RenewableXAI is a fully implemented system for interactive inspection of renewable-energy forecasting models. The system combines semantically grouped TreeSHAP explanations, model-exact one-feature explanation-stability intervals, adjacent boundary-transition analysis, interactive scenario editing, and an evidence-constrained local language interface. This research artifact contains the source code, photovoltaic and wind-power domain adapters, frozen holdout question sets, expected question plans, per-route evaluation outputs, deterministic validation decisions, aggregate evaluation reports, independent oracle tests for stability intervals, and integrity manifests. The artifact accompanies the IEEE ICDM 2026 Demo Paper “RenewableXAI: Model-Exact Explanation Stability for Renewable Energy Forecasting.” The rendered demonstration video is included. Raw datasets, serialized forecasting models, and editable video-production assets are not included. Instructions for obtaining the public datasets and reproducing the reported experiments are provided in the documentation. Development repository: https://github.com/energy-urfu-ai/renewable-xaiArchived source revision: 49930a196a8851fc16fdd52f7b547d41d8bf41e5
Павел Матренин, Alexandra I. Khalyasmaa, Stanislav A. Eroshenko et al.· Zenodo (CERN European Organi...· 0 citations
RenewableXAI is a fully implemented system for interactive inspection of renewable-energy forecasting models. The system combines semantically grouped TreeSHAP explanations, model-exact one-feature explanation-stability intervals, adjacent boundary-transition analysis, interactive scenario editing, and an evidence-constrained local language interface. This research artifact contains the source code, photovoltaic and wind-power domain adapters, frozen holdout question sets, expected question plans, per-route evaluation outputs, deterministic validation decisions, aggregate evaluation reports, independent oracle tests for stability intervals, and integrity manifests. The artifact accompanies the IEEE ICDM 2026 Demo Paper “RenewableXAI: Model-Exact Explanation Stability for Renewable Energy Forecasting.” The rendered demonstration video is included. Raw datasets, serialized forecasting models, and editable video-production assets are not included. Instructions for obtaining the public datasets and reproducing the reported experiments are provided in the documentation. Development repository: https://github.com/energy-urfu-ai/renewable-xaiArchived source revision: 49930a196a8851fc16fdd52f7b547d41d8bf41e5
Павел Матренин, Alexandra I. Khalyasmaa, Stanislav A. Eroshenko et al.· Zenodo (CERN European Organi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
