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.
1,943
datasets available to search
ShareScore release 0.9.0
Dataset results
1,943 results for “machine learning”
Sensing Performance of Artificially Intelligent Nanopores Developed by Integrating Solid-State Nanopores with Machine Learning Methods
<p>Ionic current-time data obtained from measuring nanoparticles with the diameters of 90, 100, 150, 200, 220, 270, and 300 nm, using nanopores with a diameter of 300nm.</p> <p>Test_100nm_1 means a test data of nanoparticles with a diameter of 100 nm.</p> <p>Train_100nm_1 means a training data of nanoparticles with a diameter of 100 nm.</p>
Landslide Susceptibility Mapping using Machine Learning: Details of articles published in 2009-2021
<p>To understand the trend of landslide susceptibility mapping using machine learning, we prepared a detailed list of 140 recently published articles. The Harzing desktop application was used to get the published articles by searching for "landslide susceptibility machine learning" keywords in the "Title" field of the application and searched using Google Scholar within the Harzing application. The search returned a total of 172 articles published from 2009 to 2021, and after eliminating papers that could not be accessed, we had 140 useable published articles. The articles also included some recently published articles which are pre-print and not peer-reviewed.</p>
Data from: Machine learning identifies ecological selectivity patterns across the end-Permian mass extinction
<p>The end-Permian mass extinction occurred alongside a large swathe of environmental changes that are often invoked as extinction mechanisms, even when a direct link is lacking. One way to elucidate the cause(s) of a mass extinction is to investigate extinction selectivity as it can reveal critical information on organismic traits as key determinants of extinction and survival. Here we show that machine learning algorithms, specifically gradient boosted decision trees, can be used to identify determinants of extinction as well as predict extinction risk. To understand which factors led to the end-Permian mass extinction during an extreme global warming event, we quantified the ecological selectivity of marine extinctions in the well-studied South China region. We find that extinction selectivity varies between different groups of organisms and that a synergy of multiple environmental stressors best explains the overall end-Permian extinction selectivity pattern. Extinction risk was greater for genera that had a low species richness, had narrow bathymetric ranges limited to deep-water habitats, had a stationary mode of life, possessed a siliceous skeleton or, less critically, had calcitic skeletons. These selective losses directly link the extinction to the environmental effects of rapid injections of carbon dioxide into the ocean-atmosphere system, specifically the combined effects of expanded oxygen minimum zones, rapid warming, and potentially ocean acidification.</p>
Data archive for paper "Machine Learning Emulation of Urban Land Surface Processes"
<p>This archive contains models, data* (Overview), as well as the Singularity image to optionally rerun experiments described in "<a href="https://doi.org/10.1029/2021MS002744">Machine Learning Emulation of Urban Land Surface Processes</a>".</p> <p><strong>Prerequisites</strong></p> <ul> <li>Linux or macOS with Bash shell.</li> <li><a href="https://sylabs.io/">Singularity</a> (tested with version 3.6.3-1.el8)</li> </ul> <p>Please note that all steps require <a href="https://sylabs.io/">Singularity</a> to be installed on your system. If you are looking for information on how to install or use Singularity, please refer to the <a href="https://sylabs.io/docs">Singularity documentation</a>.</p> <p><strong>Overview</strong></p> <p>A general overview of the repository structure is given below. Due to licensing restrictions analysis and forcing data (*) cannot be included and need to be requested separately (see Initialization). Data derivatives (**) from either analysis or forcing, as well as intermediary data (***), are not included as they can be generated by rerunning experiments (see Usage).</p> <pre><code>. ├── data │ ├── analysis* │ ├── forcing* │ ├── teb │ ├── utils │ ├── wps │ └── wrf ├── hpc ├── models │ ├── teb │ ├── unn │ ├── wps │ └── wrf-unn ├── notebooks ├── outputs │ ├── analysis** │ ├── benchmark*** │ ├── forcing** │ ├── kerastuner*** │ ├── notebooks │ ├── tabular │ ├── teb** │ ├── unn** │ ├── wps*** │ └── wrf ├── paper │ └── figures ├── singularity └── tools </code></pre> <p><strong>Initialization</strong></p> <p>Forcing and analysis data need to be requested separately. The following directories should map to their respective data archives:</p> <ul> <li><code>./data/analysis</code> -> <a href="http://doi.org/10.5281/zenodo.4678387">Grimmond et al. (2013)</a></li> <li><code>./data/forcing</code> -> <a href="http://doi.org/10.5281/zenodo.4679279">Grimmond et al. (2021)</a></li> </ul> <p><strong>Usage</strong></p> <p>To rerun all experiments and reproduce results, run <code>tools/run_all.sh</code> from your command prompt. After completion, all results are saved in the <code>outputs</code> directory. Note that WRF simulations require high CPU time and may take hours or days to complete.</p> <p>Alternatively, if <a href="https://en.wikipedia.org/wiki/Portable_Batch_System">Portable Batch System (PBS)</a> is available on your system, the following helpers may be used instead:</p> <pre><code>qsub hpc/submit_init.pbs qsub hpc/submit_tuner.pbs qsub hpc/submit_unn.pbs qsub hpc/submit_find_median_unn.pbs qsub hpc/submit_wrf.pbs qsub hpc/submit_postprocess.pbs qsub hpc/submit_benchmark.pbs </code></pre> <p>Note that you may need to modify PBS helper scripts to suit your specific environment.</p> <p><strong>Development notes</strong></p> <p>See DEVELOP.md.</p> <p><strong>License</strong></p> <p>The source code developed for this work is licensed under MIT (<code>LICENSE_CODE.txt</code>). For licensing information of third-party software see licenses under the <code>models</code> directory. Data files in this archive, including the initial and boundary condition data from the European Centre for Medium-Range Weather Forecasts (<code>data/wps/ungrib</code>), are licensed under CC BY-NC 4.0 (<code>LICENSE_DATA.txt</code>).</p>
Machine learning identifies girls with central precocious puberty based on multi-source data
<p><strong>Objective: </strong>The study aimed to develop simplified diagnostic models for identifying girls with central precocious puberty (CPP), without the expensive and cumbersome gonadotropin-releasing hormone (GnRH) stimulation test, which is the gold standard for CPP diagnosis.</p> <p><strong>Materials and Methods:</strong> Female patients who had secondary sexual characteristics before 8 years old and had taken a GnRH analog (GnRHa) stimulation test at a medical center in Guangzhou, China were enrolled. Data from clinical visiting, laboratory tests and medical image examinations were collected. We first extracted features from unstructured data such as clinical reports and medical images. Then, models based on each single-source data or multi-source data were developed with Extreme Gradient Boosting (XGBoost) classifier to classify patients as CPP or non-CPP.</p> <p><strong>Results: </strong>The best performance achieved an AUC of 0.88 and Youden index of 0.64 in the model based on multi-source data. The performance of single-source models based on data from basal laboratory tests and the feature importance of each variable showed that the basal hormone test had the highest diagnostic value for a CPP diagnosis.</p> <p><strong>Conclusion: </strong>We developed three simplified models that use easily accessed clinical data before the GnRH stimulation test to identify girls who are at high risk of CPP. These models are tailored to the needs of patients in different clinical settings. Machine learning technologies and multi-source data fusion can help to make a better diagnosis than traditional methods.</p>
Unified Model Atmospheric Forecast Model Data for Machine Learning Cloud-Base Height
<p>Unified Model data, in pp format, for machine learning of cloud-base height based on profiles of temperature, humidity, pressure and cloud fraction. The model configuration is Global Atmosphere 6, running with a resolution of N320 (which is coarser than what was running operationally at the time). Each simulation is run for 24 hours, re-initialising every 24 hours. A separate data file is provided every 6 hours. Data points are on a latitude-longitude grid in the horizontal and on a stretched grid in the vertical. See https://gmd.copernicus.org/articles/10/1487/2017/ for details of the model configuration.</p> <p>Data from January 2016 is for training.</p> <p>Data from July 2017 is for development/validation</p> <p>Data from October 2017 is for final testing.</p> <p> </p>
A collection of X-ray projections of 131 pieces of modeling clay containing stones for machine learning-driven object detection
<p><strong>Summary</strong></p> <p>This submission contains a collection of 235800 X-ray projections of 131 pieces of modeling clay (Play-Doh) with various numbers of stones inserted. The submission is intended as an extensive and easy-to-use training dataset for supervised machine learning driven object detection. The ground truth locations of the stones are included. The data is supplementary material to the paper titled "A tomographic workflow enabling deep learning for X-ray based foreign object detection" [Zeegers 2022].</p> <p> </p> <p><strong>Description</strong></p> <p><em>Sample information</em></p> <p>The samples are modeling clay (Play-Doh, Hasbro, RI, USA) with various numbers of pieces of gravel included. In total 131 samples are prepared, of which 20 samples contain 5-8 inserted stones, 3 samples contain three stones, 35 contain two stones, 62 contain one stone and 11 contain no stones. The stones have an average diameter of ca. 7mm (ranging from 3mm to 11mm). The Play-Doh is remolded for every sample.</p> <p><em>Apparatus</em></p> <p>The dataset is acquired in the FleX-ray Laboratory, developed by TESCAN-XRE, located at CWI in Amsterdam. The CT scanner consists consists of a cone-beam microfocus polychromatic X-ray point source, and a 1944x1536 pixel, 14-bit, flat detector panel (Dexela1512NDT). Full details can be found in [Coban 2020].</p> <p><em>Scanning setup</em></p> <p>For each sample, 1800 radiographs are collected by rotating the sample over 360 degrees in a circular and continuous motion. A peak voltage of 90kV is used, and the target power is set to 20W. The distance between the source and detector is 69.80 cm and the distance between the source and the object is 44.14 cm. An exposure time of 20 ms is used for each projection.</p> <p><em>Experimental plan</em></p> <p>This data is the result of a demonstration of a workflow to collect annotated data for supervised machine learning for X-ray based object detection. The ground truth locations are retrieved by tomographic reconstruction, segmentation and virtual projections with the same acquisition angles. A detailed description for the workflow to obtain a training dataset is given in [Zeegers 2022].</p> <p><em>Technical details</em></p> <p>All projections have been corrected with flatfield images (averaged over 10 pre and 10 post radiographs) and darkfield images (averaged over 10 pre and 10 post images). Both the X-ray projections and the ground truth images are resized to 128x128 pixels. The raw data is made available in another (larger) submission for complete reproduction (<a href="https://zenodo.org/record/5866228">https://zenodo.org/record/5866228</a>). All images are stored in .tif format. The data for samples with 5-8 stones are put in a separate folder from the data with 0-3 stones. The size of the completely unpacked dataset is 19.6 GB.</p> <p><strong>NOTE</strong>: Because the dataset consists of 471600 files, fully extracting the dataset may take a while. Therefore, an additional and significantly smaller zip-file is included for previewing the data, with one X-ray projection for each sample.</p> <p> </p> <p><strong>Additional Links</strong><br> These datasets are produced by the Computational Imaging group at Centrum Wiskunde & Informatica (CI-CWI) in Amsterdam, The Netherlands: <a href="https://www.cwi.nl/research/groups/computational-imaging">https://www.cwi.nl/research/groups/computational-imaging</a></p> <p> </p> <p><strong>Contact details</strong><br> zeegers [at] cwi [dot] nl</p> <p> </p> <p><strong>Acknowledgments</strong><br> The authors would like to acknowledge the funding from the Netherlands Organisation for Scientific Research (NWO), project number 639.073.506. The authors also acknowledge TESCAN-XRE NV for their collaboration and support of the FleX-ray laboratory.</p> <p><br> <strong>References</strong><br> [Zeegers 2022] M. T. Zeegers, T. van Leeuwen, D. M. Pelt, S. B. Coban, R. van Liere, K. J. Batenburg, "A tomographic workflow enabling deep learning for X-ray based foreign object detection", 2022 (in preparation)<br> [Coban 2020] S. B. Coban, F. Lucka, W. J. Palenstijn, D. Van Loo, and K. J. Batenburg, “Explorative imaging and its implementation at the FleX-ray Laboratory,” J. Imaging, vol. 6, no. 18, 2020, doi: 10.3390/jimaging6040018.</p> <p>If you use (parts of) this data in a publication, we would appreciate it if you would refer to the first article.</p>
WYC seismic phases for "Lighting up an 1-km fault near a hydraulic fracturing well using machine-learning based picker"
<p>In this study, we applied a state-of-the-art package on newly collected nodal-array data around a hydraulic-fracturing well. The array consists of up to 85 nodes with an average station spacing of less than a kilometer. Within the hydraulic-fracturing stimulation weeks, we detected ~3000 seismic events with magnitude down to ~-2. </p> <p>The seismic phases to associate the events are included in Zenodo_share.zip. The final catalog and station locations (in relative scale) are included in the excel spreadsheet.</p>
Machine learning enabled multiple illumination quantitative optoacoustic oximetry imaging in humans - Data
<p>Recorded raw data and result data for the paper "Machine learning enabled multiple illumination quantitative optoacoustic oximetry imaging in humans"</p>
Bayesian machine learning analysis of single-molecule fluorescence colocalization images
<p>Data files for the "Bayesian machine learning analysis of single-molecule fluorescence colocalization images" manuscript.</p>
Supporting Data for "Regional Sensitivity Patterns of Arctic Ocean Acidification Revealed With Machine Learning"
<p>This repository contains additional model simulation data used in the following paper:</p> <p>Krasting et al., 2022: Regional sensitivity patterns of Arctic Ocean acidification revealed with machine learning. <em>Communications Earth & Environment</em>.</p> <p><strong>Description of data files in this repository:</strong></p> <ol> <li>GFDL-CM4.c_ant.nc (42M) - NetCDF file of anthropogenic carbon inventory for 3 historical simulation ensemble members performed with the NOAA GFDL-CM4 climate model </li> <li>GFDL-ESM4.c_ant.nc (12M) - NetCDF file of anthropogenic carbon inventory for 3 concentration-driven historical simulation ensemble members performed with the NOAA GFDL-ESM4 Earth system model</li> <li>GFDL-ESM4e.c_ant.nc (12M) - NetCDF file of anthropogenic carbon inventory for 3 emission-driven historical simulation ensemble members performed with the NOAA GFDL-ESM4 Earth system model</li> </ol> <p>Notes:</p> <ul> <li>Anthropogenic carbon was calculated by vertically-integrating the dissolved inorganic carbon tracer (dissic) simulated at year 2002 and subtracting from the corresponding year of the preindustrial control simulation</li> <li>Results are provided on the models' native tripolar grids. Supporting grid metrics are provided in each NetCDF file</li> <li>All other model simulation data used in Krasting et al. 2022 is available publicly through the Earth System Grid Federation.</li> </ul> <p> </p>
High-Throughput Screening of Tribological Properties of Monolayer Films using Molecular Dynamics and Machine Learning: Supplemental Repository
<p>Supplemental repository for the "High-Throughput Screening of Tribological Properties of Monolayer Films using Molecular Dynamics and Machine Learning" article. Contains calculated tribological properties of dual-monolayer systems from Molecular Dynamics (MD) simulation and Machine Learning (ML).</p>
Low-cost prediction of molecular and transition state partition functions via machine learning
<p>This dataset contains the vibrational, rotational, translational, and electronic partition functions for 35,883 organic chemistry molecular structures taken from the Grambow et. al dataset [1]. It was used to train ML deep neural networks to predict unknown transition state partition functions as well as partition functions for known molecular structures [2]</p> <p>The partition functions were computed at temperatures in the range T= [50, 2000] K with the rigid rotor, rigid body, harmonic oscillator approximations. Reactions involve no more than 7 C, N, or O atoms.</p> <p>Frequencies for the vibrational partition functions were taken from [1] where they were computed with DFT at the ωB97X-D3/def2-TZVP level of theory.</p> <p>For the rotational partition function, symmetry numbers were obtained by evaluating proper and improper invariant rotations of the structures. We note that structures involving two molecules were not separated: vibrational frequencies and symmetry numbers were computed for the aggregate structure.</p> <p>For each reaction, partition functions were calculated at 50 temperatures sampled uniformly from the inverse temperature range 1/T = [1/2000, 1/50] K<sup>-1</sup>. This corresponds to 11,961 reactions, 35,883 total structures, and 1,794,150 total partition function examples.</p> <p>The file Partition_Functions.tar.gz contains directories entitled “rxnXXXXXX” where XXXXXX is a reaction number identifier. Each contain three files “rXXXXXX.csv”, “pXXXXXX.csv”, “tsXXXXXX.csv” corresponding to data from the reactant (“r”), product (“p”), and transition state (“ts”) for reaction XXXXXX. Note that the directory structure and the reaction identifiers are the same as used in the original structure dataset by Grambow et al. and the corresponding structures can easily be extracted from that dataset. Each comma separated value (csv) file contains 50 rows and the following columns:</p> <table> <tbody> <tr> <td> <p><strong> Column label</strong></p> </td> <td> <p><strong> Values</strong></p> </td> </tr> <tr> <td> <p> T [K]</p> </td> <td> <p> Temperature</p> </td> </tr> <tr> <td> <p> qpart_ele [unitless]</p> </td> <td> <p> Electronic partition function</p> </td> </tr> <tr> <td> <p> qpart_trans [unitless]</p> </td> <td> <p> Translational partition function</p> </td> </tr> <tr> <td> <p> qpart_vib [unitless]</p> </td> <td> <p> Vibrational partition function</p> </td> </tr> <tr> <td> <p> qpart_rot [unitless]</p> </td> <td> <p> Rotational partition function</p> </td> </tr> <tr> <td> <p> qpart [unitless]</p> </td> <td> <p> Partition function</p> </td> </tr> <tr> <td> <p> log_qpart_trans [unitless] </p> </td> <td> <p> Natural logarithm of translational partition function</p> </td> </tr> <tr> <td> <p> log_qpart_rot [unitless]</p> </td> <td> <p> Natural logarithm of rotational partition function</p> </td> </tr> <tr> <td> <p> log_qpart_vib [unitless]</p> </td> <td> <p> Natural logarithm of vibration partition function</p> </td> </tr> <tr> <td> <p> log_qpart [unitless]</p> </td> <td> <p> Natural logarithm of partition function</p> </td> </tr> </tbody> </table> <p> </p> <p>[1] C. A. Grambow, L. Pattanaik, and W. H. Green, “Reactants, products, and transition states of elementary chemical reactions based on quantum chemistry,” <em>Sci. Data</em>, <strong>7</strong>:1–8, 2020.</p> <p>[2] Komp, E. Valleau, S. “Low-cost prediction of molecular and transition state partition functions via machine learning”, arXiv:, 2022.</p> <p> </p>
Delineating the Controlling Factors of Hydraulic Fracturing-Induced Seismicity in the Northern Montney Play, Northeastern British Columbia, Canada, with Machine Learning
<p>Earthquake catalog for northern Montney Play from 2014-2021.</p>
Analytics, Visualisation and Machine Learning of General Practitioner Prescribing using Open Health Data
<p>Open Prescription data used in Postgraduate project into Northern Ireland General Practice prescribing.</p>
Messenger magentometer and coordinates dataset for Machine learning
<p>This dataset is based on the original MESSENGER mission magnetometer and coordinate data as made available at PDS PPI. It introduces a number of improvements upon the original [1 sec temporal resolution]:</p> <ol> <li>Magnetometer calibration signals have been removed.</li> <li>Coordinates and magnetic field measurements have been merged together.</li> <li>Additional fields, such as model dipole magnetic field and planetary position in a heliocentric coordinate system have been added.</li> <li>The dataset has been split up into files by orbit numbers, with each file centered on the periapsis.</li> <li>Data for a number of partially recorded orbits has been removed.</li> </ol>
An automated system for inspecting rock faces and detecting potential rock falls using machine learning
<p>Rockfall is a hazard in mountainous areas threatening infrastructure and human lives. Rockfall hazards are often mitigated by manual inspections using pry bars. The inspector must access the rock face, hit the rock surface, detect, and remove the loose rocks. This method is very labor demanding, unsafe, and challenging. This research presents a method that automatize the inspection of rock blocks that are prone to rockfall events. A robot is developed to replace the manual hammer tap process and collect the sound data remotely; subsequently, the sound signal is used to identify different types of the discontinuity in rocks in controlled laboratory environment. Machine learning is used to train the method to discriminate between intact rock and rock that may be prone to fall. This methodology was successfully applied to laboratory tests on rock. Finally, the research involves the implementation of this system in field to understand the potential and limitations of the proposing system in automatizing the rock inspections. This research enables the inspectors to collect data remotely, detect loose rocks, and save data for future references.</p>
On the application of an observations-based machine learning parameterization of surface layer fluxes within an atmospheric large-eddy simulation model: Trained Models
<p>Trained machine learning models and scaling values used in the paper "On the application of an observations-based machine learning parameterization of surface layer fluxes within an atmospheric large-eddy simulation model."</p>
Data from: Decipher soil organic carbon dynamics and driving forces across China using machine learning
<p><span><span>The dynamics of soil organic carbon (SOC) play a critical role in modulating global warming. However, the long-term spatiotemporal changes of SOC at large scale and the impacts of driving forces remain unclear. In this study, we investigated the dynamics of SOC in different soil layers across China through the 1980s to 2010s using a machine learning approach and quantified the impacts of the key factors based on factorial simulation experiments. Our results showed that the latest (2000-2014) SOC stock in the first meter soil (SOC<sub>100</sub>) was 80.68 ± 3.49 Pg C, of which 42.6% was stored in the top 20 cm, sequestrating carbon with a rate of 30.80 </span><span>± 12.37</span><span> g C m<sup>-2</sup> yr<sup>-1</sup> since the 1980s. Our experiments focusing on the recent two periods (2000s and 2010s) revealed that climate change exerted the largest relative contributions to SOC dynamics in both layers and warming or drying can result in SOC loss. However, the influence of climate change weakened with soil depth, while the opposite for vegetation growth. </span><span>Relationships between SOC and forest canopy height further confirmed this strengthened impact of vegetation with soil depth, and highlighted the carbon sink function of deep soil in mature forest. Moreover, our estimates suggested that SOC dynamics in 71% of topsoil were controlled by climate change and its coupled influence with environmental variation (CE). Meanwhile CE and the combined influence of climate change and vegetation growth dominated the SOC dynamics in 82.05% of the first meter soil. </span><span>Additionally, the national cropland topsoil organic carbon increased with a rate of 23.6 </span><span>± 7.6 </span><span>g C m<sup>-2</sup> yr<sup>-1</sup> since the 1980s, and the widely applied nitrogenous fertilizer was a key stimulus. </span><span>Overall, our study extended the knowledge about the dynamics of SOC and deepened our understanding about the impacts of the primary factors.</span></span></p>
Non-Functional Requirements for Machine Learning: Understanding Current Use and Challenges Among Practitioners
<p>This package contains interview data (themes, codes, and quotes) and survey data to identify, define and measure non-functional requirements for ML systems.</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.