Search Results

You are looking at 1 - 10 of 17 items for :

  • Forecasting techniques x
  • The 1st NOAA Workshop on Leveraging AI in the Exploitation of Satellite Earth Observations & Numerical Weather Prediction x
  • Refine by Access: All Content x
Clear All
Ricardo Martins Campos, Vladimir Krasnopolsky, Jose-Henrique G. M. Alves, and Stephen G. Penny

potential. Berbić et al. (2017) applied ANNs and support vector machines for short forecasts of significant wave height. Dixit and Londhe (2016) developed a neuro wavelet technique, combining discrete wavelet transform and ANNs, to explore the predictability of extreme events for five major hurricanes at four locations in the Gulf of Mexico. Deo et al. (2001) , Deo and Sridhar Naidu (1998) , and Mandal and Prabaharan (2006) developed ANN systems to predict significant wave heights in India, and

Full access
Eric D. Loken, Adam J. Clark, Amy McGovern, Montgomery Flora, and Kent Knopfmeier

, multiple-physics CAEs is an artificial inflation of ensemble spread due to the existence of systematic biases between ensemble members ( Eckel and Mass 2005 ; Clark et al. 2010b ; Loken et al. 2019 ). These shortcomings are typically resolved using one or more postprocessing techniques, including isotropic (e.g., Sobash et al. 2011 , 2016 ; Loken et al. 2017 , 2019 ; Roberts et al. 2019 ) or anisotropic (e.g., Marsh et al. 2012 ) spatial smoothing of the raw forecast probability field

Full access
Andrew E. Mercer, Alexandria D. Grimes, and Kimberly M. Wood

applied techniques known as supervised learning methods, where the user oversees many aspects of the study, including the case selection, the predictor selection, the classification criteria and method, and traditional cross-validation techniques ( Russell and Norvig 2010 ). Techniques such as regression and classification fall under the broader heading of supervised learning methods. These methods have value as evidenced by the improvements seen in RI forecasts in recent years ( Kaplan et al. 2015

Full access
Sid-Ahmed Boukabara, Vladimir Krasnopolsky, Jebb Q. Stewart, Eric S. Maddy, Narges Shahroudi, and Ross N. Hoffman

the model resolution, to extend the forecast horizon, and to increase ensemble size). Flexibility. ML techniques can accommodate (i) variables that have not been (and sometimes cannot be) included in physically based models, (ii) physical constrains (like conservation laws or balance equations), (iii) processes that are nonlinear, (iv) non-Gaussian observation errors, and (v) empirical data for processes for which the true physics is poorly understood ( Krasnopolsky 2013 ). Ease of use. Modern

Free access
Kyle A. Hilburn, Imme Ebert-Uphoff, and Steven D. Miller

1. Introduction Geostationary Operational Environmental Satellite (GOES) imagery is a key element of U.S. operational weather forecasting, supporting the need for high-resolution, rapidly refreshing imagery for situational awareness ( Line et al. 2016 ). While used extensively by human forecasters, its usage in data assimilation (DA) for numerical weather prediction (NWP) models is limited. Instead DA makes greater usage of microwave and infrared sounder data on low-Earth-orbiting satellites

Open access
Yun Fan, Vladimir Krasnopolsky, Huug van den Dool, Chung-Yu Wu, and Jon Gottschalck

Abstract

Forecast skill from dynamical forecast models decreases quickly with projection time due to various errors. Therefore, post-processing methods, from simple bias correction methods to more complicated multiple linear regression-based Model Output Statistics, are used to improve raw model forecasts. Usually, these methods show clear forecast improvement over the raw model forecasts, especially for short-range weather forecasts. However, linear approaches have limitations because the relationship between predictands and predictors may be nonlinear. This is even truer for extended range forecasts, such as Week 3-4 forecasts.

In this study, neural network techniques are used to seek or model the relationships between a set of predictors and predictands, and eventually to improve Week 3-4 precipitation and 2-meter temperature forecasts made by the NOAA NCEP Climate Forecast System. Benefitting from advances in machine learning techniques in recent years, more flexible and capable machine learning algorithms and availability of big datasets enable us not only to explore nonlinear features or relationships within a given large dataset, but also to extract more sophisticated pattern relationships and co-variabilities hidden within the multi-dimensional predictors and predictands. Then these more sophisticated relationships and high-level statistical information are used to correct the model Week 3-4 precipitation and 2-meter temperature forecasts. The results show that to some extent neural network techniques can significantly improve the Week 3-4 forecast accuracy and greatly increase the efficiency over the traditional multiple linear regression methods.

Full access
Akhil Sanjay Potdar, Pierre-Emmanuel Kirstetter, Devon Woods, and Manabendra Saharia

specific hydrologic processes. For example, the Flash Flood Guidance (FFG) system used worldwide estimates runoff generation ( Sweeney 1992 ), However, FFG only addresses parts of the flood’s characteristics and does not focus on water propagation overland or along streams. It misses any occurrence of flooding downstream of the rainfall, especially the delay, magnitude, and duration of the flood. Because a flood forecasting system needs to describe these characteristics ahead of time, modern instances

Restricted access
Hanoi Medina, Di Tian, Fabio R. Marin, and Giovanni B. Chirico

techniques and logistic regression techniques for postprocessing GEFS precipitation forecasts. For selecting optimal postprocessing methods, it would be informative to compare the performance of analog methods, which requires long-term reforecast archives, with logistic regression, which only needs a small set of training data. Given the research gaps we have identified, this study aims to 1) document the performance of the GEFS and ECMWF daily precipitation ensemble forecasts using Brazil as case study

Full access
Sid-Ahmed Boukabara, Vladimir Krasnopolsky, Stephen G. Penny, Jebb Q. Stewart, Amy McGovern, David Hall, John E. Ten Hoeve, Jason Hickey, Hung-Lung Allen Huang, John K. Williams, Kayo Ide, Philippe Tissot, Sue Ellen Haupt, Kenneth S. Casey, Nikunj Oza, Alan J. Geer, Eric S. Maddy, and Ross N. Hoffman

observations and satellite applications, including the use of neural networks for NWP model parameterization ( Krasnopolsky et al. 2010 ) and using deep learning to infer missing data ( Boukabara et al. 2019a ). NCAR, a federally funded research and development center, has a long history of developing AI techniques for weather applications. Haupt et al. (2019) highlighted the Dynamic Integrated Forecast (DICast) system, a 20-year effort at NCAR that forms the “weather engine” of many applications, as

Open access
Anthony Wimmers, Christopher Velden, and Joshua H. Cossuth

. Furthermore, a new generation of infrared imagers ( Schmit et al. 2005 , 2017 ) and emerging cubesat sensors ( Blackwell et al. 2012 ; Cahoy et al. 2015 ; Reising et al. 2016 ) require new, robust techniques for TC nowcasting and forecasting that can assimilate a spectrally diverse variety of images all at once. It is well known that the microwave imaging frequencies available on polar-orbiting meteorological satellites since the late 1980s offer unique perspectives for observing TCs. Uses of the

Full access