XBAT+ Datasets for WEEE Identification and Battery Detection and Classification

The initial release of XBAT+ [ Advanced Robotics and Artificial Intelligence for Critical Raw Materials Recycling in the Circular Economy ] provides annotated training and test datasets composed of static images of battery-WEEE devices with and/or without batteries. These training and test datasets are grouped as High-Quality (HQ), Varying-Quality (VQ) and Red-Green-Blue (RGB) datasets. The HQ datasets consist of expert-selected X-ray images derived from the VQ datasets acquired using NTB EZ 240 X-ray scanner. The RGB datasets contain color images acquired using an UltraSharp Dell webcam. As of December 2025, XBAT+ defined 50 categories of battery-WEEE devices, manually sorted from cages of mixed WEEE, during visits at KMK Metals Recycling Limited and Mungret Civic Amenity Centre, as well as during Limerick City and University of Limerick collection events. This XBAT+ 1.0 release was only created from 15 categories, each represented by more than five battery-WEEE devices. Within each of these 15 categories, 20% of the images were allocated to the test subset. The overall test set was then formed by combining these per-category subsets, to ensure the test data are representative across categories. The remaining 80% of the images, from each category, were combined to form the training set. The uploaded ZIP files, raw_XBAT+_v1.0_ ... .zip and res_XBAT+_v1.0_ ... .zip, include raw and resized data organized as follows: HQ Datasets Test data: 91 images, 91 labels Training data: 330 images, 330 labels RGB Datasets Test data: 91 images, 91 labels Training data: 330 images, 330 labels VQ Datasets Test data: 482 images, 482 labels Training data: 1,721 images, 1,721 labels In the RGB image datasets, class IDs range from 0 to 14, while in the X-ray image datasets they range from 0 to 16 due to additional battery presence (class ID → 1) /absence (class ID → 13) labels. These datasets are fully described in the accompanying data descriptor. Users of the datasets are encouraged to cite the associated data descriptor publication as follows: Cite this article: Rukundo, O., Khan, R., Grua, E.M. et al. Annotated datasets for waste electrical and electronic equipment identification and battery detection and classification. Sci Data (2026). https://doi.org/10.1038/s41597-026-07606-4 Note that these preliminary XBAT+ datasets are intended to support research and development in battery-WEEE identification, battery presence detection, and battery chemistry classification.