← Back to all news
arXiv Machine Learning By Alessandro Camilletti, Gabriele Franch, Elena Tomasi, Marco Cristoforetti

IRENE: A Convolutional GRU Ensemble Model for Radar Precipitation Nowcasting over Italy

Read the original on arXiv Machine Learning →

IRENE is a deep learning model that provides probabilistic short‑range precipitation nowcasts over Italy at 1 km spatial and 5‑minute temporal resolution. It uses an encoder–forecaster architecture built on multi‑scale Convolutional Gated Recurrent Units (ConvGRUs) and is trained on national radar composites, with an importance‑sampling scheme and the almost‑fair Continuous Ranked Probability Score as its primary loss. Three training variants—standard, adversarial (IRENE‑GAN), and spectrally constrained (IRENE‑GAN‑RAPSD)—outperform benchmark methods STEPS and DGMR in probabilistic skill, though the advantage in mean absolute error is limited to the first 90 minutes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 2

GenONet: A Generative operator Network for High-Resolution Precipitation Nowcasting

GenONet introduces a Spatio-Temporal U-DeepONet architecture that serves as a generator in a GAN framework for high‑resolution precipitation nowcasting up to three hours ahead. By learning continuous‑time precipitation dynamics with a Deep Operator Network and enforcing physics through a moisture‑conservation loss, the model produces sharp, physically consistent forecasts that outperform baselines, especially for high‑intensity events and longer lead times. Ablation studies confirm the added value of the physics‑informed regularizer and the synergy of operator learning with adversarial training.

By Mohammad Kian Golkar, Luciano Alves de Oliveira, Mohammad Khanjani
diffusionbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 27

Precipitation Downscaling Using Foundation Model-Conditioned Diffusion

The study evaluates three conditioning strategies for a denoising diffusion probabilistic model to downscale daily precipitation for the Colorado River Basin. Channel concatenation of upsampled coarse predictors yields the lowest point‑wise CRPS and MSE but tends to over‑smooth high‑intensity events. Cross‑attention conditioning—both with a learned encoder and with the frozen encoder of the pretrained Prithvi‑WxC weather foundation model—provides better distributional realism, improved spectral fidelity, and stronger performance on extreme events, especially when data are limited.

By Victor Nascimento Ribeiro, Jorge Guevara, Jorge Sebastian Moraga, Chris Lucas, Natalie Lord, Andrew Taylor, Edward Lockhart, Will Trojak, Johannes Schmude, Anne Jones
diffusion
More like this →