10.6075/J0S182Q6 Dataset Hoffman, Lauren A. Mazloff, Matthew R. Gille, Sarah T. Giglio, Donata Heimbach, Patrick UC San Diego Library Digital Collections 2025 2025 1989 to 2021 (i) MATLAB R2021b and (ii) Python 3.8-3.11 (iii) TensorFlow 2.6-2.14 (iv) iNNvestigate (https://innvestigate.readthedocs.io/en/latest/) With the aim of using explainable AI to understand predictions made by machine learning models built to predict sea-ice motion in the Arctic on one-day timescales, these data include processed satellite and reanalysis measurements of sea-ice velocity, sea-ice concentration, and wind velocity. Also included are outputs from statistical model predictions. Finally, we include all files required to download and process raw data, run statistical models, and plot analyses of outputs. Oceanography Arctic Ocean Explainable artificial intelligence (XAI) Arctic sea ice Earth sciences Task: Regression Machine learning Task: Forecasting Algorithm: Supervised learning application/pdf image/jpeg application/zip Creative Commons Attribution 4.0 International Public License -180.0 90.0 180.0 90.0 180.0 60.0 -180.0 60.0 -180.0 90.0 -180.0 90.0 https://doi.org/10.5067/8GQ8LZQVL0VL https://climate.mri-jma.go.jp/pub/ocean/JRA55-do/ https://innvestigate.readthedocs.io/en/latest/ https://doi.org/10.5067/INAWUWO7QH7B https://doi.org/10.1175/AIES-D-24-0027.1 https://doi.org/10.22033/ESGF/input4MIPs.15017