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.
13,064
datasets available to search
ShareScore release 0.9.0
Dataset results
13,064 results for “predictions”
Refined Bathymetric Prediction based on Feature Extraction of Gravity Field Signals: BATHY-FE
<p>BATHY-FE is a refined global seafloor model derived from extraction of learnt bathymetric signatures inherent in gravity field signals. It spans longitudes -180 ~ 180, and latitudes -80 ~ 80. It contains more short-wavelength seafloor features, and is superior to existing bathymetric models in almost all marine regions, especially at regions close to the poles. It is a GMT readable grid file (i.e., a matrix of seafloor model, and vectors of longitudes and latitudes) with a spatial resolution of 15 arc-seconds.</p><p>Included in this repository are a MATLAB livescript and sample data in which a demonstration of the algorithm over a region north of Alaska and Canada is presented.</p>
Plasim dataset for manuscript titled: "Extreme heatwave sampling and prediction with analog Markov chain and comparisons with deep learning"
<p>This dataset was originally generated by running a Plasim general circulation model for 8000 years. We extract a small subset of this dataset which is only 500 years long with temperature, soil moisture and 500 hPa Geopotential extracted over the northern hemisphere above 30 North. This dataset can be used to reproduce the results in https://arxiv.org/abs/2307.09060 concerning training CNN and SWG with cross-validation length of 500 years. </p>
Replication Package for "VALIDATE: A Deep Dive into Vulnerability Prediction Datasets"
<p>Replication Package for "VALIDATE: A Deep Dive into Vulnerability Prediction Datasets"</p><ul><li>SDR Results</li><li>SDR Queries</li><li>VALIDATE User Guide</li><li>Original Studies References in BibTeX</li></ul>
Data from: Spatial scale matters for predicting plant invasions along roads
<p>Biological invasions threaten global biodiversity and can have severe economic and social impacts. The complexity of this problem challenges effective management of invasive alien species as the contribution of many factors involved in the invasion processes across different spatial scales is not well understood.</p> <p>Here, we identify the most important determinants associated with the occurrence of two invasive alien plants, the North American goldenrods (<em>Solidago canadensis</em> and <em>S. gigantea</em>), commonly found in agricultural landscapes of Europe. We used Google Street View images to perform a remote, large-scale inventory of goldenrods along 1,347 roadside transects across Poland. Using open access geospatial data and machine learning techniques, we investigated the relative role of nearly 50 variables potentially affecting the distribution of studied species at five spatial scales (from within 0.25 km to 5 km of the studied locations).</p> <p>We found that the occurrence of goldenrods along roadsides was simultaneously associated with multiple drivers among which those related to human impacts, climate, soil properties and landscape structure were the most important, while local characteristics, such as road parameters or the presence of other alien plants were less influential. However, the relative contribution of different variables in predicting goldenrod distribution changed across spatial scales.</p> <p><em>Synthesis</em>:<em> </em>Mechanisms underlying plant invasions are highly complex and a number of factors can jointly influence the outcomes of this process. However, since different invasion drivers operate at different spatial scales, some important associations may be overlooked when focusing on a single spatial context. Although associations were consistent in direction (positive or negative) across scales, their relative influence on goldenrod occurrence often changed. Socio-economic factors were largely important at local scales, while the effect of landscape factors broadly increased with increasing spatial scale. We highlight that using multi-scale approaches involving a wide range of variables may enable setting priorities for the management of invasive alien plants.</p>
Wood density and leaf size jointly predict woody plant growth rates across (but not within) species along a steep precipitation gradient
<p>1. Functional traits have been proposed to define key dimensions of plant ecological strategies, but we lack consensus on whether traits can accurately predict plant demography. Despite theoretical expectations, it has been challenging to find consistent relationships between functional traits and growth. 2. In this study, we quantified inter- and intraspecific trait variation and individual growth rates of woody plants across a steep moisture gradient that varies 10-fold in annual precipitation (350–3,700 mm) in southern Chile and used a hierarchical Bayesian model to predict growth as a function of trait values. 3. We show that large-leaved species with lower stem tissue density exhibited the fastest growth rates, and these two traits exhibited the highest proportion of interspecific variation. Predictions of growth improved considerably (R2 of the best model increased from 0.28 to 0.49) when species-level multiple traits and their interactions were considered. The inclusion of intraspecific trait variation (ITV), however, did not improve models of growth rate. 4. We found that trait-growth rate relationships were not always consistent across levels of biological organization; relationships observed at the interspecific level did not necessarily hold at the intraspecific level. We found that the relationships between wood density or leaf size and growth were consistent in direction across the precipitation gradient, and the relationships between leaf economics traits and growth were weak and site-specific. 5. Synthesis. Although using more than one functional trait considerably improved growth predictions, wood density and leaf size successfully predicted growth rates across (not within) species, which is consistent with a whole-plant carbon economy. We assert that these two traits are intimately linked and ultimately describe a continuum of plant architecture and carbon economy that covers multiple trait syndromes.</p>
Utilizing Creator Profiles for Predicting Valuable User Enhancement Reports
<p>This is the dataset for paper "Utilizing Creator Profiles for Predicting Valuable User Enhancement Reports"</p>
Problem-solving skills are predicted by innovations in the wild and brain size in Passerines
<p>Code and dataset for the article "<strong>Problem-solving skills are predicted by innovations in the wild and brain size in Passerines</strong>"</p>
A cortical circuit for audio-visual predictions
<p>Raw data and Matlab code to generate the figures of the publication "<strong>A cortical circuit for audio-visual predictions</strong>" <a href="https://doi.org/10.1038/s41593-021-00974-7">https://doi.org/10.1038/s41593-021-00974-7</a>. Run generate_A1V1_figures.m to produce all figures in the publication. </p>
Santander Customer Transaction Prediction
<p> Santander's transaction prediction dataset has a total of 200 features. The data is divided into three categories: 'var0-var200' are numerical features, 'IDcode' is a character type ID column, and the 'target' feature is a binary target label represented by 1 and 0. The specific attribute descriptions are shown in the table.</p>
A spatiotemporal dataset for NDVI prediction on Sentinel-2 imagery
<p>The dataset was designed for prediction of vegetation health on Sentinel-2 imagery and utilized in the AI4Copernicus service: "Long Short-Term Memory Neural Network for NDVI prediction" in which an LSTM neural network was trained in order to create an AI model for NDVI (Normalized Difference Vegetation Index) prediction with time-horizon of one month. </p><p>The dataset needs to be enriched with more data in time dimension but currently it can be used for initial experimentation with an LSTM neural network for NDVI prediction.</p>
Dataset from publication "Predicting context-sensitive urban green space quality to support urban green infrastructure planning"
<p><strong>Data Description:</strong></p><p>This dataset presents the spatial outcome of an analysis modelling perceived green space quality across the city of Espoo, Finland. The analysis relies on data gathered through the My Espoo on the Map survey (<i>Mun Espoo kartalla</i>) in the autumn of 2020 as part of the NordForsk-funded research project NORDGREEN. A comprehensive account of the analytical process and potential applications of the dataset is available in the associated publication, "<i>Predicting context-sensitive urban green space quality to support urban green infrastructure planning</i>" (open access: <a href="https://doi.org/10.1016/j.landurbplan.2023.104952">https://doi.org/10.1016/j.landurbplan.2023.104952</a>).</p><p><strong>Data Processing:</strong></p><p>This dataset results from an analysis that integrates both primary and secondary sources of geospatial data. The primary data were collected with an online public participation GIS (PPGIS) survey directed for the adult inhabitants of Espoo. The data collection took place in September-October 2020 and was executed in collaboration with Aalto University and the City of Espoo. For a detailed overview of the data collection process, please refer to the related publication.</p><p><strong>Data characteristics:</strong></p><p>Format: Shapefile (50m x 50m grid)</p><p>Geographical area: Espoo, Finland</p><p>Spatial reference: EUREF FIN TM35FIN</p><p>Note: Only grid cells intersecting with greenspace have been included in the dataset. For the employed definition of green areas, please consult the related publication.</p><p><strong>Data attributes and their descriptions:</strong></p><p><strong>"</strong><i>P_PROB"</i>: Probability (P), positive perceived quality</p><p><i>"N_PROB"</i>: Probability (P), negative perceived quality</p><p><strong>Funding: </strong></p><p>This research was funded by NordForsk, Sustainable Urban Development and Smart Cities Programme, Project Smart Planning for Healthy and Green and Nordic Cities – NORDGREEN, under Grant Number: 95322.</p>
A dataset for tree-crops prediction in Sentinel-2 imagery
<p>The dataset was designed for semantic-segmentation-based deep learning models and utilized in the AI4Copernicus service: "Deep network for pixel-level classification of S2 patches" in which a U-net neural network was used in order to create an AI model for tree-crops prediction.</p><p>The dataset needs to be enriched with more data. However, it can be used for initial experimentation with a U-net neural network and satellite imagery.</p>
Data for "Predicting the charge density response in metal electrodes"
<p>Dataset associated with the manuscript "Predicting the charge density response in metal electrodes", as published in https://journals.aps.org/prmaterials/abstract/10.1103/PhysRevMaterials.7.125403.</p>
Analysing the distribution of SARS-CoV-2 infections in schools: integrating model predictions with real world observations
<p>Dataset and analysis for:</p> <p>Analysing the distribution of SARS-CoV-2 infections in schools: integrating model predictions with real world observations.<br>Arnab Mukherjee, Sharmistha Mishra, Vijaya Kumar Murty, Swetaprovo Chaudhuri<br> </p> <p>For any questions please contact the first author at: arnab.mukherjee@mail.utoronto.ca</p> <p><strong>Contents:</strong></p> <ol> <li><strong>school_active_cases_ON.zip:</strong> Contains datasets for number of COVID-19 infections reported by public schools in Ontario on ten different dates. The data files have been created based on the raw data in the file named 'covidtesting.csv' that has also been shared.</li> <li><strong>school_active_cases_pdf.m:</strong> Matlab code to obtain PDF of secondary infections in schools for a particular date based on the datasets in 'school_active_cases_ON.zip'. To obtain PDF for different dates, the appropriate dataset needs to be loaded. Created in MATLAB R2021b.</li> <li><strong>U_jet2.m:</strong><em> </em>User-defined Matlab function that is required to run the code 'gZ_code.m'. The function simulates the evolution of a simple jet/puff. Created in MATLAB R2021b.</li> <li><strong>gZ_code.m:</strong> Matlab code to obtain the analytical PDF of secondary infections due to long-range transmission, near-field transmission, or both. Created in MATLAB R2021b.</li> <li><strong>covidtesting.zip: </strong>Contains the data file 'covidtesting.csv' that reports the breakdown of COVID-19 infections in different public schools in Ontario on a daily basis. Data obtained from 'https://data.ontario.ca/dataset/summary-of-cases-in-schools/resource/dc5c8788-792f-4f91-a400-036cdf28cfe8'. Contains information licensed under the Open Government License – Ontario.</li> <li><strong>schoolrecentcovid2021_2022.zip:</strong> Contains the data file 'schoolrecentcovid2021_2022.csv<strong>' </strong>that reports the status of COVID-19 cases in Ontario, obtained from 'https://data.ontario.ca/en/dataset/status-of-covid-19-cases-in-ontario/resource/ed270bb8-340b-41f9-a7c6-e8ef587e6d11'. Contains information licensed under the Open Government License – Ontario.</li> </ol> <p> </p> <p> </p> <p> </p>
Genetic variants regulating the immune response improve the prediction of COVID-19 severity provided by clinical variables
<p>Data set generated to evaluate the association between SNPs from genes related to SARS-CoV-2 pathogenesis and their clinical outcome.</p>
Video for learning-based prediction of the particles catchment area of PAP sediment traps
<p>The ocean biological carbon pump plays a major role in climate and biogeochemical cycles. Photosynthesis at the surface produces particles that are exported to the deep ocean by gravity. Sediment traps, which measure the deep carbon fluxes, help to quantify the carbon stored by this process. However, it is challenging to precisely identify the surface origin of particles trapped thousands of meters deep because of the influence of ocean circulation on the carbon sinking path. In this study, we conducted a series of numerical Lagrangian experiments in the Porcupine Abyssal Plain region of the North Atlantic and developed a machine learning approach to predict the surface origin of particles trapped in a deep sediment trap.This new tool provide a better link between satellite-derived sea surface observations and deep sediment trap measurements, ultimately improving our understanding of the biological carbon pump mechanism.</p>
Convergent evolution and predictability of gene copy numbers associated with diets in mammals
<p>Convergent evolution, the evolution of the same or similar phenotypes in phylogenetically independent lineages, is a widespread phenomenon in nature. If the genetic basis for convergent evolution is predictable to some extent, it may be possible to infer organismic phenotypes and adaptability based on genome sequence data. While repeated amino acid changes have been studied in association with convergent evolution, relatively little is known about the potential contribution of repeated gene copy number changes. In this study, we explore whether certain gene copy number changes are linked to diet shifts in mammals and assess if trophic ecology can be inferred from the copy numbers of a specific set of genes. Using 86 mammalian genome sequences, we identified several genes with higher copy numbers in herbivores, carnivores, and omnivores, even after phylogenetic corrections. We were able to confirm previous findings on genes such as amylase, olfactory receptor, and xenobiotic metabolism genes, and identify novel genes whose copy numbers correlate with dietary patterns. For example, omnivores exhibited higher copy numbers of genes encoding gene expression regulators. We also established a discriminant function based on the copy numbers of 13 genes that can help predict trophic ecology based on genome sequence data. These findings highlight a possible association between convergent evolution and repeated copy number changes in specific genes, suggesting the potential to develop a method for predicting animal ecology and adaptability from genome sequence data.</p>
Subseasonal to Seasonal (S2S) Prediction Algorithms using Hybrid Machine Learning Techniques
<p>< S2S dataset.zip ></p><p>1.ECMWF observations/hindcast realizations</p><ul><li>hindcast-like-observations_2000-2019_biweekly_deterministic.zarr</li><li>forecast-like-observations_2020_biweekly_deterministic.zarr</li><li>ecmwf_hindcast-input_2000-2019_biweekly_deterministic.zarr</li><li>ecmwf_forecast-input_2020_biweekly_deterministic.zarr</li><li>hindcast-like-observations_2000-2019_biweekly_tercile-edges.nc</li></ul><p>2. External variables</p><ul><li>"nino" folder -> nino12.long.anom.data, nino34.long.anom.data : El Niño data</li><li>"Oscillation" folder<ul><li>-> ersst.v5.pdo.dat.text : PDO (Pacific Decadal Oscillation)</li><li>-> norm.nao.monthly.b5001.current.ascii.table.txt : NAO (North Atlantic Oscillation)</li><li>-> qbo.dat : QBO (Quasi Biennial Oscillation)</li></ul></li><li>"great_lake" folder -> N_seaice_extent_daily_v3.0 : Great lakes ice cover</li><li>observed-solar-cycle-indices.json : Sunspot cycles (two variables: original value and smoothed value)</li></ul><p>3. Region.txt : Region and its bound</p><p>4. Biweekly historical statistics data</p><ul><li>biw_stat_w34 folder -> data (mean, standard deviation, median, skewness, kurtosis) for Week 3-4</li><li>biw_stat_w56 folder -> data (mean, standard deviation, median, skewness, kurtosis) for Week 5-6</li></ul><p> </p><p>< ML_code.zip ></p><ul><li>ML codes for training, testing, and calculating RPSS based on Python3</li><li>Check run_val.sh and run_2020.sh </li></ul><p> </p>
Data and scripts for the submission "A locally smoothed terrain-following vertical coordinate to improve the simulation of fog and low stratus in numerical weather prediction models"
<p>Dataset and scripts used to generate Figures for "A locally smoothed terrain-following vertical coordinate to improve the simulation of fog and low stratus in numerical weather prediction models", submitted to the <strong><em>Journal of Advances in Modeling Earth Systems</em></strong> (JAMES).</p> <p>Scripts: Python and NCL</p> <p>Data: Netcdf, PNG, Python pickled objects</p>
Autonomous, multiproperty-driven molecular discovery: from predictions to measurements and back
<p>This repository contains all the data and models associated with the paper "Autonomous, multi-property-driven molecular discovery: from predictions to measurements and back" by Koscher et al. More information to follow</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.