pascalsa

• Sado, Pascal; Clausen, Lasse; Miloch, Wojciech Jacek & Nickisch, H. (2023). Substorm Onset Prediction Using Machine Learning Classified Auroral Images. Space Weather. 21(2), p. 1–9. doi: 10.1029/2022SW003300. Full text in Research Archive Show summary

  Abstract We classify all sky images from four seasons, transform the classification results into time‐series data to include information about the evolution of images and combine these with information on the onset of geomagnetic substorms. We train a lightweight classifier on this data set to predict the onset of substorms within a 15 min interval after being shown information of 30 min of aurora. The best classifier achieves a balanced accuracy of 59% with a recall rate of 39% and false positive rate of 20%. We show that the classifier is limited by the strong imbalance in the data set of approximately 50:1 between negative and positive events. All software and results are open source and freely available.

• Sado, Pascal; Clausen, Lasse; Miloch, Wojciech Jacek & Nickisch, Hannes (2021). Transfer Learning Aurora Image Classification and Magnetic Disturbance Evaluation. Journal of Geophysical Research (JGR): Space Physics. ISSN 2169-9380. doi: 10.1029/2021JA029683. Full text in Research Archive Show summary

  We develop an open source algorithm to apply Transfer learning to Aurora image classification and Magnetic disturbance Evaluation (TAME). For this purpose, we evaluate the performance of 80 pretrained neural networks using the Oslo Auroral THEMIS (OATH) data set of all-sky images, both in terms of runtime and their features' predictive capability. From the features extracted by the best network, we retrain the last neural network layer using the Support Vector Machine (SVM) algorithm to distinguish between the labels “arc,” “diffuse,” “discrete,” “cloud,” “moon” and “clear sky/ no aurora”. This transfer learning approach yields 73% accuracy in the six classes; if we aggregate the 3 auroral and 3 non-aurora classes, we achieve up to 91% accuracy. We apply our classifier to a new dataset of 550,000 images and evaluate the classifier based on these previously unseen images. To show the potential usefulness of our feature extractor and classifier, we investigate two test cases: First, we compare our predictions for the “cloudy” images to meteorological data and second we train a linear ridge model to predict perturbations in Earth's locally measured magnetic field. We demonstrate that the classifier can be used as a filter to remove cloudy images from datasets and that the extracted features allow to predict magnetometer measurements. All procedures and algorithms used in this study are publicly available, and the code and classifier are provided, which opens possibility for large scale studies of all-sky images.

• Sado, Pascal & Fredriksen, Åshild (2020). Detailed density and ion energy profiles downstream of a small ECR plasma source. IEEE Transactions on Plasma Science. ISSN 0093-3813. 48(12), p. 4181–4190. doi: 10.1109/TPS.2020.3037356. Full text in Research Archive

View all works in NVA

• Sado, Pascal & Fredriksen, Åshild (2019). On confinement and plasma acceleration from a small ECR plasma source. Full text in Research Archive Show summary

  <p>Electron Cyclotron Resonance (ECR) is a technique to create high density, low temperature plasmas that do not depend on a cathode, like arc discharges and are therefore easier to maintain and have a longer lifespan. The use of the Electron Cyclotron Resonance (ECR) for electron heating for Magnetic Nozzle (MN) thrusters have recently received increased interest, as they have been shown to provide improved thrust efficiency up to 16 % at only 30 W input power. Such performance make such thrusters viable for use on small, e.g. Cubesat, spacecraft. <p>An ECR plasma source similar to that described by Jarrige et al. (2017), was recently installed in a 30 cm diameter and 60 cm long cylindrical chamber at UiT. This source is grounded, as opposed to the previously described one, which is shielded from ground. The source consists of a cylindrical sleeve antenna of diameter 2.6 cm, and was operated at 10 -20 W, at mass flow rates from 0.2 –0.8 mg/s, which result in pressures ranging from 0.08 –0.3 Pa. High-resolution radial profiles of plasma parameters were obtained by means of Langmuir, ion energy analyzer and Mach probes, at two different axial positions 20 cm and 50 cm from the source, i.e. in the far plume of the source. The configurations were i) a monotonous expanding magnetic field, ii) a bottle-shaped magnetic field, and iii) a nearly homogeneous magnetic field with straight lines.

View all works in NVA