Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
1,549
datasets available to search
ShareScore release 0.9.0
Dataset results
1,549 results for “benchmarks”
Reports about the tools for converting IFC to CityGML and CityGML to IFC delivered within the GeoBIM benchmark 2019 - Task 4
<p>Answers delivered through the online forms, about the tests performed by participants within the Task 4 - 'conversions from IFC to CityGML and from CityGML to IFC' - of the GeoBIM benchmark 2019, funded as a Scientific Initiative 2019 by the International Society of Photogrammetry and Remote Sensing (ISPRS) and co-funded by the European association for Spatial Data Research (EuroSDR).</p> <p>Full details and additional resources about the project are available in the project website: https://3d.bk.tudelft.nl/projects/geobim-benchmark/</p> <p>The dataset results from the collaboration of the authors with all the participants to the benchmark, listed at https://3d.bk.tudelft.nl/projects/geobim-benchmark/participants.html</p> <p>It is composed by 2 files:</p> <p>- the answers to the delivered online forms, organised in excel sheet;</p> <p>- the same answers organised in a more human-readable PDF, with reliable images and links.</p>
Reports about the software behaviour delivered within the GeoBIM benchmark 2019 - Task 3
<p>Answers delivered through the online forms, about the tests performed by participants within the Task 3 - support for CityGML of the GeoBIM benchmark 2019, funded as a Scientific Initiative 2019 by the International Society of Photogrammetry and Remote Sensing (ISPRS) and co-funded by the European association for Spatial Data Research (EuroSDR).</p> <p>Full details and additional resources about the project are available in the project website: https://3d.bk.tudelft.nl/projects/geobim-benchmark/</p> <p>The dataset results from the collaboration of the authors with all the participants to the benchmark, listed at https://3d.bk.tudelft.nl/projects/geobim-benchmark/participants.html</p> <p>It is composed by 2 files:</p> <p>- the answers to the delivered online forms, organised in excel sheet;</p> <p>- the same answers organised in a more human-readable PDF, with reliable images and links.</p>
COCO BBOB-constrained Benchmark Results of Two Evolution Strategy Variants
<p>The three zip-files of this data set provide the performance data of the algorithms presented in the paper<strong> "Benchmarking 𝜖MAg-ES and BP-𝜖MAg-ES on the bbob-constrained Testbed"</strong> submitted to the GECCO 2022 Workshop "<a href="https://gecco-2022.sigevo.org/Workshops#BBOB 2022">BBOB 2022 — Black Box Optimization Benchmarking 2022</a>".</p> <ul> <li><em>coco2.6.2_bbob-constrained_epsMAg.zip</em> <-- results of the 𝜖MAg-ES on COCO version 2.6.2</li> <li><em>coco2.6.2_bbob-constrained_BPepsMAg.zip</em> <-- results of the BP-𝜖MAg-ES on COCO version 2.6.2</li> <li><em>coco2.6.2_bbob-constrained_fmincon</em><em>.zip</em> <-- results of FMINCON (Matlab 2021b) on COCO version 2.6.2</li> </ul> <p> </p>
Reports about the software behaviour delivered within the GeoBIM benchmark 2019 - Task 1
<p><strong>Answers delivered through the online forms</strong>, about the tests performed by participants within the <strong>Task 1 - support for IFC</strong> of the <strong>GeoBIM benchmark 2019</strong>, funded as a Scientific Initiative 2019 by the International Society of Photogrammetry and Remote Sensing (ISPRS) and co-funded by the European association for Spatial Data Research (EuroSDR).</p> <p>Full details and additional resources about the project are available in the project website: https://3d.bk.tudelft.nl/projects/geobim-benchmark/</p> <p>The dataset results from the collaboration of the authors with all the participants to the benchmark, listed at https://3d.bk.tudelft.nl/projects/geobim-benchmark/participants.html</p> <p>It is composed by 4 files:</p> <p>- the answers to the delivered online forms, organised in excel sheet;</p> <p>- the same answers organised in a more human-readable PDF, with reliable images;</p> <p>- the same answers organised in a more human-readable PDF, with low-resolution images and working links;</p> <p>- the answers regarding the IFCgeometries dataset in IFC 2x3 format, in excel;</p> <p>- the answers regarding the IFCgeometries dataset in IFC 4 format, in excel.</p>
TocoDecoy: a new approach to design unbiased datasets for training and benchmarking machine-learning scoring functions
<p>This dataset file contains TocoDecoy datasets generated based on the targets and active ligands of LIT-PCBA.</p> <p>1_property_filtered.zip :</p> <ul> <li>TD set: the ligand file name, 2D T-sne vectors, Smiles, molecular weight (MW), Wildman-Crippen partition coefficient (log P), number of rotatable bonds (RB), number of hydrogen-bond acceptors (HBA), number of hydrogen-bond donors (HBD), number of halogens (HAL), topology similarities of decoys to the seed active ligands, active label (active or inactive) and training set label (whether belongs to training set or test set) <strong>OF active ligands and their topologically dissimilar decoys</strong></li> <li>CD set: the decoy conformations with low docking scores generated by docking active ligands into protein pockets using Glide, Schrödinger.</li> </ul> <p> </p>
Public BI benchmark - part 2 & results
<p>Originally published on: https://github.com/cwida/public_bi_benchmark </p> <p>Originally compressed with bzip2. Compressed here with gzip.</p> <p>"User generated benchmark derived from the DBTest'18 paper [1] by Tableau. It contains real data and queries from 46 public workbooks in Tableau Public [2].</p> <p>We downloaded 46 of the biggest workbooks and converted the data to <em>.csv</em> files and collected the SQL queries that appear in the Tableau log when the workbooks are visualized. We processed the <em>.csv</em> files and queries with the purpose of making them load and run on different database systems.</p> <p>Each directory is associated with a workbook and contains:</p> <pre><code>samples: a sample of each .csv file (first 20 rows) tables: .sql files containing the schema of each .csv file queries: .sql files containing the queries data-urls.txt: links for downloading the full .csv.bz2 compressed files </code></pre> <p>There are 46 workbooks containing 206 tables (.csv files) with the total size of 41 GB compressed and 386 GB uncompressed.</p> <p>Multiple .csv files may overlap but are not identical. This is because Tableau extracts the same workbook in multiple different ways for different queries."</p>
Public BI benchmark - part 1
<p>Originally published on: https://github.com/cwida/public_bi_benchmark </p> <p>Originally compressed with bzip2. Compressed here with gzip.</p> <p>"User generated benchmark derived from the DBTest'18 paper [1] by Tableau. It contains real data and queries from 46 public workbooks in Tableau Public [2].</p> <p>We downloaded 46 of the biggest workbooks and converted the data to <em>.csv</em> files and collected the SQL queries that appear in the Tableau log when the workbooks are visualized. We processed the <em>.csv</em> files and queries with the purpose of making them load and run on different database systems.</p> <p>Each directory is associated with a workbook and contains:</p> <pre><code>samples: a sample of each .csv file (first 20 rows) tables: .sql files containing the schema of each .csv file queries: .sql files containing the queries data-urls.txt: links for downloading the full .csv.bz2 compressed files </code></pre> <p>There are 46 workbooks containing 206 tables (.csv files) with the total size of 41 GB compressed and 386 GB uncompressed.</p> <p>Multiple .csv files may overlap but are not identical. This is because Tableau extracts the same workbook in multiple different ways for different queries."</p>
RuCoLA benchmark
<p><strong>Russian Corpus of Linguistic Acceptability</strong></p> <p>The Russian Corpus of Linguistic Acceptability (RuCoLA) is a dataset consisting of Russian language sentences with their binary acceptability judgements. It includes expert-written sentences from linguistic publications and machine-generated examples. The corpus covers a variety of language phenomena, ranging from syntax and semantics to generative model hallucinations. We release RuCoLA to facilitate the development of methods for identifying errors in natural language and create a public leaderboard to track the progress made on this problem.</p> <p><strong>About</strong></p> <p>In recent years, natural language processing systems have rapidly improved in quality for a number of tasks, many of which involve concepts as difficult as common sense or even general world knowledge. This trend was enabled by the emergence of large-scale self-supervised pretraining methods that formed the backbone of mainstream language models like BERT or GPT-3. Such models have surpassed human performance on canonical NLU benchmarks and proved capable of generating texts hardly distinguishable from those written by humans.</p> <p>Despite these impressive results, modern language models are still far from perfect, particularly for the Russian language. Although passages from generative models may seem human-like at first glance, they tend to be rife with hallucinated facts or contradictory information. Furthermore, a growing number of studies have reported that even the largest language models do not properly capture various linguistic phenomena and have limited ability to make fine-grained judgments about the correct use of language.</p> <p>With that in mind, we designed RuCoLA as a benchmark for evaluating the linguistic competence of Russian language models. RuCoLA follows the general concept of linguistic acceptability: unlike grammatical correctness, which relates to the structure of language, acceptability denotes whether the utterance would be considered natural by a native speaker. Thus, a grammatical sentence can be unacceptable (e.g., “Colorless green ideas sleep furiously”), but an acceptable sentence has to be grammatical. Similarly to GLUE-style and probing benchmarks (e.g., GLUE, Russian SuperGLUE and RuSentEval), it can be used to compare the general language understanding capabilities of neural networks or to analyze and improve the fluency and consistency of text generation models.</p>
Benchmarks and scripts for ACQuA and RSAComb
<p>This dataset contains a selection of ontologies, data and queries (LUBM, UOBM and Reactome) used for testing the tools RSAComb [1] and ACQuA [2].</p> <p>In addition, we provide a collection of scripts to generate queries from ontology patterns. The output of these scripts run on the Oxford Ontology Repository [3] is attached, as well.</p> <p>[1] https://doi.org/10.5281/zenodo.5047810<br> [2] https://doi.org/10.5281/zenodo.6564387<br> [3] https://www.cs.ox.ac.uk/isg/ontologies/</p>
ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches
<p>Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding and requires careful hyperparameter tuning. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches optimized to generalize across different models and applied to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations.</p> <p>We release our dataset as a set of folders indicating the patch target label (e.g., `banana`), each containing 1000 subfolders as the ImageNet output classes.</p> <p>An example showing how to use the dataset is shown below.</p> <pre><code class="language-python"># code for testing robustness of a model import os.path from torchvision import datasets, transforms, models import torch.utils.data class ImageFolderWithEmptyDirs(datasets.ImageFolder): """ This is required for handling empty folders from the ImageFolder Class. """ def find_classes(self, directory): classes = sorted(entry.name for entry in os.scandir(directory) if entry.is_dir()) if not classes: raise FileNotFoundError(f"Couldn't find any class folder in {directory}.") class_to_idx = {cls_name: i for i, cls_name in enumerate(classes) if len(os.listdir(os.path.join(directory, cls_name))) > 0} return classes, class_to_idx # extract and unzip the dataset, then write top folder here dataset_folder = 'data/ImageNet-Patch' available_labels = { 487: 'cellular telephone', 513: 'cornet', 546: 'electric guitar', 585: 'hair spray', 804: 'soap dispenser', 806: 'sock', 878: 'typewriter keyboard', 923: 'plate', 954: 'banana', 968: 'cup' } # select folder with specific target target_label = 954 dataset_folder = os.path.join(dataset_folder, str(target_label)) normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) transforms = transforms.Compose([ transforms.ToTensor(), normalizer ]) dataset = ImageFolderWithEmptyDirs(dataset_folder, transform=transforms) model = models.resnet50(pretrained=True) loader = torch.utils.data.DataLoader(dataset, shuffle=True, batch_size=5) model.eval() batches = 10 correct, attack_success, total = 0, 0, 0 for batch_idx, (images, labels) in enumerate(loader): if batch_idx == batches: break pred = model(images).argmax(dim=1) correct += (pred == labels).sum() attack_success += sum(pred == target_label) total += pred.shape[0] accuracy = correct / total attack_sr = attack_success / total print("Robust Accuracy: ", accuracy) print("Attack Success: ", attack_sr) </code></pre> <p> </p>
Benchmark Datasets for: EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures
<p>This archive contains three benchmark datasets associated with the Equivariant Graph Refiner (EGR), two for protein complex structure refinement (PSR Test and Benchmark 2) and the other for protein complex structure assessment (M4S Test). The refinement datasets contain (1) a `pred` directory that contains decoy structure PDB files and (2) a `true` directory that contains native structure PDB files. The quality assessment dataset contains (1) `target_name` directories that each contain decoy structure PDB files for a given protein target and (2) a `label_info.csv` file listing each decoy structure's DockQ score and CAPRI class label.</p>
MELA Dataset: A Benchmark for Mediastinal Lesion Analysis (Training Set Part 1)
<p>MELA dataset is a benchmark for developing algorithms on mediastinal lesion analysis. We hope this large-scale dataset could facilitate the research and application of automatic mediastinal lesion detection and diagnosis. </p> <p>MELA dataset contains 1100 CT scans collected from patients with one or more lesions in the mediastinum. The MELA dataset is split into a subset of 770 CT scans for training, a subset of 110 CT scans for validation, and a test set of 220 CT scans for evaluation.</p> <p>Due to the size limit of zenodo.org, we split the MELA training set into 3 parts; this is the Training Set Part 1 of MELA dataset, including 260 CTs. Files include:</p> <ol> <li>Train1.zip: 130 CTs in NII format (nii.gz).</li> <li>Train2.zip: 130 CTs in NII format (nii.gz).</li> </ol>
MELA Dataset: A Benchmark for Mediastinal Lesion Analysis (Training Set Part 2)
<p>MELA dataset is a benchmark for developing algorithms on mediastinal lesion analysis. We hope this large-scale dataset could facilitate the research and application of automatic mediastinal lesion detection and diagnosis. </p> <p>MELA dataset contains 1100 CT scans collected from patients with one or more lesions in the mediastinum. The MELA dataset is split into a subset of 770 CT scans for training, a subset of 110 CT scans for validation, and a test set of 220 CT scans for evaluation.</p> <p>Due to the size limit of zenodo.org, we split the MELA training set into 3 parts; this is the Training Set Part 2 of MELA dataset, including 260 CTs. Files include:</p> <ol> <li>Train3.zip: 130 CTs in NII format (nii.gz).</li> <li>Train4.zip: 130 CTs in NII format (nii.gz).</li> </ol>
MELA Dataset: A Benchmark for Mediastinal Lesion Analysis (Training Set Part 3)
<p>MELA dataset is a benchmark for developing algorithms on mediastinal lesion analysis. We hope this large-scale dataset could facilitate the research and application of automatic mediastinal lesion detection and diagnosis. </p> <p>MELA dataset contains 1100 CT scans collected from patients with one or more lesions in the mediastinum. The MELA dataset is split into a subset of 770 CT scans for training, a subset of 110 CT scans for validation, and a test set of 220 CT scans for evaluation.</p> <p>Due to the size limit of zenodo.org, we split the MELA training set into 3 parts; this is the Training Set Part 3 of MELA dataset, including 250 CTs. Files include:</p> <ol> <li>Train5.zip: 130 CTs in NII format (nii.gz).</li> <li>Train6.zip: 120 CTs in NII format (nii.gz).</li> </ol>
Zagreb Calibration Benchmark Dataset
<p>Zagreb Calibration Benchmark Dataset is multi-modal high-resolution dataset geared at evaluating calibration solutions.</p>
A Multi-domain Benchmark for Personalized Search Evaluation
<p>We provide large-scale multi-domain benchmark datasets for Personalized Search.</p> <p>Further information can be found <a href="https://github.com/AmenRa/a-multi-domain-benchmark-for-personalized-search-evaluation">here</a>.</p>
Dataset for Surrogate Model Benchmarking for Dynamic Climate Impact Models
<p>The data represents time series of seasonal weather forecasts for rainfall and temperature. The dataset contains 10 forecasts of 6-month horizon from, two per year, from 2017 to 2021; start dates January 1 and July 1, respectively. Each forecast comprises 50 ensemble members. In total, this sums up to 91300 data points, each containing daily average rainfall, temperature.</p> <p>Each sample (row) comprises following features (columns):</p> <ul> <li><strong>datetime</strong>: Date of the forecast sample.</li> <li><strong>forecast</strong>: Identifier of the ensemble member, i.e. integer between 1 and total number of ensemblemembers.</li> <li><strong>precip</strong>: Averaged daily rainfall forecast in millimeters.</li> <li><strong>temp</strong>: Averaged daily temperature forecast in degree Celsius.</li> </ul> <p>Dataset created by The Weather Company, an IBM business. This service is based on data and products of the European Center for Medium-range Weather Forecasts (ECMWF-Archive and ECMWF-RT). Generated using Copernicus Climate Change Service information [2019 and ongoing]. ECMWF Archive data published under a Creative Commons Attribution 4.0 International (CC BY 4.0): https://creativecommons.org/licenses/by/4.0/<br> Disclaimer: Neither the European Commission nor ECMWF is responsible for any use that may be made of the information it contains.</p>
PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning
<p>PubMed Graph Benchmark (PGB) aggregates the metadata associated with the biomedical articles from PubMed into a unified source. The benchmark contains metadata including title, abstract, authors, in/out citations, MeSH terms, MeSH hierarchy, venue, publication type, and chemicals.</p>
Data Instances for: Who moves the locker? A benchmark study of alternative mobile parcel locker concepts
<p>|C|_h.txt</p> <p>|C|: number of customers<br> h: instance</p> <p>|C|;|P|;</p> <p>|C|: number of customers<br> |P|: number of parking spaces</p> <p>Customer (c;size;max_dist;min_time;L;x_1;y_1;...;x_L;y_L;s_1;e_1;...;s_L;e_L)</p> <p>c: customer index <br> size: parcel size<br> max_dist: maximum walking distance<br> min_time: minimum overlap time<br> L: number of whereabouts<br> (x_i,y_i): position of whereabouts i<br> [s_i,e_i]: time window of whereabouts i</p> <p>Parking space (p;x;y)<br> p: parking space index <br> (x,y): position</p>
TreeSatAI Benchmark Archive for Deep Learning in Forest Applications
<p><strong>Context and Aim</strong></p> <p>Deep learning in Earth Observation requires large image archives with highly reliable labels for model training and testing. However, a preferable quality standard for forest applications in Europe has not yet been determined. The <em>TreeSatAI </em>consortium investigated numerous sources for annotated datasets as an alternative to manually labeled training datasets.</p> <p>We found the federal forest inventory of Lower Saxony, Germany represents an unseen treasure of annotated samples for training data generation. The respective 20-cm Color-infrared (CIR) imagery, which is used for forestry management through visual interpretation, constitutes an excellent baseline for deep learning tasks such as image segmentation and classification.</p> <p> </p> <p><strong>Description</strong></p> <p>The data archive is highly suitable for benchmarking as it represents the <em>real-world</em> data situation of many German forest management services. One the one hand, it has a high number of samples which are supported by the high-resolution aerial imagery. On the other hand, this data archive presents challenges, including class label imbalances between the different forest stand types.</p> <p>The <em>TreeSatAI Benchmark Archive </em>contains:</p> <ul> <li> <p>50,381 image triplets (aerial, Sentinel-1, Sentinel-2)</p> </li> <li> <p>synchronized time steps and locations</p> </li> <li> <p>all original spectral bands/polarizations from the sensors</p> </li> <li> <p>20 species classes (single labels)</p> </li> <li> <p>12 age classes (single labels)</p> </li> <li> <p>15 genus classes (multi labels)</p> </li> <li> <p>60 m and 200 m patches</p> </li> <li> <p>fixed split for train (90%) and test (10%) data</p> </li> <li> <p>additional single labels such as English species name, genus, forest stand type, foliage type, land cover</p> </li> </ul> <p>The geoTIFF and GeoJSON files are readable in any GIS software, such as QGIS. For further information, we refer to the PDF document in the archive and publications in the reference section.</p> <p> </p> <p><strong>Version history</strong></p> <p>v1.0.2 - Minor bug fix multi label JSON file</p> <p>v1.0.1 - Minor bug fixes in multi label JSON file and description file</p> <p>v1.0.0 - First release</p> <p> </p> <p><strong>Citation</strong></p> <p>Ahlswede, S., Schulz, C., Gava, C., Helber, P., Bischke, B., Förster, M., Arias, F., Hees, J., Demir, B., and Kleinschmit, B.: <em>TreeSatAI Benchmark Archive</em>: a multi-sensor, multi-label dataset for tree species classification in remote sensing, Earth Syst. Sci. Data, 15, 681–695, <a href="https://doi.org/10.5194/essd-15-681-2023">https://doi.org/10.5194/essd-15-681-2023</a>, 2023.</p> <p> </p> <p><strong>GitHub</strong></p> <p>Full code examples and pre-trained models from the dataset article (Ahlswede et al. 2022) using the <em>TreeSatAI Benchmark Archive</em> are published on the GitLab and GitHub repositories of the Remote Sensing Image Analysis (RSiM) Group (<a href="https://git.tu-berlin.de/rsim/treesat_benchmark">https://git.tu-berlin.de/rsim/treesat_benchmark</a>) and the Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI) (<a href="https://github.com/DFKI/treesatai_benchmark">https://github.com/DFKI/treesatai_benchmark</a>). Code examples for the sampling strategy can be made available by Christian Schulz via email request.</p> <p> </p> <p><strong>Folder structure</strong></p> <p>We refer to the proposed folder structure in the PDF file.</p> <ul> <li> <p>Folder “aerial” contains the aerial imagery patches derived from summertime orthophotos of the years 2011 to 2020. Patches are available in 60 x 60 m (304 x 304 pixels). Band order is near-infrared, red, green, and blue. Spatial resolution is 20 cm.</p> </li> <li> <p>Folder “s1” contains the Sentinel-1 imagery patches derived from summertime mosaics of the years 2015 to 2020. Patches are available in 60 x 60 m (6 x 6 pixels) and 200 x 200 m (20 x 20 pixels). Band order is VV, VH, and VV/VH ratio. Spatial resolution is 10 m.</p> </li> <li> <p>Folder “s2” contains the Sentinel-2 imagery patches derived from summertime mosaics of the years 2015 to 2020. Patches are available in 60 x 60 m (6 x 6 pixels) and 200 x 200 m (20 x 20 pixels). Band order is B02, B03, B04, B08, B05, B06, B07, B8A, B11, B12, B01, and B09. Spatial resolution is 10 m.</p> </li> <li> <p>The folder “labels” contains a JSON string which was used for multi-labeling of the training patches. Code example of an image sample with respective proportions of 94% for Abies and 6% for Larix is: "Abies_alba_3_834_WEFL_NLF.tif": [["Abies", 0.93771], ["Larix", 0.06229]]</p> </li> <li> <p>The two files “test_filesnames.lst” and “train_filenames.lst” define the filenames used for train (90%) and test (10%) split. We refer to this fixed split for better reproducibility and comparability.</p> </li> <li> <p>The folder “geojson” contains geoJSON files with all the samples chosen for the derivation of training patch generation (point, 60 m bounding box, 200 m bounding box).</p> </li> </ul> <p>CAUTION: As we could not upload the aerial patches as a single zip file on Zenodo, you need to download the 20 single species files (aerial_60m_…zip) separately. Then, unzip them into a folder named “aerial” with a subfolder named “60m”. This structure is recommended for better reproducibility and comparability to the experimental results of Ahlswede et al. (2022), </p> <p> </p> <p><strong>Join the archive</strong></p> <p>Model training, benchmarking, algorithm development… many applications are possible! Feel free to add samples from other regions in Europe or even worldwide. Additional remote sensing data from Lidar, UAVs or aerial imagery from different time steps are very welcome. This helps the research community in development of better deep learning and machine learning models for forest applications. You might have questions or want to share code/results/publications using that archive? Feel free to contact the authors.</p> <p> </p> <p><strong>Project description</strong></p> <p>This work was part of the project <em>TreeSatAI </em>(Artificial Intelligence with Satellite data and Multi-Source Geodata for Monitoring of Trees at Infrastructures, Nature Conservation Sites and Forests). Its overall aim is the development of AI methods for the monitoring of forests and woody features on a local, regional and global scale. Based on freely available geodata from different sources (e.g., remote sensing, administration maps, and social media), prototypes will be developed for the deep learning-based extraction and classification of tree- and tree stand features. These prototypes deal with real cases from the monitoring of managed forests, nature conservation and infrastructures. The development of the resulting services by three enterprises (liveEO, Vision Impulse and LUP Potsdam) will be supported by three research institutes (German Research Center for Artificial Intelligence, TUB Remote Sensing Image Analysis Group, TUB Geoinformation in Environmental Planning Lab).</p> <p> </p> <p><strong>Project publications</strong></p> <p>Ahlswede, S., Schulz, C., Gava, C., Helber, P., Bischke, B., Förster, M., Arias, F., Hees, J., Demir, B., and Kleinschmit, B.: <em>TreeSatAI Benchmark Archive</em>: a multi-sensor, multi-label dataset for tree species classification in remote sensing, <em>Earth System Science Data</em>, 15, 681–695, <a href="https://doi.org/10.5194/essd-15-681-2023">https://doi.org/10.5194/essd-15-681-2023</a>, 2023.</p> <p>Schulz, C., Förster, M., Vulova, S. V., Rocha, A. D., and Kleinschmit, B.: Spectral-temporal traits in Sentinel-1 C-band SAR and Sentinel-2 multispectral remote sensing time series for 61 tree species in Central Europe. <em>Remote Sensing of Environment</em>, <em>307</em>, 114162, <a href="https://doi.org/10.1016/j.rse.2024.114162">https://doi.org/10.1016/j.rse.2024.114162</a>, 2024.</p> <p> </p> <p><strong>Conference contributions</strong></p> <p>Ahlswede, S. Madam, N.T., Schulz, C., Kleinschmit, B., and Demіr, B.: <em>Weakly Supervised Semantic Segmentation of Remote Sensing Images for Tree Species Classification Based on Explanation Methods</em>, IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, <a href="https://doi.org/10.48550/arXiv.2201.07495">https://doi.org/10.48550/arXiv.2201.07495</a>, 2022.</p> <p>Schulz, C., Förster, M., Vulova, S., Gränzig, T., and Kleinschmit, B.: <em>Exploring the temporal fingerprints of mid-European forest types from Sentinel-1 RVI and Sentinel-2 NDVI time series</em>, IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, <a href="https://doi.org/10.1109/IGARSS46834.2022.9884173">https://doi.org/10.1109/IGARSS46834.2022.9884173</a>, 2022.</p> <p>Schulz, C., Förster, M., Vulova, S., and Kleinschmit, B.: <em>The temporal fingerprints of common European forest types from SAR and optical remote sensing data</em>, AGU Fall Meeting, New Orleans, USA, 2021.</p> <p>Kleinschmit, B., Förster, M., Schulz, C., Arias, F., Demir, B., Ahlswede, S., Aksoy, A.K., Ha Minh, T., Hees, J., Gava, C., Helber, P., Bischke, B., Habelitz, P., Frick, A., Klinke, R., Gey, S., Seidel, D., Przywarra, S., Zondag, R., and Odermatt B.: <em>Artificial Intelligence with Satellite data and Multi-Source Geodata for Monitoring of Trees and Forests</em>, Living Planet Symposium, Bonn, Germany, 2022.</p> <p>Schulz, C., Förster, M., Vulova, S., Gränzig, T., and Kleinschmit, B.: <em>Exploring the temporal fingerprints of sixteen mid-European forest types from Sentinel-1 and Sentinel-2 time series</em>, ForestSAT, Berlin, Germany, 2022.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.