Machine Learning Enhancement of Storm-Scale Ensemble Probabilistic Quantitative Precipitation Forecasts

2014 ◽  
Vol 29 (4) ◽  
pp. 1024-1043 ◽  
Author(s):  
David John Gagne ◽  
Amy McGovern ◽  
Ming Xue
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Weather Prediction ◽  
Precipitation Forecast ◽  
Spatial And Temporal Scales ◽  
Small Areas ◽  
Probabilistic Forecasts ◽  
Quantitative Precipitation Forecasts ◽  
Wide Variability ◽  
Added Uncertainty

Abstract Probabilistic quantitative precipitation forecasts challenge meteorologists due to the wide variability of precipitation amounts over small areas and their dependence on conditions at multiple spatial and temporal scales. Ensembles of convection-allowing numerical weather prediction models offer a way to produce improved precipitation forecasts and estimates of the forecast uncertainty. These models allow for the prediction of individual convective storms on the model grid, but they often displace the storms in space, time, and intensity, which results in added uncertainty. Machine learning methods can produce calibrated probabilistic forecasts from the raw ensemble data that correct for systemic biases in the ensemble precipitation forecast and incorporate additional uncertainty information from aggregations of the ensemble members and additional model variables. This study utilizes the 2010 Center for Analysis and Prediction of Storms Storm-Scale Ensemble Forecast system and the National Severe Storms Laboratory National Mosaic & Multi-Sensor Quantitative Precipitation Estimate as input data for training logistic regressions and random forests to produce a calibrated probabilistic quantitative precipitation forecast. The reliability and discrimination of the forecasts are compared through verification statistics and a case study.

scholarly journals Storm-Based Probabilistic Hail Forecasting with Machine Learning Applied to Convection-Allowing Ensembles

2017 ◽  
Vol 32 (5) ◽  
pp. 1819-1840 ◽  
Author(s):  
David John Gagne ◽  
Amy McGovern ◽  
Sue Ellen Haupt ◽  
Ryan A. Sobash ◽  
John K. Williams ◽  
...  
Keyword(s):  
Machine Learning ◽  
Size Distribution ◽  
Prediction Models ◽  
Weather Prediction ◽  
Radar Data ◽  
Object Identification ◽  
Atmospheric Conditions ◽  
Learning Models ◽  
Probabilistic Machine Learning ◽  
Machine Learning Models

Abstract Forecasting severe hail accurately requires predicting how well atmospheric conditions support the development of thunderstorms, the growth of large hail, and the minimal loss of hail mass to melting before reaching the surface. Existing hail forecasting techniques incorporate information about these processes from proximity soundings and numerical weather prediction models, but they make many simplifying assumptions, are sensitive to differences in numerical model configuration, and are often not calibrated to observations. In this paper a storm-based probabilistic machine learning hail forecasting method is developed to overcome the deficiencies of existing methods. An object identification and tracking algorithm locates potential hailstorms in convection-allowing model output and gridded radar data. Forecast storms are matched with observed storms to determine hail occurrence and the parameters of the radar-estimated hail size distribution. The database of forecast storms contains information about storm properties and the conditions of the prestorm environment. Machine learning models are used to synthesize that information to predict the probability of a storm producing hail and the radar-estimated hail size distribution parameters for each forecast storm. Forecasts from the machine learning models are produced using two convection-allowing ensemble systems and the results are compared to other hail forecasting methods. The machine learning forecasts have a higher critical success index (CSI) at most probability thresholds and greater reliability for predicting both severe and significant hail.

scholarly journals Hybrid Machine Learning for Solar Radiation Prediction in Reduced Feature Spaces

Energies ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 7970
Author(s):  
Abdel-Rahman Hedar ◽  
Majid Almaraashi ◽  
Alaa E. Abdel-Hakim ◽  
Mahmoud Abdulrahim
Keyword(s):  
Machine Learning ◽  
Solar Radiation ◽  
Root Mean Square ◽  
Prediction Models ◽  
Weather Prediction ◽  
Hybrid Models ◽  
Mean Square ◽  
Learning Models ◽  
Mean Square Errors ◽  
Machine Learning Models

Solar radiation prediction is an important process in ensuring optimal exploitation of solar energy power. Numerous models have been applied to this problem, such as numerical weather prediction models and artificial intelligence models. However, well-designed hybridization approaches that combine numerical models with artificial intelligence models to yield a more powerful model can provide a significant improvement in prediction accuracy. In this paper, novel hybrid machine learning approaches that exploit auxiliary numerical data are proposed. The proposed hybrid methods invoke different machine learning paradigms, including feature selection, classification, and regression. Additionally, numerical weather prediction (NWP) models are used in the proposed hybrid models. Feature selection is used for feature space dimension reduction to reduce the large number of recorded parameters that affect estimation and prediction processes. The rough set theory is applied for attribute reduction and the dependency degree is used as a fitness function. The effect of the attribute reduction process is investigated using thirty different classification and prediction models in addition to the proposed hybrid model. Then, different machine learning models are constructed based on classification and regression techniques to predict solar radiation. Moreover, other hybrid prediction models are formulated to use the output of the numerical model of Weather Research and Forecasting (WRF) as learning elements in order to improve the prediction accuracy. The proposed methodologies are evaluated using a data set that is collected from different regions in Saudi Arabia. The feature-reduction has achieved higher classification rates up to 8.5% for the best classifiers and up to 15% for other classifiers, for the different data collection regions. Additionally, in the regression, it achieved improvements of average root mean square error up to 5.6% and in mean absolute error values up to 8.3%. The hybrid models could reduce the root mean square errors by 70.2% and 4.3% than the numerical and machine learning models, respectively, when these models are applied to some dataset. For some reduced feature data, the hybrid models could reduce the root mean square errors by 47.3% and 14.4% than the numerical and machine learning models, respectively.

scholarly journals Performance of IMD multi-model ensemble and WRF (ARW) model for sub-basin wise rainfall forecast during monsoon 2012

MAUSAM ◽  
2021 ◽  
Vol 67 (2) ◽  
pp. 323-332
Author(s):  
ASHOK KUMAR DAS ◽  
SURINDER KAUR
Keyword(s):  
Prediction Models ◽  
Weather Prediction ◽  
India Meteorological Department ◽  
Precipitation Forecast ◽  
False Alarms ◽  
Model Ensemble ◽  
Rainfall Forecast ◽  
Quantitative Precipitation Forecast ◽  
Arw Model ◽  
Nwp Model

The Numerical Weather Prediction models, Multi-model Ensemble (MME) (27 km × 27 km) and WRF (ARW) (9 km × 9 km) operationally run by India Meteorological Department (IMD) have been utilized to estimate sub-basin wise rainfall forecast. The sub-basin wise operational Quantitative Precipitation Forecast (QPF) have been issued by 10 field offices named Flood Meteorological Offices (FMOs) of IMD located at different flood prone areas of the country. The daily sub-basin wise NWP model rainfall forecast for 122 sub basins under these 10 FMOs for the flood season 2012 have been estimated on operational basis which are used by forecasters at FMOs as a guidance for the issue of operational sub-basin QPF for flood forecasting purposes. The performance of the MME and WRF (ARW) models rainfall at the sub-basin level have been studied in detail. The performance of WRF (ARW) and MME models is compared in the heavy rainfall case over the river basins (Mahanadi etc.) falls under FMO, Bhubaneswar and it is found that WRF (ARW) model gives better result than MME. It is also found that performance of WRF (ARW) is little better than MME when compared over all the flood prone river sub basins of India. For high rainfall categories (51-100,  >100 mm), generally these leads to floods, the success rate of model rainfall forecasts are less and false alarms are more. The NWP models are able to capture the rainfall events but there is difference in magnitudes of sub basin wise rainfall estimates.

scholarly journals Can machine learning improve the model representation of TKE dissipation rate in the boundary layer for complex terrain?

2020 ◽  
Author(s):  
Nicola Bodini ◽  
Julie K. Lundquist ◽  
Mike Optis
Keyword(s):  
Machine Learning ◽  
Numerical Weather Prediction ◽  
Complex Terrain ◽  
Dissipation Rate ◽  
Prediction Models ◽  
Weather Prediction ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Tke Dissipation Rate ◽  
Numerical Weather Prediction Models

Abstract. Current turbulence parameterizations in numerical weather prediction models at the mesoscale assume a local equilibrium between production and dissipation of turbulence. As this assumption does not hold at fine horizontal resolutions, improved ways to represent turbulent kinetic energy (TKE) dissipation rate (ε) are needed. Here, we use a 6-week data set of turbulence measurements from 184 sonic anemometers in complex terrain at the Perdigão field campaign to suggest improved representations of dissipation rate. First, we demonstrate that a widely used Mellor, Yamada, Nakanishi, and Niino (MYNN) parameterization of TKE dissipation rate leads to a large inaccuracy and bias in the representation of ε. Next, we assess the potential of machine-learning techniques to predict TKE dissipation rate from a set of atmospheric and terrain-related features. We train and test several machine-learning algorithms using the data at Perdigão, and we find that multivariate polynomial regressions and random forests can eliminate the bias MYNN currently shows in representing ε, while also reducing the average error by up to 30 %. Of all the variables included in the algorithms, TKE is the variable responsible for most of the variability of ε, and a strong positive correlation exists between the two. These results suggest further consideration of machine-learning techniques to enhance parameterizations of turbulence in numerical weather prediction models.

scholarly journals A multiscale approach for precipitation verification applied to the FORALPS case studies

2008 ◽  
Vol 16 ◽  
pp. 3-9 ◽  
Author(s):  
A. Lanciani ◽  
S. Mariani ◽  
M. Casaioli ◽  
C. Accadia ◽  
N. Tartaglione
Keyword(s):  
Power Spectrum ◽  
Prediction Models ◽  
Weather Prediction ◽  
Power Spectra ◽  
Multiscale Methods ◽  
Precipitation Forecast ◽  
Diagnostic Tools ◽  
Small Scale ◽  
Multiscale Approach ◽  
Skill Scores

Abstract. Multiscale methods, such as the power spectrum, are suitable diagnostic tools for studying the second order statistics of a gridded field. For instance, in the case of Numerical Weather Prediction models, a drop in the power spectrum for a given scale indicates the inability of the model to reproduce the variance of the phenomenon below the correspondent spatial scale. Hence, these statistics provide an insight into the real resolution of a gridded field and must be accurately known for interpolation and downscaling purposes. In this work, belonging to the EU INTERREG IIIB Alpine Space FORALPS project, the power spectra of the precipitation fields for two intense rain events, which occurred over the north-eastern alpine region, have been studied in detail. A drop in the power spectrum at the shortest scales (about 30 km) has been found, as well as a strong matching between the precipitation spectrum and the spectrum of the orography. Furthermore, it has also been shown how the spectra help understand the behavior of the skill scores traditionally used in Quantitative Precipitation Forecast verification, as these are sensitive to the amount of small scale detail present in the fields.

scholarly journals Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?

2020 ◽  
Vol 13 (9) ◽  
pp. 4271-4285
Author(s):  
Nicola Bodini ◽  
Julie K. Lundquist ◽  
Mike Optis
Keyword(s):  
Machine Learning ◽  
Kinetic Energy ◽  
Complex Terrain ◽  
Dissipation Rate ◽  
Prediction Models ◽  
Weather Prediction ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Tke Dissipation Rate ◽  
Numerical Weather Prediction Models

Abstract. Current turbulence parameterizations in numerical weather prediction models at the mesoscale assume a local equilibrium between production and dissipation of turbulence. As this assumption does not hold at fine horizontal resolutions, improved ways to represent turbulent kinetic energy (TKE) dissipation rate (ϵ) are needed. Here, we use a 6-week data set of turbulence measurements from 184 sonic anemometers in complex terrain at the Perdigão field campaign to suggest improved representations of dissipation rate. First, we demonstrate that the widely used Mellor, Yamada, Nakanishi, and Niino (MYNN) parameterization of TKE dissipation rate leads to a large inaccuracy and bias in the representation of ϵ. Next, we assess the potential of machine-learning techniques to predict TKE dissipation rate from a set of atmospheric and terrain-related features. We train and test several machine-learning algorithms using the data at Perdigão, and we find that the models eliminate the bias MYNN currently shows in representing ϵ, while also reducing the average error by up to almost 40 %. Of all the variables included in the algorithms, TKE is the variable responsible for most of the variability of ϵ, and a strong positive correlation exists between the two. These results suggest further consideration of machine-learning techniques to enhance parameterizations of turbulence in numerical weather prediction models.

Probabilistic fire-danger forecasting: A framework for week-two forecasts using statistical post-processing techniques and the Global ECMWF Fire Forecast System (GEFF)

2021 ◽  
Author(s):  
Rochelle P. Worsnop ◽  
Michael Scheuerer ◽  
Francesca Di Giuseppe ◽  
Christopher Barnard ◽  
Thomas M. Hamill ◽  
...  
Keyword(s):  
Prediction Models ◽  
Weather Prediction ◽  
Weather Forecast ◽  
Reanalysis Data ◽  
Post Processing ◽  
Medium Range Weather Forecast ◽  
Skill Scores ◽  
Probabilistic Forecasts ◽  
Systematic Biases ◽  
Processing Techniques

AbstractWildfire guidance two weeks ahead is needed for strategic planning of fire mitigation and suppression. However, fire forecasts driven by meteorological forecasts from numerical weather prediction models inherently suffer from systematic biases. This study uses several statistical-postprocessing methods to correct these biases and increase the skill of ensemble fire forecasts over the contiguous United States 8–14 days ahead. We train and validate the post-processing models on 20 years of European Centre for Medium-range Weather Forecast (ECMWF) reforecasts and ERA5 reanalysis data for 11 meteorological variables related to fire, such as surface temperature, wind speed, relative humidity, cloud cover, and precipitation. The calibrated variables are then input to the Global ECMWF Fire Forecast (GEFF) system to produce probabilistic forecasts of daily fire-indicators which characterize the relationships between fuels, weather, and topography. Skill scores show that the post-processed forecasts overall have greater positive skill at Days 8–14 relative to raw and climatological forecasts. It is shown that the post-processed forecasts are more reliable at predicting above- and below-normal probabilities of various fire indicators than the raw forecasts and that the greatest skill for Days 8–14 is achieved by aggregating forecast days together.

Probabilistic Wind Vector Forecasting Using Ensembles and Bayesian Model Averaging

2013 ◽  
Vol 141 (6) ◽  
pp. 2107-2119 ◽  
Author(s):  
J. McLean Sloughter ◽  
Tilmann Gneiting ◽  
Adrian E. Raftery
Keyword(s):  
Bayesian Model ◽  
Bayesian Model Averaging ◽  
Prediction Models ◽  
Weather Prediction ◽  
Model Averaging ◽  
Wind Vector ◽  
Bivariate Distributions ◽  
Ensemble Forecasts ◽  
Probabilistic Forecasts ◽  
Wide Range

Abstract Probabilistic forecasts of wind vectors are becoming critical as interest grows in wind as a clean and renewable source of energy, in addition to a wide range of other uses, from aviation to recreational boating. Unlike other common forecasting problems, which deal with univariate quantities, statistical approaches to wind vector forecasting must be based on bivariate distributions. The prevailing paradigm in weather forecasting is to issue deterministic forecasts based on numerical weather prediction models. Uncertainty can then be assessed through ensemble forecasts, where multiple estimates of the current state of the atmosphere are used to generate a collection of deterministic predictions. Ensemble forecasts are often uncalibrated, however, and Bayesian model averaging (BMA) is a statistical way of postprocessing these forecast ensembles to create calibrated predictive probability density functions (PDFs). It represents the predictive PDF as a weighted average of PDFs centered on the individual bias-corrected forecasts, where the weights reflect the forecasts’ relative contributions to predictive skill over a training period. In this paper the authors extend the BMA methodology to use bivariate distributions, enabling them to provide probabilistic forecasts of wind vectors. The BMA method is applied to 48-h-ahead forecasts of wind vectors over the North American Pacific Northwest in 2003 using the University of Washington mesoscale ensemble and is shown to provide better-calibrated probabilistic forecasts than the raw ensemble, which are also sharper than probabilistic forecasts derived from climatology.

Sign in / Sign up

Export Citation Format

Share Document