Search Results

You are looking at 1 - 10 of 86 items for :

  • Forecasting techniques x
  • Artificial Intelligence for the Earth Systems x
  • Refine by Access: Content accessible to me x
Clear All
Martin Rempel
,
Peter Schaumann
,
Reinhold Hess
,
Volker Schmidt
, and
Ulrich Blahak

dissemination to users, the perception and decision-making, and the outcomes and values. The currently ongoing project Seamless Integrated Forecasting System (SINFONY) of Deutscher Wetterdienst (DWD) can be assigned to the topic of seamless prediction, since it focuses on the seamless prediction of precipitation within the short-term range up to +12 h ahead. Here, the term seamless is referred to as the combination of forecasts of observation-based precipitation nowcasting techniques with those of the

Free access
Ignacio Lopez-Gomez
,
Amy McGovern
,
Shreya Agrawal
, and
Jason Hickey

learn about causal physical mechanisms that are common to both the extreme and general forecasting tasks. The rare nature of heatwaves implies that this learning process occurs in the low data regime, and that improved models may be obtained through data augmentation techniques ( Miloshevich et al. 2022 ). In this context, an interesting research direction would be to train deep learning models using a much larger synthetic dataset as a first step ( Chattopadhyay et al. 2020 ; Jacques-Dumas et al

Open access
Clément Brochet
,
Laure Raynaud
,
Nicolas Thome
,
Matthieu Plu
, and
Clément Rambour

1. Introduction Having access to large sets of weather forecasts or reforecasts is of plain importance in many applications. For instance, some fundamental and applied studies in weather science rely on large reforecasts of events, for example, to detect climatological trends on specific patterns such as extratropical depressions ( Pantillon et al. 2017 ) or heavy precipitating events ( Ponzano et al. 2020 ). Such reforecasts, like operational forecasts in many centers, are usually based

Open access
Yanan Duan
,
Sathish Akula
,
Sanjiv Kumar
,
Wonjun Lee
, and
Sepideh Khajehei

postprocessing tool for NWM forecast using a long-term short-term memory model, an ML technique. Kratzert et al. (2019) found improvement in ML model performance with the catchment attributes as the additional input parameters (in addition to meteorological inputs). Barnes et al. (2019) have employed an artificial neural network (ANN) to extract climate change signals from the model uncertainty and internal climate variability. Mayer and Barnes (2021) have used the ANN to identify teleconnection

Open access
Amy McGovern
,
Randy J. Chase
,
Montgomery Flora
,
David J. Gagne II
,
Ryan Lagerquist
,
Corey K. Potvin
,
Nathan Snook
, and
Eric Loken

convective storms is the principal tool used by NWS forecasters for detecting tornadoes and issuing warnings. Current operational techniques are largely based on expert systems that detect areas of strong rotation ( Mitchell et al. 1998 ). Early researchers explored using machine learning for detecting tornadic rotation signatures (e.g., Marzban 2000 ; Trafalis et al. 2003 ; Wang and Yu 2015 ), but they were restricted by small datasets. A priori, given enough data, ML should be well suited for

Open access
Mary Ruth Keller
,
Christine Piatko
,
Mary Versa Clemens-Sewall
,
Rebecca Eager
,
Kevin Foster
,
Christopher Gifford
,
Derek Rollend
, and
Jennifer Sleeman

complex network of monthly interconnections to which linear Gaussian process regression has been applied ( Drobot et al. 2006 ). The monthly forecasts exhibit some skill above climatology ( Gregory et al. 2020 ). Bayesian logistic regression has been used to forecast September minimum ice cover at one-month to seven-month lead times ( Horvath et al. 2020 ). The technique permitted a direct measure of uncertainty for assessing reliability. Both these efforts targeted global outputs. A deep neural

Open access
Junsu Kim
,
Yeon-Hee Kim
,
Hyejeong Bok
,
Sungbin Jang
,
Eunju Cho
, and
Seungbum Kim

technology, data-driven methodologies, and improved computing capabilities have contributed to the progress in precipitation forecasting. Certain techniques such as the use of high-resolution models to simulate realistic spatial patterns or postprocessing methods to correct systematic biases, have shown promise. Particularly, studies have attempted to enhance prediction models using data analysis techniques such as machine learning. Recent studies have explored diverse topics related to numerical weather

Open access
Alexander J. DesRosiers
and
Michael M. Bell

ML currently being realized in the field of meteorology ( Boukabara et al. 2019 ) to advance remote sensing retrievals, data assimilation, model physics calculation, forecasting, and data QC. Although scanning geometry and wavelength create considerable differences between airborne and ground-based radar data, the recent successful use of ML for ground-based radar QC ( Lakshmanan et al. 2014 ) further motivated an attempt with airborne data. A relatively straightforward ML technique, the random

Open access
Sem Vijverberg
,
Raed Hamed
, and
Dim Coumou

Sciences, Engineering, and Medicine 2016 ; Scaife and Smith 2018 ). The poor skill of dynamical seasonal forecasts ( Ramírez-Rodrigues et al. 2016 ) combined with imperfect crop simulation models generates a cascade of uncertainty making the approach unsuited for presowing harvest predictions ( Brown et al. 2018 ; Iizumi et al. 2018 ). Machine learning techniques have the potential to circumvent the problem of low signal-to-noise ratios of dynamical models by directly learning from observations. Of

Open access
Ashesh Ashesh
,
Chia-Tung Chang
,
Buo-Fu Chen
,
Hsuan-Tien Lin
,
Boyo Chen
, and
Treng-Shi Huang

(NWP) models driven by physics simulation generally provide more stable predictions due to proper use of the domain knowledge ( Kain et al. 2010 ; Sun et al. 2014 ) and are usually considered superior to data-driven techniques. On the other hand, for 0–1-h forecasts, that is, quantitative precipitation nowcasting (QPN), data-driven techniques such as the radar echo extrapolation models are powerful solutions ( Dixon and Wiener 1993 ; Germann and Zawadzki 2002 , 2004 ; Chung and Yao 2020

Free access