Jorge Amaya

Brecht Laperre, Jorge Amaya, Sara Jamal et al.

Simulations of large-scale plasma systems are typically based on a fluid approximation approach. These models construct a moment-based system of equations that approximate the particle-based physics as a fluid, but as a result lack the small-scale physical processes available to fully kinetic models. Traditionally, empirical closure relations are used to close the moment-based system of equations, which typically approximate the pressure tensor or heat flux. The more accurate the closure relation, the stronger the simulation approaches kinetic-based results. In this paper, new closure terms are constructed using machine learning techniques. Two different machine learning models, a multi-layer perceptron and a gradient boosting regressor, synthesize a local closure relation for the pressure tensor and heat flux vector from fully kinetic simulations of a 2D magnetic reconnection problem. The models are compared to an existing closure relation for the pressure tensor, and the applicability of the models is discussed. The initial results show that the models can capture the diagonal components of the pressure tensor accurately, and show promising results for the heat flux, opening the way for new experiments in multi-scale modeling. We find that the sampling of the points used to train both models play a capital role in their accuracy.

Maria Elena Innocenti, Jorge Amaya, Joachim Raeder et al.

In magnetospheric missions, burst mode data sampling should be triggered in the presence of processes of scientific or operational interest. We present an unsupervised classification method for magnetospheric regions, that could constitute the first-step of a multi-step method for the automatic identification of magnetospheric processes of interest. Our method is based on Self Organizing Maps (SOMs), and we test it preliminarily on data points from global magnetospheric simulations obtained with the OpenGGCM-CTIM-RCM code. The dimensionality of the data is reduced with Principal Component Analysis before classification. The classification relies exclusively on local plasma properties at the selected data points, without information on their neighborhood or on their temporal evolution. We classify the SOM nodes into an automatically selected number of classes, and we obtain clusters that map to well defined magnetospheric regions. We validate our classification results by plotting the classified data in the simulated space and by comparing with K-means classification. For the sake of result interpretability, we examine the SOM feature maps (magnetospheric variables are called features in the context of classification), and we use them to unlock information on the clusters. We repeat the classification experiments using different sets of features, we quantitatively compare different classification results, and we obtain insights on which magnetospheric variables make more effective features for unsupervised classification.

Brecht Laperre, Jorge Amaya, Giovanni Lapenta

Models based on neural networks and machine learning are seeing a rise in popularity in space physics. In particular, the forecasting of geomagnetic indices with neural network models is becoming a popular field of study. These models are evaluated with metrics such as the root-mean-square error (RMSE) and Pearson correlation coefficient. However, these classical metrics sometimes fail to capture crucial behavior. To show where the classical metrics are lacking, we trained a neural network, using a long short-term memory network, to make a forecast of the disturbance storm time index at origin time $t$ with a forecasting horizon of 1 up to 6 hours, trained on OMNIWeb data. Inspection of the model's results with the correlation coefficient and RMSE indicated a performance comparable to the latest publications. However, visual inspection showed that the predictions made by the neural network were behaving similarly to the persistence model. In this work, a new method is proposed to measure whether two time series are shifted in time with respect to each other, such as the persistence model output versus the observation. The new measure, based on Dynamical Time Warping, is capable of identifying results made by the persistence model and shows promising results in confirming the visual observations of the neural network's output. Finally, different methodologies for training the neural network are explored in order to remove the persistence behavior from the results.