TY - JOUR A1 - Cherif, Eya A1 - Hell, Maximilian A1 - Brandmeier, Melanie T1 - DeepForest: novel deep learning models for land use and land cover classification using multi-temporal and -modal sentinel data of the amazon basin JF - Remote Sensing N2 - Land use and land cover (LULC) mapping is a powerful tool for monitoring large areas. For the Amazon rainforest, automated mapping is of critical importance, as land cover is changing rapidly due to forest degradation and deforestation. Several research groups have addressed this challenge by conducting local surveys and producing maps using freely available remote sensing data. However, automating the process of large-scale land cover mapping remains one of the biggest challenges in the remote sensing community. One issue when using supervised learning is the scarcity of labeled training data. One way to address this problem is to make use of already available maps produced with (semi-) automated classifiers. This is also known as weakly supervised learning. The present study aims to develop novel methods for automated LULC classification in the cloud-prone Amazon basin (Brazil) based on the labels from the MapBiomas project, which include twelve classes. We investigate different fusion techniques for multi-spectral Sentinel-2 data and synthetic aperture radar Sentinel-1 time-series from 2018. The newly designed deep learning architectures—DeepForest-1 and DeepForest-2—utilize spatiotemporal characteristics, as well as multi-scale representations of the data. In several data scenarios, the models are compared to state-of-the-art (SotA) models, such as U-Net and DeepLab. The proposed networks reach an overall accuracy of up to 75.0%, similar to the SotA models. However, the novel approaches outperform the SotA models with respect to underrepresented classes. Forest, savanna and crop were mapped best, with F1 scores up to 85.0% when combining multi-modal data, compared to 81.6% reached by DeepLab. Furthermore, in a qualitative analysis, we highlight that the classifiers sometimes outperform the inaccurate labels. KW - deep learning KW - land use and land cover classification KW - multi-modal and multi-temporal data Y1 - 2022 U6 - https://doi.org/10.3390/rs14195000 SN - 2072-4292 VL - 14 IS - 19 ER - TY - JOUR A1 - Hell, Maximilian A1 - Brandmeier, Melanie A1 - Briechle, Sebastian A1 - Krzystek, Peter T1 - Classification of Tree Species and Standing Dead Trees with Lidar Point Clouds Using Two Deep Neural Networks: PointCNN and 3DmFV-Net JF - PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science N2 - Knowledge about tree species distribution is important for forest management and for modeling and protecting biodiversity in forests. Methods based on images are inherently limited to the forest canopy. Airborne lidar data provide information about the trees’ geometric structure, as well as trees beneath the upper canopy layer. In this paper, the potential of two deep learning architectures (PointCNN, 3DmFV-Net) for classification of four different tree classes is evaluated using a lidar dataset acquired at the Bavarian Forest National Park (BFNP) in a leaf-on situation with a maximum point density of about 80 pts/m2. Especially in the case of BFNP, dead wood plays a key role in forest biodiversity. Thus, the presented approaches are applied to the combined classification of living and dead trees. A total of 2721 single trees were delineated in advance using a normalized cut segmentation. The trees were manually labeled into four tree classes (coniferous, deciduous, standing dead tree with crown, and snag). Moreover, a multispectral orthophoto provided additional features, namely the Normalized Difference Vegetation Index. PointCNN with 3D points, laser intensity, and multispectral features resulted in a test accuracy of up to 87.0%. This highlights the potential of deep learning on point clouds in forestry. In contrast, 3DmFV-Net achieved a test accuracy of 73.2% for the same dataset using only the 3D coordinates of the laser points. The results show that the data fusion of lidar and multispectral data is invaluable for differentiation of the tree classes. Classification accuracy increases by up to 16.3% points when adding features generated from the multispectral orthophoto. Y1 - 2022 U6 - https://doi.org/10.1007/s41064-022-00200-4 SN - 2512-2819 VL - 90 SP - 103 EP - 121 ER - TY - CHAP A1 - Erbe, Karin A1 - Brandmeier, Melanie A1 - Schmitt, Michael A1 - Donbauer, Andreas A1 - Liebscher, Jan-Andreas A1 - Kolbe, Thomas ED - Kersten, Thomas P. ED - Tilly, Nora T1 - Detektion von Fahrradständern in Luftbildern mittels Deep Learning T2 - 42. Wissenschaftlich-Technische Jahrestagung der DGPF. 5.-6. Oktober 2022 in Dresden Y1 - 2022 U6 - https://doi.org/10.24407/KXP:1795622415 SN - 0942-2870 VL - 30 SP - 27 EP - 39 ER - TY - JOUR A1 - Zimmermann, Robert A1 - Brandmeier, Melanie A1 - Andreani, Louis A1 - Mhopjeni, Kombada A1 - Gloaguen, Richard T1 - Remote Sensing Exploration of Nb-Ta-LREE-Enriched Carbonatite (Epembe/Namibia) JF - Remote Sensing KW - carbonatite KW - decision tree KW - geomorphology KW - HyMap KW - Namibia KW - REE KW - self-organizing maps KW - spectral feature fitting KW - SRTM Y1 - 2016 U6 - https://doi.org/10.3390/rs8080620 SN - 2072-4292 VL - 8 IS - 8 SP - 620 EP - 620 ER - TY - JOUR A1 - Scharvogel, Daniel A1 - Brandmeier, Melanie A1 - Weis, Manuel T1 - A Deep Learning Approach for Calamity Assessment Using Sentinel-2 Data JF - Forests KW - CNNs KW - Deep Learning KW - forest KW - GIS KW - remote sensing KW - windthrow Y1 - 2020 U6 - https://doi.org/10.3390/f11121239 SN - 1999-4907 VL - 11 IS - 12 SP - 1239 EP - 1239 ER - TY - CHAP A1 - Hell, Maximilian A1 - Brandmeier, Melanie A1 - Nüchter, Andreas ED - Kersten, Thomas P. ED - Tilly, Nora T1 - Transferability of Deep Learning Models for Land Use/Land Cover Classification T2 - 43. Wissenschaftlich-Technische Jahrestagung der DGPF in München. 22.-23. März 2023 in München - Publikationen der DGPF Y1 - 2023 U6 - https://doi.org/10.24407/KXP:1841078182 VL - 31 SP - 142 EP - 149 ER - TY - CHAP A1 - Brandmeier, Melanie T1 - The Anatomy of Supervolcanoes T2 - GIS for Science: Applying Mapping and Spatial Analytics Y1 - 2019 UR - https://www.gisforscience.com/chapter3/v1/ PB - Esri ER - TY - JOUR A1 - Deigele, Wolfgang A1 - Brandmeier, Melanie A1 - Straub, Christoph T1 - A Hierarchical Deep-Learning Approach for Rapid Windthrow Detection on PlanetScope and High-Resolution Aerial Image Data JF - Remote Sensing N2 - 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. KW - convolutional neural networks KW - forest damage assessment KW - GIS KW - remote sensing KW - windthrow Y1 - 2020 U6 - https://doi.org/10.3390/rs12132121 SN - 2072-4292 VL - 12 IS - 13 SP - 2121 EP - 2121 ER - TY - CHAP A1 - Brandmeier, Melanie A1 - Wessel, M. ED - Meinel, Gotthard ED - Schumacher, Ulrich ED - Schwarz, Steffen ED - Richter, Benjamin ED - für Ökologische Raumentwicklung, Leibniz-Institut T1 - Workflows für Bilddaten und Big Data Analytics - Das Potenzial von Sentinel-2-Daten zur Baumartenklassifizierung T2 - Flächennutzungsmonitoring. IX: Nachhaltigkeit der Siedlungs- und Verkehrsentwicklung? Y1 - 2017 SN - 978-3-944101-73-6 N1 - Additional Note: Literaturangaben IS - Band 73 SP - 135 EP - 142 PB - Rhombos CY - Berlin ER - TY - JOUR A1 - Hamdi, Zayd Mahmoud A1 - Brandmeier, Melanie A1 - Straub, Christoph T1 - Forest Damage Assessment Using Deep Learning on High Resolution Remote Sensing Data JF - Remote Sensing KW - convolutional neural networks KW - forest damage assessment KW - GIS KW - remote sensing KW - windthrow Y1 - 2019 U6 - https://doi.org/10.3390/rs11171976 SN - 2072-4292 VL - 11 IS - 17 SP - 1976 EP - 1976 ER -