scholarly journals Verification Results from the 2017 HMT–WPC Flash Flood and Intense Rainfall Experiment

2019 ◽  
Vol 58 (12) ◽  
pp. 2591-2604 ◽  
Author(s):  
Michael J. Erickson ◽  
Joshua S. Kastman ◽  
Benjamin Albright ◽  
Sarah Perfater ◽  
James A. Nelson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Flash Flood ◽  
Weather Prediction ◽  
Stage Iv ◽  
Skill Score ◽  
Machine Learning Techniques ◽  
Intense Rainfall ◽  
Deterministic Models ◽  
Relative Operating Characteristic ◽  
Risk Categories

AbstractThe Flash Flood and Intense Rainfall (FFaIR) Experiment developed within the Hydrometeorology Testbed (HMT) of the Weather Prediction Center (WPC) is a pseudo-operational platform for participants from across the weather enterprise to test emerging flash flood forecasting tools and issue experimental forecast products. This study presents the objective verification portion of the 2017 edition of the experiment, which examines the performance from a variety of guidance tools (deterministic models, ensembles, and machine-learning techniques) and the participants’ forecasts, with occasional reference to the participants’ subjective ratings. The skill of the model guidance used in the FFaIR Experiment is evaluated using performance diagrams verified against the Stage IV analysis. The operational and FFaIR Experiment versions of the excessive rainfall outlook (ERO) are evaluated by assessing the frequency of issuances, probabilistic calibration, Brier skill score (BSS), and area under relative operating characteristic (AuROC). An ERO first-guess field called the Colorado State University Machine-Learning Probabilities method (CSU-MLP) is also evaluated in the FFaIR Experiment. Among convection-allowing models, the Met Office Unified Model generally performed optimally throughout the FFaIR Experiment when using performance diagrams (at the 0.5- and 1-in. thresholds; 1 in. = 25.4 mm), whereas the High-Resolution Rapid Refresh (HRRR), version 3, performed best subjectively. In terms of subjective and objective ensemble scores, the HRRR ensemble scored optimally. The CSU-MLP overpredicted lower risk categories and underpredicted higher risk categories, but it shows future promise as an ERO first-guess field. The EROs issued by the FFaIR Experiment forecasters had improved BSS and AuROC relative to the operational ERO, suggesting that the experimental guidance may have aided forecasters.

Exploring multi-modalities in weather prediction using a univariate graph based on machine learning techniques

2021 ◽  
Author(s):  
Natacha Galmiche ◽  
Nello Blaser ◽  
Morten Brun ◽  
Helwig Hauser ◽  
Thomas Spengler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Standard Deviation ◽  
Probability Distributions ◽  
Weather Prediction ◽  
A Priori ◽  
Clustering Algorithms ◽  
Quantitative Information ◽  
Machine Learning Techniques ◽  
Topological Data Analysis ◽  
Learning Techniques

<p>Probability distributions based on ensemble forecasts are commonly used to assess uncertainty in weather prediction. However, interpreting these distributions is not trivial, especially in the case of multimodality with distinct likely outcomes. The conventional summary employs mean and standard deviation across ensemble members, which works well for unimodal, Gaussian-like distributions. In the case of multimodality this misleads, discarding crucial information. </p><p>We aim at combining previously developed clustering algorithms in machine learning and topological data analysis to extract useful information such as the number of clusters in an ensemble. Given the chaotic behaviour of the atmosphere, machine learning techniques can provide relevant results even if no, or very little, a priori information about the data is available. In addition, topological methods that analyse the shape of the data can make results explainable.</p><p>Given an ensemble of univariate time series, a graph is generated whose edges and vertices represent clusters of members, including additional information for each cluster such as the members belonging to them, their uncertainty, and their relevance according to the graph. In the case of multimodality, this approach provides relevant and quantitative information beyond the commonly used mean and standard deviation approach that helps to further characterise the predictability.</p>

Forecasting excessive rainfall with random forests and a deterministic convection-allowing model

2021 ◽  
Author(s):  
Aaron J. Hill ◽  
Russ S. Schumacher
Keyword(s):  
Great Plains ◽  
Flash Flood ◽  
Weather Prediction ◽  
Stage Iv ◽  
Careful Consideration ◽  
Forecast Skill ◽  
Northern Great Plains ◽  
Training Models ◽  
Early Fall ◽  
Recurrence Intervals

AbstractApproximately seven years of daily initializations from the convection-allowing National Severe Storms Laboratory Weather Research and Forecasting model are used as inputs to train random forest (RF) machine learning models to probabilistically predict instances of excessive rainfall. Unlike other hazards, excessive rainfall does not have an accepted definition, so multiple definitions of excessive rainfall and flash flooding – including flash flood reports and 24-hr average recurrence intervals (ARIs) – are used to explore RF configuration forecast sensitivities. RF forecasts are analogous to operational Weather Prediction Center (WPC) day-1 Excessive Rainfall Outlooks (EROs) and their resolution, reliability, and skill are strongly influenced by rainfall definitions and how inputs are assembled for training. Models trained with 1-y ARI exceedances defined by the Stage-IV (ST4) precipitation analysis perform poorly in the northern Great Plains and southwest U.S., in part due to a high bias in the number of training events in these regions. Increasing the ARI threshold to 2 years or removing ST4 data from training, optimizing forecast skill geographically, and spatially averaging meteorological inputs for training generally results in improved CONUS-wide RF forecast skill. Both EROs and RF forecasts have seasonal skill – poor forecasts in the late fall and winter and skillful forecasts in the summer and early fall. However, the EROs are consistently and significantly better than their RF counterparts, regardless of RF configuration, particularly in the summer months. The results suggest careful consideration should be made when developing ML-based probabilistic precipitation forecasts with convection-allowing model inputs, and further development is necessary to consider these forecast products for operational implementation.

scholarly journals A Precipitation Nowcasting Mechanism for Real-World Data Based on Machine Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Yanfei Xiang ◽  
Jianbing Ma ◽  
Xi Wu
Keyword(s):  
Machine Learning ◽  
Optical Flow ◽  
Weather Prediction ◽  
Radar Data ◽  
Machine Learning Techniques ◽  
Economic Losses ◽  
Model Parameters ◽  
Real World Data ◽  
Flow Method ◽  
Optical Flow Method

Unpredicted precipitations, even mild, may cause severe economic losses to many businesses. Precipitation nowcasting is hence significant for people to make correct decisions timely. For traditional methods, such as numerical weather prediction (NWP), the accuracy is limited because the smaller scale of strong convective weather must be smaller than the minimum scale that the model can capture. And it often requires a supercomputer. Furthermore, the optical flow method has been proved to be available for precipitation nowcasting. However, it is difficult to determine the model parameters because the two steps of tracking and extrapolation are separate. In contrast, current machine learning applications are based on well-selected full datasets, ignoring the fact that real datasets quite often contain missing data requiring extra consideration. In this paper, we used a real Hubei dataset in which a few radar echo data are missing and proposed a proper mechanism to deal with the situation. Furthermore, we proposed a novel mechanism for radar reflectivity data with single altitudes or cumulative altitudes using machine learning techniques. From the experimental results, we conclude that our method can predict future precipitation with a high accuracy when a few data are missing, and it outperforms the traditional optical flow method. In addition, our model can be used for various types of radar data with a type-specific feature extraction, which makes the method more flexible and suitable for most situations.

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 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.

Towards Predicting Flood Event Peak Discharge in Ungauged Basins by Learning Universal Hydrological Behaviors with Machine Learning

2021 ◽  
Author(s):  
Akhil Sanjay Potdar ◽  
Pierre-Emmanuel Kirstetter ◽  
Devon Woods ◽  
Manabendra Saharia
Keyword(s):  
Machine Learning ◽  
Spatial Variability ◽  
Spatial Organization ◽  
Flash Flood ◽  
Rainfall Variability ◽  
Peak Discharge ◽  
Machine Learning Techniques ◽  
Major Influence ◽  
Flood Peak ◽  
Basin Scale

AbstractIn the hydrological sciences, the outstanding challenge of regional modeling requires to capture common and event-specific hydrologic behaviors driven by rainfall spatial variability and catchment physiography during floods. The overall objective of this study is to develop robust understanding and predictive capability of how rainfall spatial variability influences flood peak discharge relative to basin physiography. A machine learning approach is used on a high-resolution dataset of rainfall and flooding events spanning 10 years, with rainfall events and basins of widely varying characteristics selected across the continental United States. It overcomes major limitations in prior studies that were based on limited observations or hydrological model simulations. This study explores first-order dependencies in the relationships between peak discharge, rainfall variability, and basin physiography, and it sheds light on these complex interactions using a multi-dimensional statistical modeling approach. Amongst different machine learning techniques, XGBoost is used to determine the significant physiographical and rainfall characteristics that influence peak discharge through variable importance analysis. A parsimonious model with low bias and variance is created which can be deployed in the future for flash flood forecasting. The results confirm that although the spatial organization of rainfall within a basin has a major influence on basin response, basin physiography is the primary driver of peak discharge. These findings have unprecedented spatial and temporal representativeness in terms of flood characterization across basins. An improved understanding of sub-basin scale rainfall spatial variability will aid in robust flash flood characterization as well as with identifying basins which could most benefit from distributed hydrologic modeling.

scholarly journals Multi-Step Ahead Wind Power Generation Prediction Based on Hybrid Machine Learning Techniques

Energies ◽  
2018 ◽  
Vol 11 (8) ◽  
pp. 1975 ◽  
Author(s):  
Wei Dong ◽  
Qiang Yang ◽  
Xinli Fang
Keyword(s):  
Machine Learning ◽  
Phase Space ◽  
Fuzzy Inference ◽  
Weather Prediction ◽  
Wind Farms ◽  
Machine Learning Techniques ◽  
Multiple Time ◽  
Inference System ◽  
Learning Techniques ◽  
Benchmark Solutions

Accurate generation prediction at multiple time-steps is of paramount importance for reliable and economical operation of wind farms. This study proposed a novel algorithmic solution using various forms of machine learning techniques in a hybrid manner, including phase space reconstruction (PSR), input variable selection (IVS), K-means clustering and adaptive neuro-fuzzy inference system (ANFIS). The PSR technique transforms the historical time series into a set of phase-space variables combining with the numerical weather prediction (NWP) data to prepare candidate inputs. A minimal redundancy maximal relevance (mRMR) criterion based filtering approach is used to automatically select the optimal input variables for the multi-step ahead prediction. Then, the input instances are divided into a set of subsets using the K-means clustering to train the ANFIS. The ANFIS parameters are further optimized to improve the prediction performance by the use of particle swarm optimization (PSO) algorithm. The proposed solution is extensively evaluated through case studies of two realistic wind farms and the numerical results clearly confirm its effectiveness and improved prediction accuracy compared to benchmark solutions.

scholarly journals Combining Ensemble Kalman Filter and Reservoir Computing to predict spatio-temporal chaotic systems from imperfect observations and models

2020 ◽  
Author(s):  
Futo Tomizawa ◽  
Yohei Sawada
Keyword(s):  
Machine Learning ◽  
Kalman Filter ◽  
Chaotic Systems ◽  
Weather Prediction ◽  
Machine Learning Techniques ◽  
Reservoir Computing ◽  
Learning Techniques ◽  
Spatio Temporal ◽  
Ensemble Transform Kalman Filter ◽  
Lorenz 96

Abstract. Prediction of spatio-temporal chaotic systems is important in various fields, such as Numerical Weather Prediction (NWP). While data assimilation methods have been applied in NWP, machine learning techniques, such as Reservoir Computing (RC), are recently recognized as promising tools to predict spatio-temporal chaotic systems. However, the sensitivity of the skill of the machine learning based prediction to the imperfectness of observations is unclear. In this study, we evaluate the skill of RC with noisy and sparsely distributed observations. We intensively compare the performances of RC and Local Ensemble Transform Kalman Filter (LETKF) by applying them to the prediction of the Lorenz 96 system. Although RC can successfully predict the Lorenz 96 system if the system is perfectly observed, we find that RC is vulnerable to observation sparsity compared with LETKF. To overcome this limitation of RC, we propose to combine LETKF and RC. In our proposed method, the system is predicted by RC that learned the analysis time series estimated by LETKF. Our proposed method can successfully predict the Lorenz 96 system using noisy and sparsely distributed observations. Most importantly, our method can predict better than LETKF when the process-based model is imperfect.

scholarly journals Using High-Resolution Numerical Weather Forecasts to Improve Remotely Sensed Rainfall Estimates: The Case of the 2013 Colorado Flash Flood

2015 ◽  
Vol 16 (4) ◽  
pp. 1742-1751 ◽  
Author(s):  
E. I. Nikolopoulos ◽  
N. S. Bartsotas ◽  
E. N. Anagnostou ◽  
G. Kallos
Keyword(s):  
High Resolution ◽  
Flash Flood ◽  
Weather Prediction ◽  
Stage Iv ◽  
Bias Reduction ◽  
Atmospheric Modeling ◽  
Limited Area ◽  
Numerical Weather ◽  
Satellite Rainfall ◽  
Rainfall Estimates

Abstract The September 2013 flash flood–triggering rainfall event in Colorado highlighted the strong underestimation of remote sensing techniques over mountainous terrain. In this work, the use of high-resolution rainfall forecasts for adjusting weather radar– [Multi-Radar Multi-Sensor (MRMS) quantitative precipitation estimation (Q3)] and satellite-based [CPC morphing technique (CMORPH) and TRMM 3B42RT] rainfall estimates is examined. Evaluation of the adjustment procedures is based on the NCEP Stage IV product. Results show that 1-km-grid-resolution rainfall forecasts provided by a numerical weather prediction model [Regional Atmospheric Modeling System and Integrated Community Limited Area Modeling System (RAMS-ICLAMS)] adequately captured total rainfall amounts during the event and could therefore be used to adjust biases in radar and satellite rainfall estimates. Two commonly used adjustment procedures according to 1) mean field bias and 2) probability density function matching are examined. Findings indicate that both procedures are successful in improving the original radar and satellite rainfall estimates, with the first method consistently providing the highest bias reduction while the second exhibits higher improvement in RMSE and correlation.

Sign in / Sign up

Export Citation Format

Share Document