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.

Regime-dependent statistical post-processing of wind speed forecasts

2020 ◽  
Author(s):  
Sam Allen ◽  
Chris Ferro ◽  
Frank Kwasniok
Keyword(s):  
Wind Speed ◽  
Prediction Models ◽  
Weather Prediction ◽  
Lead Times ◽  
Post Processing ◽  
Ensemble Forecasts ◽  
Atmospheric Flow ◽  
Wind Speeds ◽  
Systematic Biases ◽  
Processing Techniques

<p>Raw output from deterministic numerical weather prediction models is typically subject to systematic biases. Although ensemble forecasts provide invaluable information regarding the uncertainty in a prediction, they themselves often misrepresent the weather that occurs. Given their widespread use, the need for high-quality wind speed forecasts is well-documented. Several statistical approaches have therefore been proposed to recalibrate ensembles of wind speed forecasts, including a heteroscedastic censored regression approach. An extension to this method that utilises the prevailing atmospheric flow is implemented here in a quasigeostrophic simulation study and on reforecast data. It is hoped that this regime-dependent framework can alleviate errors owing to changes in the synoptic-scale atmospheric state. When the wind speed strongly depends on the underlying weather regime, the resulting forecasts have the potential to provide substantial improvements in skill upon conventional post-processing techniques. This is particularly pertinent at longer lead times, where there is more improvement to be gained upon current methods, and in weather regimes associated with wind speeds that differ greatly from climatology. In order to realise this potential, however, an accurate prediction of the future atmospheric regime is required.</p>

scholarly journals Statistical post-processing of wind speed forecasts using convolutional neural networks

2021 ◽  
Author(s):  
Simon Veldkamp ◽  
Kirien Whan ◽  
Sjoerd Dirksen ◽  
Maurice Schmeits
Keyword(s):  
Neural Networks ◽  
Wind Speed ◽  
Convolutional Neural Networks ◽  
Weather Prediction ◽  
Estimation Methods ◽  
Post Processing ◽  
Skill Scores ◽  
Probabilistic Forecasts ◽  
Truncated Normal ◽  
Nwp Model

AbstractCurrent statistical post-processing methods for probabilistic weather forecasting are not capable of using full spatial patterns from the numerical weather prediction (NWP) model. In this paper we incorporate spatial wind speed information by using convolutional neural networks (CNNs) and obtain probabilistic wind speed forecasts in the Netherlands for 48 hours ahead, based on KNMI’s deterministic Harmonie-Arome NWP model. The probabilistic forecasts from the CNNs are shown to have higher Brier skill scores for medium to higher wind speeds, as well as a better continuous ranked probability score (CRPS) and logarithmic score, than the forecasts from fully connected neural networks and quantile regression forests. As a secondary result, we have compared the CNNs using 3 different density estimation methods (quantized softmax (QS), kernel mixture networks, and fitting a truncated normal distribution), and found the probabilistic forecasts based on the QS method to be best.

Calibration of solar radiation ensemble forecasts using convolutional neural network

2021 ◽  
Author(s):  
Florian Dupuy ◽  
Yen-Sen Lu ◽  
Garrett Good ◽  
Michaël Zamo
Keyword(s):  
Neural Network ◽  
Solar Radiation ◽  
Convolutional Neural Network ◽  
Prediction Models ◽  
Weather Prediction ◽  
Special Kind ◽  
Ground Truth ◽  
Weather Forecast ◽  
Ensemble Forecasts ◽  
Processing Techniques

<p><span>E</span><span>nsemble </span><span>forecast </span><span>approaches have become state-of-the-art for the quantification of weather forecast uncertainty. </span><span>However</span><span>, ensemble forecasts </span><span>from</span><span> numerical weather prediction models (NWPs) still tend to be biased and underdispersed, </span>hence justifying the use of statistical post-processing techniques <span>to improve forecast skill. </span></p><p>In this study, ensemble forecasts are post-processed using a convolutional neural network (CNN). CNNs are the most popular machine learning tool to deal with images. In our case, CNNs allow to integrate information from spatial patterns contained in NWP outputs.</p><p>We focus on solar radiation forecasts for 48 hours ahead over Europe from the 35-members ARPEGE (Météo-France global NWP) and a 512-members WRF (Weather Research and Forecasting) ensembles. We used a U-Net (a special kind of CNN) designed to produce a probabilistic forecast (quantiles) using as ground truth the CAMS (Copernicus Atmosphere Monitoring System) radiation service dataset with a spatial resolution of 0.2°.</p>

scholarly journals A framework for probabilistic weather forecast post-processing across models and lead times using machine learning

2021 ◽  
Vol 379 (2194) ◽  
pp. 20200099 ◽  
Author(s):  
Charlie Kirkwood ◽  
Theo Economou ◽  
Henry Odbert ◽  
Nicolas Pugeault
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Probability Distributions ◽  
Weather Prediction ◽  
Weather Forecast ◽  
Predictive Distribution ◽  
Lead Times ◽  
Climate Modelling ◽  
Post Processing ◽  
Probabilistic Forecasts

Forecasting the weather is an increasingly data-intensive exercise. Numerical weather prediction (NWP) models are becoming more complex, with higher resolutions, and there are increasing numbers of different models in operation. While the forecasting skill of NWP models continues to improve, the number and complexity of these models poses a new challenge for the operational meteorologist: how should the information from all available models, each with their own unique biases and limitations, be combined in order to provide stakeholders with well-calibrated probabilistic forecasts to use in decision making? In this paper, we use a road surface temperature example to demonstrate a three-stage framework that uses machine learning to bridge the gap between sets of separate forecasts from NWP models and the ‘ideal’ forecast for decision support: probabilities of future weather outcomes. First, we use quantile regression forests to learn the error profile of each numerical model, and use these to apply empirically derived probability distributions to forecasts. Second, we combine these probabilistic forecasts using quantile averaging. Third, we interpolate between the aggregate quantiles in order to generate a full predictive distribution, which we demonstrate has properties suitable for decision support. Our results suggest that this approach provides an effective and operationally viable framework for the cohesive post-processing of weather forecasts across multiple models and lead times to produce a well-calibrated probabilistic output. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

scholarly journals Detection and thermal description of medicanes from numerical simulation

2014 ◽  
Vol 14 (5) ◽  
pp. 1059-1070 ◽  
Author(s):  
M. A. Picornell ◽  
J. Campins ◽  
A. Jansà
Keyword(s):  
Numerical Simulation ◽  
Thermal Structure ◽  
Weather Prediction ◽  
Weather Forecast ◽  
Small Scale ◽  
Medium Range Weather Forecast ◽  
Warm Core ◽  
Strong Winds ◽  
Nwp Model ◽  
Ecmwf Model

Abstract. Tropical-like cyclones rarely affect the Mediterranean region but they can produce strong winds and heavy precipitations. These warm-core cyclones, called MEDICANES (MEDIterranean hurriCANES), are small in size, develop over the sea and are infrequent. For these reasons, the detection and forecast of medicanes are a difficult task and many efforts have been devoted to identify them. The goals of this work are to contribute to a proper description of these structures and to develop some criteria to identify medicanes from numerical weather prediction (NWP) model outputs. To do that, existing methodologies for detecting, characterizating and tracking cyclones have been adapted to small-scale intense cyclonic perturbations. First, a mesocyclone detection and tracking algorithm has been modified to select intense cyclones. Next, the parameters that define the Hart's cyclone phase diagram are tuned and calculated to examine their thermal structure. Four well-known medicane events have been described from numerical simulation outputs of the European Centre for Medium-Range Weather Forecast (ECMWF) model. The predicted cyclones and their evolution have been validated against available observational data and numerical analyses from the literature.

scholarly journals Understanding the relationship between clouds and surface downward radiation forecast errors with Unsupervised Deep Learning

2021 ◽  
Author(s):  
Matthias Zech ◽  
Lueder von Bremen
Keyword(s):  
Deep Learning ◽  
Unsupervised Learning ◽  
Prediction Models ◽  
Weather Prediction ◽  
Reanalysis Data ◽  
Cloud Formation ◽  
Trade Wind ◽  
Forecast Errors ◽  
Model Learning ◽  
Unsupervised Deep Learning

<p>Cloudiness is a difficult parameter to forecast and has improved relatively little over the last decade in numerical weather prediction models as the EMCWF IFS. However, surface downward solar radiation forecast (ssrd) errors are becoming more important with higher penetration of photovoltaics in Europe as forecasts errors induce power imbalances that might lead to high balancing costs. This study continues recent approaches to better understand clouds using satellite images with Deep Learning. Unlike other studies which focus on shallow trade wind cumulus clouds over the ocean, this study investigates the European land area. To better understand the clouds, we use the daily MODIS optical cloud thickness product which shows both water and ice phase of the cloud. This allows to consider both cloud structure and cloud formation during learning. It is also much easier to distinguish between snow and cloud in contrast to using visible bands. Methodologically, it uses the Unsupervised Learning approach <em>tile2vec</em> to derive a lower dimensional representation of the clouds. Three cloud regions with two similar neighboring tiles and one tile from a different time and location are sampled to learn lower-rank embeddings. In contrast to the initial <em>tile2vec</em> implementation, this study does not sample arbitrarily distant tiles but uses the fractal dimension of the clouds in a pseudo-random sampling fashion to improve model learning.</p><p>The usefulness of the cloud segments is shown by applying them in a case study to investigate statistical properties of ssrd forecast errors over Europe which are derived from hourly ECMWF IFS forecasts and ERA5 reanalysis data. This study shows how Unsupervised Learning has high potential despite its relatively low usage compared to Supervised Learning in academia. It further shows, how the generated land cloud product can be used to better characterize ssrd forecast errors over Europe.</p>

scholarly journals Generating wind power scenarios for probabilistic ramp event prediction using multivariate statistical post-processing

2018 ◽  
Author(s):  
Rochelle P. Worsnop ◽  
Michael Scheuerer ◽  
Thomas M. Hamill ◽  
Julie K. Lundquist
Keyword(s):  
Wind Speed ◽  
Wind Power ◽  
Wind Farm ◽  
Weather Prediction ◽  
Model Performance ◽  
The United States ◽  
Numerical Weather Prediction Model ◽  
Post Processing ◽  
Skill Scores ◽  
Ramp Events

Abstract. Wind power forecasting is gaining international significance as more regions promote policies to increase the use of renewable energy. Wind ramps, large variations in wind power production during a period of minutes to hours, challenge utilities and electrical balancing authorities. A sudden decrease in wind energy production must be balanced by other power generators to meet energy demands, while a sharp increase in unexpected production results in excess power that may not be used in the power grid, leading to a loss of potential profits. In this study, we compare different methods to generate probabilistic ramp forecasts from the High Resolution Rapid Refresh (HRRR) numerical weather prediction model with up to twelve hours of lead time at two tall-tower locations in the United States. We validate model performance using 21 months of 80-m wind speed observations from towers in Boulder, Colorado and near the Columbia River Gorge in eastern Oregon. We employ four statistical post-processing methods, three of which are not currently used in the literature for wind forecasting. These procedures correct biases in the model and generate short-term wind speed scenarios which are then converted to power scenarios. This probabilistic enhancement of HRRR point forecasts provides valuable uncertainty information of ramp events and improves the skill of predicting ramp events over the raw forecasts. We compute Brier skill scores for each method at predicting up- and down-ramps to determine which method provides the best prediction. We find that the Standard Schaake Shuffle method yields the highest skill at predicting ramp events for these data sets, especially for up-ramp events at the Oregon site. Increased skill for ramp prediction is limited at the Boulder, CO site using any of the multivariate methods, because of the poor initial forecasts in this area of complex terrain. These statistical methods can be implemented by wind farm operators to generate a range of possible wind speed and power scenarios to aid and optimize decisions before ramp events occur.

scholarly journals Evaluation of Combined Satellite and Radar Data Assimilation with POD-4DEnVar Method on Rainfall Forecast

2020 ◽  
Vol 10 (16) ◽  
pp. 5493 ◽  
Author(s):  
Jingnan Wang ◽  
Lifeng Zhang ◽  
Jiping Guan ◽  
Mingyang Zhang
Keyword(s):  
Data Assimilation ◽  
Weather Prediction ◽  
Weather Forecast ◽  
Radar Data ◽  
Precipitation Forecast ◽  
Rainfall Forecast ◽  
Skill Scores ◽  
The Individual ◽  
The Impact ◽  
Radar Data Assimilation

Satellite and radar observations represent two fundamentally different remote sensing observation types, providing independent information for numerical weather prediction (NWP). Because the individual impact on improving forecast has previously been examined, combining these two resources of data potentially enhances the performance of weather forecast. In this study, satellite radiance, radar radial velocity and reflectivity are simultaneously assimilated with the Proper Orthogonal Decomposition (POD)-based ensemble four-dimensional variational (4DVar) assimilation method (referred to as POD-4DEnVar). The impact is evaluated on continuous severe rainfall processes occurred from June to July in 2016 and 2017. Results show that combined assimilation of satellite and radar data with POD-4DEnVar has the potential to improve weather forecast. Averaged over 22 forecasts, RMSEs indicate that though the forecast results are sensitive to different variables, generally the improvement is found in different pressure levels with assimilation. The precipitation skill scores are generally increased when assimilation is carried out. A case study is also examined to figure out the contributions to forecast improvement. Better intensity and distribution of precipitation forecast is found in the accumulated rainfall evolution with POD-4DEnVar assimilation. These improvements are attributed to the local changes in moisture, temperature and wind field. In addition, with radar data assimilation, the initial rainwater and cloud water conditions are changed directly. Both experiments can simulate the strong hydrometeor in the precipitation area, but assimilation spins up faster, strengthening the initial intensity of the heavy rainfall. Generally, the combined assimilation of satellite and radar data results in better rainfall forecast than without data assimilation.

scholarly journals The Diurnal Cycle of Precipitation from Continental Radar Mosaics and Numerical Weather Prediction Models. Part II: Intercomparison among Numerical Models and with Nowcasting

2012 ◽  
Vol 140 (8) ◽  
pp. 2689-2705 ◽  
Author(s):  
Marc Berenguer ◽  
Madalina Surcel ◽  
Isztar Zawadzki ◽  
Ming Xue ◽  
Fanyou Kong
Keyword(s):  
Diurnal Cycle ◽  
Prediction Models ◽  
Numerical Models ◽  
Weather Prediction ◽  
Model Performance ◽  
Radar Data ◽  
Skill Scores ◽  
Diurnal Cycle Of Precipitation ◽  
Timing Of Initiation ◽  
Short Term Forecasting

Abstract This second part of a two-paper series compares deterministic precipitation forecasts from the Storm-Scale Ensemble Forecast System (4-km grid) run during the 2008 NOAA Hazardous Weather Testbed (HWT) Spring Experiment, and from the Canadian Global Environmental Multiscale (GEM) model (15 km), in terms of their ability to reproduce the average diurnal cycle of precipitation during spring 2008. Moreover, radar-based nowcasts generated with the McGill Algorithm for Precipitation Nowcasting Using Semi-Lagrangian Extrapolation (MAPLE) are analyzed to quantify the portion of the diurnal cycle explained by the motion of precipitation systems, and to evaluate the potential of the NWP models for very short-term forecasting. The observed diurnal cycle of precipitation during spring 2008 is characterized by the dominance of the 24-h harmonic, which shifts with longitude, consistent with precipitation traveling across the continent. Time–longitude diagrams show that the analyzed NWP models partially reproduce this signal, but show more variability in the timing of initiation in the zonal motion of the precipitation systems than observed from radar. Traditional skill scores show that the radar data assimilation is the main reason for differences in model performance, while the analyzed models that do not assimilate radar observations have very similar skill. The analysis of MAPLE forecasts confirms that the motion of precipitation systems is responsible for the dominance of the 24-h harmonic in the longitudinal range 103°–85°W, where 8-h MAPLE forecasts initialized at 0100, 0900, and 1700 UTC successfully reproduce the eastward motion of rainfall systems. Also, on average, MAPLE outperforms radar data assimilating models for the 3–4 h after initialization, and nonradar data assimilating models for up to 5 h after initialization.

scholarly journals Climatology and Trend of Severe Drought Events in the State of Sao Paulo, Brazil, during the 20th Century

Atmosphere ◽  
2019 ◽  
Vol 10 (4) ◽  
pp. 190 ◽  
Author(s):  
Luiz Gozzo ◽  
Doris Palma ◽  
Maria Custodio ◽  
Jeferson Machado
Keyword(s):  
20Th Century ◽  
Linear Trend ◽  
Weather Forecast ◽  
Reanalysis Data ◽  
Sao Paulo ◽  
The State ◽  
Economic Consequences ◽  
Severe Drought ◽  
São Paulo ◽  
Medium Range Weather Forecast

Drought is a natural hazard with critical societal and economic consequences to millions of people around the world. In this paper, we present the climatology of severe drought events that occurred during the 20th century in the region of Sao Paulo, Brazil. To account for the effects of rainfall deficit and changes in temperature at a climatic timescale, we chose the Standardized Precipitation Evapotranspiration Index (SPEI) to identify severe droughts over the city of Sao Paulo, and the eastern and central-western regions of the state. Events were identified using weather station data and European Centre for Medium-Range Weather Forecast (ECMWF) reanalysis data, in order to assess the representation of drought periods in both datasets. Results show that the reanalysis seems suitable to represent the number of events and their mean duration, severity and intensity, but the timing and characteristics of individual events are not well reproduced. The correlation between observation and reanalysis SPEI time series is low to moderate in all cases. A linear trend analysis between 1901 and 2010 shows a tendency of increasing (decreasing) severe drought events in the central and western (eastern) Sao Paulo state, according to observational data. This is in agreement with previous findings, and the reanalysis presents this same signal. The weakened trend values in the reanalysis may be associated with issues in representing precipitation in this dataset.

Sign in / Sign up

Export Citation Format

Share Document