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.
481
datasets available to search
ShareScore release 0.9.0
Dataset results
481 results for “network model”
Data from: Mental health ecosystem of Gipuzkoa (2015) for Bayesian network modelling
Open the record for dataset details and reuse information.
Simulated results from an agent-based model examining inequality and innovation in social networks
Open the record for dataset details and reuse information.
Data from: Combining geostatistical and biotic interactions modelling to predict amphibian refuges under crayfish invasion across dendritic stream networks
Open the record for dataset details and reuse information.
Data for: Fishing triggers trophic cascade in terms of variation, not abundance, in an allometric trophic network model
Open the record for dataset details and reuse information.
Data from: A hands-on guide to use network video recorders, internet protocol cameras, and deep learning models for dynamic monitoring of trout and salmon in small streams
Open the record for dataset details and reuse information.
MVCNN++: CAD model shape classification and retrieval using multi-view convolutional neural networks
Open the record for dataset details and reuse information.
The disruption index suffers from citation inflation and is confounded by shifts in scholarly citation practice: synthetic citation networks for bibliometric null models
Open the record for dataset details and reuse information.
Data of A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths
<pre>Data related to the publication (we would be grateful if you could cite the paper in the case in which you are using the data) title = "A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths", journal = "Computer Methods in Applied Mechanics and Engineering", pages = " 113234", year = "2020", issn = "0045-7825", doi = "https://doi.org/10.1016/j.cma.2020.113234", author = "Wu, Ling and Nguyen, Van Dung and Kilingar, Nanda Gopala and Noels, Ludovic"</pre>
Supplementary Materials (An Artificial Neural Network Model for Assessing Frailty-Associated Factors in the Thai Population)
<p>Supporting information for an Artificial Neural Network Model for Assessing Frailty-Associated Factors in the Thai Population</p>
Data from: Modelling the current and future biodiversity distribution in the Chilean Mediterranean Hotspot. The role of protected areas network in a warmer future
Aim: Mediterranean Chile is part of the five recognized Mediterranean-type climates in the world and harbors a very rich floral diversity. Climate change has been reported as a significant threat to its biodiversity. We used the flora of Mediterranean Chile to analyze how biodiversity patterns, as measured by Phylogenetic Diversity, genus and species richness will respond to climate change scenarios and identify the areas that will harbor the greatest evolutionary potential and biodiversity richness. We also evaluated how these spatial patterns are depicted within the current network of protected areas. Location: Chilean Mediterranean climate-type Region, South America. Methods: Biodiversity metrics were evaluated for current and future climatic scenarios. Species distribution models were done using Maxent for 1.727 species and 571 genera. Relationships between species/genera gain, loss and turnover were evaluated. For Mediterranean endemic species, loss and gain was also related to life form. Finally, variation in species gain, loss and turnover was evaluated in future climate change scenarios within and outside Mediterranean Chile state protected areas. Results: We found a general decrease in species richness in the entire Region toward future climate change scenarios. Phylogenetic Diversity is predicted to be higher than expected by richness in the north and south of the area, and lower than expected by richness in the Andes mountain. The highest average species and genus loss is predicted to occur outside the protected areas, meanwhile species and genus gain is higher within them. Main conclusions: Future biodiversity patterns are reported here for the first time in the Chilean Mediterranean Region. Our findings enhance the importance of the current protected areas to harbor this future variation, despite their reduced number and size along the region.
Approximation of a marine ecosystem model by artificial neural networks designed using a genetic algorithm
<p>Data from the Paper: Approximation of a marine ecosystem model by artificial neural networks designed using a genetic algorithm.</p> <p>Abstract: </p> <p>Marine ecosystem models are important to identify the processes that affects for example the global carbon cycle. Computation of an annually periodic solution (i.e., a steady annual cycle) for these models requires a high computational effort. To reduce this effort, we approximated an exemplary marine ecosystem model by different artificial neural networks. We used a fully connected network, then applied the sparse evolutionary training (SET) procedure, and finally applied a genetic algorithm (GA) to optimize both the network topology. With all three approaches, a direct approximation of the steady annual cycle was not sufficiently accurate. However, using the mass-corrected prediction of the ANN as initial concentration for additional model runs, the results were in very good agreement. In this way, we achieved a runtime reduction by about 15 \%. The result from the SET algorithm were comparable to those of the full network. Further application of the GA may lead to an even higher reduction.</p> <p>Content:</p> <p>Database sqlite <a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/ANN_Database.db">ANN_Database.db</a></p> <p>zip-files with data: </p> <p><a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/ANN-Data.zip">ANN-Data.zip</a> structure and weights of used networks</p> <p><a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/ANN-Results.zip">ANN-Results.zip</a> results obtained with networks</p> <p><a href="https://zenodo.org/api/files/669d208b-7304-4d31-a6cc-3ad78e3544e9/Reference-Results.zip">Reference-Results.zip</a> reference results and training data</p> <p> </p> <p> </p> <p> </p> <p> </p>
Models and Predictions for "Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network"
<p><strong>Models and Predictions for the paper "Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network"</strong></p> <p>GitHub: <a href="https://github.com/gauchm/mts-lstm">https://github.com/gauchm/mts-lstm</a></p> <p><strong>Results</strong></p> <p>The file `results.tar.gz` contains:</p> <ul> <li>ensembled predictions for all models (generated from the models in `models/` using the <a href="https://neuralhydrology.readthedocs.io/en/latest/api/neuralhydrology.utils.nh_results_ensemble.html">`nh-results-ensemble` command</a>). These predictions were used in the `results-analysis.ipynb` and `odelstm-analysis.ipynb` notebooks on the GitHub repository for the paper.</li> <li>the NWM predictions <ul> <li>`nwm_chrt_v2_1h.p` contains hourly NWM predictions for the CAMELS basins between 1993 and 2007. The file is derived from the reanalysis on <a href="https://docs.opendata.aws/nwm-archive/readme.html">aws</a>.</li> <li>`nwm_results.p` is derived from `nwm_chrt_v2_1h.p` and contains hourly and day-aggregated results and performance metrics for the test period of our paper.</li> </ul> </li> <li>a file `signatures.p` with hydrologic signatures that were calculated from the models' predictions. These signatures were used in the `results-analysis.ipynb` notebook on the GitHub repository for the paper.</li> </ul> <p><strong>Models</strong></p> <p>The tar.gz files prefixed with `models-` contain the trained MTS-LSTM, sMTS-LSTM, and ODE-LSTM models from our experiments. For each experiment, there exist 10 model setups (one for each random seed).<br> Besides the trained models, each model's tar.gz also contains the predictions on the test or validation perod and the configuration file used to train the model.</p> <p><em>MTS-LSTM</em></p> <ul> <li>`mtslstm_seed*` -- the MTS-LSTM from the benchmarking section of the paper (using one forcings product, trained on daily and hourly data)</li> <li>`mtslstm_multiforcing_seed*` -- the MTS-LSTM from the section on per-timescale input data, experiment "multi-forcing B" (using just NLDAS as hourly inputs)</li> <li>`mtslstm_multiforcing_dailyhourly_seed*` -- the MTS-LTSM from the section on per-timescale input data, experiment "multi-forcing A" (ingesting daily forcings into the hourly model)</li> <li>`mtsltsm_136H1D_seed*` -- the MTS-LTSM from the section on prediction at other timescales (1-, 3-, 6-hourly and daily predictions)</li> </ul> <p><em>sMTS-LSTM</em></p> <ul> <li>`smtslstm_seed*` -- the sMTS-LSTM from the benchmarking section of the paper (using one forcings product, trained on daily and hourly data)</li> <li>`smtslstm_noregularization_seed*` -- the sMTS-LSTM from the section on cross-timescale consistency (trained without regularization)</li> </ul> <p><em>Time-Continuous Experiments</em></p> <p>The file `models-timecontinuous.tar.gz` contains one sub-folder per basin on which we conducted our initial experiments.<br> Each basin directory contains:</p> <ul> <li>Experiment A (trained on daily and 12-hourly, evaluated on hourly): <ul> <li>`odelstm_a_seed*` -- the ODE-LSTM from experiment A</li> <li>`mtslstm_a_seed*` -- the MTS-LSTM from experiment A</li> </ul> </li> <li>Experiment B (trained on hourly and 3-hourly, evaluated on daily) <ul> <li>`odelstm_b_seed*` -- the ODE-LSTM from experiment B</li> <li>`mtslstm_b_seed*` -- the MTS-LSTM from experiment B</li> </ul> </li> </ul> <p><em>Related Datasets: </em><a href="https://doi.org/10.5281/zenodo.4072700">https://doi.org/10.5281/zenodo.4072700</a> contains the hourly NLDAS forcings and USGS streamflow required to use the models from this dataset.</p>
Joint Autoregressive and Graph Models for Software and Developer Social Networks
<p>This zip contains three CSV files and one folder. This dataset contains information for the recent ten distributions.</p> <ul> <li><strong>developer_attributes.csv</strong>: There are seven columns in this file. "distro" (str) represents distribution name. "source" (str) denotes source package name. "person_id" (str) indicates developer identity. "closes" (int), "high" (int), "medium" (int), "low" (int) are the features.</li> <li><strong>source_bugs.csv</strong>: In this file, three columns are present. "distro" (str) represents the distribution name. "source" (str) represents the source package name. "bug_count" (int) denotes the number of bugs that source package has at a particular distribution.</li> <li><strong>source_sizes.csv</strong>: In this file, three columns are present. "distro" (str) represents the distribution name. "source" (str) represents source package name. "size" (int) denotes the size of the package.</li> <li><strong>Dependency folder:</strong> Within this folder, ten dependency lists are present. Each file contains two columns i.e "start" (str) and "target" (str). Both of them represent source packages. So, we read as the "start" source package depends on "target" source package. </li> </ul> <p>Here is the arxiv version of our paper: <a href="https://arxiv.org/abs/2101.08729">https://arxiv.org/abs/2101.08729</a>. </p> <p>Here is the portal link: <a href="https://sites.google.com/view/rima-hazra/swnet">https://sites.google.com/view/rima-hazra/swnet</a></p>
Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment
<p>This repository contains the raw results (by word information-theoretic measures for the experimental stimuli) and the LSTM models analyzed in <a href="https://www.aclweb.org/anthology/2020.acl-main.179/">Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment</a>. The models from the synthetic experiments are given in the synthetic archive, as well as the training data generation script. There is a README included that gives more details for recreating/evaluating results from those experiments.</p> <p>The naming convention for each model in the models directory is:<br> [Language]_hidden[Hidden Units]_batch[Batch Size]_dropout[Dropout Rate]_lr[Learning Rate]_[Model Number].pt</p> <p>Language: en for English and es for Spanish<br> Hidden Units: All models had two layers with 650 hidden units per layer<br> Batch Size: The size of the batch (128 for English, 64 for Spanish)<br> Dropout Rate: All models used a dropout rate of 0.2<br> Learning Rate: All models has a learning rate of 20<br> Model Number: Identifier of the model (English model 0 is the best model from <a href="https://github.com/facebookresearch/colorlessgreenRNNs">Gulordava et al. (2018)</a>) </p> <p> </p> <p> </p>
Cluster configurations of the Hegselmann-Krause model on network ensembles
<p>This is the raw data underlying the results of the preprint [arxiv:2102.10910](https://arxiv.org/abs/2102.10910).</p> <p> </p> <p>## Data</p> <p>For each measured combination of the confidence and system size, there is one gzipped<br> file. For different ensembles, we collected data in different ranges and quality.<br> The paramters are:</p> <p>* Number of samples `m` per parameter combination<br> * Range `r` of confidences epsilon<br> * Distances `d` between values of epsilon (basically the resolution of the data)<br> * Largest size `N_max`</p> <p>The single files follow a naming scheme of `n{N}_e{epsilon}.cluster.dat.gz`, where<br> `{N}` signals the system size of the simulation and `{epsilon}` is the confidence<br> value of the simulation (without a decimal point, i.e., `0050` corresponds to `epsilon = 0.050`).<br> The sizes `N` are usually powers of two (or for the lattices, perfect squares close to powers of two).</p> <p>We present the data for each ensemble in one archive.</p> <p><br> * Fully connected `full.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.001`, `N_max = 262144`<br> * Barabasi Albert with a mean degree of 4 `BA4.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.002`, `N_max = 32768`<br> * Barabasi Albert with a mean degree of 10 `BA10.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.001`, `N_max = 65536`<br> * Square lattice with first nearest neighbors `lat1.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.001`, `N_max = 16384`<br> * Square lattice with second nearest neighbors `lat2.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.001`, `N_max = 16384`<br> * Square lattice with third nearest neighbors `lat3.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.001`, `N_max = 65536`<br> * Square lattice with fourth nearest neighbors `lat4.tar`<br> * `m = 1000`, `r = [0.0, 0.6]`, `d = 0.001`, `N_max = 65536`<br> * Square lattice with third nearest neighbors and 1% rewired edges `lat3_ws.tar`<br> * `m = 1000`, `r = [0.0, 0.3]`, `d = 0.001`, `N_max = 16384`<br> * connected Erdos Renyi with mean degree of 10 `ER10.tar`<br> * `m = 1000`, `r = [0.0, 0.3]`, `d = 0.002`, `N_max = 32768`</p> <p> </p> <p>## Data format</p> <p>Each final state is encoded as three lines:</p> <p>* The convergence time is a single integer with a line prefix '# sweeps: '<br> * The positions of all clusters in opinion space with a line prefix '# ' (unsorted)<br> * The number of agents in each of the clusters without a line prefix</p> <p> </p> <p>## Python example for reading the format</p> <p>An example script, which visualizes the S vs eps graph for the largest size of the fully connected<br> case, with a function to read this format is given in `example.py`.</p>
Data from: Predicting species occurrences with habitat network models
1. Biodiversity conservation requires modelling tools capable of predicting the presence or absence (i.e. occurrence-state) of species in habitat patches. Local habitat characteristics of a patch (lh), the cost of traversing the landscape matrix between patches (weighted connectivity; (wc), and the position of the patch in the habitat network topology (nt) all influence occurrence-state. Existing models are data demanding or consider only local habitat characteristics. We address these shortcomings and present a network-based modelling approach, which aims to predict species occurrence-state in habitat patches using readily available presence-only records. 2. For the tree frog Hyla arborea on the Swiss Plateau, we delineated habitat network nodes from an ensemble habitat suitability model, and used different cost surfaces to generate the edges of three networks: one limited only by dispersal distance (Uniform), another incorporating traffic, and a third based on inverse habitat suitability. For each network, we calculated explanatory variables representing the three categories (lh, wc and nt). The response variable, occurrence-state, was parametrized by a sampling-intensity procedure assessing observations of comparable species over a threshold of patch visits. The explanatory variables from the three networks and an additional non-topological model were related to the response variable with boosted regression trees. 3. The habitat network models had a similar fit; they all outperformed the non-topological model. Habitat suitability index ((lh) was the most important predictor in all networks, followed by third-order neighborhood (nt). Patch size (lh) was unimportant in all three networks. 4. We found that topological variables of habitat networks are relevant for the prediction of species occurrence-state, a step-forward from models considering only local habitat characteristics. For any habitat patch, occurrence-state is most prominently influenced by its habitat suitability, and then by the number of patches in a wide neighborhood. Our approach is generic and can be applied to multiple species in different habitats.
Neural network weights for the xrv.baseline_models.chexpert.DenseNet model for torchxrayvision
<p>https://github.com/mlmed/torchxrayvision</p> <p>xrv.baseline_models.chexpert.DenseNet</p>
Products developed through the "What About Model Data?, Determining Best Practices for Preservation and Replicability, EarthCube Research Coordination Network" project
This dataset includes products developed through the "What About Model Data? Determining Best Practices for Preservation and Replicability, EarthCube Research Coordination Network (RCN)" project. Products include: 1) a rubric worksheet to assist researchers in deciding what simulation output needs to be preserved in a trusted, community repository to communicate knowledge and satisfy publisher and funder requirements, 2) instructions on how to use the rubric worksheet, which include reference use cases, and 3) outputs and presentations from the three project workshops.
Input Data for A Fast Surrogate Model for 3D-Earth Glacial Isostatic Adjustment using Tensorflow (v2.8.0) Artificial Neural Networks
<p>Training datasets for the manuscript A Fast Surrogate Model for 3D-Earth Glacial Isostatic Adjustment using Tensorflow (v2.8.0) Artificial Neural Networks. Two separate datasets are contained for training the ANNs: the 3D-spherically-symmetric (SS) rate-of-change of relative sea level (ROCRSL) and the 3D-SS rate of change of radial displacement (ROCRAD) as a function of SS profiles. Two other datasets contain RSL projections from the explicit (i.e. Seakon 3D - Seakon SS + NMSS ) model and the NMSS model, labelled Seakon_plus_NMSS_RSL and NMSS respectively.</p> <p>Filenames denote the structure of the SS profile: </p> <p>???_?.??_??.*.csv = LT_UMV_LMV.*.{csv,nc}<br> </p> <p>LT = elastic lithosphere thickness (km)</p> <p>UMV = upper mantle viscosity (1E21 Pa s)</p> <p>LMV = lower mantle viscosity (1E21 Pa s)</p> <p>i.e. 96_0.5_10.seakon_S40RTS_lr18-SS.rrad.roc.r360x180.P5.density_wSSRRADROC.csv.bz2 has the SS profile</p> <p>96km elastic lithosphere, 0.5E21 Pa s upper mantle viscosity, 10E21 Pa s lower mantle viscosity</p> <p> </p> <p>The columns of the input files are as follows:</p> <p>LT, UMV, LMV, longitude, latitude, time(t=0), ice(t=0), SS_ROC_RSL (t=0), time(t=-1), ice(t=-1), time(t=-2), ice(t=-2), time(t=-3), ice(t=-3), time(t=-4), ice(t=-4), 3D-SS_ROC_RSL(t=0)</p> <p>units for the above are as follows:</p> <p>km, 1E21 Pas, 1E2 Pas, degrees east (0->360), degrees (-180->180), days since 2000, m, mm/year, days since 2000, m, days since 2000, m, days since 2000, m, days since 2000, m, mm/year</p> <p>where 'days since 2000' assumes exactly 365.25 days per year.</p>
Supplementary data and code for "A network toxicology approach for mechanistic modelling of nanomaterial hazard and adverse outcomes"
<p>This repository contains the relevant data and code supporting the study "A network toxicology approach for mechanistic modelling of nanomaterial hazard and adverse outcomes". Files are password protected during the revision process. A completely public version of the repository will be availble after the revision process is completed. </p> <p>In detail, the uploaded archive folder contains the following data sources:</p> <ul> <li>the relevant code and supporting data (code_to_upload and supporting_data);</li> <li>supplementary materials of the paper, including: <ul> <li>individual enrichment results of the 93 exposures to the 31 ENMs (enrichments_results);</li> <li>comparison between the mechanism of action retrieved from differentially expressed genes and network modelling (network_comparison_results);</li> <li>overrepresented network edges in categories of networks (overrepresented_structures)</li> </ul> </li> </ul>
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.