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.
1,075
datasets available to search
ShareScore release 0.7.1
Dataset results
1,075 results for “ml”
Concentration of nanoparticles per mL for water samples collected from Venice Lagoon
<p>The concentration of nanoparticles from surface seawater collected from the three sites of Venice Lagoon, Venice-Lido Port Inlet, Grand Canal under Rialto Bridge, and Saint Marc basin was analyzed via the Nanoparticle Tracking Analysis technique. Five replications were tested for each sample. Sampling locations: Venice-Lido Port Inlet, GPS coordinates: latitude: 45.431508, longi-tude: 12.406952; Grand Canal under Rialto Bridge, GPS coordinates: latitude: 45.438350, longitude: 12.336311; and Saint Marc basin, GPS coordinates: latitude: 45.431962, longitude: 12.340953.</p>
ML-TOMCAT V2.0: Machine-Learning-Based Satellite-Corrected Global Stratospheric Ozone Profile Dataset
<p>MLTOMCAT V2 is 46 years (1979-2024) of gap free ozone profile data sets that is created by correcting biases in a TOMCAT Chemical Transport Model (CTM) simulated ozone profiles. We use Random Forest regression model to correct model biases. </p> <p>Each file contain monthly mean zonal mean ozone profiles. There are 6 data files.</p> <p><a href="https://zenodo.org/api/files/0416f9bd-c908-4d3f-9368-47ca2e04d7bd/MLTOMCAT_1979_2020_72_ht_vmr.nc">MLTOMCAT_1979_2024_72_ht_vmr_V2.nc</a> contains ozone profiles on geometric height levels (1 to 60 km) in mixing ratio units, whereas <a href="https://zenodo.org/api/files/0416f9bd-c908-4d3f-9368-47ca2e04d7bd/MLTOMCAT_1979_2020_72_ht_vmr.nc">MLTOMCAT_1979_2024_72_ht_nd_V2.nc</a> contains ozone profile in number density units.</p> <p>Similarly, </p> <p><a href="https://zenodo.org/api/files/0416f9bd-c908-4d3f-9368-47ca2e04d7bd/MLTOMCAT_1979_2020_72_ht_vmr.nc">MLTOMCAT_1979_2024_72_plev_vmr_V2.nc</a> contains ozone profiles on 43 MLS pressure levels (1000 to 0.1 hPa) in mixing ratio units, whereas <a href="https://zenodo.org/api/files/0416f9bd-c908-4d3f-9368-47ca2e04d7bd/MLTOMCAT_1979_2020_72_ht_vmr.nc">MLTOMCAT_1979_2024_72_plev_nd_V2.nc</a> contains ozone profile in number density units.</p> <p>Please note that data below 300 hPa (~8km) and 1 hPa (~50 km) should be used with caution.</p> <p>There are two straospheric column files</p> <p>ML-TOMCAT-SCO_120ppb_boundary_V2_197901-202412.nc and</p> <p>ML-TOMCAT-SCO_150ppb_boundary_V2_197901-202412.nc</p> <p>Stratospheric column files calculated using 120 ppb and 150 ppb as a chemical ozone boundaries.</p> <p>A manuscript describing MLTOMCAT would be published in EESD (Dhomse et al., 2021).</p>
CRISM ML dataset
<p>This dataset is required to train the models in the <a href="https://github.com/Banus/crism_ml" target="_blank" rel="noopener">CRISM ML toolbox</a> [1].</p> <p>In the project, we demonstrate the utility of machine learning in two essential CRISM analysis tasks: nonlinear noise removal and mineral classification. We train a hierarchical Bayesian model for estimating distributions of spectral patterns on pixel-scale training data collected from dozens of well-characterized CRISM images. </p> <p>The following files are included:</p> <ul> <li><em>CRISM_bland_unratioed.mat</em>: unratioed training spectra for bland pixels.</li> <li><em>CRISM_labeled_pixels_ratioed.mat</em>: ratioed training spectra for mineral classes.</li> <li><em>CRISM_labeled_pixel_patterns.pdf</em>: visualization of the training segmentation maps and average spectra.</li> </ul> <p>The training spectra are in Matlab v7.3 (and newer) format. To load them in Python, use the <a href="https://pypi.org/project/mat73/">mat73</a> library, because <em>scipy </em>doesn't support the format.</p> <p>The <strong>bland unratioed spectra</strong> have the following variables:</p> <table> <tbody> <tr> <th>Name</th> <th>Size</th> <th>Description</th> </tr> </tbody> <tbody> <tr> <td><em>pixspec</em></td> <td>337 617 × 350</td> <td>Unratioed spectra</td> </tr> <tr> <td><em>im_names</em></td> <td>340</td> <td>List of CRISM image names, mapping them to numerical IDs</td> </tr> <tr> <td><em>pixims</em></td> <td>337 617</td> <td>Numerical ID of the image the spectrum is from</td> </tr> <tr> <td><em>pixcrds</em></td> <td>337 617 × 2</td> <td>(x,y) coordinates of the points in the original image</td> </tr> </tbody> </table> <p> </p> <p>The <strong>labeled ratioed pixels</strong> have the following variables:</p> <table> <tbody> <tr> <td><strong>Name</strong></td> <td><strong>Size</strong></td> <td><strong>Description</strong></td> </tr> <tr> <td><em>pixspec</em></td> <td>592 413 × 350</td> <td>Ratioed spectra</td> </tr> <tr> <td><em>pixlabs</em></td> <td>592 413</td> <td>Mineral labels</td> </tr> <tr> <td><em>im_names</em></td> <td>77</td> <td>List of CRISM image names, mapping them to numerical IDs</td> </tr> <tr> <td><em>pixims</em></td> <td>592 413</td> <td>Numerical ID of the image the spectrum is from</td> </tr> <tr> <td><em>pixpat</em></td> <td>592 413</td> <td>ID of the connected patch in the image the pixel belongs to</td> </tr> <tr> <td><em>pixcrds</em></td> <td>592 413 × 2</td> <td>(x,y) coordinates of pixels in their respective image</td> </tr> </tbody> </table> <p> </p> <p><strong>Citation </strong>(cite this paper when using the data)<strong>:</strong></p> <ol> <li>Plebani, E., Ehlmann, B. L., Leask, E. K., Fox, V. K., & Dundar, M. M. (2022). A machine learning toolkit for CRISM image analysis. <em>Icarus</em>, <em>376</em>, 114849.</li> </ol>
UDP Synthetic Dataset for training ML time series models
<p>The dataset available has been produced by the "Next-Generation IoT solutions for the universal supply chain" (iNGENIOUS) project’s consortium under EC grant agreement 957216, made publicly available as part of the Horizon 2020 Open Research Data Pilot (<a href="https://www.openaire.eu/what-is-the-open-research-data-pilot">ORD pilot</a>).<br> The European Commission is not liable for any use that may be made of the information contained herein.</p> <p>The available dataset is in csv format and contains synthetic data of UDP packets received and sent by a single User Plane Function (UPF) covering a span of 6 weeks. The format of the datafile is:</p> <ul> <li>index</li> <li>timestamp </li> <li>UDP packets_rcvd - Total number of UDP packets received</li> <li>UDP packets sent - Total number of UDP packets sent</li> </ul> <p>The simulation was performed based on behavior of UPF and 5GC Network functions inferred from stress tests performed in the iNGENIOUS project's Automated Robots with Heterogeneous Networks Use Case, as well as patterns in urban mobility taken from available UE datasets [NCS+19].</p> <p>More information on the iNGENIOUS project can be found on the project’s website: <a href="https://ingenious-iot.eu/">https://ingenious-iot.eu/</a></p> <p>[NCS+19] Noussan M, Carioni G, Sanvito FD, Colombo E. Urban Mobility Demand Profiles:<br> Time Series for Cars and Bike-Sharing Use as a Resource for Transport and Energy<br> Modeling. Data. 2019; 4(3):108. https://doi.org/10.3390/data4030108</p>
Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches (Replication Package Part 3: OpenSSL dataset)
<h1><strong>The Replication Package of</strong></h1> <h1><strong>"Today's cat is tomorrow's dog: accounting for time-based changes in the labels of ML vulnerability detection approaches"</strong></h1> <h3><strong>Part 3 (OPENSSL Dataset)</strong></h3> <div> <div>This repository includes:</div> <ol> <li><em><strong>Code.zip</strong></em> that contains the codes to replicate some parts of this study:<br>a. <em>1_generate_datasets</em> implements our methodology to generate the datasets.<br>b. <em>2_run_models</em> runs the ML models during the evaluation.<br>c. <em>3_result_replication </em>generates charts presented in the paper from the ML evaluation results.</li> <li><em><strong>Datasets.zip</strong></em> that contain 2 folders:<br>a. <em>original</em> datasets: 1 from <a href="https://github.com/CGCL-codes/VulDeePecker" target="_blank" rel="noopener">NVD Vuldeepecker</a> and 3 extracted from <a href="https://github.com/ZeoVan/MSR_20_Code_vulnerability_CSV_Dataset" target="_blank" rel="noopener">BigVul</a>.<br> <div> <div>b. <em>OPENSSL</em> datasets: train, validation, test sets for each time of observation extracted using our methodology from <a href="https://github.com/ZeoVan/MSR_20_Code_vulnerability_CSV_Dataset" target="_blank" rel="noopener">BigVul</a> dataset for project <em>openssl</em>.</div> </div> </li> <li><em><strong>Pretrained-models.zip</strong></em> that we generated during our evaluation (3 test results for each time point in the timeline [2013-2019]).</li> <li><em><strong>Results.zip</strong></em> of our evaluation, the folder <em>ALL</em> contains the overall results and other folders are results by model.</li> </ol> <p><strong>UPDATED version 5<br></strong>- added a GLOBAL_README.md which contains the 3 stages and how they are connected to each other<br>- updated LineVul.ipynb: import AdamW from torch.optim instead of transformers<br>- updated README.md in Code2Vec with the prerequisites of Java to run gradlew for astmine</p> <p><strong>UPDATED version 6<br></strong>- updated CodeBert.ipynb: import AdamW from torch.optim instead of transformers</p> <p>Documentations</p> <ol> <li><em><strong>INSTALL.pdf </strong></em>: how to install the codes</li> <li><em><strong>README.pdf</strong></em>: readme file</li> <li><em><strong>REQUIREMENTS.pdf</strong></em>: hardware and software requirements</li> <li><em><strong>STATUS.pdf</strong></em> : status for artifact submission</li> <li><em><strong>LICENSE.pdf</strong></em>: the license of this artifact</li> <li><em><strong>PAPER.pdf</strong></em>: the camera-ready version of the paper</li> </ol> </div> <div> <div>Please refer to the following repositories for the other datasets and pre-trained models:</div> <div>- Part 1 NVD Vuldeeepecker : <a href="https://doi.org/10.5281/zenodo.8207883" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.8207883</a></div> - Part 2 LINUX : <a href="https://doi.org/10.5281/zenodo.10960662" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.10960662</a><br> <div>- Part 4 POPPLER : <a href="https://doi.org/10.5281/zenodo.14713143">https://doi.org/10.5281/zenodo.14713143</a></div> <div> </div> <div>This work was partly funded by the EU under the H2020 Program AssureMOSS (Grant n. 952647) and the Horizon Europe Program Sec4AI4Sec (Grant n. 101120393), by the Italian Ministry of University and Research (MUR) under the P.N.R.R. – NextGenerationEU grant n.\ PE00000014 (SERICS subproject COVERT), and by the Dutch Research Council (NWO) under the grant NWA.1215.18.006 (Theseus) and grant KIC1.VE01.20.004 (HEWSTI). </div> </div>
Board Leadership Database (U.S. Public Firms) + ML Script for Scaling Human Coded Data
<p>Files include: (1) an open sourced database of CEO duality and board chair orientations developed by scaling human coded data using supervised machine learning techniques (in both .dta and .csv formats), as well as (2) the accompanying training and scoring scripts to scale human coded data.</p> <p>Users may apply the scoring script to score the same variables from company proxy statements, or may adapt the training/scoring scripts and retrain models to scale human coded data of other constructs or measures. </p> <p>We note that early steps in the process to develop our database and script required web-scraping of company filings from SEC Edgar and text extraction from collected filings. We relied on other publicly available scripts to develop our own fetcher and extraction scripts. Users seeking to duplicate those parts of the process may benefit from the following resources from Kai Chen and pipy.org: </p> <p>For resources from Kai Chen: see <a href="https://urldefense.com/v3/__https:/www.kaichen.work/?p=681__;!!K6Z8K8YTIA!BizP9-ZnzgV0Pq7ck-UENJ1EBDrFkAkNoCaO34Ad1ezxH_okstsfxniagvxXdWudkDP44fPACbY9vaIG5A$">https://www.kaichen.work/?p=681</a> and <a href="https://urldefense.com/v3/__https:/www.kaichen.work/?p=946__;!!K6Z8K8YTIA!BizP9-ZnzgV0Pq7ck-UENJ1EBDrFkAkNoCaO34Ad1ezxH_okstsfxniagvxXdWudkDP44fPACbZhp5N_Tw$">https://www.kaichen.work/?p=946</a></p> <p>For resources from pipy.org, see <a href="https://urldefense.com/v3/__https:/pypi.org/project/sec-edgar-downloader/__;!!K6Z8K8YTIA!BizP9-ZnzgV0Pq7ck-UENJ1EBDrFkAkNoCaO34Ad1ezxH_okstsfxniagvxXdWudkDP44fPACbYxYSZGGw$">sec-edgar-downloader</a> and <a href="https://urldefense.com/v3/__https:/pypi.org/project/sec-api/__;!!K6Z8K8YTIA!BizP9-ZnzgV0Pq7ck-UENJ1EBDrFkAkNoCaO34Ad1ezxH_okstsfxniagvxXdWudkDP44fPACbZ_FwY6jw$">sec-api</a></p> <p> </p>
ML-Enabled Systems Model Deployment and Monitoring: Status Quo and Problems
<p>Contained within this directory is the latest dataset utilized in the research titled 'ML-Enabled Systems Model Deployment and Monitoring: Status Quo and Problems'. We are providing a downloadable ZIP file that includes the survey questionnaire, the amassed data, and the Jupyter Notebooks utilized for our analytical process.</p>
Datasets for benchmarking and ML modelling
<p><em><span>hydrogen-harm</span></em><span> data set of crystalline hydrogen configurations: energies at VMC and LRDMS level; purpose: benchmark for MLP; developed in the group of Michele Casula (CNRS) </span></p> <p><span><em>prot-hex</em> data set for protonated water hexamer: trajectories from classical molecular dynamics with nuclear forces at VMC level of theory; purpose: ML modelling; developed in the group of Michele Casula (CNRS)</span></p> <p><span><em>intexcit</em> data sets for a set of organic molecular complexes in lowest excited states: dispersion interaction energies, interaction energies, components of SAPT interaction energies at the CAS wavefunction level; purpose: benchmarking <em>ab initio</em> methods and density functional dispersion correction modelling; developed by Kasia Pernal (TUL) and Michal Hapka (University of Warsaw) </span></p>
EUV-ML solar physics dataset from STEREO + SOHO, 2 solar cycles
<p>A unified ML-ready dataset of all SOHO EIT and STEREO EUVI EUV images, aligned and set to 512x512 pixels, are available via the NASA TOPS ODR in HelioCloud at s3://gov-nasa-hdrl-data1/contrib/euvml/ (inside of AWS, and with free egress via https). We also provide the software used to create it via a public github repository, and a sample Python Jupyter Notebook (in this Zenodo link, and in the HelioCloud sample tutorials) for accessing them via the 'cloudcatalog' Python client.We</p> <p>We created a full set of ML-ready EUV data from 1995 to present, accessible via the cloud, by bringing in historical restoration of the STEREO/SOHO era into a machine-learning (ML) -ready dataset. This work will enable research on events, evolution of solar irradiance, segmentation approaches, 360 degree maps of the sun, and other research topics as well as for use with space weather. The reduced dataset is 6TB in size. The data will be freely available to scientists both within the AWS cloud and for downloading for local use on their laptops. The creation of this dataset had several steps, starting with the mechnical ingest stage (get the raw data), an analysis of best approach to create the ML-ready set, bulk processing, uploading the cloud, and dissemination and promotion. The task also required determination best approaches for cadence matching, interpolation, and effective spans of contiguous data for ML applications.</p> <p>Work was funded under NASA Heliophysics 21-LWSTM21_2-0018, award number 80NSSC22K0643.</p>
TOPAZ4-ML Sea Ice Thickness (1992-2022)
<p> </p> <p>Subject: Natural sciences, Field: Earth Science, Subfield: Oceanography</p> <p>Key words: sea ice, thickness, Arctic, TOPAZ, machine learning, data assimilation</p> <p> </p> <p>The scientific manuscript associated to the dataset is:</p> <p>https://doi.org/10.5194/tc-19-731-2025</p> <p> </p> <p>The dataset can be visualized as an animation using the following link:</p> <p><a href="https://av.tib.eu/media/68161" target="_blank" rel="noopener">https://av.tib.eu/media/68161 (https://doi.org/10.5446/68161)</a></p> <p>or:</p> <p>https://www.youtube.com/watch?v=UPPcJXfNMbY (faster)</p>
Alignments and ML trees of cassava brown streak virus and Ugandana cassava brown streak virus polyprotein nucleotide sequences
<p>Alignments of full and nearly full polyprotein-length nucleotide sequences from GenBank for the two ipomoviruses that cause cassava brown streak disease, in fasta format. Separate alignments for 67 cassava brown streak virus sequences and 81 Ugandan cassava brown streak virus sequences are provided, as well as a combined alignment of 148 sequences. Alignments were created with MUSCLE and then modified by eye in AliView.</p> <p>Also, two tree files (in nexus) format are supplied, resulting from a maximum likelihood analysis with IQTree on each of the two single-species datasets. Support for nodes with aLRT and 100 actual bootstrap replicates are provided (aLRT/bootstrap).</p>
CLGAN: Guizhou ML-AWS precipitation dataset
<p>This repository provides the preprocessed datasets and source codes, which are used in the study 'CLGAN: A GAN-based video prediction model for precipitation nowcasting' by Ji et al. (2022). This allows the user to reproduce the presented results for the precipitation nowcasting task.<br> <br> To build the dataset, minute-level precipitation measurements by rain gauges of Automatic Weather Stations over Guizhou, China is collected and preprocessed. The raw AWS data comprise measurements from 93 national basic stations and 1740 automatic weather stations across Guizhou at a high observation frequency (every minute). The raw data spans from 1st Jan 2015 and 31st Dec 2019 and is provided by the Guizhou Meteorological Bureau. A series of preprocessing are performed to obtain the proposed dataset, including bilinear interpolation, rainy sequence selection, log transformation and normalization. The details of preprocessing can be found in the paper mentioned above.<br> <br> This folder holds five single netCDF-files which respectively record the data from 2015 to 2019. Each netCDF-file contains preprocessed precipitation sequences with a shape of [n_sequence, len_sequence, n_lat, n_lon]. n_sequence is the number of the recorded sequences, len_sequence is the length of each sequence, n_lat and n_lon are the number of grid points in the meridian and zonal directions. In our case, the target domain covers from 24.625°N to 29.50°N and 103.625°E to 109.50°E (40x48 grid points) with a resolution of 0.125° and the length of each sequence is 24.<br> </p>
A map of global peatland extent created using machine learning (Peat-ML)
<p>Map of global peatland extent estimated by machine learning. The download includes both a netcdf file version and a GeoTIFF (as a zip archive)</p> <p>Abstract from associated paper:</p> <p>Peatlands store large amounts of soil carbon and freshwater, constituting an important component of the global carbon and<br> hydrologic cycles. Accurate information on the global extent and distribution of peatlands is presently lacking but is needed<br> by Earth System Models (ESMs) to simulate the effects of climate change on the global carbon and hydrologic balance. Here,<br> we present Peat-ML, a spatially continuous global map of peatland fractional coverage generated using machine learning<br> techniques suitable for use as a prescribed geophysical field in an ESM. Inputs to our statistical model follow drivers of<br> peatland formation and include spatially distributed climate, geomorphological and soil data, along with remotely-sensed<br> vegetation indices. Available maps of peatland fractional coverage for 14 relatively extensive regions were used along with<br> mapped ecoregions of non-peatland areas to train the statistical model. In addition to qualititative comparisons to other maps<br> in the literature, we estimated model error in two ways. The first estimate used the training data in a blocked leave-one-out<br> cross-validation strategy designed to minimize the influence of spatial autocorrelation. That approach yielded an average r<sup>2</sup><br> of 0.73 with a root mean squared error and mean bias error of 9.11% and -0.36%, respectively. Our second error estimate<br> was generated by comparing Peat-ML against a high-quality, extensively ground-truthed map generated by Ducks Unlimited<br> Canada for the Canadian Boreal Plains region. This comparison suggests our map to be of comparable quality to mapping<br> products generated through more traditional approaches, at least for boreal peatlands.</p>
Dataset and structure database for an ML model to predict diffusivity in ZIF variants
<p>This dataset accompanies the publication titled "Data Mining for Predicting Gas Diffusivity in Zeolitic-imidazolate Frameworks (ZIFs)" (DOI: <a href="https://doi.org/10.1039/D2TA02624D">https://doi.org/10.1039/D2TA02624D</a>)</p> <p><a href="https://zenodo.org/api/files/b80f6d07-3bf4-484c-97ac-5d579fb0cc27/ESI_2_dataset.xlsx?versionId=dc4525d0-1c5c-478c-9bef-a156587ad69b">ESI_2_dataset.xlsx</a>: Descriptors for all ZIFs of the publication and simulations output, in the form of diffusivities of gas molecules (He up to iso-butane), in all ZIFs.</p> <p>ZIF_database.zip: ZIP file containing all ZIFs prepared by the authors (as discussed in the publication), through various units replacements, in the SOD topology, in .pdb format.</p>
Sample of high-resolution climate dataset based on ML downscaling.
<p>The ClimateByte project created a high-resolution (downscaled) climate dataset for specific regions based on the CINECA MISTRAL observational dataset. AMIGO selected one region from the larger dataset and made that portion openly available to the other members of the EUH4D project for research and non-commercial purposes. Resolution of this dataset is 300m and covers the Adige Valley of Trentino Alto-Adige (Italy)</p>
LuoZiya/ML_in_regulatome_of_HB_TFs: ML_in_regulatome_of_HB_TFs
<p>The machine learning code, input and output files, and results for the regulatome of SAM-related TFs.</p>
On the Co-evolution of ML Pipelines and Source Code - Empirical Study of DVC Projects
<p>This is a replication package of our paper submission to the Saner 2021 entitled:</p> <p>On the Co-evolution of ML Pipelines and Source Code - Empirical Study of DVC Projects</p>
Designing With: AI, ML and DV - Interactive Framework Tools Dataset
<p>This dataset presents a compilation of 182 AI tools, specifically designed for incorporation into design education. The collection was meticulously assembled through a process of rigorous mining of existing internet repositories and academic literature, resulting in a diverse array of AI tools that are applicable to a multitude of design methodologies.</p>
Identifying Easy Instances to Improve Efficiency of ML Pipelines for Algorithm-Selection - Code and Data
<p>This repository contains the code and data for reproducibility of the paper 'Identifying Easy Instances to Improve Efficiency of ML Pipelines for Algorithm-Selection'. </p> <p>The following files are included:</p> <ul> <li>best_algo.csv : labels for the classification and median performance of algorithms;</li> <li>ML_models.ipyb : jupyter notebook with the definition of the neural networks for both classifiers;</li> <li>pickle.zip : pickled models for the hardness classification and the algorithm selector;</li> <li>trajectories.zip : raw data files containing parts of the trajectories of each algorithm;</li> <li>Results.zip : results obtained using the approach on the stream of instances.</li> </ul>
SOCAT+USV sampling masks for ML reconstruction of surface ocean pCO2 using the Large Ensemble Testbed
<p>Here we provide sampling masks used in the study "Assessing improvements in global ocean pCO2 machine learning reconstructions with Southern Ocean autonomous sampling" (Heimdal et al., 2023, https://doi.org/10.5194/bg-2023-160). In this paper, we reconstruct surface ocean pCO2 using the Large Ensemble Testbed (Gloege et al., 2021, https://doi.org/10.1029/2020GB006788) and the pCO2-Residual method (Bennington et al., 2022, https://doi.org/10.1029/2021MS002960). We provide 11 different sampling masks that correspond to the experiments presented in Heimdal et al. (2023), which include different sampling patterns of USV Saildrones in the Southern Ocean (SOCAT+USV sampling).</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.