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.
921
datasets available to search
ShareScore release 0.7.1
Dataset results
921 results for “neural networks”
Deep convolutional neural network for owl vocal identification
<p>This repository contains all the code and data necessary to replicate the results presented in Ruff et al. 2019, "Automated identification of avian vocalizations with deep convolutional neural networks", and is published in support of that manuscript. The folder includes several Python scripts, our trained convolutional neural network (CNN), and a set of 164,210 spectrogram images that were reviewed to generate CNN performance metrics. We include the CNN's predicted class scores for the test images as well as the set of labels assigned to the same images by experienced human technicians. The published article can be found here: <a href="https://zslpublications.onlinelibrary.wiley.com/doi/full/10.1002/rse2.125">https://zslpublications.onlinelibrary.wiley.com/doi/full/10.1002/rse2.125</a></p> <p>As presented, the CNN is designed to accept grayscale PNG images at 500x129 resolution and will generate a set of seven class scores for each image. Class scores are the softmax activation from the final (seven unit) fully-connected layer of the CNN. Scores are bounded between 0 and 1 and sum to 1 for each image. This means target classes are implicitly treated as mutually exclusive (i.e., each image belongs to exactly one class), although in reality some images contain calls from >1 target species.</p> <p>The different scripts and their functions are as follows:<br> - Code used to construct and train the CNN is in Owl_CNN_train_model.py<br> - Code to generate spectrograms with randomized parameters based on tagged calls in audio files is in Owl_CNN_generate_training_data.py<br> - Code to generate random spectrograms from a set of audio files (used to generate training data for the Noise class) can be generated with Owl_CNN_make_noise_data.py<br> - Code used to process raw audio files, including segmenting them into 12 s clips, generating spectrograms, and generating class scores using a pre-trained CNN is in Owl_CNN_process_audio.py<br> - Code to generate class scores for an existing set of spectrogram images using a pre-trained CNN are in Owl_CNN_process_images.py</p> <p>Our seven target classes are as follows:<br> AEAC - Northern saw-whet owl, Aegolius acadicus.<br> BUVI - Great horned owl, Bubo virginianus.<br> GLGN - Northern pygmy-owl, Glaucidium gnoma.<br> MEKE - Western screech-owl, Megascops kennicottii.<br> STOC - (Northern) spotted owl, Strix occidentalis caurina.<br> STVA - Barred owl, Strix varia.<br> Noise - Catch-all for any clip that did not contain vocalizations of at least one of the six owl species listed above.</p> <p>The CNN was trained for 100 epochs and saved only after epochs in which validation loss improved. Loss was measured as categorical cross-entropy. The CNN was last saved at epoch 97 with reported metrics:<br> Training loss = 0.218<br> Training accuracy = 0.972<br> Validation loss = 0.165<br> Validation accuracy = 0.987</p> <p>Although this code has been tested and works on our system, we make no guarantee that it will work for others without modification. Created using Python version 2.7.14, TensorFlow version 1.2.1, Keras version 2.2, and SoX version 14.4. Code was developed by Bharath Padmaraju, Zack Ruff, and Chris Sullivan. Questions and comments may be directed to zjruff at gmail dot com.</p> <p>Zack Ruff<br> 15 July 2019</p>
A neural network-based estimate of the seasonal variability of total alkalinity in the East China Sea shelf
<p>In order to estimate the seasonal variability of total alkalinity in the ECS shelf, an artificial neural network (ANN) model was developed using 5 cruise datasets from 2008 to 2018. The model used temperature, salinity, and dissolved oxygen to estimate A<sub>T</sub> with a root-mean-square error of ~7 umol kg<sup>-1</sup>, and was applied to fill missing alkalinity data for 8 cruises during 2013-2016. In addition, monthly water column A<sub>T</sub> for the period 2000-2016 was also obtained passing temperature, salinity, and dissolved oxygen from the Changjiang Biology Finite-Volume Coastal Ocean Model (FVCOM) Data. Spatial distributions, seasonal cycles and correlations of surface A<sub>T</sub> indicated that the seasonal fluctuation of the Changjiang River discharge is the major factor affecting seasonal variation of surface total alkalinity in the ECS shelf. The largest seasonal fluctuation of surface total alkalinity was found on the inner shelf near the Changjiang Estuary.</p>
Retrieving monthly and interannual pHT in the East China Sea shelf using an artificial neural network: ANN-pHT-v1
<p><br> The reliability of the artificial neural network model was evaluated by independent sampled data from 3 cruises in 2018.</p> <p>Monthly water column pHT for the period 2000-2016 was obtained passing T, S, DO, N, P, and Si from the Finite-Volume Coastal Ocean Model with the European Regional Sea Ecosystem Model through the artificial neural network. The spatiotemporal resolution of monthly pHT is 1-10 km in the horizontal, 10 depth levels in the vertical, and 12 months. Seasonal pHT dynamics in the East China Sea shelf can be primarily attributed to temperature changes and the shifting balance of production and respiration processes.</p>
Channel State Information (CSI) analysis for predictive maintenance using Convolutional Neural Network (CNN)
<p>Dataset manual:</p> <p>This dataset contains CSI amplitude values for rotating motors in an office environment. Details of the experiments may be found in the corresponding paper published in the DATA'19 workshop, SenSys (<a href="https://doi.org/10.1145/3359427.3361917">https://doi.org/10.1145/3359427.3361917</a>). </p> <p>Folder structure:<br> The folders for servo motor and stepper motor contains separate folders for network reconnection conditions (w_recc: with reconnections, wo_recc: without recconnections) and load conditions (w_load: with load and wo_load: without load). The data is stores as Matlab files with .mat extentions. </p> <p>File structure:<br> In each file name, the digits after the '_' at the end of the file name correspond to the speed of the motor. In case of stepper motor these numbers could be directly interpreted as rpm. Ex: table_inj_with_load_5_0.mat corresponds to stationary motor (0 rpm) and table_inj_with_load_5_250.mat corresponds to motor rotating with 250 rpm speed. In the case of servo motor these numbers should be mapped with the following table in order to get the speeds.</p> <p>0: 0 rpm<br> 50: 14.45 rpm<br> 100: 8.02 rpm<br> 150: 5.38 rpm<br> 200: 4.05 rpm<br> 250: 3.26 rpm<br> 300: 2.67 rpm<br> Ex: table_inj_with_load_50.mat corresponds to motor running with 14.45 rpm.</p> <p>Each file has 3 columns, each corresponding to CSI value, labels (speed/last digits in the file name) and the data sample number (not in sequence as a result of packer loss) respectively. CSI values are typically a matrix of size 3000*180 (3000 CSI samples for 3sec data @1kHz sampling rate and 180 channels for 6 antenna pairs @ 30 subcarrier data per antenna).</p>
Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation [Models]
<p>This file contains the pretrained models and the evaluation of the pipelines described in the paper <em>Convolutional Neural Networks for Classification of Alzheimer’s Disease: Overview and Reproducible Evaluation</em>.</p> <p>Source code can be downloaded at: <a href="https://github.com/aramis-lab/AD-DL">https://github.com/aramis-lab/AD-DL</a></p> <p>Also, single files can be obtained at: <a href="https://aramislab.paris.inria.fr/clinicadl/files/models/v0.0.1/">https://aramislab.paris.inria.fr/clinicadl/files/models/v0.0.1/</a></p> <p>The structure of the compressed file is as follows:</p> <p>clinicadl_models/<br> ├── 2D_slice<br> │ ├── baseline<br> │ │ ├── AD_CN<br> │ │ │ ├── best_model<br> │ │ │ └── performances<br> │ │ └── AD_CN_dataleakage<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── longitudinal<br> │ └── AD_CN<br> │ ├── best_model<br> │ └── performances<br> ├── 3D_patch<br> │ ├── baseline<br> │ │ ├── AD_CN<br> │ │ │ ├── best_model<br> │ │ │ └── performances<br> │ │ └── sMCI_pMCI<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── longitudinal<br> │ ├── AD_CN<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── sMCI_pMCI<br> │ ├── best_model<br> │ └── performances<br> ├── 3D_ROI_based<br> │ ├── baseline<br> │ │ ├── AD_CN<br> │ │ │ ├── best_model<br> │ │ │ └── performances<br> │ │ └── sMCI_pMCI<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── longitudinal<br> │ ├── AD_CN<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── sMCI_pMCI<br> │ ├── best_model<br> │ └── performances<br> ├── 3D_subject<br> │ ├── baseline<br> │ │ ├── AD_CN<br> │ │ │ ├── best_model<br> │ │ │ └── performances<br> │ │ └── sMCI_pMCI<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── longitudinal<br> │ ├── AD_CN<br> │ │ ├── best_model<br> │ │ └── performances<br> │ └── sMCI_pMCI<br> │ ├── best_model<br> │ └── performances<br> ├── autoencoders<br> │ ├── 3D_patch<br> │ │ ├── baseline<br> │ │ │ └── best_model<br> │ │ └── longitudinal<br> │ │ └── best_model<br> │ ├── 3D_ROI_based<br> │ │ ├── baseline<br> │ │ │ └── best_model<br> │ │ └── longitudinal<br> │ │ └── best_model<br> │ └── 3D_subject<br> │ └── baseline<br> │ ├── extensive<br> │ └── minimal<br> └── svm<br> ├── baseline<br> │ ├── AD_CN<br> │ │ ├── all_subjects.tsv<br> │ │ └── classifier<br> │ └── sMCI_pMCI<br> │ ├── all_subjects.tsv<br> │ └── classifier<br> └── longitudinal<br> ├── AD_CN<br> │ ├── all_subjects.tsv<br> │ └── classifier<br> └── sMCI_pMCI<br> ├── all_subjects.tsv<br> └── classifier</p> <p>We provide the pretrained CNN models for the frameworks 3D subject-level, 3D ROI-based, 3D patch-level and 2D slice-level. This models can be found as a <strong><em>.pth.tar</em> </strong>file (<em>Pytorch</em> format) inside the <em>best_model</em> folder for each framework (and for each fold). We also provide the autoencoders that initialize the training stage of the CNN networks. The <em>performances </em>folder contains the computed metrics for the correponding model (ACC, BA, etc). <em> </em></p> <p>For the svn classification, we provide files with the dual coefficients, the support vector indices and the weights. Also, <em>tsv</em> files with the subject list.</p>
Data for the prediction of chatter vibrations in robotic milling of aluminium parts based on previous experiences using neural network
<p>This data has been used for the validation of the software developed by DFKI in collaboration with IDEKO for the prediction of stability in robotic milling of aluminium parts, in the framework of COROMA research project funded by the European Union. www.coroma-project.eu</p> <p>The source of information is stability lobes obtained from FRFs obtained mixing by receptance coupling experimental FRFs of the robot, spindle and toolholder with FRFs of the tool obtained analitycally using beams theory. Real machinings have not been done since they would be very time consuming. Once the stability lobes where available random sampling has been done in the lobes between certain boundaries of axial depth of cut and spindle speed to represent machining with different conditions.</p> <p>The information contained here includes:</p> <p>- Data sets for different conditions, with tools of different diameters and different number of cutting teeth. (in the naming of the folder D represents diameter, Z represents number of teeth).</p> <p>- Most of the data sets also include figures with the milling stability lobe charts for different radial depths of cut and different diameters and number of teeth. In these figures the random sampling representing machining tests has been marked with a black X.</p> <p>- There are also versions of the data sets with different number of samples (20 or 40) in order to test the prediction algorithm with a different number of information.</p> <p>- In the data sets an extended version has been created, representing the know-how of the operator that if a machining is unstable all the machinings with higher axial depth of cut will be unstable, and if a machining is stable all the machinings with lower axial depth of cut will be stable.</p> <p>- Companion documents in PDF format in order to provide more detailed information on the datasets and results.</p> <p>Keywords: Milling, machining, vibration, chatter, stability, prediction, neural network, robot, robotic, AI, artificial intelligence.</p> <p>www.ideko.es<br> www.dfki.de</p> <p>Asier Barrios<br> IDEKO research centre<br> Arriaga Kalea, 2<br> Elgoibar 20870, Spain<br> Phone: +34 943748000<br> abarrios@ideko.es</p> <p>October 2019</p>
Dataset for supervised learning with a deep neural network to assess azimuthal localisation in sound field synthesis
<p>Dataset for supervised learning with a deep neural network to assess azimuthal localisation in sound field synthesis.<br> Released as part of the Master Thesis 'An Auditory Model for Azimuthal Localisation in Sound Field Synthesis'.</p> <p>This database is calculated from the data of listening experiments.</p>
Data for: Redshift Prediction with Images for Cosmology using a Bayesian Convolutional Neural Network with Conformal Predictions
<p>These files contain the predictions from the CNN and BCNN model from the paper titled: "Redshift Prediction with Images for Cosmology using a Bayesian Convolutional Neural Network with Conformal Predictions" (Jones et al. 2024). These files will allow reproduction of the performance metrics described in the paper.</p> <p> </p> <p>full_prediction_set_CNN.csv - predictions for the redshift using the CNN model of the entire dataset<br>cnn_evaluation.csv - predictions from just the evaluation dataset that was not used in training</p> <p>Columns are:</p> <p>photoz - predicted photoz from the model<br>specz - spectroscopic redshift<br>objectid - object ID from HSC PDR2 data release (Aihara et al. 2019)</p> <p><br>full_prediction_set_BCNN.csv - predictions for the redshift using the BCNN model of the entire dataset<br>bcnn_evaluation.csv - predictions from just the evaluation dataset that was not used in training</p> <p>Columns are:</p> <p>photoz - predicted photoz from the model<br>specz - spectroscopic redshift<br>objectid - object ID from HSC PDR2 data release (Aihara et al. 2019)<br>photoz_uncertainty - uncertainty in the predicted photoz</p>
Part 2 of real-time testing data for: "Identifying data sources and physical strategies used by neural networks to predict TC rapid intensification"
<p>Each file in the dataset contains machine-learning-ready data for one unique tropical cyclone (TC) from the real-time testing dataset. "Machine-learning-ready" means that all data-processing methods described in the journal paper have already been applied. This includes cropping satellite images to make them TC-centered; rotating satellite images to align them with TC motion (TC motion is always towards the +x-direction, or in the direction of increasing column number); flipping satellite images in the southern hemisphere upside-down; and normalizing data via the two-step procedure.</p> <p>The file name gives you the unique identifier of the TC -- e.g., "learning_examples_2010AL01.nc.gz" contains data for storm 2010AL01, or the first North Atlantic storm of the 2010 season. Each file can be read with the method `example_io.read_file` in the ml4tc Python library (https://zenodo.org/doi/10.5281/zenodo.10268620). However, since `example_io.read_file` is a lightweight wrapper for `xarray.open_dataset`, you can equivalently just use `xarray.open_dataset`. Variables in the table are listed below (the same printout produced by `print(xarray_table)`):</p> <p>Dimensions: (<br> satellite_valid_time_unix_sec: 289,<br> satellite_grid_row: 380,<br> satellite_grid_column: 540,<br> satellite_predictor_name_gridded: 1,<br> satellite_predictor_name_ungridded: 16,<br> ships_valid_time_unix_sec: 19,<br> ships_storm_object_index: 19,<br> ships_forecast_hour: 23,<br> ships_intensity_threshold_m_s01: 21,<br> ships_lag_time_hours: 5,<br> ships_predictor_name_lagged: 17,<br> ships_predictor_name_forecast: 129)<br>Coordinates:<br> * satellite_grid_row (satellite_grid_row) int32 2kB ...<br> * satellite_grid_column (satellite_grid_column) int32 2kB ...<br> * satellite_valid_time_unix_sec (satellite_valid_time_unix_sec) int32 1kB ...<br> * ships_lag_time_hours (ships_lag_time_hours) float64 40B ...<br> * ships_intensity_threshold_m_s01 (ships_intensity_threshold_m_s01) float64 168B ...<br> * ships_forecast_hour (ships_forecast_hour) int32 92B ...<br> * satellite_predictor_name_gridded (satellite_predictor_name_gridded) object 8B ...<br> * satellite_predictor_name_ungridded (satellite_predictor_name_ungridded) object 128B ...<br> * ships_valid_time_unix_sec (ships_valid_time_unix_sec) int32 76B ...<br> * ships_predictor_name_lagged (ships_predictor_name_lagged) object 136B ...<br> * ships_predictor_name_forecast (ships_predictor_name_forecast) object 1kB ...<br>Dimensions without coordinates: ships_storm_object_index<br>Data variables:<br> satellite_number (satellite_valid_time_unix_sec) int32 1kB ...<br> satellite_band_number (satellite_valid_time_unix_sec) int32 1kB ...<br> satellite_band_wavelength_micrometres (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_longitude_deg_e (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_cyclone_id_string (satellite_valid_time_unix_sec) |S8 2kB ...<br> satellite_storm_type_string (satellite_valid_time_unix_sec) |S2 578B ...<br> satellite_storm_name (satellite_valid_time_unix_sec) |S10 3kB ...<br> satellite_storm_latitude_deg_n (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_longitude_deg_e (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_intensity_number (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_u_motion_m_s01 (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_v_motion_m_s01 (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_predictors_gridded (satellite_valid_time_unix_sec, satellite_grid_row, satellite_grid_column, satellite_predictor_name_gridded) float64 474MB ...<br> satellite_grid_latitude_deg_n (satellite_valid_time_unix_sec, satellite_grid_row, satellite_grid_column) float64 474MB ...<br> satellite_grid_longitude_deg_e (satellite_valid_time_unix_sec, satellite_grid_row, satellite_grid_column) float64 474MB ...<br> satellite_predictors_ungridded (satellite_valid_time_unix_sec, satellite_predictor_name_ungridded) float64 37kB ...<br> ships_storm_intensity_m_s01 (ships_valid_time_unix_sec) float64 152B ...<br> ships_storm_type_enum (ships_storm_object_index, ships_forecast_hour) int32 2kB ...<br> ships_forecast_latitude_deg_n (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_forecast_longitude_deg_e (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_v_wind_200mb_0to500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_vorticity_850mb_0to1000km_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_vortex_latitude_deg_n (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_vortex_longitude_deg_e (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_850mb_0to600km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_max_tangential_wind_850mb_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_1000mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_850mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_500mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_300mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_srh_1000to700mb_200to800km_j_kg01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_srh_1000to500mb_200to800km_j_kg01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_threshold_exceedance_num_6hour_periods (ships_storm_object_index, ships_intensity_threshold_m_s01) int32 2kB ...<br> ships_v_motion_observed_m_s01 (ships_storm_object_index) float64 152B ...<br> ships_v_motion_1000to100mb_flow_m_s01 (ships_storm_object_index) float64 152B ...<br> ships_v_motion_optimal_flow_m_s01 (ships_storm_object_index) float64 152B ...<br> ships_cyclone_id_string (ships_storm_object_index) object 152B ...<br> ships_storm_latitude_deg_n (ships_storm_object_index) float64 152B ...<br> ships_storm_longitude_deg_e (ships_storm_object_index) float64 152B ...<br> ships_predictors_lagged (ships_valid_time_unix_sec, ships_lag_time_hours, ships_predictor_name_lagged) float64 13kB ...<br> ships_predictors_forecast (ships_valid_time_unix_sec, ships_forecast_hour, ships_predictor_name_forecast) float64 451kB ...</p> <p>Variable names are meant to be as self-explanatory as possible. Potentially confusing ones are listed below.</p> <ul> <li>The dimension ships_storm_object_index is redundant with the dimension ships_valid_time_unix_sec and can be ignored.</li> <li>ships_forecast_hour ranges up to values that we do not actually use in the paper. Keep in mind that our max forecast hour used in machine learning is 24.</li> <li>The dimension ships_intensity_threshold_m_s01 (and any variable including this dimension) can be ignored.</li> <li>ships_lag_time_hours corresponds to lag times for the SHIPS satellite-based predictors. The only lag time we use in machine learning is "NaN", which is a stand-in for the best available of all lag times. See the discussion of the "priority list" in the paper for more details.</li> <li>Most of the data variables can be ignored, unless you're doing a deep dive into storm properties. The important variables are satellite_predictors_gridded (full satellite images), ships_predictors_lagged (satellite-based SHIPS predictors), and ships_predictors_forecast (environmental and storm-history-based SHIPS predictors). These variables are all discussed in the paper.</li> <li>Every variable name (including elements of the coordinate lists ships_predictor_name_lagged and ships_predictor_name_forecast) includes units at the end. For example, "m_s01" = metres per second; "deg_n" = degrees north; "deg_e" = degrees east; "j_kg01" = Joules per kilogram; ...; etc.</li> </ul>
Real-time testing data for: "Identifying data sources and physical strategies used by neural networks to predict TC rapid intensification"
<p>Each file in the dataset contains machine-learning-ready data for one unique tropical cyclone (TC) from the real-time testing dataset. "Machine-learning-ready" means that all data-processing methods described in the journal paper have already been applied. This includes cropping satellite images to make them TC-centered; rotating satellite images to align them with TC motion (TC motion is always towards the +x-direction, or in the direction of increasing column number); flipping satellite images in the southern hemisphere upside-down; and normalizing data via the two-step procedure.</p> <p>The file name gives you the unique identifier of the TC -- e.g., "learning_examples_2010AL01.nc.gz" contains data for storm 2010AL01, or the first North Atlantic storm of the 2010 season. Each file can be read with the method `example_io.read_file` in the ml4tc Python library (https://zenodo.org/doi/10.5281/zenodo.10268620). However, since `example_io.read_file` is a lightweight wrapper for `xarray.open_dataset`, you can equivalently just use `xarray.open_dataset`. Variables in the table are listed below (the same printout produced by `print(xarray_table)`):</p> <p>Dimensions: (<br> satellite_valid_time_unix_sec: 289,<br> satellite_grid_row: 380,<br> satellite_grid_column: 540,<br> satellite_predictor_name_gridded: 1,<br> satellite_predictor_name_ungridded: 16,<br> ships_valid_time_unix_sec: 19,<br> ships_storm_object_index: 19,<br> ships_forecast_hour: 23,<br> ships_intensity_threshold_m_s01: 21,<br> ships_lag_time_hours: 5,<br> ships_predictor_name_lagged: 17,<br> ships_predictor_name_forecast: 129)<br>Coordinates:<br> * satellite_grid_row (satellite_grid_row) int32 2kB ...<br> * satellite_grid_column (satellite_grid_column) int32 2kB ...<br> * satellite_valid_time_unix_sec (satellite_valid_time_unix_sec) int32 1kB ...<br> * ships_lag_time_hours (ships_lag_time_hours) float64 40B ...<br> * ships_intensity_threshold_m_s01 (ships_intensity_threshold_m_s01) float64 168B ...<br> * ships_forecast_hour (ships_forecast_hour) int32 92B ...<br> * satellite_predictor_name_gridded (satellite_predictor_name_gridded) object 8B ...<br> * satellite_predictor_name_ungridded (satellite_predictor_name_ungridded) object 128B ...<br> * ships_valid_time_unix_sec (ships_valid_time_unix_sec) int32 76B ...<br> * ships_predictor_name_lagged (ships_predictor_name_lagged) object 136B ...<br> * ships_predictor_name_forecast (ships_predictor_name_forecast) object 1kB ...<br>Dimensions without coordinates: ships_storm_object_index<br>Data variables:<br> satellite_number (satellite_valid_time_unix_sec) int32 1kB ...<br> satellite_band_number (satellite_valid_time_unix_sec) int32 1kB ...<br> satellite_band_wavelength_micrometres (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_longitude_deg_e (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_cyclone_id_string (satellite_valid_time_unix_sec) |S8 2kB ...<br> satellite_storm_type_string (satellite_valid_time_unix_sec) |S2 578B ...<br> satellite_storm_name (satellite_valid_time_unix_sec) |S10 3kB ...<br> satellite_storm_latitude_deg_n (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_longitude_deg_e (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_intensity_number (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_u_motion_m_s01 (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_storm_v_motion_m_s01 (satellite_valid_time_unix_sec) float64 2kB ...<br> satellite_predictors_gridded (satellite_valid_time_unix_sec, satellite_grid_row, satellite_grid_column, satellite_predictor_name_gridded) float64 474MB ...<br> satellite_grid_latitude_deg_n (satellite_valid_time_unix_sec, satellite_grid_row, satellite_grid_column) float64 474MB ...<br> satellite_grid_longitude_deg_e (satellite_valid_time_unix_sec, satellite_grid_row, satellite_grid_column) float64 474MB ...<br> satellite_predictors_ungridded (satellite_valid_time_unix_sec, satellite_predictor_name_ungridded) float64 37kB ...<br> ships_storm_intensity_m_s01 (ships_valid_time_unix_sec) float64 152B ...<br> ships_storm_type_enum (ships_storm_object_index, ships_forecast_hour) int32 2kB ...<br> ships_forecast_latitude_deg_n (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_forecast_longitude_deg_e (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_v_wind_200mb_0to500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_vorticity_850mb_0to1000km_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_vortex_latitude_deg_n (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_vortex_longitude_deg_e (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_850mb_0to600km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_max_tangential_wind_850mb_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_1000mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_850mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_500mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_mean_tangential_wind_300mb_at500km_m_s01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_srh_1000to700mb_200to800km_j_kg01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_srh_1000to500mb_200to800km_j_kg01 (ships_storm_object_index, ships_forecast_hour) float64 3kB ...<br> ships_threshold_exceedance_num_6hour_periods (ships_storm_object_index, ships_intensity_threshold_m_s01) int32 2kB ...<br> ships_v_motion_observed_m_s01 (ships_storm_object_index) float64 152B ...<br> ships_v_motion_1000to100mb_flow_m_s01 (ships_storm_object_index) float64 152B ...<br> ships_v_motion_optimal_flow_m_s01 (ships_storm_object_index) float64 152B ...<br> ships_cyclone_id_string (ships_storm_object_index) object 152B ...<br> ships_storm_latitude_deg_n (ships_storm_object_index) float64 152B ...<br> ships_storm_longitude_deg_e (ships_storm_object_index) float64 152B ...<br> ships_predictors_lagged (ships_valid_time_unix_sec, ships_lag_time_hours, ships_predictor_name_lagged) float64 13kB ...<br> ships_predictors_forecast (ships_valid_time_unix_sec, ships_forecast_hour, ships_predictor_name_forecast) float64 451kB ...</p> <p>Variable names are meant to be as self-explanatory as possible. Potentially confusing ones are listed below.</p> <ul> <li>The dimension ships_storm_object_index is redundant with the dimension ships_valid_time_unix_sec and can be ignored.</li> <li>ships_forecast_hour ranges up to values that we do not actually use in the paper. Keep in mind that our max forecast hour used in machine learning is 24.</li> <li>The dimension ships_intensity_threshold_m_s01 (and any variable including this dimension) can be ignored.</li> <li>ships_lag_time_hours corresponds to lag times for the SHIPS satellite-based predictors. The only lag time we use in machine learning is "NaN", which is a stand-in for the best available of all lag times. See the discussion of the "priority list" in the paper for more details.</li> <li>Most of the data variables can be ignored, unless you're doing a deep dive into storm properties. The important variables are satellite_predictors_gridded (full satellite images), ships_predictors_lagged (satellite-based SHIPS predictors), and ships_predictors_forecast (environmental and storm-history-based SHIPS predictors). These variables are all discussed in the paper.</li> <li>Every variable name (including elements of the coordinate lists ships_predictor_name_lagged and ships_predictor_name_forecast) includes units at the end. For example, "m_s01" = metres per second; "deg_n" = degrees north; "deg_e" = degrees east; "j_kg01" = Joules per kilogram; ...; etc.</li> </ul>
The dataset used in the article "A point cloud graph neural network for protein-ligand binding site prediction"
Open the record for dataset details and reuse information.
COCO dataset and neural network weights for micro-FTIR particle detection on filters.
<h3>The IMPTOX project has received funding from the EU's H2020 framework programme for research and innovation under grant agreement n. 965173. Imptox is part of the European MNP cluster on human health.</h3> <p>More information about the project <a href="https://www.imptox.eu/en/">here</a>.</p> <p><strong>Description:</strong> This repository includes the trained weights and a custom COCO-formatted dataset used for developing and testing a Faster R-CNN R_50_FPN_3x object detector, specifically designed to identify particles in micro-FTIR filter images.</p> <p><strong>Contents:</strong></p> <ol> <li> <p><strong>Weights File (<code>neuralNetWeights_V3.pth</code>):</strong></p> <ul> <li>Format: .pth</li> <li>Description: This file contains the trained weights for a Faster R-CNN model with a ResNet-50 backbone and a Feature Pyramid Network (FPN), trained for 3x schedule. These weights are specifically tuned for detecting particles in micro-FTIR filter images.</li> </ul> </li> <li> <p><strong>Custom COCO Dataset (<code>uFTIR_curated_square.v5-uftir_curated_square_2024-03-14.coco-segmentation.zip</code>):</strong></p> <ul> <li>Format: .zip</li> <li>Description: This zip archive contains a custom COCO-formatted dataset, including JPEG images and their corresponding annotation file. The dataset consists of images of micro-FTIR filters with annotated particles.</li> <li>Contents: <ul> <li><strong>Images:</strong> JPEG format images of micro-FTIR filters.</li> <li><strong>Annotations:</strong> A JSON file in COCO format providing detailed annotations of the particles in the images.</li> </ul> </li> <li>Management: The dataset can be managed and manipulated using the <a href="https://pypi.org/project/pycocotools/">Pycocotools</a> library, facilitating easy integration with existing COCO tools and workflows.</li> </ul> </li> </ol> <p><strong>Applications:</strong> The provided weights and dataset are intended for researchers and practitioners in the field of microscopy and particle detection. The dataset and model can be used for further training, validation, and fine-tuning of object detection models in similar domains.</p> <p><strong>Usage Notes:</strong></p> <ul> <li>The <code>neuralNetWeights_V3.pth</code> file should be loaded into a PyTorch model compatible with the Faster R-CNN architecture, such as Detectron2.</li> <li>The contents of <code>uFTIR_curated_square.v5-uftir_curated_square_2024-03-14.coco-segmentation.zip</code> should be extracted and can be used with any COCO-compatible object detection framework for training and evaluation purposes.</li> <li>Code can be found on the related <a href="https://github.com/ThibaultSchowing/IMPTOX" target="_blank" rel="noopener">Github repository.</a></li> </ul> <p> </p>
Dataset for the study: Closed-boundary reflections of shallow water waves as an open challenge for physics-informed neural networks
<p>This dataset supports a study on using Physics-Informed Neural Networks (PINNs) to solve the 1D-Shallow Water Equations. It focuses on closed boundary reflection test cases, which are crucial for accurately modeling geophysical fluid dynamics in coastal regions, particularly for storm surge and flood modeling. Properly representing reflections is also essential for accurately modeling related phenomena, such as Kelvin waves and amphidromic systems, which influence coastal water levels during such events. The individual sub-datasets in NetCDF format provide the results used for one figure each. The data arrays within the datasets are named with reference to the figures for ease of comparison. <br><br>Cite as: Demir, K.T.; Logemann, K.; Greenberg, D.S. Closed-Boundary Reflections of Shallow Water Waves as an Open Challenge for Physics-Informed Neural Networks. <em>Mathematics</em> 2024, <em>12</em>, 3315. <a href="https://doi.org/10.3390/math12213315">https://doi.org/10.3390/math12213315</a></p>
Estimating transpiration globally by integrating the Priestley-Taylor model with neural networks
Open the record for dataset details and reuse information.
Raw datasets for paper "Multi-scale hydraulic graph neural networks for flood modelling"
<p>The repository contains two zip folders for the synthetic and case study datasets (raw_datasets_mesh.zip, raw_datasets_dk15.zip). </p> <p>Each zip folder comprises 4 subfolders (DEM, Geometry, Hydrograph, Simulations), containing the elevation, boundary polygon, discharge hydrograph, and full hydrodynamic results for all simulations.</p> <p>The overview.csv file provides the seeds used for experiment replicability and the runtime of the numerical model on each simulation.</p>
Forecasting model of seasonal dynamics of boll weevil Anthonomus grandis grandis (Coleoptera: Curculionidae) in cotton crops using artificial neural networks
Open the record for dataset details and reuse information.
Experimental online quantum dots charge autotuning using neural networks - Output data
<p>Outputs of the model training and the online autotuning experiments presented in the paper: "Experimental online quantum dots charge autotuning using neural networks".</p> <p>Each folder in the zipped files represent a run that includes:</p> <ul> <li>log file</li> <li>plots / images</li> <li>run settings</li> <li>performance results</li> <li>pytorch model parameters</li> </ul> <p>See README.txt for more information about the file strucutre.</p>
Datasets from "A new method for the detection of siliceous microfossils on sediment microscope slides using convolutional neural networks". JGR Biogeosciences.
<p>This repository contains the datasets linked to "A new method for the detection of siliceous microfossils on sediment microscope slides using convolutional neural networks" (Journal of Geophysical Research: Biogeosciences, <a href="https://doi.org/10.1029/2024JG008047">https://doi.org/10.1029/2024JG008047</a>). This includes:</p> <ul> <li>The images and annotation* text files (in YOLO format) used for the detection of siliceous microfossils. </li> <li>The models and training results for the trainings presented in the main text and supporting information.</li> </ul> <p>*Note that while annotations were attributed to 14 general categories, only twelve of these were used during training (<em>i.e. </em>Pennate, Centric, Silicoflagellate, Centric_debris, Spore, Other_Biomin, Cocco, Silicoflagellate_debris, Undetermined_silica, Chateoceros_Bacteriastrum, Calcispheres, Foraminifer), and all were pooled into a single "Microfossil" category for the purpose of the training.</p>
Neural network prediction of strong lensing systems with domain adaptation and uncertainty quantification
<p>This project combines the emerging field of Domain Adaptation with Uncertainty Quantification, working towards applying machine learning to real scientific datasets with limited labelled data. For this project, simulated images of strong gravitational lenses are used as source and target dataset, and the Einstein radius θ E and its uncertainty are determined through regression.</p> <p>Applying machine learning in science domains such as astronomy is difficult. With models trained on simulated data being applied to real data, models frequently underperform - simulations cannot perfectlty capture the true complexity of real data. Enter domain adaptation (DA). The DA techniques used in this work use Maximum Mean Discrepancy (MMD) Loss to train a network to being embeddings of labelled "source" data gravitational lenses in line with unlabeled "target" gravitational lenses. With source and target datasets made similar, training on source datasets can be used with greater fidelity on target datasets.</p> <p>Scientific analysis requires an estimate of uncertainty on measurements. We adopt an approach known as mean-variance estimation, which seeks to estimate the variance and control regression by minimizing the beta negative log-likelihood loss. To our knowledge, this is the first time that domain adaptation and uncertainty quantification are being combined, especially for regression on an astrophysical dataset.</p>
Phyloformer: Fast, accurate and versatile phylogenetic reconstruction with deep neural networks
<p>This record is composed of: </p> <ul> <li>The <code>results.tar.gz</code> file which contains all the output files necessary to reproduce the figures and tables from the linked paper</li> <li>The 3 datasets used to fine tune different versions of Phylofofmer: <ol> <li><code>cherry_fine_tune.tar.xz</code> used to fine tune Phyloformer on the CherryML model</li> <li><code>LG_fine_tune_mre.tar.xz</code> used to fine tune Phyloformer on LG+GC data with an MRE loss</li> <li><code>pastek_fine_tune.tar.xz</code> used to fine tune Phyloformer on the SelReg model</li> </ol> </li> <li>The <code>paper_test_sets.tar.xz</code> file contains the test sets used to generate data in <code>results.tar.gz</code>, with simulated tree/msa pairs and trees inferred by different methods</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.