the entropy of the probability maps in arbitrary units. Higher values mean that there is no clear classification, which can indicate a mix of several species or degraded classification performance
A Sentinel-2 machine learning dataset for tree species classification in Germany
No full textAbstract. We present a machine learning dataset for tree species classification in Sentinel-2 satellite image time series of bottom-of-atmosphere reflectance. It is geared towards training classifiers but is less suitable for validating the resulting maps. The dataset is based on the German National Forest Inventory of 2012 as well as analysis-ready satellite imagery computed using the Framework for Operational Radiometric Correction for Environmental monitoring (FORCE) processing pipeline. From the National Forest Inventory data, we extracted the tree positions, filtered 387 775 trees in the upper canopy layer, and automatically extracted the corresponding bottom-of-atmosphere reflectance time series from Sentinel-2 L2A images. These time series are labeled with the corresponding tree species, which allows pixel-wise classification tasks. Furthermore, we provide auxiliary information such as the approximate tree position, the year of possible disturbance events, or the diameter at breast height. Temporally, the dataset spans the years from July 2015 to the end of October 2022, with approx. 75.3 million data points for trees of 48 species and 3 species groups as well as 13.8 million observations for non-tree backgrounds. Spatially, it covers the whole of Germany. The dataset is available at the following DOI (Freudenberg et al., 2024): https://doi.org/10.3220/DATA20240402122351-0
Individual tree crown delineation in high-resolution remote sensing images based on U-Net
No full textAbstractWe present a deep learning-based framework for individual tree crown delineation in aerial and satellite images. This is an important task, e.g., for forest yield or carbon stock estimation. In contrast to earlier work, the presented method creates irregular polygons instead of bounding boxes and also provides a tree cover mask for areas that are not separable. Furthermore, it is trainable with low amounts of training data and does not need 3D height information from, e.g., laser sensors. We tested the approach in two scenarios: (1) with 30 cm WorldView-3 satellite imagery from an urban region in Bengaluru, India, and (2) with 5 cm aerial imagery of a densely forested area near Gartow, Germany. The intersection over union between the reference and predicted tree cover mask is 71.2% for the satellite imagery and 81.9% for the aerial images. On the polygon level, the method reaches an accuracy of 46.3% and a recall of 63.7% in the satellite images and an accuracy of 52% and recall of 66.2% in the aerial images, which is comparable to previous works that only predicted bounding boxes. Depending on the image resolution, limitations to separate individual tree crowns occur in situations where trees are hardly separable even for human image interpreters (e.g., homogeneous canopies, very small trees). The results indicate that the presented approach can efficiently delineate individual tree crowns in high-resolution optical images. Given the high availability of such imagery, the framework provides a powerful tool for tree monitoring. The source code and pretrained weights are publicly available at https://github.com/AWF-GAUG/TreeCrownDelineation.</jats:p
Spatial resolution and landscape structure along an urban-rural gradient: Do they relate to remote sensing classification accuracy? – A case study in the megacity of Bengaluru, India
No full textUnveiling urbanization effects on trees outside forests along the urban-rural gradient in megacity Bengaluru
No full textOpen-Access-Publikationsfonds 202
- …
