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.
54
datasets available to search
ShareScore release 0.9.0
Dataset results
54 results for “Gaussian process”
Global Ocean Heat Content Anomalies and Ocean Heat Uptake based on mapping Argo data using local Gaussian processes
<p>Monthly Ocean Heat Content Anomalies (OHCA) in the top 2000 dbar of the ocean are calculated (during 2004-2024, equatorward of 65 degree latitude) subtracting the mean over the period 2004-2024 from the monthly time series of OHC. Yearly OHCA time series are then calculated that include 1. one point per year, i.e., from averaging Jan to Dec (see files ending in “yearly.nc”), and 2. two points per year, i.e., from averaging Jan to Dec and Jul to Jun, respectively (see files ending in “yearly2.nc”). OHC fields are mapped using locally stationary Gaussian processes (defined over space and time) with data-driven decorrelation scales (Kuusela and Stein, 2018). A linear time trend was included in the estimate of the mean field (along with spatial terms and harmonics for the annual cycle). Mapping is done separately for different vertical sections: 15-20 dbar, 15-300 dbar, 300-700 dbar, 700-1850 dbar, 1800-1850 dbar. The 15-20 dbar (1800-1850 dbar) section is used to estimate OHCA for 0-15 dbar (1850-2000 dbar), where observations are sparser. Different vertical sections are combined to estimate global OHCA time series for 0-2000 dbar, 0-700 dbar, 700-2000 dbar (as indicated in the file names). The attribute "area" is included in the netcdf files and it tells the corresponding surface area for the estimates. Regions of the ocean that are shallower than 300 m or are not sufficiently well sampled by the Argo array are not included. Maps of the ocean masks used for the different vertical sections can be found in the .png files (blue shading indicates the area used for the horizontal integral); the bathymetry mask by Roemmich and Gilson (included in the file RG_ArgoClim_Temperature_2019.nc at https://sio-argo.ucsd.edu/RG_Climatology.html) is also used to define the ocean mask. Ocean Heat Uptake is calculated from the monthly OHCA and then averaged as described above to produce yearly time series included in the files for the different layers.</p> <p>For the uncertainty at each time point, the standard deviation of each OHCA/OHU value in the time series is included. When plotting a time series, the user may consider, e.g., shading plus/minus 1* or 1.96*standard deviation (corresponding to a confidence level of 68% or 95% respectively). These standard deviations in the files are estimated using spatially and temporally dependent conditional simulations of monthly gridded anomalies. When combining different layers, the standard deviation of the sum is conservatively estimated as the sum of the standard deviations. </p> <p>Finally, OHCA/OHU trends are estimated via a least-squares fit and reported in the variable metadata with uncertainties (confidence level of 68%). Trend uncertainties are estimated by repeating the fit for each member of the conditional simulation ensemble described above.</p> <p> </p>
pKaDatabase for Stacking Gaussian Processes to Improve pKa Predictions in the SAMPL7 Challenge
<p>A curated a database of small molecules with experimentally measured pKa values. </p> <p>This pickle file can be loaded into memory using Pandas. In the code block below we will print out the columns of the DataFrame:</p> <pre><code class="language-python">import pandas as pd df = pd.load("pKaDatabase.pkl") print(df.keys()). # print the columns</code></pre> <blockquote> <p>['deprotonated microstate ID', 'protonated microstate ID', 'deprotonated microstate smiles', 'protonated microstate smiles', 'AM1BCC partial charge (prot. atom)', 'AM1BCC partial charge (deprot. atom)', 'AM1BCC partial charge (prot. atoms 1 bond away)', 'AM1BCC partial charge (deprot. atoms 1 bond away)', 'AM1BCC partial charge (prot. atoms 2 bond away)', 'AM1BCC partial charge (deprot. atoms 2 bond away)', 'Gasteiger partial charge (prot. atom)', 'Gasteiger partial charge (deprot. atom)', 'Gasteiger partial charge (prot. atoms 1 bond away)', 'Gasteiger partial charge (deprot. atoms 1 bond away)', 'Gasteiger partial charge (prot. atoms 2 bond away)', 'Gasteiger partial charge (deprot. atoms 2 bond away)', 'Extented Hückel partial charge (prot. atom)', 'Extented Hückel partial charge (deprot. atom)', 'Extented Hückel partial charge (prot. atoms 1 bond away)', 'Extented Hückel partial charge (deprot. atoms 1 bond away)', 'Extented Hückel partial charge (prot. atoms 2 bond away)', 'Extented Hückel partial charge (deprot. atoms 2 bond away)', '∆G_solv (kJ/mol) (prot-deprot)', 'SASA (Shrake)', 'SASA (Lee)', 'Bond Order', 'Change in Enthalpy (kJ/mol) (prot-deprot)', 'pKa','href', 'num ionizable groups', 'Weight', 'pKa source']</p> </blockquote> <p> </p> <p>For more information regarding feature calculations, please read the following paper:</p> <blockquote> <p>Raddi, Robert, and Vincent Voelz. "Stacking Gaussian Processes to Improve pKa Predictions in the SAMPL7 Challenge." (2021). <a href="https://doi.org/10.26434/chemrxiv.14650302.v1">10.26434/chemrxiv.14650302.v1</a></p> </blockquote>
Gaussian Process Model and Sensor Placement for Detroit Green Infrastructure: Datasets and Code
<ol> <li><strong>code.zip: </strong>Zip folder containing a folder titled "code" which holds: <ol> <li>csv file titled "MonitoredRainGardens.csv" containing the 14 monitored green infrastructure (GI) sites with their design and physiographic features;</li> <li>csv file titled "storm_constants.csv" which contain the computed decay constants for every storm in every GI during the measurement period;</li> <li>csv file titled "newGIsites_AllData.csv" which contain the other 130 GI sites in Detroit and their design and physiographic features;</li> <li>csv file titled "Detroit_Data_MeanDesignFeatures.csv" which contain the design and physiographic features for all of Detroit;</li> <li>Jupyter notebook titled "GI_GP_SensorPlacement.ipynb" which provides the code for training the GP models and displaying the sensor placement results;</li> <li>a folder titled "MATLAB" which contains the following: <ol> <li>folder titled "SFO" which contains the SFO toolbox for the sensor placement work</li> <li>file titled "sensor_placement.mlx" that contains the code for the sensor placement work</li> <li>several .mat files created in Python for importing into Matlab for the sensor placement work: "constants_sigma.mat", "constants_coords.mat", "GInew_sigma.mat", "GInew_coords.mat", and "R1_sensor.mat" through "R6_sensor.mat"</li> <li>several .mat files created in Matalb for importing into Python for visualizing the results: "MI_DETselectedGI.mat" and "DETselectedGI.mat"</li> </ol> </li> </ol> </li> </ol>
Datasets of fitted toy Monte Carlo samples for "Gaussian Process-based calculation of look-elsewhere trials factor"
<p>For the paper "Gaussian Process-based calculation of look-elsewhere trials factor", we generated and fitted a number of toy Monte Carlo samples which can be used to reproduce figures from the paper or do tests of hypotheses inspired by the method suggested in the article.</p> <p>Together with the hdf5 files containing the samples, we also provide a Jupyter notebook which was used to produce the figures.</p>
Exploring Gaussian processes for short-term forecasting in offshore energy systems: Supplementary material
<p>Two supplementary videos are provided. The first video analyses the performance of wave excitation force forecasting across different horizons in a noise-free case. The second video examines the impact of noise on the forecast. Both videos include results from a Gaussian-based forecaster, an AR forecaster, and show the uncertainty bounds provided by the Gaussian forecaster. The variable analysed and forecasted in these videos is the wave excitation force.</p>
Data release: Searching for binary black hole sub-populations in gravitational wave data using binned Gaussian processes
<p>The data required to reproduce the analyses of "Searching for binary black hole sub-populations in gravitational wave data using binned Gaussian processes" (<a href="https://arxiv.org/abs/2404.03166" target="_blank" rel="noopener">arxiv:2404.03166</a>). The main inference code can be found at <a href="https://github.com/AnaryaRay1/gppop/tree/spin-dev" target="_blank" rel="noopener">https://github.com/AnaryaRay1/gppop/tree/spin-dev </a> (commit: <a href="https://github.com/AnaryaRay1/gppop/commit/ee5ffc421e2c96eeed15a0e0d3839da42b982842">ee5ffc</a>). To reproduce the analyses, follow the instructions at <a href="https://github.com/AnaryaRay1/bbh-subpopulations-scripts">https://github.com/AnaryaRay1/bbh-subpopulations-scripts</a> (commit <a href="https://github.com/AnaryaRay1/bbh-subpopulations-scripts/commit/de88f931d8c1a2cb31ad2fa9d6fdf9a5a00a3c3b">de88f93</a>). Frozen versions of these repositories that were used to generate all the results are available as part of this data release, in the files "gppop_spin_dev_ee5ffc421.tar.gz" and "bbh-subpopulations-scripts_de88f931.tar.gz" respectively.</p>
Cell to Whole Organ Global Sensitivity Analysis on a Four-chamber Heart Electromechanics Model Using Gaussian Processes Emulators - Training Datasets
<p>This database contains all training datasets for the Gaussian processes emulators (GPEs) trained in the study entitled "Cell to Whole Organ Global Sensitivity Analysis on a Four-chamber Electromechanics Model Using Gaussian Processes Emulators", submitted to PLOS Computational Biology.</p> <p>Every folder contains two csv files:</p> <p>- parameters.csv: the rows are the samples and the columns represent the parameters that were varied in the analysis</p> <p>- outputs.csv: the rows are the samples and the columns represent the values for the output features simulated for each sample</p> <p>In ventricular_cell_model, there are four folders:</p> <p>- ionic: ToR-ORd model samples used to train GPEs to predict the ventricular calcium transient features</p> <p>- contraction_isometric_stretch1.0: ToR-ORd model coupled with the Land contraction model samples used to train GPEs to predict the ventricular active tension transient features. The simulations were isometric contractions with no strain (or stretch 1.0).</p> <p>- contraction_isometric_stretch1.1: ToR-ORd model coupled with the Land contraction model samples used to train GPEs to predict the ventricular active tension transient features. The simulations were isometric contractions with 0.1 strain (or stretch 1.1).</p> <p>- contraction_isotonic: ToR-ORd model coupled with the Land contraction model samples used to train GPEs to predict the ventricular active tension transient features. The simulations were isotonic.</p> <p>The folder atrial_contraction_model follows the same structure, but the ionic model was Courtemanche, used to represent an atrial rather than ventricular calcium transient.</p> <p>The folder tissue_electrophysiology contains the training dataset for the GPEs to predict total atrial and ventricular activation times with an Eikonal model.</p> <p>The folder passive_mechanics contains the training dataset for the GPEs to predict inflated volumes and mean atrial and ventricular fiber strains for a passive inflation.</p> <p>The folder CircAdapt contains the training dataset for the GPEs to predict four-chamber pressure and volume features with the CircAdapt ODE model.</p> <p>Finally, the folder fourchamber contains the samples generated with a 3D-0D four-chamber electromechanics model to predict pressure and volume biomarkers for cardiac function.</p> <p>The details about the model can be found in the original publication.</p>
Multi-fidelity Gaussian Process Emulation for Atmospheric Radiative Transfer Models
<p>This repository contains several datasets of spectral atmospheric transfer functions (i.e. path radiance, transmittances, spherical albedo) simulated with MODTRAN6 atmospheric radiative transfer model. The simulations are stored in hdf5 files using the Atmospheric Look-up table Generator (ALG) toolbox (<a href="https://doi.org/10.5194/gmd-13-1945-2020">https://doi.org/10.5194/gmd-13-1945-2020</a>). Each dataset has an associated .xml file that includes the configuration of ALG/MODTRAN6 executions. All datasets include the input atmospheric/geometric variables that are summarized in the following table. Each dataset file has a random distribution (based on latin hypercube sampling) these input variables with varying number of points (e.g. train500.h5 contains 500 samples). The <em>reference </em>dataset contains 10000 samples and was used as reference for evaluating Gaussian Processes emulators.</p> <table> <tbody><tr> <th>Input Variables</th> <th>Units</th> <th>Min</th> <th>Max</th> </tr> </tbody><tbody> <tr> <td>O3 column concentration</td> <td>atm-cm</td> <td>0.25</td> <td>0.45</td> </tr> <tr> <td>Columnar Water Vapor</td> <td>g/cm2</td> <td>0.2</td> <td>4</td> </tr> <tr> <td>Aerosol Optical Thickness</td> <td>-</td> <td>0.04</td> <td>0.6</td> </tr> <tr> <td>Asymmetry parameter</td> <td>-</td> <td>0.5</td> <td>0.85</td> </tr> <tr> <td>Angstrom exponent</td> <td>-</td> <td>0.1</td> <td>2</td> </tr> <tr> <td>Single Scattering Albedo</td> <td>-</td> <td>0.8</td> <td>1</td> </tr> <tr> <td>Surface elevation</td> <td>km</td> <td>0</td> <td>2.5</td> </tr> <tr> <td>Solar Zenith Angle</td> <td>deg</td> <td>0</td> <td>70</td> </tr> <tr> <td>Relative Zenith Angle</td> <td>deg</td> <td>0</td> <td>180</td> </tr> </tbody> </table> <p> </p>
Data for Gaussian-Process-Based Emulators for Building Performance Simulation
<p>The ZIP folder contains the MAT files you need to rerun the experiment described in</p> <p>Rastogi, Parag, Mohammad Emtiyaz Khan, and Marilyne Andersen. 2017. “<strong>Gaussian-Process-Based Emulators for Building Performance Simulation</strong>.” In <em>Proceedings of BS 2017</em>. San Francisco, CA, USA: IBPSA.</p> <p>-------------------------------------------------------------</p> <p>The two m-scripts (MATLAB) help you to load the results reported in the paper. Make sure to CHECK the file paths inside the scripts, especially to the MAT files. Usually, the paths should be fine if you update the variable <em>pathMATfolder</em> inside the script <em>RunThis.m</em> .</p> <p>There are two types of MAT files inside the folder called "Data" :</p> <p>1. Original data (building simulations) --> gpdata_BaseSimulation.mat</p> <p>2. Errors and predictions - errs_BaseSimulation_N_M.mat and ystore_BaseSimulation_N_M.mat --> The first contains all the error quantities and the second the 'y' predictions. The number N represents the run number (subset of master training data set sampled for the given run). The number M can take only two values - 1 or 2. The models for heating load are represented by 1 and for cooling by 2.</p> <p>3. Metadata - trainN* --> These files contain metadata for setting up the plots.</p> <p>See github repository <strong>https://github.com/paragrastogi/GPregressionInBS.git</strong> for more scripts. See <strong>www.paragrastogi.com</strong> or <strong>www.ibpsa.org</strong> for the conference paper.</p>
Quasi-periodic Gaussian process rotation period posterior samples of Kepler light curves.
<p>.h5 files containing light curves, hyperparameter priors, period priors and posterior samples for the QP-GP rotation period model in Angus, Morton, Aigrain, Foreman-Mackey & Rajpaul (2017). </p> <p>koi_results_02_15.tgz contains posterior samples for 1132 Kepler objects of interest.</p> <p>results_acfprior_02_16.tgz contains posterior samples for 998 simulated light curves (previously published in Aigrain et al., 2015: https://arxiv.org/abs/1504.04029) with an ACF-based prior.</p> <p>results_noprior_02_16.tgz contains posterior samples for 997 simulated light curves (previously published in Aigrain et al., 2015) with an uninformative prior.</p> <p>To load the samples in python:</p> <p>>>> df = pd.read_hdf("<filename>", key="samples")</p> <p>>>> ln_period_samples = df.ln_period</p> <p>>>> ln_A_samples = df.ln_A</p> <p>>>> ln_l_samples = df.ln_l</p> <p>>>> ln_G_samples = df.ln_G</p> <p>>>> ln_sigma_samples = df.ln_sigma</p> <p> </p>
Quasi-periodic Gaussian process rotation period posterior samples (with an uninformative prior) for 998 simulated Kepler light curves.
<p>997.h5 files containing light curves, hyperparameter priors, period priors and posterior samples for the QP-GP rotation period model in Angus, Morton, Aigrain, Foreman-Mackey & Rajpaul (2017).</p> <p>997 .png light curve images.</p> <p>To load the samples in python:</p> <p>>>> df = pd.read_hdf("1.h5", key="samples")</p> <p>>>> ln_period_samples = df.ln_period</p> <p>>>> ln_A_samples = df.ln_A</p> <p>>>> ln_l_samples = df.ln_l</p> <p>>>> ln_G_samples = df.ln_G</p> <p>>>> ln_sigma_samples = df.ln_sigma</p> <p> </p>
Quasi-periodic Gaussian process rotation period posterior samples (with an ACF prior) for 998 simulated Kepler light curves.
<p>998.h5 files containing light curves, hyperparameter priors, period priors and posterior samples for the QP-GP rotation period model in Angus, Morton, Aigrain, Foreman-Mackey & Rajpaul (2017).</p> <p>998 .png light curve images.</p> <p>To load the samples in python:</p> <p>>>> df = pd.read_hdf("1.h5", key="samples")</p> <p>>>> ln_period_samples = df.ln_period</p> <p>>>> ln_A_samples = df.ln_A</p> <p>>>> ln_l_samples = df.ln_l</p> <p>>>> ln_G_samples = df.ln_G</p> <p>>>> ln_sigma_samples = df.ln_sigma</p>
Ocean Heat Content Anomalies in the North Atlantic based on mapping Argo data using local Gaussian processes defined over space
<p>Monthly Ocean Heat Content Anomalies (OHCA) in the top 2000 dbar of the ocean are calculated (during 2005-2022, in the North Atlantic, north of 20N) subtracting the time mean over the period 2005-2021 from the monthly time series of OHC. OHC fields are mapped using a locally stationary Gaussian process (defined over space) with data-driven decorrelation scales (Kuusela and Stein, 2018). A linear time trend was included in the estimate of the mean field (along with spatial terms and harmonics for the annual cycle). In this product, mapping is done in latitude and longitude with monthly subsets of data. Mapping is done separately for different vertical sections: 15-20 dbar, 15-300 dbar, 300-700 dbar, 700-1850 dbar, 1800-1850 dbar. The 15-20 dbar (1800-1850 dbar) section is used to estimate OHCA for 0-15 dbar (1850-2000 dbar), where observations are sparser. Different vertical sections are combined to estimate global OHCA for 0-2000 dbar. Regions of the ocean that are shallower than 300 m or are not sufficiently well sampled by the Argo array are not included. </p>
Research data for "Fabrication uncertainty guided design optimization of a photonic crystal cavity by using Gaussian processes"
<h1>Data publication for the paper "Fabrication uncertainty guided design optimization of a photonic crystal cavity by using Gaussian processes"</h1> <div>Contains scripts for performing fabrication uncertainty guided design optimization, example scripts, research data (raw data), cleanup), additional information on models, convergence plots, and field exports.</div> <h2>Funding</h2> <div> <div> <div>We acknowledge funding by the German Federal Ministry of Education and Research (BMBF project siMLopt number 05M20ZAA and BMBF Forschungscampus MODAL number 05M20ZBM) as well as funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy -- The Berlin Mathematics Research Center MATH+ (EXC-2046/1, project ID: 390685689). This project (20FUN05 SEQUME) has received funding from the EMPIR programme co-financed by the Participating States and from the European Union’s Horizon 2020 research and innovation programme. This project is co-financed by the European Regional Development Fund (EFRD, application no. 10184206, QD-Sense).</div> </div> </div> <p> </p> <p> </p> <p> </p> <p> </p>
Datasets and Code for "A Gaussian process model-guided surface polishing process in additive manufacturing"
<p>These are the datasets and computer code for reproducing the results in Jin, Iquebal, Bukkapatnam, Gaynor, and Ding, 2020, “A Gaussian process model-guided surface polishing process in additive manufacturing.” <em>ASME Transactions, Journal of Manufacturing Science and Engineering</em>, Vol. 142(1), pp. 011003.1–011003.12.</p>
Spatio-thermal depth correction of RGB-D sensors based on Gaussian Processes in real-time
<p>This RGB-D dataset is part is part of our publication</p> <p>Heindl, Christoph, et al. "Spatio-thermal depth correction of RGB-D sensors based on Gaussian processes in real-time." <em>Tenth International Conference on Machine Vision (ICMV 2017)</em>. Vol. 10696. SPIE, 2018.</p> <p>Our capture setup consists of a RGB-D sensor looking towards a known planar object. The sensor is coupled with an electronic linear axis to adjust distance. We captured data at distances [40cm, 90cm, 10cm steps] in the temperate range of [25°C, 35°C, 1°C steps]. At each temperature/distance tuple we grabbed 50 images from both RGB and IR (aligned with RGB) sensors. We then created an artificial depth map for all RGB images utilizing the known calibration target in sight.</p> <p>For more information visit https://github.com/cheind/rgbd-correction</p>
Land cover maps: Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features
<p>Land cover maps obtained with Gaussian Processes, Random Forest, Multilayer Perceptron and Lightweight Temporal Self-Attention models for the year 2018 with Sentinel-2 acquisitions.</p> <p>For further details see section VII-A-2 (Results-Performance results in the Southfrance area-Qualitative results) of the article "Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features ". This article is available <a href="https://hal.archives-ouvertes.fr/hal-03781332">here</a>.</p>
Classification Data set : Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features
<p>Classification data set (train, validation, test) from the study area based on 27 tiles on the south of the France. Data set are provided for each eco-climatic region. The size corresponds to the data set DS-A. Only one random pixel sampling is provided: seed 0. This data set was used to train Gaussian Processes, Random Forest, Multilayer Perceptron and Lightweight Temporal Self-Attention models.</p> <p>For further details see section VI-A-1 of the pre-print article "Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features ". This article is available <a href="https://hal.archives-ouvertes.fr/hal-03781332">here</a>.</p> <p>The implementation of the models is available in the <a href="https://gitlab.cesbio.omp.eu/belletv/land_cover_southfrance_gp">open source repository</a>.</p>
Data for publication of "Gaussian process regression-based Bayesian optimisation (G-BO) of model parameters - a WRF model case study of southeast Australia heat extremes"
<p>Implementation of Gaussian process regression-based Bayesian optimisation (G-BO) using the emcee package (<a href="https://emcee.readthedocs.io/en/stable/" rel="nofollow">https://emcee.readthedocs.io/en/stable/</a>).</p> <p>For more information about the implementation of G-BO in optimising the Weather Research and Forecasting (WRF) model parameters, please refer to the paper - <a href="https://essopenarchive.org/doi/full/10.22541/essoar.171292045.52489731" rel="nofollow">Gaussian process regression-based Bayesian optimisation (G-BO) of model parameters - a WRF model case study of southeast Australia heat extremes</a>.</p> <p><code>G-BO_script.ipynb</code> implements the GPR-based Bayesian optimisation using the Affine Invariant Markov chain Monte Carlo (MCMC) Ensemble sampler.</p> <ul> <li><strong>QMC_sobol_samples</strong>: This file contains the 128 parameter samples across the parameter space of three sensitive parameters utilizing the Quasi Monte-Carlo (QMC) Sobol sequence design.</li> <li><strong>nmae_all_128_ens_T_Rh</strong>: This file contains the normalised mean absolute error (NMAE) values of temperature (T) and relative humidity (Rh) of the 128 parameter sample WRF simulations. For more details, please refer to <a href="https://essopenarchive.org/doi/full/10.22541/essoar.171292045.52489731" rel="nofollow">this link</a>.</li> </ul>
A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identification
<p><strong>Introduction</strong></p> <p>The Robot Inverse Dynamics Dataset is a collection of trajectories and joint torque measurements of two robotic manipulators, a 7 DoF Franka Emika Panda, and a 6 DOF MELFA RV4FL. Additionally, the dataset contains the inverse dynamical models and other useful quantities learned to reproduce the results reported on our reference paper "A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identification". The proposed model relies on a novel multidimensional kernel, called Lagrangian Inspired Polynomial (LIP) kernel.</p> <p><strong>At a Glance</strong></p> <ul> <li>The size of the unzipped dataset is ~700MB.</li> <li>The dataset contains</li> <ul> <li>collections of joint trajectories and joint torque measurements of two robot manipulators: a 7 DoF Franka Emika Panda, and a 6 DOF MELFA RV4FL.</li> <li>models of the inverse dynamics of the two manipulators learned on the datasets</li> </ul> <li>The main directories are</li> <ul> <li>Simulated_PANDA/ contains the trajectories, models and results obtained on different configurations of a Franka Emika PANDA robot, simulated in sympybotics.</li> <li>Robots/ contains the data, models and results obtained on two real robots, a Franka Emika PANDA and a Mitsubishi Electric MELFA RV4FRL</li> </ul> <li>See the README.md file for a detailed description of the directories.</li> </ul> <p><strong>Other Resources</strong></p> <p>Python code to train the models and reproduce the results in the paper are available <a href="https://github.com/merlresearch/LIP4RobotInverseDynamics">here</a>.</p> <p><strong>Citation</strong></p> <p>If you use the Robot Inverse Dynamics dataset in your research, please cite our contribution:</p> <pre><code>@InProceedings{ title={A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identification}, author={Giacomuzzo, G., Dalla Libera, A., Romeres, D.,}, booktitle={IEEE Transaction on Robotics}, year={2024} } </code></pre> <p><strong>License</strong></p> <p>The Robot Inverse Dynamics dataset is released under <a href="https://creativecommons.org/licenses/by-sa/4.0/">CC-BY-SA-4.0 license</a>.</p> <p>All data:</p> <pre><code>Created by Mitsubishi Electric Research Laboratories (MERL), 2024 SPDX-License-Identifier: CC-BY-SA-4.0</code></pre>
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.