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.
251
datasets available to search
ShareScore release 0.7.1
Dataset results
251 results for “deep learning models”
Phase picker models and training data for paper "Deep learning models for regional phase detection on seismic stations in Northern Europe and the European Arctic"
<p>This ZIP file includes tensorflow models for seismic phase detection. Please see how to use these models here: https://github.com/NorwegianSeismicArray/tphasenet</p> <p>The HDF5 files includes waveforms and labels which are part of the training data set (only NORSAR event catalogue and station ARA0).</p>
Global Physically-Constrained Deep Learning Water Cycle Model with Vegetation: Model Simulations
<p>Welcome to our repository, which features simulations from the Hybrid Hydrological Model with Vegetation (H2MV). This collection includes 11 NetCDF files, representing temporal model simulations on a monthly scale and the static output of maximum soil moisture capacity (also known as plant rooting water storage) derived from a 10-fold cross-validation (CV) setup:</p> <ul> <li><strong>Temporal Simulations</strong>: The files named "fold1.nc" through "fold10.nc" contain the temporal model simulations, aggregated to a monthly scale, from 10 fold cross-validation (CV) setup.</li> <li><strong>Static Output</strong>: The "sm_max.nc" file presents the H2MV's estimation of the maximum soil moisture capacity</li> </ul> <h3>Contents of the Temporal Simulation Files</h3> <p>Each of the "fold" files ("fold1.nc" to "fold10.nc") contains the following variables:</p> <ul> <li><strong>Snow Dynamics</strong> <ul> <li><span><code>snow_acc</code></span>: Snow accumulation (mm/day)</li> <li><span><code>snow_melt</code></span>: Snow melt (mm/day)</li> <li><span><code>swe</code></span>: Snow water equivalent (mm)</li> </ul> </li> <li><strong>Evapotranspiration and its components</strong> <ul> <li><span><code>Ei</code></span>: Interception evaporation (mm/day)</li> <li><span><code>Es</code></span>: Soil evaporation (mm/day)</li> <li><span><code>T</code></span>: Transpiration (mm/day)</li> <li><span><code>ET</code></span>: Evapotranspiration (mm/day)</li> </ul> </li> <li><strong>Recharge</strong> <ul> <li><span><code>r_soil</code></span>: Soil recharge (mm/day)</li> <li><span><code>r_gw</code></span>: Groundwater recharge (mm/day)</li> </ul> </li> <li><strong>Runoff</strong> <ul> <li><span><code>runoff_surface</code></span>: Surface runoff (mm/day)</li> <li><span><code>baseflow</code></span>: Baseflow (mm/day)</li> <li><span><code>runoff_total</code></span>: Total runoff (mm/day)</li> </ul> </li> <li><strong>Water Storages </strong> <ul> <li><span><code>GW</code></span>: Groundwater (mm)</li> <li><span><code>SM</code></span>: Soil moisture (mm)</li> <li><span><code>tws</code></span>: Terrestrial water storage (mm)</li> <li><span><code>tws_anomaly</code></span>: Anomalies of terrestrial water storage (mm)</li> </ul> </li> <li><strong>Vegetation</strong> <ul> <li><span><code>fapar</code></span>: Fraction of absorbed photosynthetically active radiation (-)</li> </ul> </li> </ul> <h3>Contents of the Static Output File</h3> <p>The "sm_max.nc" file contains 10 variables corresponding to the 10 folds of CV, with each variable (e.g., "fold1") referring to the respective fold.</p> <h3>Additional Information</h3> <p>It's important to note that the original model simulations were conducted with a daily temporal resolution, but the data shared here have been aggregated to a monthly scale. We are open to sharing the original daily simulations and additional variables not included in this repository upon request. Please feel free to reach out to us for more information or data requests.</p>
Benchmarking Study of Deep Generative Models for Inverse Polymer Design: Reinforcement Learning
<p>Well-trained models and generation results for reinforcement learning part of <a href="https://github.com/ytl0410/Polymer-Generative-Models-Benchmark">ytl0410/Polymer-Generative-Models-Benchmark: Well-trained models and generative outcomes for the paper "Benchmarking Study of Deep Generative Models for Inverse Polymer Design" (github.com)</a></p>
Codes, Catalogues and Data for "Deep Learning Phase Pickers: How Well Can Existing Models Detect Hydraulic-Fracturing Induced Seismicity from a Downhole Array"
<p><strong>Codes, Catalogues and Data available for:</strong> <br>"Deep Learning Phase Pickers: How Well Can Existing Models Detect Hydraulic-Fracturing Induced Seismicity from a Downhole Array"</p> <p><strong>Catalog</strong> folder: Contains the CMM (beam-forming based) event catalogue as well as event and station information for the PNR-1z site.</p> <p><strong>Classification Test</strong> folder: Jupyter notebooks that run the classification tests and mseed input data of isolated phases (P, S, Noise).</p> <p><strong>DL_model_catalogues</strong> folder: Contains full catalogues for each DL phase picker (GPD, U-GPD, EQT and PhaseNet) and the LinMEF-filtered catalogues.</p> <p><strong>Model_run_docs</strong> folder: Util/core files for PhaseNet and EQTransformer to read data with different sampling frequencies (i.e., not 100 Hz)</p> <p><strong>Data</strong> folder: Contains one hour of continuous downhole data (11th December 2018, 9am-10am) from the PNR-1z dataset.</p>
Jingju a cappella singing voice test dataset for "An efficient deep learning model for musical onset detection"
<p>Jingju a cappella singing voice test dataset used in the paper "An efficient deep learning model for musical onset detection".</p> <p>Arxiv paper link: <a href="https://arxiv.org/abs/1806.06773">https://arxiv.org/abs/1806.06773</a></p> <p>Supplementary information and code for the paper: <a href="https://github.com/ronggong/musical-onset-efficient">https://github.com/ronggong/musical-onset-efficient</a></p> <p><strong>Content:</strong></p> <ol> <li>ismir_2018_dataset_for_reviewing.zip: audio, syllable boundary and label annotation</li> <li>jingju dataset train test split filenames.xlsx: train and test split filename list</li> </ol> <p><strong>Citation:</strong></p> <pre>@article{gong2018towards, title={Towards an efficient deep learning model for musical onset detection}, author={Gong, Rong and Serra, Xavier}, journal={arXiv preprint arXiv:1806.06773}, year={2018} } </pre> <p><strong>Contact:</strong></p> <p>Rong Gong: rong.gong<at>upf.edu</p>
Surrogate Model Optimisation of a 'micro core' PWR fuel assembly arrangement using deep learning models - Figures
<p>Figures for Physior 2020 paper</p>
Saved model and preprocessed data for "CRMnet:a deep learning model for predicting gene expression from large regulatory sequence datasets"
<p>Saved TUNet model and preprocessed training data for "CRMnet: a deep learning model for predicting gene expression from large regulatory sequence datasets"</p> <p>To load the trained model:</p> <pre><code class="language-python">import tensorflow as tf tf.keras.models.load_model("path to the model folder")</code></pre> <p>for more information please find our repository: https://github.com/jiayuwen/CRMnet</p>
Pretrained models and results for "Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model"
<p>This dataset contains the pretrained model weights and precomputed results for the paper "Thunderstorm nowcasting with deep learning: a multi-hazard data fusion model" submitted to <em>Geophysical Research Letters</em>. A preprint of the paper can be found at <a href="https://arxiv.org/abs/2211.01001">https://arxiv.org/abs/2211.01001</a>.</p> <p>The ML code can be found at <a href="https://github.com/MeteoSwiss/c4dl-multi">https://github.com/MeteoSwiss/c4dl-multi</a>. Download all the files here and extract the contents to the following subdirectories in the ML code directory:</p> <ul> <li>Results (<a href="https://zenodo.org/api/files/d4829f50-55fd-4d86-b875-7f2b91dba74f/c4dl-results-lightningdl.zip?versionId=54046830-4c7e-48c6-af42-d6d5606af86b">c4dl-results-lightningdl.zip</a>) -> results/</li> <li>Pretrained models (<a href="https://zenodo.org/api/files/d4829f50-55fd-4d86-b875-7f2b91dba74f/c4dl-models-lightningdl.zip?versionId=364bca7c-e6ad-4ed9-9264-57c759ea0ac6">c4dl-models-lightningdl.zip</a>) -> models/</li> <li>If you want to train models, data (<a href="https://zenodo.org/api/files/0cfc0cf4-755a-4618-8341-39b107a3901c/c4dl-patches-2020-additional.zip">c4dl-patches-2020-additional.zip</a>) -> data/2020/</li> </ul> <p>Additionally, you will need the datasets from <a href="https://zenodo.org/deposit/6802292">this Zenodo archive</a>. Follow the instructions there for downloading.</p>
Integration of a deep-learning-based fire model into a global land surface model
<p>JSBACH4+DL-fire simulation results & their comparison (DL-fire, JSB4-DL-fire, JSB4-simple)</p>
Deep Learning Regional Climate Model Emulators: a comparison of two downscaling training frameworks [datasets]
<p>Outputs used in:</p> <p><em>van der Meer, M., de Roda Husman, S., Lhermitte, S.: </em>Deep Learning Regional Climate Model Emulators: a comparison of two downscaling training frameworks</p> <ul> <li>MAR(ACCESS1-3)_monthly_SMB.nc: MAR outputs with monthly values of SMB and components over the Antarctic ice sheet (1980--2100)</li> <li>MAR(ACCESS1-3)-stereographic_monthly_GCM_like.nc: MAR outputs upscaled to GCM resolution (1980--2100)</li> <li>ACCESS1-3-stereographic_monthly_cleaned.nc: GCM monthly outputs over the Antarctic ice sheet (1980--2100)</li> </ul> <p>The up-to-date working versions of our experiments and source code can be found and are available on our GitHub: <a href="https://github.com/marvande/RCM-Emulator">https://github.com/marvande/RCM-Emulator</a> and at this link: <a href="https://doi.org/10.5281/zenodo.7875967">https://doi.org/10.5281/zenodo.7875967</a></p> <p>Data usage notice:</p> <p>If you use any of these results, please acknowledge the work of the people involved in producing them. You should also refer to and cite the following paper:</p> <p><strong>Cite as: </strong>Marijn van der Meer, Sophie de Roda Husman, S Lhermitte. Deep Learning Regional Climate Model Emulators: a comparison of two downscaling training frameworks. <em>Authorea.</em> December 27, 2022 <br> DOI: <a href="https://doi.org/10.22541/essoar.167214210.02213149/v1">10.22541/essoar.167214210.02213149/v1</a> </p>
Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP
<p>Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often considered a "black box" that lacks transparency and interpretability. In this project, we explore the use of LIME and SHAP, two popular explainable AI techniques, to generate local and global explanations for a deep learning model based on InceptionV3 architecture trained on retinoblastoma and non-retinoblastoma fundus images. We collected and labeled a dataset of 400 retinoblastoma and 400 non-retinoblastoma images, split it into training, validation, and test sets, and trained the model using transfer learning from the pre-trained InceptionV3 model. We then applied LIME and SHAP to generate explanations for the model's predictions on the validation and test sets. Our results demonstrate that LIME and SHAP can effectively identify the regions and features in the input images that contribute the most to the model's predictions, providing valuable insights into the decision-making process of the deep learning model. In addition, the use of InceptionV3 architecture with spatial attention mechanism achieved high accuracy of 97\% on the test set, indicating the potential of combining deep learning and explainable AI for improving retinoblastoma diagnosis and treatment.</p>
STL files: Modeling and design of heterogeneous hierarchical bioinspired spider web structures using deep learning and additive manufacturing
<p>STL files for paper titled modeling and design of heterogeneous hierarchical bioinspired spider web structures using deep learning and additive manufacturing</p>
Synergy between deep learning and numerical modeling in estimating NOx emissions at a fine spatiotemporal resolution
<p>This study focused on the remarkable applicability of deep learning (DL) together with numerical modeling in estimating NO<sub>x</sub> emissions at a fine spatiotemporal resolution in the summer of 2017 over the contiguous United States (CONUS). We leveraged the partial convolutional neural network (PCNN) and the deep neural network (DNN) to impute gaps in the OMI tropospheric NO<sub>2</sub> column and estimate the daily complete surface NO<sub>2</sub> map at a spatial resolution of 10 km × 10 km, showing high capability with a strong correspondence (R: 0.92, IOA: 0.96, MAE: 1.43). We then used the Community Multi-scale Air Quality (CMAQ) model at 12 km grid spacing to conduct an inversion of NO<sub>x</sub> emissions that allowed us to promote a comprehensive understanding of the chemical evolution. Compared to the prior emissions, the inversion suggested 3.21 ± 3.34 times higher NO<sub>x</sub> emissions over CONUS, significantly mitigating the underestimation of surface NO<sub>2</sub> concentrations with the prior emissions. The results displayed the primary benefits of incorporating DL-estimated daily complete surface NO<sub>2</sub> map, which in turn greatly reduced bias (-1.53 ppb to 0.26 ppb) and enhanced daily variability with higher correspondence (0.84 to 0.92) and lower error (0.48 ppb to 0.10 ppb) over the CONUS. </p>
PIGNet2: A versatile deep learning-based protein-ligand interaction prediction model for accurate binding affinity scoring and virtual screening
<p>Training and test datasets of the paper "Improving the versatility of deep learning-based protein-ligand interaction prediction for accurate binding affinity scoring and virtual screening".</p>
High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia Part 8
<p>Future projections of precipitation by the BM10 model forced by the seven GCMs used in the GMD paper "High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia".</p>
High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia Part 5
<p>Future projections of precipitation by the BM1 model forced by the seven GCMs used in the GMD paper "High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia".</p>
High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia Part 3
<p>Future projections of 2-meter minimum temperature by the CNN models (BM1, BM10 and BMdense) forced by the seven GCMs used in the GMD paper "High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia".</p>
High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia Part 2
<p>Future projections of 2-meter maximum temperature by the CNN models (BM1, BM10 and BMdense) forced by the seven GCMs used in the GMD paper "High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia".</p>
High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia Part 11
<p>Future projections of 2-meter maximum, mean and minimum temperatures by the BMlinear model forced by the seven GCMs used in the GMD paper "High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia".</p>
High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia Part 1
<p>Input data (ERA5 and the seven GCMs) used to train the CNN models (BMlinear, BM1, BM10 and BMdense) used in the GMD paper "High resolution downscaling of CMIP6 Earth System and Global Climate Models using deep learning for Iberia".</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.