Researchers have developed a new machine learning technique using gated recurrent units (GRU) to predict nuclear properties like masses and charge radii. This method integrates learnable product-unit mappings to model multiplicative dependencies between neighboring nuclei, performing computations in the complex domain to capture amplitude and phase dynamics. The proposed AM-PU-GRU model achieved a mean mass interpolation RMSE of 0.2698 MeV and a temporal RMSE of 0.1905 MeV, while a variant, MI-PU-GRU, predicted charge radii with an RMSE of 0.019947 fm, outperforming a fixed WS* prior by 14.40%. This work extends a previous conference paper presented at ICCS 2026. AI
IMPACT This research demonstrates a novel application of recurrent neural networks for complex scientific modeling, potentially improving the accuracy and efficiency of nuclear physics research.
RANK_REASON The cluster contains an academic paper detailing a new machine learning model for scientific prediction. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →