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”
Biological and environmental data for a study on transferability of statistical and machine learning models using North Sea Macrozoobenthos
<p>General</p> <p>Data documented here are not the product of our research but was scraped from various sources and processed - so no genuine reupload. This collection is a contribution to reproduceable reseach. All datasets are given in "RData" binary format</p> <p> </p> <p>Data description</p> <p>majornorthseabenthos </p> <p>This is macrozoobenthos data as data frame scraped from the GBIF repository (gbif.org). Species are Corbula gibba, Tellina fabula, Turritella communis, Euspira pulchella, Corystes cassive- launus, Upogebia deltaura, Lanice conchilega, Nephtys hombergii, Echinocardium cordatum, and Amphiura filiformis. data was postprocessed to have only single occurrence fon the approxinatel 1x1 km grid used for this study. Also, occurrences closer than 5 km close to shore were removed - including occurrences on land.</p> <p> </p> <p>Predictors</p> <p>A SpatialPixelsDataFrame in EPSG 4326 with five layers: Median grain size in micrometers, mud content in percent (both MUDAB database), water depth in meters above MSL (Weatherall et al, 2015), modelled average bottom shear stress from waves in N/sqrm (The Wamdi Group, 1988) and climatologival average winter bottom water temperature in deg. C (Stips et al, 2004).</p> <p> </p> <p> </p> <p>References</p> <p>Stips A, Bolding K, Pohlmann T, Burchard H (2004) Simulating the temporal and spatial dy- namics of the North Sea using the new model GETM (general estuarine transport model). Ocean Dynamics 54(2):266–283</p> <p>The Wamdi Group (1988) The WAM model-a third generation ocean wave prediction model. Journal of Physical Oceanography 18(12):1775–1810</p> <p>Weatherall P, Marks K, Jakobsson M, Schmitt T, Tani S, Arndt JE, Rovere M, Chayes D, Ferrini V, Wigley R (2015) A new digital bathymetric model of the world’s oceans. Earth and Space Science 2(8):331–345</p> <p> </p>
Global snow water equivalent product derived from machine learning model trained with in situ measurement data
<p>This dataset is a global snow water equivalent dataset using machine learning trained with in-situ measurements. The temporal resolution of the SWEML product is daily, and the spatial resolution is 0.25˚ (approximately 25km). It covers latitudes of 90S to 90N and longitudes of 180W to 180E with global scales, excluding Antarctica. The dataset is provided in NetCDF format, organized by year. Each year contains daily SWE data, including leap days in leap years.</p>
IMBALANCED MACHINE LEARNING CLASSIFICATION MODELS FOR REMOVAL BIOSIMILAR DRUGS AND INCREASED ACTIVITY IN PATIENTS WITH RHEUMATIC DISEASES
<p>Objective: Predict long-term disease worsening and the removal of biosimilar medication in patients with rheumatic diseases.</p><p>Methodology: Observational, retrospective, and descriptive study. Review of a database of patients with immune-mediated inflammatory rheumatic diseases. Disease worsening and removing biosimilars are imbalanced variables, that require using imbalanced machine learning models selected based on their superior f1-scores and great accuracy. Previously, we selected the most important variables using mutual information tests.</p><p>Results: The best imbalanced machine learning models to predict disease worsening and the removal of the biosimilar obtained f1-scores of 0.52 and 0.63, respectively. Both models are decision trees. In the first one, two important factors are switching of biosimilar and age, and in the second, the relevant variables are optimization and the value of the initial CRP. </p><p>Conclusions: Biosimilar drugs do not always work well for rheumatic diseases. We obtained two imbalanced machine learning models to detect those cases, where the drug should be removed or where the activity of the disease increases from low to high. Our decision trees use variables, such as age or switching, not considered in previous studies.</p>
ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries – Data and Models
<p>This repository contains data and models used in the following paper.</p> <p> </p> <p>Swanson, K., Walther, P., Leitz, J., Mukherjee, S., Wu, J. C., Shivnaraine, R. V., & Zou, J. ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries. In review.</p> <p> </p> <p>The data and models are meant to be used with the <a href="https://github.com/swansonk14/admet_ai">ADMET-AI</a> code, which runs the ADMET-AI web server at <a href="https://admet.ai.greenstonebio.com/">admet.ai.greenstonebio.com</a>.</p> <p> </p> <p>The data.zip file has the following structure.</p> <p>data</p> <p> drugbank: Contains files with drugs from the <a href="https://go.drugbank.com/">DrugBank</a> that have received regulatory approval. drugbank_approved.csv contains the full set of approved drugs along with ADMET-AI predictions, while the other files contain subsets of these molecules used for testing the speed of ADMET prediction tools.</p> <p> tdc_admet_all: Contains the data (.csv files) and RDKit features (.npz files) for all 41 single-task ADMET datasets from the <a href="https://tdcommons.ai/">Therapeutics Data Commons</a> (TDC).</p> <p> tdc_admet_multitask: Contains the data (.csv files) and RDKit features (.npz files) for the two multi-task datasets (one regression and one classification) constructed by combining the tdc_admet_all datasets.</p> <p> tdc_admet_all.csv: A CSV file containing all 41 ADMET datasets from tdc_admet_all. This can be used to easily look up all ADMET properties for a given molecule in the TDC.</p> <p> tdc_admet_group: Contains the data (.csv files) and RDKit features (.npz files) for the 22 TDC ADMET Benchmark Group datasets with five splits per dataset.</p> <p> tdc_admet_group_raw: Contains the raw data (.csv files) used to construct the five splits per dataset in tdc_admet_group.</p> <p> </p> <p>The models.zip file has the following structure. Note that the ADMET-AI website and Python package use the multi-task Chemprop-RDKit models below.</p> <p>models</p> <p> tdc_admet_all: Contains Chemprop and Chemprop-RDKit models trained on all 41 single-task TDC ADMET datasets.</p> <p> tdc_admet_all_multitask: Contains Chemprop and Chemprop-RDKit models trained on the two multi-task TDC ADMET datasets (one regression and one classification).</p> <p> tdc_admet_group: Contains Chemprop and Chemprop-RDKit models trained on the 22 TDC ADMET Benchmark Group datasets.</p>
Data for simultaneous inference of sea ice state and surface emissivity model using machine learning and data assimilation
<h2>Overview</h2> <p>This dataset supports the draft manuscript "Simultaneous inference of sea ice state and surface emissivity model using machine learning and data assimilation" which describes a way to infer the daily maps of the sea ice concentration and empirical properties of the sea ice (relating to its snow cover and its physical properties, such as air inclusions) along with the creation of a new empirical model for the sea ice surface emissivity. This is done using knowledge of the atmosphere state, skin temperature and ocean water emissivity from the European Centre for Medium-range Weather Forecasts (ECMWF) weather forecasting model and the observed radiances at microwave frequencies from the Advanced Microwave Scanning Radiometer 2 (AMSR2). The inverse modelling and state estimation is achieved by combining empirical machine learning elements in a Bayesian-inspired network along with a number of physical components. The work also introduces the idea of an "empirical state", in this case describing the aspects of the sea ice physical state which affect the observations, and which is defined by the inputs to the new empirical model component (in machine learning terms, it is defined by the latent input state of a neural network). This dataset includes the data used in training the model and inferring the sea ice parameters, as well as the outputs from that training process. The software used to perform the training is in Python and uses the Keras and Tensorflow software. See the draft manuscript for full details of this data.</p> <p>The code used in the draft manuscript is archived at <a href="https://doi.org/10.5281/zenodo.10013542">https://doi.org/10.5281/zenodo.10013542</a></p> <p>The data used in the draft manuscript is archived at <a href="https://doi.org/10.5281/zenodo.10033377">https://doi.org/10.5281/zenodo.10033377</a></p> <h2>Training data </h2> <h3>Observation space training and ancillary data</h3> <p>Training is done at the location of AMSR2 superobservations (superobs) over ocean with less than 1% land contamination and polewards of 45 degrees latitude, between 1st July 2020 and 30th June 2021. There are 64,184,021 superobs used. A superob is the average of all raw JAXA level 1B observations from one orbit falling into a grid box on an approximately constant area (reduced Gaussian) grid at approximately 40 km by 40 km resolution (noting that polar regions can thus have up to around 7 superobs per day). The superobs have been computed using the field of view central locations for each channel as derived from the JAXA level 1B data. A subset of 10 of the AMSR2 channels is used, from 10 GHz, V polarised, to 89 GHz, H polarised.</p> <p>At each superob location, the relevant fields from the ECMWF 12 hour 'background' forecast are interpolated to the observation time and location. The atmosphere is represented indirectly by the relevant radiative transfer terms from a scattering radiative transfer model. The sea ice concentration from the ECMWF OCEAN5 analysis is included as a validation reference but is not used in the training itself, except to provide a monthly mean first guess to speed up the training. Each field is provided in a separate netCDF file:</p> <ul> <li>field_v2_JULIAN_DAY.nc - superob time in days since 12 UTC on Nov 24th 4714 BC on the proleptic Gregorian calendar</li> <li>field_v2_LAT.nc - superob central latitude in degrees</li> <li>field_v2_LON.nc - superob central longitude in degrees</li> <li>field_v2_IGRID.nc - corresponding grid number on the map grid used in this work (see below)</li> <li>field_v2_OBSVALUE.nc - observed superob brightness temperature at each of 10 AMSR2 channels.</li> <li>field_v2_TSFC.nc - skin temperature computed by the ECMWF forecast model</li> <li>field_v2_WINDSPEED10M.nc - 10m wind speed computed by the ECMWF forecast model</li> <li>field_v2_EMIS_WATER.nc - Ocean water surface emissivity at 10 AMSR2 channels, simulated from the ECMWF forecast fields using the FASTEM-6 model</li> <li>field_v2_CLOUD_FRACTION.nc - Effective cloud fraction used in the atmospheric radiative transfer model at each of 10 AMSR2 channels</li> <li>field_v2_TAUSFC_CLD.nc - Surface to space transmittance in the cloudy column at each of 10 AMSR2 channels</li> <li>field_v2_TUP_CLD.nc - Upwelling brightness temperature from the atmosphere in the cloudy column at each of 10 AMSR2 channels</li> <li>field_v2_TDOWN_CLD.nc - Downwelling brightness temperature from the atmosphere in the cloudy column at each of 10 AMSR2 channels</li> <li>field_v2_TAUSFC.nc - Equivalently for the clear column</li> <li>field_v2_TUP.nc - Equivalently for the clear column</li> <li>field_v2_TDOWN.nc - Equivalently for the clear column</li> <li>field_v2_SEAICE.nc - Sea ice concentration from the ECMWF OCEAN5 analysis, for validation only (not used in training)</li> </ul> <h3>Grid space data: initial data for training; validation sea ice data</h3> <p>A number of properties are provided to the hybrid physical-empirical model that is being trained, on a special map grid defined in this project, including all 62,499 of the reduced Gaussian 40km grid points that have at least one superob at some point during the year of training data. These are:</p> <ul> <li>ifs_seaice_initials_year.nc - sea ice concentration from OCEAN5, monthly averaged on the grid, and then provided on all days of the relevant month as initial conditions (technically, first guess) for the training. This includes an additional day before the beginning of the training, used for time-lagging (see draft paper).</li> <li>ifs_tsfc_year_dailyx.nc - skin temperature from ECMWF forecast fields at observation locations, averaged onto the daily grid, to help provide constraints on the likelihood of sea ice as part of a sea ice loss function.</li> </ul> <p>For diagnostic and validation purposes, the ECMWF OCEAN5 analysis is also provided on the grid:</p> <ul> <li>ifs_seaice_year.nc - sea ice concentration from OCEAN5 at observation locations, averaged onto the daily grid</li> </ul> <p>All these fields are provided on the following dimensions:</p> <ul> <li>LON - the longitude of the grid point in degrees</li> <li>DAY - the day through the training year (0-364, 1st July 2020 to 30th June 2021) or through the training year extended forward by one day (30th June 2020) for the sea ice (0-365). In practice the days are offset by 3 hours from the UTC day to match the ECMWF data assimilation windows, which start at 21 UTC the day before.</li> </ul> <p>The latitude is also provided</p> <ul> <li>LAT - the latitude of the grid point in degrees</li> </ul> <p>Note that the observation location IGRID is on the custom grid of the ML model that is defined implicitly in these gridded files. The LON and LAT vectors in these files are the longitude and latitude points of the grid and are of 62499 in length. The IGRID number for an observation is the index into these arrays from 0-62498.</p> <h2>Outputs from training</h2> <p>The following files are the output and diagnostics from the year-long training. The python code and the draft paper are the primary documentation for these:</p> <ul> <li>models_year.nc - settings of the model are recorded here, along with the trained values of the smaller empirical components/layers within the hybrid model. For example, the layer weights of the wind speed bias correction, the observation space bias correction, and the empirical surface emissivity model are recorded here. The values of the loss function at each epoch are also recorded here.</li> <li>properties_year.nc - trained values of each of 3 empirical properties of sea ice on the map grid (3 properties by 62499 locations by 365 days from 1st July 2020)</li> <li>seaice_year.nc - inferred values of sea ice fraction on the map grid (62499 locations by 365 days from 1st July 2020, discarding the additional day at the start)</li> <li>tbsim_year.nc - simulated AMSR2 brightness temperatures from the trained network</li> <li>tbsim_initial_year.nc - simulated AMSR2 brightness temperatures using the untrained network</li> </ul> <p>The longitude and latitude of the map grid is found in any of the initial data files described in the previous section. The days are 0-364 corresponding to 1st July 2020 to 30th June 2021.</p> <h3>Sea ice surface emissivity at grid locations</h3> <p>A packaged version of the sea ice surface emissivity is provided at grid locations, alongside the surface emissivity model, the sea ice concentration and the four inputs to the model, i.e. the normalised skin temperature and the three empirical variables:</p> <ul> <li>emissivity_grid_year.nc</li> </ul> <p>Note that in the training, the surface emissivity is computed at observation locations and has not been stored due to memory limitations. For easier comparison to other datasets, the surface emissivity has been recomputed on grid locations in this package, using the year-long trained emissivity model and its trained inputs. The sea ice surface emissivity is only physically meaningful for sea ice concentrations above around 0.25. Also be aware of the "hole at the pole" which is the small region of the Arctic ocean that is sometimes not covered by an AMSR2 overpass, and which is found from 88 degrees N. On days where the hole or part of the hole exists, the sea ice emissivity on the grid is not valid at these locations. These locations can be identified by having all values of the empirical properties zero (because the empirical properties were never constrained by any observations on that day, and remain at their initial values before training).</p> <h2>Sensitivity tests</h2> <p>Extensive sensitivity tests were carried out, as described in the appendices of the draft paper and as documented in the Python code, using the month of August 2020 as an example. These required equivalent month-long training and initial data similar to those described above, but all observation space fields are contained within the same file in this case. Output files follow similar principles to those described above. The full package is provided as a tar file:</p> <ul> <li>sensitivity.tar</li> </ul> <p>This contains the training and initial files:</p> <ul> <li>amsr2_v2_202008.nc</li> <li>ifs_tsfc_dailyx_202008.nc</li> <li>ifs_seaice_202008.nc</li> </ul> <p>as well as directories containing the trained model outputs and diagnostics at each of the sensitivity tests, using the same formats as described for the yearly training, with these names:</p> <ul> <li>nprop - number of empirical properties</li> <li>epoch - number of epochs</li> <li>deep - configuration of the empirical sea ice emissivity model, including multiple layers of nonlinear dense neural network</li> <li>bseaice - background error for the sea ice physical bounds background error (loss) term</li> <li>bemis - background error for the sea ice emissivity background error (loss) term</li> <li>bbias - background error for the bias correction background error (loss) term</li> <li>batchsize - batch size used in training</li> <li>bbatchsize - extended epochs testing of batch size used in training</li> </ul> <h2>Licensing</h2> <p>This data product is published under a Creative Commons Attribution 4.0 International (CC BY 4.0). To view a copy of this licence, visit <a href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</a></p> <p>You are free to:</p> <ul> <li>Share — copy and redistribute the material in any medium or format</li> <li>Adapt — remix, transform, and build upon the material for any purpose, even commercially.</li> </ul> <p>Under the following terms:</p> <ul> <li>You must give appropriate credit (attribution) to ECMWF as outlined below, provide a link to the licence, and indicate if changes were made.</li> <li>No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the licence permits.</li> </ul> <p>The following wording shall be attached to the use of this ECMWF data product: </p> <ol> <li>Copyright statement: Copyright "© 2023 European Centre for Medium-Range Weather Forecasts (ECMWF)".</li> <li>Source <a href="http://www.ecmwf.int/">www.ecmwf.int </a>and <a href="https://doi.org/10.5281/zenodo.10009497">https://doi.org/10.5281/zenodo.10009497</a></li> <li>Licence Statement: This data is published under a Creative Commons Attribution 4.0 International (CC BY 4.0). <a href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</a></li> <li>Disclaimer: ECMWF does not accept any liability whatsoever for any error or omission in the data, their availability, or for any loss or damage arising from their use.</li> <li>Where applicable, an indication if the material has been modified and an indication of previous modifications.</li> <li>DOI: 10.5281/zenodo.10009498</li> </ol> <p>Original data for this value-added product was provided by Japan Aerospace Exploitation Agency (JAXA). Specifically, this dataset builds on the Advanced Microwave Scanning Radiometer 2 (AMSR2) level 1B data available from the JAXA G-Portal, https://gportal.jaxa.jp/gpr/, which has the following attribution and licensing:</p> <ol> <li>Give credit for the original data to JAXA, i.e. "Original data for this value added data product was provided by Japan Aerospace Exploration Agency"</li> <li>DOI for original JAXA data is L1B-Brightness temperature (TB) GCOM-W/AMSR2 L1B Brightness Temperature: <a href="https://doi.org/10.57746/EO.01gs73ans548qghaknzdjyxd2h">https://doi.org/10.57746/EO.01gs73ans548qghaknzdjyxd2h</a></li> <li>Original terms of data service from JAXA, with highlighted extracts: <ul> <li><a href="https://gportal.jaxa.jp/gpr/index/eula?lang=en">https://gportal.jaxa.jp/gpr/index/eula</a> <ol> <li>The user is entitled to use G-Portal data free of charge without any restrictions (including commercial use) except for the condition about acknowledgement of data credit as stipulated in Article 7.(2). (see above)</li> <li>JAXA is collecting results (papers, theses, reports, etc.) using G-Portal data. If you have any results using G-Portal data, please mail/e-mail a copy of the result to G-Portal Support Desk (Contact Information written at the end of the Terms of Use). We appreciate your cooperation very much.</li> </ol> </li> </ul> </li> </ol>
Supplementary material: Machine learning and phylogenetic models identify predictors of genetic variation in Neotropical amphibians
<p><strong>Aim: </strong>Intraspecific genetic variation is key for adaptation and survival in changing environments and is known to be influenced by many factors, including population size, dispersal, and life history traits. We investigated genetic variation within Neotropical amphibian species to provide insights into how natural history traits, phylogenetic relatedness, climatic, and geographic characteristics can explain intraspecific genetic diversity.</p> <p><strong>Location:</strong> Neotropics.</p> <p><strong>Taxon:</strong> Amphibians.</p> <p><strong>Methods: </strong>We assembled datasets using open-access databases for natural history traits, genetic sequences, phylogenetic trees, climatic, and geographic data. For each species, we calculated overall nucleotide diversity (<em>π</em>) and tested for isolation by distance (IBD) and isolation by environment (IBE). We then identified predictors of <em>π</em>, IBD, and IBE using Random Forest (RF) regression or RF classification. We also fitted phylogenetic generalized linear mixed models (PGLMMs) to predict<em> π</em>, IBD, and IBE.</p> <p><strong>Results:</strong> We compiled 4,052 mitochondrial DNA sequences from 256 amphibian species (230 frogs and 26 salamanders), georeferencing 2,477 sequences from 176 species that were not linked to occurrence data. RF regressions and PGLMMs were congruent in identifying range size and precipitation (σ) as the most important predictors of <em>π</em>, influencing it positively. RF classification and PGLMMs identified minimum elevation as an important predictor of IBD; most species without IBD tended to occur at higher elevations. Maximum latitude and precipitation (σ) were the best predictors of IBE, and most species without IBE occur at lower latitudes and in areas with more variable precipitation.</p> <p><strong>Main conclusions: </strong>This study identified predictors of genetic variation in Neotropical amphibians using both machine learning and phylogenetic methods. This approach was valuable to determine which predictors were congruent between methods. We found that species with small ranges or living in zones with less variable precipitation tended to have low genetic diversity. We also showed that Western Mesoamerica, Andes, and Atlantic Forest biogeographic units harbor high diversity across many species that should be prioritized for protection. These results could play a key role in the development of conservation strategies for Neotropical amphibians.</p>
RAM-SCB ROPE Dataset and Machine Learning Models with Code
<p>This repository contains the machine learning datasets and programs used in the development of the RAM-SCB ROPE.</p>
dataset for Machine Learning Surrogates for Surface Complexation Model of Uranium Sorption to Oxides
<p>The data sets are used to train, validate, and test SCM surrogates for uranium sorption on oxide surfaces. </p> <p>train_norm.csv, val_norm.csv, and test_norm.csv are used to train, validate, and evaluate DNN-SCM surrogate. </p> <p>test_set1.csv and test_set2.csv are two additional datasets to evaluate the model's performance. </p>
Data and R code for machine learning modelling of favourite places and routes of outdoor recreation
<p>This is a script showing the analysis used in a paper submitted for review in Landscape and Urban Planning, titled "Seeing through their eyes: Revealing recreationists’ landscape preferences through viewshed analysis and machine learning", by Carl Lehto, Marcus Hedblom, Anna Filyushkina and Thomas Ranius. </p> <p>The zip file contains an R script, data saved in .rds format and a R workspace. </p>
Aerial Images_Part 2_Integrating Remote Sensing and Machine Learning for Developing Spatio-Temporal Model to Predict Aquatic Larval Habitats of Malaria
<p>Aerial Images_Part 2_Integrating Remote Sensing and Machine Learning for Developing Spatio-Temporal Model to Predict Aquatic Larval Habitats of Malaria</p>
Aerial Images_Part 1_Integrating Remote Sensing and Machine Learning for Developing Spatio-Temporal Model to Predict Aquatic Larval Habitats of Malaria
<p>Aerial Images_Part 1_Integrating Remote Sensing and Machine Learning for Developing Spatio-Temporal Model to Predict Aquatic Larval Habitats of Malaria</p>
Data from:Modelling the spatiotemporal dynamics of soil nitrogen in croplands of Northeast China from 1980 to 2023 using multisource data and machine learning
<p>This dataset include the spatiotemporal distribution and uncertainty of cropland soil total nitrogen content at 0-30, 30-60, 60-100 cm depths in Northeast China from 1980 to 2023. The long-time series of TN were estimated by using an space-time automatic machine learning. The detail information on the products were given below:</p> <p>Period: 1980-2023</p> <p>Spatial resolution: 0.004166667 degree (~500 m)</p> <p>Temporal resolution: 1 year</p> <p>CRS: geographic latitude/longitude (EPSG:4326 - WGS 84 – Geographic)</p> <p>Data format: GeoTIFF</p>
Data for: A comprehensive dataset of forest above-ground biomass from field observations, machine learning and topographically augmented allometric models over the Kashmir Himalaya
<p>The repository contains observed Above Ground Biomass (AGB) estimates at about 275 sample plots chosen for AGB assessment in the forests of Kashmir Himalaya. The AGB is assessed as a fucntion of dbh using various allometric equations developed specifically for the region. It also contains the AGB for years 1978, 1990, 2000, 2010 and 2021 predicted using topographcally augmeneted multivariate regression model. The extent of forest, delineated using on-screen digitization using Landsat and Sentinel image collection at decadal scale is also provided for the years 1978, 1990, 2000, 2010 and 2021.</p>
Modeling surface pCO2 variability in two contrasting basins of North Indian Ocean using advanced machine learning algorithms
<p>The dataset contains surface ocean <em>p</em>CO2, uncertainty and air-sea CO2 flux for the North Indian Ocean region. The data is available from 1993 to 2020 on a monthly time scale. Each of these data has a spatial resolution of 1/12º. Air-sea CO2 flux is calculated using a bulk parameterization, which is a function of wind speed. A positive CO2 flux value signifies CO2 outgassing, while a negative value indicates atmospheric CO2 uptake. </p> <p><strong>**It is recommended to use the latest version V3. Previous versions are depricated.</strong></p>
Dataset for: Anniés et al., "Accessing structural, electronic, transport and mesoscale properties of Li-GICs via a complete DFTB-model with machine-learned repulsion potential"
<p>GPrep training data, GPrep jupyter notebook, .skf files.</p> <p>The GPrep code is available at https://doi.org/10.5281/zenodo.3697913</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>
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>
Supplementary information for: A continuous-score occupancy modeling framework for incorporating uncertain machine learning output in autonomous biodiversity surveys
<p><span>Ecologists often study biodiversity by evaluating species occupancy and the relationship between occupancy and other covariates. Occupancy models are now widely used to account for false absences in field surveys and to reduce bias in estimates of covariate relationships. Existing occupancy models take as inputs binary detection/non-detection observations of species at each visit to each site. However, autonomous sensing devices and machine learning models are increasingly used to survey biodiversity, generating a new type of observation record (i.e., continuous-score data) that reflects the model's confidence a species is present in each autonomously sensed file, instead of binary detection/non-detection data. These data are not directly compatible with traditional binary occupancy modeling methods.</span></p> <p><span>Here, we develop a new occupancy model that models continuous scores on a visit level as a Gaussian mixture, combining a distribution of scores for files that do contain the species of interest and a distribution of scores for files that do not. The model takes as input continuous scores for each autonomously sensed and classified file, along with an optional small number of binary, manually verified detection and non-detection annotations.</span></p> <p><span>We present a simulation study that shows that over a range of empirically realistic parameters, our model outperforms traditional occupancy models that are based on binary annotation alone. We also apply this new model to an empirical case study using data generated from five machine learning classifiers applied to autonomous acoustic recordings gathered in the eastern United States.</span></p> <p><span>Because our occupancy model generalizes allowable input data beyond binary observations, it is particularly well-suited to the increasing volume of machine learning classified data in ecology and conservation.</span></p>
Modeling Crash Severity and Collision Types Using Machine Learning
<p>Traffic safety analysis is the fundamental step for reducing economic, social, and environmental cost incurred due to traffic accidents. The essence of traffic safety is understanding the factors affecting crash occurrence, injury severity and collision type and their underlying relationships and predict-prevent future crash instances. Crash injury severity studies in past have utilized numerous statistical, econometric and Machine Learning (ML) and Artificial Intelligence (AI) tools to extract the underlying relationship between the crash causal factors and the consequent severity or collision type. The study aims to explore the Multi-Label Classification (MLC) tool from the domain of Artificial Intelligence (AI) for classification problems in the setting of traffic safety. MLC finds its application primarily in protein function, semantic scene, and music categorization problems. In the real world, multiple heterogenous subjective factors decide the extent of damage/severity of a particular crash instance. Theoretically, the traffic collision type and crash severity type can be correlated, and thus, it is intuitive to model them simultaneously. The ability of MLC to categorize an entity under analysis to more than one labels, correlated or uncorrelated, provides the approach an edge over the single-class (binary) or multi-class classification approach. The MLC based classification model was calibrated and tested using the historical crash data extracted for the state of Texas. The selection of study area was based on a link-level unsupervised principal component analysis-based clustering approach. Similar clustering approach was also tested at the county-level to understand the spatial behavior and thus transferability of the MLC approach to other key cities in the state. The performance of the proposed approach was tested, compared, and quantified with the conventional binary/multi-class classification tools used in the traffic safety domain. Inferences from the preliminary numerical analysis indicates that the proposed multi-label classification approach has promising performance compared to the traditional classification approaches, specifically found in traffic safety literatures.</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.