Convective Storm Nowcasting Research Articles

Pixel-CRN: A New Machine Learning Approach for Convective Storm Nowcasting

The short-term convective storm forecasting (i.e., nowcasting) mainly rely on weather radar which can resolve the 3D structure of convective storms. With the rapid development of numerical models, modern models can produce 3D reanalysis data which gives atmospheric background information of convective storms. Current deep learning nowcasting models use only 2D radar images for nowcasting and often require massive historical data for training. But it may not be operationally feasible to collect long-term radar data to train a new model. Hence, how to establish a nowcasting model using only a small dataset has become an important issue. In addition, existing models do not effectively use the state-of-the-art model reanalysis data, which is a shortcoming of these models. To tackle these problems, this article develops a pixel-wise convolutional recurrent neural network (Pixel-CRN) for precipitation nowcasting. It has three key designs: (1) Through a concise pixel-wise sampling and oversampling technique, Pixel-CRN can be trained using only a small dataset. (2) In spatial learning, Pixel-CRN embeds a spatial convolution subnet into the recurrent unit, which can input raw 3D radar and model reanalysis data, thus valuable atmospheric background information can be learned to assist nowcasting. (3) In spatiotemporal learning, according to the information bottleneck principle, Pixel-CRN builds a heterogeneous encoder-decoder structure to squeeze multi-channel 3D input data into latent space, and recurrently generates 30 and 60 min nowcasts. Compared with existing deep learning nowcasting methods, the experimental results show that Pixel-CRN can provide skillful results with a rather small training dataset.

Three-Dimensional Gridded Radar Echo Extrapolation for Convective Storm Nowcasting Based on 3D-ConvLSTM Model

Radar echo extrapolation has been widely developed in previous studies for precipitation and storm nowcasting. However, most studies have focused on two-dimensional radar images, and extrapolation of multi-altitude radar images, which can provide more informative and visual forecasts about weather systems in realistic space, has been less explored. Thus, this paper proposes a 3D-convolutional long short-term memory (ConvLSTM)-based model to perform three-dimensional gridded radar echo extrapolation for severe storm nowcasting. First, a 3D-convolutional neural network (CNN) is used to extract the 3D spatial features of each input grid radar volume. Then, 3D-ConvLSTM layers are leveraged to model the spatial–temporal relationship between the extracted 3D features and recursively generate the 3D hidden states correlated to the future. Nowcasting results are obtained after applying another 3D-CNN to up-sample the generated 3D hidden states. Comparative experiments were conducted on a public National Center for Atmospheric Research Data Archive dataset with a 3D optical flow method and other deep-learning-based models. Quantitative evaluations demonstrate that the proposed 3D-ConvLSTM-based model achieves better overall and longer-term performance for storms with reflectivity values above 35 and 45 dBZ. In addition, case studies qualitatively demonstrate that the proposed model predicts more realistic storm evolution and can facilitate early warning regarding impending severe storms.

Advancing Radar Nowcasting Through Deep Transfer Learning

Deep learning is emerging as a powerful tool in scientific applications, such as radar-based convective storm nowcasting. However, it is still a challenge to extend the application of a well-trained deep learning nowcasting model, which demands to incorporate the learned knowledge at a certain location to other locations characterized by different precipitation features. This article designs a transfer learning framework to tackle this problem. A convolutional neural network (CNN)-based nowcasting method is utilized as the benchmark, based on which two transfer learning models are constructed through fine-tune and maximum mean discrepancy (MMD) minimization. The base CNN model is trained using radar data in the source study domain near Beijing, China, whereas the transferred models are applied to the target domain near Guangzhou, China, with only a small amount of data in the target area. The influence of a varying number of target data samples on the nowcasting performance is quantified. The experimental results demonstrate that the deep transfer learning models can improve the nowcasting skills.

Convolutional Neural Network for Convective Storm Nowcasting Using 3-D Doppler Weather Radar Data

Convective storms are one of the severe weather hazards found during the warm season. Doppler weather radar is the only operational instrument that can frequently sample the detailed structure of convective storm which has a small spatial scale and short lifetime. For the challenging task of short-term convective storm forecasting, 3-D radar images contain information about the processes in convective storm. However, effectively extracting such information from multisource raw data has been problematic due to a lack of methodology and computation limitations. Recent advancements in deep learning techniques and graphics processing units now make it possible. This article investigates the feasibility and performance of an end-to-end deep learning nowcasting method. The nowcasting problem was transformed into a classification problem first, and then, a deep learning method that uses a convolutional neural network was presented to make predictions. On the first layer of CNN, a cross-channel 3D convolution was proposed to fuse 3D raw data. The CNN method eliminates the handcrafted feature engineering, i.e., the process of using domain knowledge of the data to manually design features. Operationally produced historical data of the Beijing-Tianjin-Hebei region in China was used to train the nowcasting system and evaluate its performance; 3737332 samples were collected in the training data set. The experimental results show that the deep learning method improves nowcasting skills compared with traditional machine learning methods.

Severe Convective Weather Nowcasting System in Heilongjiang Meteorological Bureau and Its Preliminary Performance Evaluation

In this paper, we present the severe convective weather nowcasting system in Heilongjiang Meteorological Bureau and its preliminary performance evaluation, which has been in operational use since 2018. We believe that a good workflow design and intelligently integrated system plays an important role in the weather forecast service. Based on the current data environment, the system builds a unified data environment. Both the functions of automatic nowcasting system and Very-short-range Interactive Prediction System are presented too. The results show that this system plays a key role in the production of rapidly updated, convective storm nowcasting for end users.

A machine learning nowcasting method based on real‐time reanalysis data

AbstractDespite marked progress over the past several decades, convective storm nowcasting remains a challenge because most nowcasting systems are based on linear extrapolation of radar reflectivity without much consideration for other meteorological fields. The variational Doppler radar analysis system (VDRAS) is an advanced convective‐scale analysis system capable of providing analysis of 3‐D wind, temperature, and humidity by assimilating Doppler radar observations. Although potentially useful, it is still an open question as to how to use these fields to improve nowcasting. In this study, we present results from our first attempt at developing a support vector machine (SVM) box‐based nowcasting (SBOW) method under the machine learning framework using VDRAS analysis data. The key design points of SBOW are as follows: (1) The study domain is divided into many position‐fixed small boxes, and the nowcasting problem is transformed into one question, i.e., will a radar echo > 35 dBZappear in a box in 30 min? (2) Box‐based temporal and spatial features, which include time trends and surrounding environmental information, are constructed. (3) And the box‐based constructed features are used to first train the SVM classifier, and then the trained classifier is used to make predictions. Compared with complicated and expensive expert systems, the above design of SBOW allows the system to be small, compact, straightforward, and easy to maintain and expand at low cost. The experimental results show that although no complicated tracking algorithm is used, SBOW can predict the storm movement trend and storm growth with reasonable skill.

A ZDR Column Detection Algorithm to Examine Convective Storm Updrafts

AbstractObservations and recent high-resolution numerical model simulations indicate that liquid water and partially frozen hydrometeors can be lofted considerably above the environmental 0°C level in the updrafts of convective storms owing to the warm thermal perturbation from latent heating within the updraft and to the noninstantaneous nature of drop freezing. Consequently, upward extensions of positive differential reflectivity (i.e., ZDR ≥ 1 dB)—called ZDR columns—may be a useful proxy for detecting the initiation of new convective storms and examining the evolution of convective storm updrafts. High-resolution numerical simulations with spectral bin microphysics and a polarimetric forward operator reveal a strong spatial association between updrafts and ZDR columns and show the utility of examining the structure and evolution of ZDR columns for assessing updraft evolution. This paper introduces an automated ZDR column algorithm designed to provide additional diagnostic and prognostic information pertinent to convective storm nowcasting. Although suboptimal vertical resolution above the 0°C level and limitations imposed by commonly used scanning strategies in the operational WSR-88D network can complicate ZDR column detection, examples provided herein show that the algorithm can provide operational and research-focused meteorologists with valuable information about the evolution of convective storms.

Impacts of Forecaster Involvement on Convective Storm Initiation and Evolution Nowcasting

Abstract A forecaster-interactive capability was added to an automated convective storm nowcasting system [Auto-Nowcaster (ANC)] to allow forecasters to enhance the performance of 1-h nowcasts of convective storm initiation and evolution produced every 6 min. This Forecaster-Over-The-Loop (FOTL-ANC) system was tested at the National Weather Service Fort Worth–Dallas, Texas, Weather Forecast Office during daily operations from 2005 to 2010. The forecaster’s role was to enter the locations of surface convergence boundaries into the ANC prior to dissemination of nowcasts to the Center Weather Service Unit. Verification of the FOTL-ANC versus ANC (no human) nowcasts was conducted on the convective scale. Categorical verification scores were computed for 30 subdomains within the forecast domain. Special focus was placed on subdomains that included convergence boundaries for evaluation of forecaster involvement and impact on the FOTL-ANC nowcasts. The probability of detection of convective storms increased by 20%–60% with little to no change observed in the false-alarm ratios. Bias values increased from 0.8–1.0 to 1.0–3.0 with human involvement. The accuracy of storm nowcasts notably improved with forecaster involvement; critical success index (CSI) values increased from 0.15–0.25 (ANC) to 0.2–0.4 (FOTL-ANC). Over short time periods, CSI values as large as 0.6 were also observed. This study demonstrated definitively that forecaster involvement led to positive improvement in the nowcasts in most cases while causing no degradation in other cases; a few exceptions are noted. Results show that forecasters can play an important role in the production of rapidly updated, convective storm nowcasts for end users.

Nowcasting Convective Storm Initiation Using Satellite-Based Box-Averaged Cloud-Top Cooling and Cloud-Type Trends

Abstract Short-term (0–1 h) convective storm nowcasting remains a problem for operational weather forecasting, and convective storms pose a significant monetary sink for the aviation industry. Numerical weather prediction models, traditional meteorological observations, and radar are all useful for short-term convective forecasting, but all have shortcomings. Geostationary imagers, while having their own shortcomings, are valuable assets for addressing the convective initiation nowcast problem. The University of Wisconsin Convective Initiation (UWCI) nowcasting algorithm is introduced for use as an objective, satellite-based decision support tool. The UWCI algorithm computes Geostationary Operational Environmental Satellite (GOES) Imager infrared window channel box-averaged cloud-top cooling rates and creates convective initiation nowcasts based on a combination of cloud-top cooling rates and satellite-derived cloud-top type–phase trends. The UWCI approach offers advantages over existing techniques, such as increased computational efficiency (decreased runtime) and day–night independence. A validation of the UWCI algorithm relative to cloud-to-ground lightning initiation events is also presented for 23 convective afternoons and 11 convective nights over the central United States during April–June and 1 night of July during 2008 and 2009. The mean probability of detection and false-alarm ratio are 56.3% (47.0%) and 25.5% (34.8%), respectively, for regions within a Storm Prediction Center severe storm risk area (entire validation domain). The UWCI algorithm is shown to perform 1) better in regimes with storms developing in previously clear to partly cloudy skies and along sharp boundaries and 2) poorer in other regimes such as scenes covered with cirrus shields, existing convective anvils, and fast cloud motion.

Sydney 2000 Forecast Demonstration Project: Convective Storm Nowcasting

Abstract Five of the nowcasting systems that were available during the Sydney 2000 Forecast Demonstration Project (FDP) were selected for evaluation. These systems, from the United States, the United Kingdom, and Australia, had the capability to nowcast the location and, with one exception, the intensity of convective storms. Six of the most significant convective storm cases from the 3-month FDP were selected for evaluating the performance of these state-of-the-art nowcasting systems, which extrapolated storms using a variety of methods, including cell and area tracking, model winds, and sounding winds. Three of the systems had the ability to forecast the initiation and growth of storms. Nowcasts for 30 and 60 min were evaluated, and it was found that even for such short time periods the skill of the extrapolation-only systems was often very low. Extrapolation techniques that allowed for differential motion performed slightly better, since high-impact storms often have motions different than surrounding ...

Nowcasting Storm Initiation and Growth UsingGOES-8and WSR-88D Data

The evolution of cumulus clouds over a variety of radar-detected, boundary layer convergence features in eastern Colorado has been examined using Geostationary Operational Environmental Satellite (GOES) imagery and Weather Surveillance Radar-1988 Doppler (WSR-88D) data. While convective storms formed above horizontal rolls in the absence of any additional surface forcing, the most intense storms initiated in regions above: gust fronts, gust front interaction with horizontal rolls, and terrain-induced stationary convergence zones. The onset of vigorous cloud growth leading to storm development was characterized by cloud tops that reached subfreezing temperatures and exhibited large cooling rates at cloud top 15 min prior to the first detection of 10dBZ radar echoes aloft and 30 min before 35 dBZ. The rate of cloud-top temperature change was found to be important for discriminating between weakly precipitating storms (,35 dBZ) and vigorous convective storms (.35 dBZ). Results from this study have been used to increase the lead time of thunderstorm initiation nowcasts with the NCAR automated, convective storm nowcasting system. This improvement is demonstrated at two operational forecast offices in Virginia and New Mexico.