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.
11
datasets available to search
ShareScore release 0.9.0
Dataset results
11 results for “XAI”
Finding the right XAI Method --- Dataset
<p>This dataset provides the complementary preprocessed data for the training of the neural networks used in Bommer et. al. and according source code (<a href="https://github.com/philine-bommer/Climate_X_Quantus">https://github.com/philine-bommer/Climate_X_Quantus</a>). In the publication , we introduce XAI evaluation in the context of climate research and assess different desired explanation properties, namely, robustness, faithfulness, randomization, complexity, and localization. To this end we build upon previous work (Labe and Barnes et. al. 2021) and<br> train a multi-layer perceptron (MLP) and a convolutional neural network (CNN) to predict the decade based on annual-mean temperature maps.</p> <p>Following Labe and Barnes et. al. 2021, we use data simulated by the general climate model, CESM1 (Hurrell et. al. 2013). We use the global 2-m air temperature (T2m) temperature maps from 1920 to 2080. The data consist of 40 ensemble members and each member is generated by varying the atmospheric initial conditions with fixed external forcing, i.e. historical forcings are imposed from 1920 to 2005 and Representative Concentration Pathways 8.5 for the following years (Kay et. al. 2015).<br> Following Labe and Barnes et. al. 2021, we compute annual averages and apply a bilinear interpolation. This results in T=161 temperature maps for each member, with v=144 longitude grid cells and h=95 latitude grid cells, given the 1.9° sampling in latitude and 2.5° sampling in longitude. The temperature maps are finally standardized by removing the multi-year (1920 to 2080) mean and subsequently dividing by the corresponding standard deviation.</p> <p>Unlike the flattened input used for the MLP (temperature maps are flattened into a vector), the CNN maintains the longitude-latitude grid of the temperature maps. Similar to Labe and Barnes et. al. 2021, for training, validation and testing we use the model data discussed above. For both MLP and CNN we consider 20% of the data as test set and the remaining 80% is split into a training (64%) and validation (16%) set. We train both networks to solve a fuzzy classification problem which combines classification and regression. In the classification setting, the network assigns each map to one of the 20 different classes, where each class corresponds to one decade between 1900 and 2100 (necessary class devision for later regression, as done by Labe and Barnes et. al. 2021). The network output thus, is a probability vector containing a probability for each class.</p> <p>To assess the network performance we use the monthly 2m air temperature of the 20th century Reanalysis data (V3) (Slivinski et. al. 2019) from 1920 to 2015.</p> <p>The dataset includes two compressed .npz-files and a Readme.md. A full description of the data contained in this dataset and instructions on the data usage are provided in the Readme-file. </p>
To Trust or Not to Trust: Towards a novel approach to measure trust for XAI systems
<p>Experimental data from unpublished work <em>To Trust or Not to Trust: Towards a novel approach to measure trust for XAI systems</em></p>
Replication Package - From Research to Practice: A Survey of XAI Process Frameworks
<p>Replication package for the ICSE NIER Submission "From Research to Practice: A Survey of XAI Process Frameworks." Provides details about the methods and data used in our analysis. For more information, please take a look at the README.</p>
AquaXAI: Visual and Textual Dataset for XAI in Aquatic Environments
<p>This Dataset is for the publication: "Interactive Simulator Framework for XAI Applications in Aquatic Environments"<br><br>AquaXAI is a synthetic dataset aiming to explain boat skippers' actions in aquatic environments, using Unity Simulator.</p> <p>The dataset consists of:</p> <p>Image: RGB + Semantic Segmentation + Instance Segmentation + Bounding Box</p> <p>Textual Explanations: Action + Explanation</p>
xAI Ship Wakes in Sentinel-2 L2A images
<h2><strong>xS2Wakes: A dataset for xAI of Wakes in S-2 (L2A).</strong></h2><h3><strong>Summary</strong></h3><p>The dataset is derived from Sentinel-2 Level-2A (L2A) satellite images and focuses on the marine domain over Danish fjords. It provides a comprehensive collection of ship wakes and background clutter (referred to as "no_<i>wake</i>_crop") for remote sensing applications. The dataset has undergone post-processing through the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm with a clip limit value of 0.12 and a tile size of 16x16. The dataset comprises four spectral bands: B2, B3, B4, and B8.</p><h3><strong>Importance and Relevance to Remote Sensing Community</strong></h3><h4>Multifaceted Applications of Wake Detection</h4><p>Ship wake detection serves as a cornerstone in a multitude of domains that are critical to both human and environmental well-being:</p><p><strong>Navigational Safety</strong>: Understanding ship wakes can provide insights into water currents and traffic patterns. This is vital for ensuring the safe passage of marine vessels, particularly in narrow straits and busy ports.</p><p><strong>Environmental Monitoring</strong>: The study of ship wakes can reveal the influence of vessels on aquatic ecosystems. For instance, excessive wake turbulence can lead to coastal erosion and can disrupt marine habitats.</p><p><strong>Maritime Surveillance</strong>: Wake detection plays a crucial role in maintaining maritime security. Tracking the wakes of vessels can help in identifying illegal activities such as smuggling or unauthorized fishing.</p><h3><strong>Specifications</strong></h3><ul><li><strong>Data Source</strong>: Sentinel-2 L2A</li><li><strong>Region of Interest</strong>: Danish fjords</li><li><strong>Classes</strong>: Wake, No-Wake</li><li><strong>Number of Samples</strong>:<ul><li>Wake: 123</li><li>No-Wake: 150</li></ul></li><li><strong>Spectral Bands</strong>: B2 (Blue), B3 (Green), B4 (Red), B8 (NIR)</li><li><strong>Post-Processing</strong>: CLAHE (Clip Limit = 0.12, Tile Size = 16x16)</li><li><strong>Average Wake Chip Size</strong>: 390x351 pixels</li><li><strong>Average No-Wake Chip Size</strong>: 380x390 pixels</li></ul><h3><strong>Wake Detection and Analysis</strong></h3><h4>Traditional Methods and Their Limitations</h4><p>Traditionally, the process of ship wake detection has largely been a manual endeavor or employed simplistic statistical algorithms. Analysts would sift through satellite or aerial images to identify ship wakes, a process that is both time-consuming and prone to human error. Even automated statistical methods often lack the robustness needed to differentiate between true wakes and false positives, such as aquatic plants or natural water disturbances.</p><h4>Role of xAI (Explainable AI) in Wake Identification</h4><p>The introduction of explainable AI (xAI) techniques brings another layer of sophistication to wake analysis. While traditional machine learning models may offer high performance, they often act as "black boxes," making it difficult to understand how they arrive at a certain conclusion. In a critical domain like navigational safety or maritime surveillance, the ability to interpret and understand model decisions is indispensable. xAI methods can make these machine learning models more transparent, providing insights into their decision-making processes, which in turn can aid in fine-tuning or fully trusting the models.</p><h4>Spectral Bands Selected</h4><p>The inclusion of four key spectral bands—B2, B3, B4, and B8—offers the scope for multi-spectral analysis. Different bands can capture varying features of water and wake textures, thereby offering a richer feature set for machine learning models. We use these spectral bands as referred to in [Liu, Yingfei, Jun Zhao, and Yan Qin. "A novel technique for ship wake detection from optical images." <i>Remote Sensing of Environment</i> 258 (2021): 112375.] </p><h4>Understanding Optical vs. SAR Imaging Modalities</h4><p>It is important to note the fundamental differences between wakes captured in Synthetic Aperture Radar (SAR) images and those in optical imagery. In SAR images, narrow-V wakes often arise due to Bragg scattering, a phenomenon that does not exist at optical wavelengths. In optical images, bright lines close to turbulent wakes are actually foams generated by the interaction between the surface horizontal flow of turbulent wakes and the surrounding background waves (Ermakov et al., 2014; Milgram et al., 1993; Peltzer et al., 1992). This can make the detection of wakes in optical images more challenging as there are usually no bright lines near turbulent wakes, and Kelvin arms may also show dark contrast. Methods that solely rely on searching for a trough and peak pair, taking the trough as the turbulent wake, would miss many actual wakes and could also result in the identification of false wakes.</p><h4>Contrast Enhancement</h4><p>The application of the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm to this dataset allows for enhanced local contrast, enabling subtle features to become more pronounced. This significantly aids machine learning algorithms in feature extraction, thereby improving their ability to distinguish between complex patterns.</p><h4>Environment and Clutter Assessment</h4><p>In addition to wakes, the dataset contains samples labeled as "No-Wake," which include environmental clutter and clouds. These samples are crucial for training robust models that can differentiate wakes from similar-looking natural phenomena.</p>
Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)
<p>This repository includes the input and output dataset, and python scripts used in the article, "Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)," of J. Chem. Phys. 156, 154108 (2022) [DOI: <a href="http://doi.org/10.1063/5.0087310">10.1063/5.0087310</a>] The repository also includes source data of figures in the article.</p>
XAI Sedimentation Use Case
<p>Presented is a dataset describing the environmental characteristics of coastal Louisiana. A machine learning workflow accompanies the workflow.</p>
retauló xai
És un petit quadre de fusta amb un marrà dibuixat.Fa uns 30 cm de llargada i és policromat El posaven els carnissers a la porta de la botiga el dia que tenien carn de xai per vendre, i com que tenien poc xai sobretot a l'hivern, cada setmana o cada dia una carnisseria li tocava vendre carn de xai, i així els clients sabien a on podien anar a comprar-lo. Source: Objaverse 1.0 / Sketchfab
XAI Dataset
<p>XAI dataset</p>
Explainable artificial intelligence (XAI) detects wildfire occurrence in the Mediterranean countries of Southern Europe
Open the record for dataset details and reuse information.
Data for "Exploring the Monthly Contribution of Drivers on European Summer Wildfires with Explainable Artificial Intelligence (XAI)"
<h3>Abstract</h3> <div> <p>We applied an XAI method to analyze the monthly contribution of wildfire drivers on summer fires in European forest, shrub and herbaceous vegetation areas from 2014 to 2023. Using burn area data and 18 features including meteorology, vegetation, topography, and anthropogenic activity, we developed a reliable wildfire occurrence model using the LSTM method.</p> </div> <h3>Methods</h3> <div> <p>The fire point data is provided by the European Forest Fire Information System (EFFIS). A total of 18 features were selected for modeling. Among these features, the four meteorological variables (Prep, LST, SM, and SR), along with the corresponding four condition indexes (RCI, TCI, SMCI, SRCI) derived from them, the Wind Speed (WS), and the two vegetation variables (Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI)), were used as monthly time series. The Lightning Frequency dataset is monthly but represents an average of data from 2012 to 2021, remaining constant across different years. The remaining six feature datasets do not vary over time. Data download and analysis were conducted using Google Earth Engine, QGIS, and Python.</p> </div> <h3>Subject keywords</h3> <p><span>Deep learning</span>, <span>Europe</span>, <span>Earth and related environmental sciences</span>, <span>vegetation</span>, <span>wildfire</span></p> <h3>Description of the data and file structure</h3> <ul> <li><strong><code>train_data_no_2023.npy</code></strong> and <strong><code>train_Y_data_no_2023.npy</code></strong>: These contain the features and labels for the training set (excluding data from 2023).</li> <li><strong><code>TEST_X_2023.npy</code></strong> and <strong><code>TEST_Y_2023.npy</code></strong>: These represent the features and labels for the test set, specifically for the year 2023.</li> <li><strong><code>model.h5</code></strong>: This is the final trained model.</li> <li><strong><code>shap_values_train_data.npy</code></strong>: This file contains the SHAP values for the training set, used to explain model predictions.</li> </ul> <p>The order of features:</p> <p>Label = ['Prep', 'LST', 'SM', 'SR', 'RCI', 'TCI', 'SMCI', 'SRCI', 'WS', 'NDVI', 'LAI', 'LF', 'CH', 'Elevation', 'Slope', 'Aspect', 'DR', 'DS']</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.