Results 91 to 100 of about 1,500 (207)

GNSS Zenith Wet Delay as a Boundary Layer Diagnostic: Regime‐Dependent Turbulence Signatures From Large Eddy Simulation and Observations

Journal of Geophysical Research: Atmospheres, Volume 131, Issue 12, 28 June 2026.
Abstract Global Navigation Satellite Systems (GNSS) provide continuous measurements of zenith wet delay (ZWD), reflecting column‐integrated atmospheric water vapor. While the slowly varying ZWD is routinely assimilated in numerical weather prediction, the rapid fluctuations on timescales of seconds to minutes that arise from boundary‐layer turbulence ...
Gaël Kermarrec, Tim Schrader, Xavier Calbet, Zhiguo Deng   +3 more
wiley   +1 more source

All convolutional neural networks for radar-based precipitation nowcasting [PDF]

, 2018
Today deep learning is taking its rise in hydrometeorological applications, and it is critical to extensively evaluate its prediction performance and robustness.
Lukyanova, Olga, Nikitin, Oleg, Heistermann, Maik, Ayzel, Georgy, Sorokin, Alexey   +4 more
core   +1 more source

Characteristics and Trends in Short‐Duration Heavy Rain in Wet‐Season in Hong Kong

International Journal of Climatology, Volume 46, Issue 7, 15 June 2026.
This study examines the characteristics of heavy rain events (hourly rainfall ≥ 30 mm) in Hong Kong from 2000 to 2024. A statistically significant increasing trend in short‐duration (1–3 h) heavy rain events (3.4 events per decade) in the wet season is observed, primarily due to other mechanisms rather than surface troughs or tropical cyclones. Notably,
Lai‐lai Leung, Chi‐wai Andy So, Man‐chi Wu, Chun‐wing Choy, Yuk‐sing Lui, Pak‐wai Chan   +5 more
wiley   +1 more source

GPTCast: a weather language model for precipitation nowcasting

Geoscientific Model Development
Abstract. This work introduces GPTCast, a generative deep learning method for ensemble nowcasting of radar-based precipitation, inspired by advancements in large language models (LLMs). We employ a generative pre-trained transformer (GPT) model as a forecaster to learn spatiotemporal precipitation dynamics using tokenized radar images. The tokenizer is
Gabriele Franch, Elena Tomasi, Rishabh Wanjari, Virginia Poli, Chiara Cardinali, Pier Paolo Alberoni, Marco Cristoforetti   +6 more
openaire   +2 more sources

Precipitation nowcasting using a generative adversarial network [PDF]

, 2022
Nedávne pokroky v oblasti umelej inteligencie umožnili použitie strojového učenia ako nástroja k nowcastingu - krátkodobej predpovedi zrážok. V posledných rokoch sme mohli vidieť mnoho publikácií na túto tému, keďže je to stále otvorený problém.
Matej Murín
core  

CPrecNet: Enhanced Nowcast of High‐Resolution Short‐Term Precipitation Using Deep Learning

Geophysical Research Letters
Accurate short‐term precipitation nowcasting is essential for disaster prevention and water resource management. Traditional numerical weather prediction faces challenges in delivering high‐resolution nowcasts due to computational limitations.
Jun Park, Changhoon Lee
doaj   +1 more source

Precipitation Nowcasting using a Generative Adversarial Network [PDF]

Nowcasting high-intensity precipitation is crucial for emergency services and municipalities when making weather-dependent decisions. This research implements and trains a deep generative model for nowcasting using a cleaned precipitation radar composite
van Os, Sven (author)
core  

Skill in nowcasting high-impact heavy precipitation events [PDF]

, 2014
The objective of this study is to assess the skill of a precipitation nowcasting (very short range forecasting) system, with particular emphasis on hig-impact Heavy Precipitation Events (HPE).
Bech, Joan, Berenguer Ferrer, Marc
core   +2 more sources

Exploring the ability of regional extrapolation for precipitation nowcasting with deep learning

Meteorologische Zeitschrift
Precipitation nowcasting refers to the prediction of precipitation intensity in a local region and in a short timeframe up to 6 hours. The evaluation of spatial and temporal information still challenges state-of-the-art numerical weather prediction ...
Tarek Beutler, Annette Rudolph, Daniel Goehring, Nikki Vercauteren   +3 more
doaj   +1 more source

Towards a Spatiotemporal Fusion Approach to Precipitation Nowcasting

2025 28th International Conference on Information Fusion (FUSION)
With the increasing availability of meteorological data from various sensors, numerical models and reanalysis products, the need for efficient data integration methods has become paramount for improving weather forecasts and hydrometeorological studies.
Felipe Curcio, Pedro Castro, Augusto José Fonseca, Rafaela Castro, Raquel Franco, Eduardo S. Ogasawara, Victor Stepanenko, Fábio Porto 0001, Mariza Ferro, Eduardo Bezerra 0002   +9 more
openaire   +2 more sources