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.
356
datasets available to search
ShareScore release 0.9.0
Dataset results
356 results for “Machine learning models”
Machine learning models predict calculation outcomes with the transferability necessary for computational catalysis
<p>data files, including ML models of dynamic classifiers, trajectories of electronic structure and geometric features, optimized geometries, and final csv files.</p>
Data for "Machine Learning Parameterization of Subgrid-Scale Orographic Gravity Wave Drag in a Middle-Atmosphere General Circulation Model" by Lu et al., submitted to JAMES, 2022.
<p>The NetCDF data file involving the decision tree strucutre attributes of the random forest emulator.</p> <p>gcm_regressors/<br> The data file involving the decision tree strucutre attributes (in NetCDF format)</p>
SynPhoRest - Synthetic Photorealistic Forest Dataset with Depth Information for Machine Learning Model Training
<p><strong>SynPhoRest </strong>is a synthetic dataset collected on virtual forests. It features RGB images, semantic segmentation maps, depth maps and the projection of LIDAR point clouds on the RGB FOV for two different LIDAR scanning patterns. The dataset has a total of 3154 frames.<br> <br> A description of the available data follows:</p> <p><strong>RGB images</strong></p> <ul> <li>Resolution: 848 x 480 pixels.</li> <li>PNG files with 8 bits encoding per channel.</li> </ul> <p><strong>Segmentation Maps</strong></p> <ul> <li>Resolution: 848 x 480 pixels.</li> <li>PNG files with a single 8 bit channel.</li> <li>Classes are encoded as follows:</li> <li> <table> <thead> <tr> <th scope="col"><strong>Value</strong></th> <th scope="col"><strong>Class</strong></th> </tr> </thead> <tbody> <tr> <td>0</td> <td>Background</td> </tr> <tr> <td>1</td> <td>Soil</td> </tr> <tr> <td>2</td> <td>Traversable</td> </tr> <tr> <td>3</td> <td>Canopy</td> </tr> <tr> <td>4</td> <td>Fuel</td> </tr> <tr> <td>5</td> <td>Trunks</td> </tr> </tbody> </table> <p>Fuel represents flammable material such as shrubbery and grass.</p> </li> </ul> <p><strong>Depth Maps</strong></p> <ul> <li>Resolution: 848 x 480 pixels.</li> <li>PNG files with a single 16 bit channel</li> <li>The depth value is encoded in the unsigned integer format.</li> <li>Infinite depth is represented by the value 65535.</li> <li>To obtain the depth values in meters, the original values must by divided by 256.</li> <li>The FOV of the virtual depth camera was the same as the FOV of the RGB camera.</li> </ul> <p><strong>LIDAR Point Cloud Projections on the RGB Camera FOV</strong></p> <ul> <li>Resolution: 848 x 480 pixels.</li> <li>PNG files with a single 16 bit channel.</li> <li>The distance values are encoded in the unsigned integer format.</li> <li>To obtain the distance values in meters the original values must by divided by 256.</li> <li>On average, the projection images have a point density of 5.5%. In practice, this means that 5.5% of the pixels in the projection image have distance information.</li> <li>Two LIDAR Point Cloud Projections were made available. One for a LIDAR with a repeating line pattern and other resembling the commercially available Livox Horizon LIDAR scanner.</li> </ul>
Research data for "A machine-learned interatomic potential for silica and its relation to empirical models"
<p>This dataset supports the paper "A machine-learned interatomic potential for silica and its relation to empirical models". The paper is online here:</p> <p>The following files are provided:</p> <ul> <li>xyz-file containing all structures in the training database including forces and energies</li> <li>GAP file containing the corresponding parameters, which can be used for example for Lammps MD simulations</li> <li>Amorphous structure files for silica created by different interatomic potentials.</li> </ul>
Uncertainty quantification in cerebral circulation simulations focusing on the collateral flow: Surrogate model approach with machine learning
<p>Data and code underlying the findings reported in the paper titled "Uncertainty quantification in cerebral circulation simulations focusing on the collateral flow: Surrogate model approach with machine learning."</p>
On the application of an observations-based machine learning parameterization of surface layer fluxes within an atmospheric large-eddy simulation model: Article Data
<p>NetCDF datatset of presented results from the publication titled "On the application of an observations-based machine learning parameterization of surface layer fluxes within an atmospheric large-eddy simulation model" in the Journal of Geophysical Research - Atmospheres, Paper #2021JD036214R.</p>
Climate data for Machine Learning based 100-year flood flow prediction model
<p>This study evaluates the application of ML technique over northeast United States regions and compares its performance to the U.S. Geological Survey (USGS) Streamflow Statistics (StreamStats)</p>
Blinded Predictions and Post-hoc Analysis of the Second Solubility Challenge Data: Exploring Training Data and Feature Set Selection for Machine and Deep Learning Models
<p>Training and test datasets and scripts for training models.</p>
Dataset and results for "Comparing machine learning and deep learning models for probabilistic post-processing of satellite precipitation-driven streamflow simulation"
<p>Dataset and results for "Comparing machine learning and deep learning models for probabilistic post-processing of satellite precipitation-driven streamflow simulation"</p> <p>Yuhang Zhang1, Aizhong Ye1*, Phu Nguyen2, Bita Analui2, Soroosh Sorooshian2, Kuolin Hsu2</p> <p>1 State Key Laboratory of Earth Surface Processes and Resource Ecology, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China.</p> <p>2 Center for Hydrometeorology and Remote Sensing, Department of Civil and Environmental Engineering, University of California, Irvine, Irvine, California, CA 92697, USA.</p> <p>## Dataset </p> <p>Streamflow simulations from one observed precipitation (CMA) and three satellite precipitation products (PDIR, IMERG-F, and GSMaP) for 522 sub-basins.</p> <p>- Q-CMA (streamflow reference)<br> - Q-PDIR (uncorrected)<br> - Q-IMERGF (uncorrected)<br> - Q-GSMAP (uncorrected)</p> <p>### Data structure</p> <p>- Head section (row1-row5)<br> - SubNO: 522 <br> - BeginT: 2003-01-01 00:00 <br> - EndT: 2019-12-31 00:00 <br> - Interval: 1440s (daily)<br> - Revise: 10 (scaling factor to keep int datatype)<br> - Point1 Point2 ... (Subbasin No.)<br> - Data section<br> - 6209 rows, 522 cols</p> <p>## Results</p> <p>Two post-processing model results for test period (2015-1-1 to 2018-12-31).</p> <p>### Data structure</p> <p>- 1462 rows, every row denotes each day from 2015-1-1 to 2018-12-31</p> <p>- 100 columns, every column denotes each quantile from 0.005 to 0.995, total 100 quantiles.</p> <p>### qrf-output</p> <p>- pdir (single input)<br> - imergf (single input)<br> - gsmap (single input)<br> - all (multiple inputs)</p> <p>### lstm-output</p> <p>- pdir (single input)<br> - imergf (single input)<br> - gsmap (single input)<br> - all (multiple inputs)</p> <p> </p>
The developmental and evolutionary characteristics of transcription factor binding site clustered regions based on an explainable machine learning model
<p>## Identification of transcription factor binding sites clustered regions</p> <p>First, the TFBSs were identified from ATAC-seq peaks by FIMO. The position-specific weight matrices (PWMs) of transcription factors were downloaded from CIS-BP databases. The genomic sequences under the open chromatin regions were used as inputs for FIMO with a custom library of all motifs for each species to scan for motif instances at a p-value threshold of 1e-5. </p> <p>Then, an established method was used to identify TFCRs by performing the Gaussian kernel density estimations across the genome (with a bandwidth of 300bp centered on each TFBS). Each peak in density profile was considered a TFCR. To determine the complexity of each TFCR, the Gaussian kernelized distances from each peak that contributed at least 0.1 to its strength were determined. The complexity of each TFCR was determined by the quantity and proximity of the contributing TFBS. We combined motif instances based on the TF family information from CIS-BP to calculate the complexity of TFCR. The window for each TFCR was determined by finding the maximum distance (in bp) from the TFCR to a contributing TF and then adding 150 bp (one-half of the bandwidth). Each window was centered on the TFCR. The identified TFCR was grouped into 10 groups based on their complexity from low to high. </p> <p>usage: <br>indir="Human_fimo" # the directory where you put the output files of FIMO <br>motifMap="Homo_sapiens_2020_0920/TF_Information_all_motifs_plus.txt" # the mapping relationship of TF and its TF family from CIS-BP <br>cd Codes/TFCR_embryo <br>perl d-motif_combine.pl $indir TFfamily $motifMap <br>perl e-tfpos_combine.pl TFfamily <br>perl f1-tf_bed-new-c.pl TFfamily <br>perl 0-merge-TFCR.pl $indir TFfamily </p>
Training data for building a machine learning wildfire model over the CONUS
Open the record for dataset details and reuse information.
Data for Modeling Snow on Sea Ice using Physics Guided Machine Learning
Open the record for dataset details and reuse information.
Machine Learning Models for cfMeDIP data from Shen et al.
<p>Contains raw markdowns and knit markdown with plots for machine learning analyses in Shen et al, "<strong>Highly sensitive tumor detection and classification using methylome analysis of plasma cell-free DNA".</strong></p>
Distillation of crop models to learn plant physiology theories using machine learning
<p>Full Paper available for download at LINK</p>
Data and machine-learning model for fcc-FeHx at the CMB conditions
<p>Data including melting temperatures and sound velocities. The machine-learning model was trained by DeePMD-kit. The initial configuration for two-phase coexistence simulations is provided.</p>
First global machine learning model to predict solar flare impact on Earth's ionosphere
Open the record for dataset details and reuse information.
A multi-species benchmark for training and validating large scale mass spectrometry proteomics machine learning models
<p>This is a de novo sequencing benchmark dataset derived from nine<br>publicly available mass spectrometry datasets. There are two versions<br>of the benchmark: main and balanced. The balanced version randomly<br>eliminates some spectra associated with some species in order to<br>create a smaller, more evenly balanced dataset. Also provided are two<br>zip files containing the raw data as well as intermediate results.<br>Details about how the benchmark was created are provided in an<br><a href="../records/13653420">associated zenodo release</a>, which contains the source code as well as a<br>manuscript describing the benchmark.</p> <p>This release fixes a bug that incorrectly detected shared peptides <br>between different species. It also includes the annotated spectra in <br>mzSpecLib format.</p> <p> </p>
DFT datasets for training machine-learning potential to model Cl-doped lithium borosilicate glasses using DeePMD
<h2><strong>Li diffusion in oxygen-chlorine mixed anion borosilicate glasses using</strong></h2> <h2><strong>a machine-learning simulation</strong></h2> <h5>Shingo Urata, Noriyoshi Kayaba</h5> <ul> <li>DFT_Data_for_Cl-doped_LBSCl_glass.zip inlucudes atom configurations, energies, forces, box size, atom types, atom kinds, and virial in coord.raw, energy.raw, force.raw, type.raw, type_map.raw, and virial.raw, respectively. </li> <li>All DFT data were evaluated using PBE with a cutoff energy of 600 eV by VASP.</li> <li>The other detasets are available from https://doi.org/10.5281/zenodo.10577559</li> <li>LBSCl_DMD_model.pb is force field developed using DeePMD-kit.</li> <li>LBSCl_DMD_model_c.pb.zip is the compressed version of LBSCl_DMD_model.pb.</li> </ul>
Supplemental materials for "Boosting Barlow Twins reduced order modeling for machine learning-based surrogate models in multiphase flow problems"
<p>Supplemental materials for "Boosting Barlow Twins reduced order modeling for machine learning-based surrogate models in multiphase flow problems" in Water Resources Research. Detailed information is available in readme.md.</p>
ADVANCEMENTS IN AIRLINE SECURITY: EVALUATING MACHINE LEARNING MODELS FOR THREAT DETECTION
<p>This study assessed the performance of four machine learning algorithms—Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NN)—for predicting airline security threats using a dataset of 100,000 entries with 30 features. The models were evaluated based on accuracy, precision, recall, F1-Score, and AUC-ROC. The Neural Network achieved the highest performance, with an accuracy of 88%, precision of 86%, recall of 85%, F1-Score of 85.5%, and AUC-ROC of 0.90, demonstrating superior capability in capturing complex, non-linear patterns. The Random Forest model followed, with an accuracy of 85%, precision of 83%, recall of 82%, F1-Score of 82.5%, and AUC-ROC of 0.87, offering a robust and generalizable solution. The SVM model attained an accuracy of 81%, precision of 80%, recall of 78%, F1-Score of 79%, and AUC-ROC of 0.84, showing effective binary classification but with higher computational costs. The Decision Tree model, while interpretable, had the lowest performance metrics: accuracy of 78%, precision of 76%, recall of 72%, F1-Score of 74%, and AUC-ROC of 0.79. The results indicate that Neural Networks and Random Forests are the most effective models for airline security threat detection, with Neural Networks providing the highest overall accuracy and AUC-ROC.</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.