New benchmark compares visual backbones for solar irradiance forecasting

A new research paper introduces a controlled benchmark for evaluating visual backbones in multimodal short-term solar irradiance forecasting. The study fixes the overall forecasting pipeline and isolates the visual backbone for comparison, testing models like ConvNeXt, Swin Transformer, and various Mamba-based architectures. Results on Folsom and NREL datasets show that while all evaluated backbones improve over smart persistence, specific models like VMamba Small and Swin Base achieve competitive RMSE values, though smart persistence remains strongest on the NREL split. AI

IMPACT Provides a standardized method for comparing visual backbones in AI-driven forecasting applications.

RANK_REASON Research paper introducing a new benchmark and evaluation of models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• ConvNeXt
• Dilshara Herath
• Folsom
• MambaVision
• National Laboratory of the Rockies
• Swin Transformer
• VmambaSCI: Dynamic Deep Unfolding Network with Mamba for Compressive Spectral Imaging

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →