Search

This paper aims to explore machine learning techniques for post‐processing high‐resolution Numerical Weather Prediction (NWP) products for the early detection of convection. Data from the Arome Ensemble Prediction System and satellite observations from the Rapidly Developing Thunderstorm (RDT) product by Météo‐France are used to train a recurrent neural network model to predict areas of total convection and moderate convection. The learning task is formulated as a binary classification problem using a long short‐term memory (LSTM) network architecture. Results from the LSTM model are compared with an object‐based probabilistic approach to forecast convection using metrics such as a receiver operating characteristics (ROC) curve, the Brier score and reliability. Results indicate that the LSTM model performs similarly to the object‐based probabilistic benchmark when classifying moderate convection areas and shows improved skill when classifying areas of total convective. Finally, the LSTM model results are presented within an air traffic management context to showcase the potential use of machine learning models within an operational application. [ABSTRACT FROM AUTHOR]

In order to contribute to ongoing efforts on tropical cyclone (TC) forecasting, a new, convection‐permitting, limited‐area coupled model called AROME‐Indian Ocean (AROME‐IO) was deployed in the Southwest Indian Ocean basin (SWIO) in April 2016. The skill of this numerical weather predicting system for TC prediction is evaluated against its coupling model (European Center for Medium Range Weather Forecasting‐Integrated Forecasting System [ECMWF‐IFS]) using 120‐hr reforecasts of 11 major storms that developed in this area over TC seasons 2017–2018 and 2018–2019. Results show that AROME‐IO generally provides significantly better performance than IFS for intensity (maximum wind) and structure (wind extensions, radius of maximum wind) forecasts at all lead times, with similar performance in terms of trajectories. The performance of a prototype, 12‐member ensemble prediction system (EPS), of AROME‐IO is also evaluated on the case of TC Fakir (April 2018), a storm characterized by an extremely low predictability in global deterministic and ensemble models. AROME‐IO EPS is shown to significantly improve the predictability of the system with two scenarios being produced: a most probable one (~66%), which follows the prediction of AROME‐IO, and a second one (~33%) that closely matches reality. [ABSTRACT FROM AUTHOR]

Limited‐area ensemble predictions can be sensitive to the specification of lateral boundary conditions, which are often built by subsampling larger ensembles. Using the operational PEARP and AROME‐EPS ensembles, we compare several subsampling methods, including random selection, representative members, and a new selection method. The tests show that the algorithms used for the clustering and the member selection have a significant impact on the resulting ensembles. Clustering‐based methods are shown to outperform random subsampling, mostly (but not only) because they change the ensemble spread. Cluster sizes can be highly variable, which can complicate ensemble interpretation. We present a subsampling algorithm that has little impact on performance scores, but better preserves ensemble spread and produces nearly equally likely members by limiting cluster size variability. Limited‐area ensemble predictions can be sensitive to the specification of lateral boundary conditions, which are often built by subsampling larger ensembles. Using the operational PEARP and AROME‐EPS ensembles, we compare several subsampling methods, including random selection, representative members, and a new selection method. [ABSTRACT FROM AUTHOR]

Since agriculture is highly exposed to weather-related risks such as drought constraints, Decision Support Tools (DSTs) are now frequently used in irrigation management. The current use of DSTs mainly relies on deterministic weather forecasts that do not account for the associated weather uncertainties. Few irrigation DST users take uncertainty into consideration by utilizing an ensemble of historical weather observations (EHO) as input to their models. In order to account for the atmospheric state uncertainties, weather centers are progressively shifting to ensemble predictions. This is done by running several times the numerical weather prediction model with slightly perturbed initial conditions and model formulations. The final forecast hence takes the form of an ensemble instead of a deterministic single value. However, ensemble forecasts could present bias and dispersion errors and therefore need post-processing. In this work, we introduce a novel approach that uses ensemble weather forecasts as input to a vine irrigation DST, named "Water baLance for Intercropped Systems" (WaLIS), that computes a crop water stress index as output. Our results show that this approach has significantly better probabilistic performance than the use of EHO as input to the WaLIS model, especially between forecast days 5 and 7 (∼ 35% of gain in performance). We also investigate the effect of statistical post-processing on the probabilistic skill of the water stress index with two different approaches. In the first case, we directly post-process the output of the WaLIS model. In the second case, only weather forecasts are post-processed, before being used as inputs of the WaLIS model. Our results show that locally in 4 out of 10 tested sites in southern France, the raw ensemble forecasts could be significantly improved by the post-processing, and that generally there is no significant performance difference between the two competing post-processing approaches. • Weather-induced uncertainty on a crop water stress model predictions is studied. • WaLIS model is used to simulate water stress in 10 southern France vine sites. • Weather ensemble forecasts are better than historical data in predicting water stress. • The most significant performance gain (∼ 35%) is between 5 and 7 days of forecast. • Post-processing predictions with Ensemble Model Output Statistics can improve the performance. [ABSTRACT FROM AUTHOR]