Showing papers on "Nowcasting published in 2021"

Skilful precipitation nowcasting using deep generative models of radar.

Abstract: Precipitation nowcasting, the high-resolution forecasting of precipitation up to two hours ahead, supports the real-world socioeconomic needs of many sectors reliant on weather-dependent decision-making1,2. State-of-the-art operational nowcasting methods typically advect precipitation fields with radar-based wind estimates, and struggle to capture important non-linear events such as convective initiations3,4. Recently introduced deep learning methods use radar to directly predict future rain rates, free of physical constraints5,6. While they accurately predict low-intensity rainfall, their operational utility is limited because their lack of constraints produces blurry nowcasts at longer lead times, yielding poor performance on rarer medium-to-heavy rain events. Here we present a deep generative model for the probabilistic nowcasting of precipitation from radar that addresses these challenges. Using statistical, economic and cognitive measures, we show that our method provides improved forecast quality, forecast consistency and forecast value. Our model produces realistic and spatiotemporally consistent predictions over regions up to 1,536 km × 1,280 km and with lead times from 5–90 min ahead. Using a systematic evaluation by more than 50 expert meteorologists, we show that our generative model ranked first for its accuracy and usefulness in 89% of cases against two competitive methods. When verified quantitatively, these nowcasts are skillful without resorting to blurring. We show that generative nowcasting can provide probabilistic predictions that improve forecast value and support operational utility, and at resolutions and lead times where alternative methods struggle. A deep generative model using radar observations is used to create skilful precipitation predictions that are accurate and support real-world utility.

Nowcasting the COVID-19 pandemic in Bavaria.

Abstract: To assess the current dynamics of an epidemic, it is central to collect information on the daily number of newly diseased cases. This is especially important in real-time surveillance, where the aim is to gain situational awareness, for example, if cases are currently increasing or decreasing. Reporting delays between disease onset and case reporting hamper our ability to understand the dynamics of an epidemic close to now when looking at the number of daily reported cases only. Nowcasting can be used to adjust daily case counts for occurred-but-not-yet-reported events. Here, we present a novel application of nowcasting to data on the current COVID-19 pandemic in Bavaria. It is based on a hierarchical Bayesian model that considers changes in the reporting delay distribution over time and associated with the weekday of reporting. Furthermore, we present a way to estimate the effective time-varying case reproduction number R e ( t ) based on predictions of the nowcast. The approaches are based on previously published work, that we considerably extended and adapted to the current task of nowcasting COVID-19 cases. We provide methodological details of the developed approach, illustrate results based on data of the current pandemic, and evaluate the model based on synthetic and retrospective data on COVID-19 in Bavaria. Results of our nowcasting are reported to the Bavarian health authority and published on a webpage on a daily basis (https://corona.stat.uni-muenchen.de/). Code and synthetic data for the analysis are available from https://github.com/FelixGuenther/nc_covid19_bavaria and can be used for adaption of our approach to different data.

Advancing Radar Nowcasting Through Deep Transfer Learning

Abstract: 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.

The Role of Weather Radar in Rainfall Estimation and Its Application in Meteorological and Hydrological Modelling—A Review

Abstract: Radar-based rainfall information has been widely used in hydrological and meteorological applications, as it provides data with a high spatial and temporal resolution that improve rainfall representation. However, the broad diversity of studies makes it difficult to gather a condensed overview of the usefulness and limitations of radar technology and its application in particular situations. In this paper, a comprehensive review through a categorization of radar-related topics aims to provide a general picture of the current state of radar research. First, the importance and impact of the high temporal resolution of weather radar is discussed, followed by the description of quantitative precipitation estimation strategies. Afterwards, the use of radar data in rainfall nowcasting as well as its role in preparation of initial conditions for numerical weather predictions by assimilation is reviewed. Furthermore, the value of radar data in rainfall-runoff models with a focus on flash flood forecasting is documented. Finally, based on this review, conclusions of the most relevant challenges that need to be addressed and recommendations for further research are presented. This review paper supports the exploitation of radar data in its full capacity by providing key insights regarding the possibilities of including radar data in hydrological and meteorological applications.

Convective precipitation nowcasting using U-Net Model

Abstract: Convective precipitation nowcasting remains challenging due to the fast change of convective weather. Radar images are the most important data source in nowcasting research area. This study proposes a radar data-based U-Net model for precipitation nowcasting. The input of the model is five consecutive radar images; the output is 30-min prediction of radar reflectivity image. The model consists of three parts: upsampling, downsampling and skip-connection. Two models, U-Net and TrajGRU, are used for comparison in the experiments. Different from U-Net, which is a CNN-based (Convolution Neural Network) model, TrajGRU is an RNN-based (Recurrent Neural Network) model, which is good at time-series processing and has been widely used in precipitation research community. The experimental results show that the CNN-based U-Net can achieve almost the same performance as TrajGRU. This result shows the great potential of CNN-based models in handling time-series applications.

Nowcasting Earthquakes:Imaging the Earthquake Cycle in California with Machine Learning

Abstract: We propose a new machine learning-based method for nowcasting earthquakes to image the time-dependent earthquake cycle. The result is a timeseries which may correspond to the process of stress accu...

Nowcasting COVID-19 incidence indicators during the Italian first outbreak.

Abstract: A novel parametric regression model is proposed to fit incidence data typically collected during epidemics. The proposal is motivated by real-time monitoring and short-term forecasting of the main epidemiological indicators within the first outbreak of COVID-19 in Italy. Accurate short-term predictions, including the potential effect of exogenous or external variables are provided. This ensures to accurately predict important characteristics of the epidemic (e.g., peak time and height), allowing for a better allocation of health resources over time. Parameter estimation is carried out in a maximum likelihood framework. All computational details required to reproduce the approach and replicate the results are provided.

Prediction of Short-Time Rainfall Based on Deep Learning

Abstract: Short-time heavy rainfall is a kind of sudden strong and heavy precipitation weather, which seriously threatens people’s life and property safety. Accurate precipitation nowcasting is of great significance for the government to make disaster prevention and mitigation decisions in time. In order to make high-resolution forecasts of regional rainfall, this paper proposes a convolutional 3D GRU (Conv3D-GRU) model to predict the future rainfall intensity over a relatively short period of time from the machine learning perspective. Firstly, the spatial features of radar echo maps with different heights are extracted by 3D convolution, and then, the radar echo maps on time series are coded and decoded by using GRU. Finally, the trained model is used to predict the radar echo maps in the next 1-2 hours. The experimental results show that the algorithm can effectively extract the temporal and spatial features of radar echo maps, reduce the error between the predicted value and the real value of rainfall, and improve the accuracy of short-term rainfall prediction.

Introduction of the Advanced Meteorological Imager of Geo-Kompsat-2a: In-Orbit Tests and Performance Validation

Abstract: Geo-Kompsat-2A (Geostationary-Korean Multi-Purpose SATtellite-2A, GK2A), a new generation of Korean geostationary meteorological satellite, carry state-of-the-art optical sensors with significantly higher radiometric, spectral, and spatial resolution than the Communication, Ocean, and Meteorological Satellite (COMS) previously available in the geostationary orbit The new Advanced Meteorological Imager (AMI) on GK2A has 16 observation channels, and its spatial resolution is 05 or 1 km for visible channels and 2 km for near-infrared and infrared channels These advantages, when combined with shortened revisit times (around 10 min for full disk and 2 min for sectored regions), provide new levels of capacity for the identification and tracking of rapidly changing weather phenomena and for the derivation of quantitative products These improvements will bring about unprecedented levels of performance in nowcasting services and short-range weather forecasting systems Imagery from the satellites is distributed and disseminated to users via multiple paths, including internet services and satellite broadcasting services In post-launch performance validation, infrared channel calibration is accurate to within 02 K with no significant diurnal variation using an approach developed under the Global Space-based Inter-Calibration System framework Visible and near infrared channels showed unexpected seasonal variations of approximately 5 to 10% using the ray matching method and lunar calibration Image navigation was accurate to within requirements, 42 µrad (15 km), and channel-to-channel registration was also validated This paper describes the features of the GK2A AMI, GK2A ground segment, and data distribution Early performance results of AMI during the commissioning period are presented to demonstrate the capabilities and applications of the sensor

Applications for solar irradiance nowcasting in the control of microgrids: A review

Abstract: The integration of solar photovoltaic (PV) into electricity networks introduces technical challenges due to varying PV output. Rapid ramp events due to cloud movements are of particular concern for the operation of remote islanded microgrids (MGs) with high penetration of solar PV generation. PV plants and optionally controllable distributed energy resources (DERs) in MGs can be operated in an optimized way based on nowcasting, which is also called very short-term solar irradiance forecasting up to 60 min ahead. This study presents an extensive literature review on nowcasting technologies along with their current and future possible applications in the control of MGs. Ramp rates control and scheduling of spinning reserves are found to be the most recognized applications of nowcasting in MGs. An online survey has been conducted to identify the limitations, benefits and challenges of deploying nowcasting in MGs. The survey outcomes show that the incorporation of nowcasting tools in MG operations is still limited, though the possibility of increasing solar PV penetration levels in MGs if nowcasting tools are incorporated is acknowledged. Additionally, recent nowcasting tools, such as sky camera-based tools, require further validation under various conditions for more widespread adaptation by power system operators.

Evaporation Duct Height Nowcasting in China’s Yellow Sea Based on Deep Learning

Abstract: The evaporation duct is a weather phenomenon that often occurs in marine environments and affects the operation of shipborne radar. The most important evaluation parameter is the evaporation duct height (EDH). Forecasting the EDH and adjusting the working parameters and modes of the radar system in advance can greatly improve radar performance. Traditionally, short-term forecast methods have been used to estimate the EDH, which are characterized by low time resolution and poor forecast accuracy. In this study, a novel approach for EDH nowcasting is proposed based on the deep learning network and EDH data measured in the Yellow Sea, China. The factors that affect nowcasting were analyzed. The time resolution and forecast time were 5 min and 0–2 h, respectively. The results show that our proposed method has a higher forecast accuracy than traditional time series forecasting methods and confirm its feasibility and effectiveness.

Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting

Abstract: Short or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as inputs. In order to determine whether using other meteorological parameters such as wind would improve forecasts, we trained a deep learning model on a fusion of rainfall radar images and wind velocity produced by a weather forecast model. The network was compared to a similar architecture trained only on radar data, to a basic persistence model, and to an approach based on optical flow. Our network outperforms by 8% the F1-score calculated for the optical flow on moderate and higher rain events for forecasts at a horizon time of 30 minutes. Furthermore, it outperforms by 7% the same architecture trained using only rainfall radar images. Merging rain and wind data has also proven to stabilize the training process and enabled significant improvement especially on the difficult-to-predict high precipitation rainfalls.

Nowcasting for Real-Time COVID-19 Tracking in New York City: An Evaluation Using Reportable Disease Data From Early in the Pandemic.

Abstract: Background: Nowcasting approaches enhance the utility of reportable disease data for trend monitoring by correcting for delays, but implementation details affect accuracy. Objective: To support real-time COVID-19 situational awareness, the New York City Department of Health and Mental Hygiene used nowcasting to account for testing and reporting delays. We conducted an evaluation to determine which implementation details would yield the most accurate estimated case counts. Methods: A time-correlated Bayesian approach called Nowcasting by Bayesian Smoothing (NobBS) was applied in real time to line lists of reportable disease surveillance data, accounting for the delay from diagnosis to reporting and the shape of the epidemic curve. We retrospectively evaluated nowcasting performance for confirmed case counts among residents diagnosed during the period from March to May 2020, a period when the median reporting delay was 2 days. Results: Nowcasts with a 2-week moving window and a negative binomial distribution had lower mean absolute error, lower relative root mean square error, and higher 95% prediction interval coverage than nowcasts conducted with a 3-week moving window or with a Poisson distribution. Nowcasts conducted toward the end of the week outperformed nowcasts performed earlier in the week, given fewer patients diagnosed on weekends and lack of day-of-week adjustments. When estimating case counts for weekdays only, metrics were similar across days when the nowcasts were conducted, with Mondays having the lowest mean absolute error of 183 cases in the context of an average daily weekday case count of 2914. Conclusions: Nowcasting using NobBS can effectively support COVID-19 trend monitoring. Accounting for overdispersion, shortening the moving window, and suppressing diagnoses on weekends—when fewer patients submitted specimens for testing—improved the accuracy of estimated case counts. Nowcasting ensured that recent decreases in observed case counts were not overinterpreted as true declines and supported officials in anticipating the magnitude and timing of hospitalizations and deaths and allocating resources geographically.

Artificial Intelligence Revolutionises Weather Forecast, Climate Monitoring and Decadal Prediction

Abstract: Artificial Intelligence (AI) is an explosively growing field of computer technology, which is expected to transform many aspects of our society in a profound way. AI techniques are used to analyse large amounts of unstructured and heterogeneous data and discover and exploit complex and intricate relations among these data, without recourse to an explicit analytical treatment of those relations. These AI techniques are unavoidable to make sense of the rapidly increasing data deluge and to respond to the challenging new demands in Weather Forecast (WF), Climate Monitoring (CM) and Decadal Prediction (DP). The use of AI techniques can lead simultaneously to: (1) a reduction of human development effort, (2) a more efficient use of computing resources and (3) an increased forecast quality. To realise this potential, a new generation of scientists combining atmospheric science domain knowledge and state-of-the-art AI skills needs to be trained. AI should become a cornerstone of future weather and climate observation and modelling systems.

Nowcasting thunderstorm hazards using machine learning: the impact of data sources on performance

Abstract: . In order to aid feature selection in thunderstorm nowcasting, we present an analysis of the utility of various sources of data for machine-learning-based nowcasting of hazards related to thunderstorms. We considered ground-based radar data, satellite-based imagery and lightning observations, forecast data from numerical weather prediction (NWP) and the topography from a digital elevation model (DEM), ending up with 106 different predictive variables. We evaluated machine-learning models to nowcast radar reflectivity (representing precipitation), lightning occurrence, and the 45 dBZ radar echo top height that can be used as an indicator of hail, producing predictions for lead times up to 60 min. The study was carried out in an area in the northeast United States, where observations from the Geostationary Operational Environmental Satellite 16 are available and can be used as a proxy for the upcoming Meteosat Third Generation capabilities in Europe. The benefits of the data sources were evaluated using two complementary approaches: using feature importance reported by the machine learning model based on gradient boosted trees, and by repeating the analysis using all possible combinations of the data sources. The two approaches sometimes yielded seemingly contradictory results, as the feature importance reported by the gradient boosting algorithm sometimes disregards certain features that are still useful in the absence of more powerful predictors, while at times it overstates the importance of other features. We found that the radar data is overall the most important predictor, the satellite imagery is beneficial for all of the studied predictands, and the lightning data is very useful for nowcasting lightning but of limited use for the other hazards. The benefits of the NWP data are more limited over the nowcast period, and we did not find evidence that the nowcast benefits from the DEM data.

A Novel LSTM Model with Interaction Dual Attention for Radar Echo Extrapolation

Abstract: The task of precipitation nowcasting is significant in the operational weather forecast. The radar echo map extrapolation plays a vital role in this task. Recently, deep learning techniques such as Convolutional Recurrent Neural Network (ConvRNN) models have been designed to solve the task. These models, albeit performing much better than conventional optical flow based approaches, suffer from a common problem of underestimating the high echo value parts. The drawback is fatal to precipitation nowcasting, as the parts often lead to heavy rains that may cause natural disasters. In this paper, we propose a novel interaction dual attention long short-term memory (IDA-LSTM) model to address the drawback. In the method, an interaction framework is developed for the ConvRNN unit to fully exploit the short-term context information by constructing a serial of coupled convolutions on the input and hidden states. Moreover, a dual attention mechanism on channels and positions is developed to recall the forgotten information in the long term. Comprehensive experiments have been conducted on CIKM AnalytiCup 2017 data sets, and the results show the effectiveness of the IDA-LSTM in addressing the underestimation drawback. The extrapolation performance of IDA-LSTM is superior to that of the state-of-the-art methods.

Photovoltaic Nowcasting With Bi-Level Spatio-Temporal Analysis Incorporating Sky Images

Abstract: Today many large-scale photovoltaic (PV) plants have been equipped with sky imaging systems. The sky images contain abundant spatio-temporal information of the local climate condition at the PV plant. Meanwhile, power outputs of the PV systems located at different sites in a certain geographical area also exhibit spatio-temporal correlation. It is of interest to improve the accuracy of PV nowcasting by fully utilizing spatio-temporal information embedded in both sky images and PV output measurements of distributed PV systems. In this article, we incorporate the above two aspects into a unified framework and propose the Bi-level spatio-temporal (BILST) PV nowcasting model. The proposed model learns features from local spatio-temporal information embedded in sky images, global spatio-temporal correlations embedded in PV output datasets of a number of distributed PV systems and weather characteristics embedded in exogenous dataset simultaneously. Then the obtained three types of hidden features are aggregated and applied to predict the PV output at the PV site of interest. Experiments using real-world datasets show that the proposed BILST model can enable sky images to contribute to the PV nowcasting task and achieve the desirable accuracy of PV nowcasting consistently.