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.
285
datasets available to search
ShareScore release 0.9.0
Dataset results
285 results for “Machine learning dataset”
A robust synthetic data generation framework for machine learning in High-Resolution Transmission Electron Microscopy (HRTEM): Datasets
Open the record for dataset details and reuse information.
A dataset for establishing a machine learning-based QSAR model to screen beta-lactamase inhibitors using the FARM -BIOMOL chemical library
Open the record for dataset details and reuse information.
Dataset of "Machine Learning Uncovers Provenance of Source Rocks for Volcano-Sedimentary Lithium Mineralizations in South China"
Open the record for dataset details and reuse information.
Image dataset from Automatic analysis of Trypanosoma cruzi: A machine learning approach for the detection of blood trypomastigotes in low resolution images
<p>Image files of mice blood smear containing <em>T. cruzi</em> trypomastigotes. The images were used to train and test the classification model of the objects (nuclei and/or kinetoplasts) present in the images.</p>
PYTHIA6 Dataset: Machine learning-based jet and event classification at the Electron-Ion Collider with applications to hadron structure and spin physics
<p>Dataset corresponding to: https://inspirehep.net/literature/2164495</p> <p>The data set contains PYTHIA6 jets in ep collisions, with separate files for LO DIS and photoproduction samples. For further details about the data set, see https://inspirehep.net/literature/2164495. Examples of how to analyze the data set can be found at: https://github.com/jdmulligan/ml-eic-flavor.</p> <p>Please contact james.mulligan@berkeley.edu with any questions.</p>
Optimizing Performance and Energy Across Problem Sizes Through a Search Space Exploration and Machine Learning - dataset
<p>Dataset used for a journal submission at JPDC.</p>
Machine learning for predicting the average length of vertically aligned TiO2 nanotubes. Dataset Description
<p>Machine learning for predicting the average length of vertically aligned TiO2 nanotubes. Dataset Description. Dataset is found in two versions: MATLAB mat file and CSV format. Rows contains samples and Columns Features. Last Column represents the Response variable.</p>
Dataset "Machine learning for natural hazard mapping"
Open the record for dataset details and reuse information.
Machine Learning class final project datasets
<p>This is the zip file for the machine learning course final project. it has training and testing data sets.</p>
A Dataset for Applying Machine Learning and Eddy Covariance Approaches to Model Mangrove Carbon Production (ML-MCP)
<p>The Mangrove Carbon Production (ML-MCP) dataset (daily time scale) encompasses comprehensive measurements of carbon production in mangrove ecosystems from four EC tower station in the USA and China, derived using advanced machine learning models and eddy covariance techniques. This dataset includes various variables such as carbon fluxes, environmental factors. By integrating machine learning algorithms, the dataset enhances the accuracy of carbon productivity estimations, facilitating better understanding and management of mangrove ecosystems' role in carbon sequestration and climate regulation.</p>
A large synthetic dataset for machine learning applications in power transmission grids
<p>With the ongoing energy transition, power grids are evolving fast. They operate more and more often close to their technical limit, under more and more volatile conditions. Fast, essentially real-time computational approaches to evaluate their operational safety, stability and reliability are therefore highly desirable. Machine Learning methods have been advocated to solve this challenge, however they are heavy consumers of training and testing data, while historical operational data for real-world power grids are hard if not impossible to access. </p> <p>This dataset contains long time series for production, consumption, and line flows, amounting to 20 years of data with a time resolution of one hour, for several thousands of loads and several hundreds of generators of various types representing the ultra-high-voltage transmission grid of continental Europe. The synthetic time series have been statistically validated agains real-world data.</p> <h2>Data generation algorithm</h2> <p>The algorithm is described in a <a href="https://doi.org/10.1038/s41597-025-04479-x">Nature Scientific Data paper</a>. It relies on <a href="https://zenodo.org/records/2642175" target="_blank" rel="noopener">the PanTaGruEl model of the European transmission network</a> -- the admittance of its lines as well as the location, type and capacity of its power generators -- and aggregated data gathered from <a href="https://transparency.entsoe.eu/" target="_blank" rel="noopener">the ENTSO-E transparency platform</a>, such as power consumption aggregated at the national level.</p> <h2>Network</h2> <p>The network information is encoded in the file <a href="https://zenodo.org/records/13378476/files/europe_network.json">europe_network.json</a>. It is given in <a href="https://lanl-ansi.github.io/PowerModels.jl/stable/" target="_blank" rel="noopener">PowerModels format</a>, which it itself derived from <a href="https://matpower.org/" target="_blank" rel="noopener">MatPower</a> and compatible with <a href="https://www.pandapower.org/" target="_blank" rel="noopener">PandaPower</a>. The network features 7822 power lines and 553 transformers connecting 4097 buses, to which are attached 815 generators of various types.</p> <h2>Time series</h2> <p>The time series forming the core of this dataset are given in CSV format. Each CSV file is a table with 8736 rows, one for each hourly time step of a 364-day year. All years are truncated to exactly 52 weeks of 7 days, and start on a Monday (the load profiles are typically different during weekdays and weekends). The number of columns depends on the type of table: there are 4097 columns in load files, 815 for generators, and 8375 for lines (including transformers). Each column is described by a header corresponding to the element identifier in the network file. All values are given in per-unit, both in the model file and in the tables, i.e. they are multiples of a base unit taken to be 100 MW.</p> <p>There are 20 tables of each type, labeled with a reference year (2016 to 2020) and an index (1 to 4), zipped into archive files arranged by year. This amount to a total of 20 years of synthetic data. When using loads, generators, and lines profiles together, it is important to use the same label: for instance, the files <em>loads_2020_1.csv</em>, <em>gens_2020_1.csv</em>, and <em>lines_2020_1.csv</em> represent a same year of the dataset, whereas <em>gens_2020_2.csv</em> is unrelated (it actually shares some features, such as nuclear profiles, but it is based on a dispatch with distinct loads).</p> <h2>Usage</h2> <p>The time series can be used without a reference to the network file, simply using all or a selection of columns of the CSV files, depending on the needs. We show below how to select series from a particular country, or how to aggregate hourly time steps into days or weeks. These examples use Python and the data analyis library <em>pandas</em>, but other frameworks can be used as well (Matlab, Julia). Since all the yearly time series are periodic, it is always possible to define a coherent time window modulo the length of the series.</p> <h3>Selecting a particular country</h3> <p>This example illustrates how to select generation data for Switzerland in Python. This can be done without parsing the network file, but using instead <a href="https://zenodo.org/records/13378476/files/gens_by_country.csv">gens_by_country.csv</a>, which contains a list of all generators for any country in the network. We start by importing the <em>pandas</em> library, and read the column of the file corresponding to Switzerland (country code CH):</p> <pre><code>import pandas as pd CH_gens = pd.read_csv('gens_by_country.csv', usecols=['CH'], dtype=str)</code></pre> <p>The object created in this way is Dataframe with some null values (not all countries have the same number of generators). It can be turned into a list with:</p> <pre><code>CH_gens_list = CH_gens.dropna().squeeze().to_list()</code></pre> <p>Finally, we can import all the time series of Swiss generators from a given data table with</p> <pre><code>pd.read_csv('gens_2016_1.csv', usecols=CH_gens_list)</code></pre> <p>The same procedure can be applied to loads using the list contained in the file <a href="https://zenodo.org/records/13378476/files/loads_by_country.csv">loads_by_country.csv</a>.</p> <h3>Averaging over time</h3> <p>This second example shows how to change the time resolution of the series. Suppose that we are interested in all the loads from a given table, which are given by default with a one-hour resolution:</p> <pre><code>hourly_loads = pd.read_csv('loads_2018_3.csv')</code></pre> <p>To get a daily average of the loads, we can use: </p> <pre><code>daily_loads = hourly_loads.groupby([t // 24 for t in range(24 * 364)]).mean()</code></pre> <p>This results in series of length 364. To average further over entire weeks and get series of length 52, we use: </p> <pre><code>weekly_loads = hourly_loads.groupby([t // (24 * 7) for t in range(24 * 364)]).mean()</code></pre> <h2>Source code</h2> <p>The code used to generate the dataset is freely available at <a href="https://github.com/GeeeHesso/PowerData" target="_blank" rel="noopener">https://github.com/GeeeHesso/PowerData</a>. It consists in two packages and several documentation notebooks. The first package, written in Python, provides functions to handle the data and to generate synthetic series based on historical data. The second package, written in Julia, is used to perform the optimal power flow. The documentation in the form of Jupyter notebooks contains numerous examples on how to use both packages. The entire workflow used to create this dataset is also provided, starting from raw ENTSO-E data files and ending with the synthetic dataset given in the repository.</p> <h2>Funding</h2> <p>This work was supported by the <a href="https://www.cydcampus.admin.ch">Cyber-Defence Campus of armasuisse</a> and by an internal research grant of the Engineering and Architecture domain of <a href="https://www.hes-so.ch">HES-SO</a>.</p>
Supporting dataset for "27Al NMR chemical shifts in zeolite MFI via machine learning acceleration of structure sampling and shift prediction"
<p>This dataset includes includes training databases of CHA, MOR and MFI zeolites, trained kernel ridge regression (KRR) models, and the initial structures utilized in the study. A more detailed description of the dataset can be found in the README file.</p> <p>Note, all MD simulations were performed using SiAlOH1 ML potential from the work of Erlebach et al. (Erlebach et al., Nat Commun 15, 4215 (2024)), available at: https://doi.org/10.5281/zenodo.10361794.</p>
Curated Dataset of Association Constants Between a Cyclodextrin and a Guest for Machine Learning
<p>Determining the association constant between a cyclodextrin and a guest molecule is an important task for various applications in various industrial and academical fields. However, such a task is time consuming, tedious and requires samples of both molecules. A significant number of association constants and relevant data is available from the literature. The availability of data makes the use of machine learning techniques to predict association constants possible. However, such data is mainly available from tables in articles or appendices. It is necessary to make them available in a computer friendly format and to curate them. Furthermore, the raw data need to be enriched with physicochemical information about each molecule and when such information does not allow to discriminate molecules, some additional data is needed. We present a dataset built from data gathered from the literature.</p>
Dataset for machine learning guided prediction of the yield strength and hardness of multi-principal element alloys
<p>These data sets were used to develop machine-learning models to predict yield strength and hardness of multi-principal element alloys. We mainly collected the alloys and their mechanical properties from different published works. A list of references is provided at the end of each data set.</p>
Dataset for "Polarimetric retrieval of raindrop size distribution: double-moment normalization approach and machine learning techniques"
<p>This is the dataset for the publication [1]. This dataset contains:<br>1) Training dataset (train_data.pkl)<br>2) Independent validation dataset (test_data.pkl)</p> <p>This dataset was also used for the publication [2]. The training and validation datasets were merged in [2].</p> <p> </p> <p>References</p> <p>[1] Shin, K., Kim, K., Song, J. J., & Lee, G. (2024). Polarimetric Retrieval of Raindrop Size Distribution: Double‐Moment Normalization Approach and Machine Learning Techniques. <em>Geophysical Research Letters</em>, <em>51</em>(1), e2023GL106057. <a href="https://doi.org/10.1029/2023GL106057">https://doi.org/10.1029/2023GL106057</a></p> <p>[2] Tapiador, F. J., Shin, K., Leganés, L. J., Lim, K.-S., Juárez, G., Bang, W., et al. (2025). A Physically Consistent Particle Size Distribution Modelling of the Microphysics of Precipitation for Weather and Climate Models. <em>Submitted</em>.</p>
Dataset A of article "A machine learning approach for classifying Mediterranean obsidian of archaeometric interest by SEM investigation"
<p>Dataset A used for the manuscript titled "A machine learning approach for classifying Mediterranean obsidian of archaeometric interest by SEM investigation".</p><p>This dataset is a txt file, tab separated, encoded in UTF-8, with newline line terminator.</p><p>A compressed zip file is also provided, which, expanded, will create a directory containing 890 files. The files come in couples with the same name and two different extensions: spc (with SEM-EDS spectroscopy data) and tif (with SEM-BSE images). The SEM-EDS data refers to the same sample area shown in the SEM-BSE image going under the same name.</p>
Dataset fot the study of Documentation Practices of Machine Learning Resources
Open the record for dataset details and reuse information.
A Dataset and Machine Learning Approach to Classify and Augment Interface Elements of Household Appliances to Support People with Visual Impairment
<p>Here, we provide a dataset of images of interfaces from household appliances, where all interface elements are labled with one of five different types of interface elements. Further, we provide auxillary materials to use and extend the dataset.</p>
Machine learning-assisted classification of responders and non-responders to bortezomib treatment regimens PAD and VCD using new experimental dataset of 58 multiple myeloma RNA sequencing profiles
GEO Series GSE159426. Homo sapiens. 58 samples. Type: Expression profiling by high throughput sequencing.
The microglia cytotoxicity dataset of Manuscript ci-2023-017235, entitled "Prediction and interpretation microglia cytotoxicity by machine learning"
<p> The microglia cytotoxicity dataset of manuscript ci-2023-017235, entitled "Prediction and interpretation microglia cytotoxicity by machine learning", in Journal of Chemical Information and Modeling. Including all molecular SMILES and their cytotoxicity.</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.