On the generation of probabilistic forecasts from deterministic models

Abstract

Most of the methods that produce space weather forecasts are based on deterministic models. In order to generate a probabilistic forecast, a model needs to be run several times sampling the input parameter space, in order to generate an ensemble from which the distribution of outputs can be inferred. However, ensemble simulations are costly and often preclude the possibility of real-time forecasting. We introduce a simple and robust method to generate uncertainties from deterministic models, that does not require ensemble simulations. The method is based on the simple consideration that a probabilistic forecast needs to be both accurate and well-calibrated (reliable). We argue that these two requirements are equally important, and we introduce the Accuracy-Reliability cost function that quantitatively measures the trade-off between accuracy and reliability. We then define the optimal uncertainties as the standard deviation of the Gaussian distribution that minimizes the cost function. We demonstrate that this simple strategy, implemented here by means of a regularized deep neural network, produces accurate and well-calibrated forecasts, showing examples both on synthetic and real-world space weather data.

under review

References in corpus (8)

• Toward Reliable Benchmarking of Solar Flare Forecasting Methods
• A Comparison of Flare Forecasting Methods, I: Results from the "All-Clear" Workshop
• A Bayesian Approach to Solar Flare Prediction
• Forward modeling of coronal mass ejection flux ropes in the inner heliosphere with 3DCORE
• Flare forecasting at the Met Office Space Weather Operations Centre
• Verification of Space Weather Forecasts issued by the Met Office Space Weather Operations Centre
• Wave-particle interactions with parallel whistler waves: nonlinear and time-dependent effects revealed by Particle-in-Cell simulations
• Adaptive selection of sampling points for Uncertainty Quantification

Cited by in corpus (3)

• The Challenge of Machine Learning in Space Weather Nowcasting and Forecasting
• Evaluation of Machine Learning Techniques for Forecast Uncertainty Quantification
• Bayesian inference of quasi-linear radial diffusion parameters using Van Allen Probes