Data accompaniment for Prototype-based Explainable Neural Networks with Channel-specific Reasoning for Geospatial Learning Tasks

Data and models accompaniment for Narayanan A and Bergen KJ, Prototype-based Explainable Neural Networks with Channel-specific Reasoning for Geospatial Learning Tasks. (submitted, 2026) Github repo: https://github.com/anaray23/ChannelSpecific_PrototypeNetwork Acknowledgement: Data used to replicate findings in this study is freely available. Data used in the MJO classification task can be found at https://zenodo.org/records/3968896 (B Toms 2020). Data used in the land use classification task is obtained from TorchGeo package at Stewart AJ, Robinson C, Corley IA, Ortiz A, Lavista Ferres JM and Banerjee A (2025) TorchGeo: Deep Learning With Geospatial Data. ACM Transactions on Spatial Algorithms and Systems 11(4), 1–28 (https://torchgeo.readthedocs.io/en/latest/api/datasets.html#torchgeo.datasets.EuroSAT). This work was partially supported by the SciAI Center, funded by the Office of Naval Research (ONR), under Grant Number N00014-23-1-2729. We are grateful to an anonymous donor for their contribution to support the work of early-career researchers impacted by award terminations.