New deep learning model Dense-Cast forecasts precipitation with high accuracy

Researchers have developed Dense-Cast, a new lightweight deep learning model designed for short-term precipitation nowcasting. The model integrates DenseNet architecture, residual connections, and transformer encoders to effectively predict precipitation with fewer parameters. Tested in the monsoon-prone North-Eastern region of India, Dense-Cast uses historical precipitation data to forecast the next two half-hours. It achieved a best MAE of 0.235 mm, RMSE of 0.735 mm, and KGE score of 0.816. AI

IMPACT This model could improve disaster management and preparedness through more accurate short-term precipitation forecasting.

RANK_REASON Publication of a research paper detailing a new deep learning model. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• Dense-Cast
• DenseNet
• Gourav Jyoti Kalita
• Hugging Face
• India

• paper
• model release

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