Prediction and understanding of soft proton contamination in XMM-Newton: a machine learning approach

2021 ◽  
Author(s):  
Elena Kronberg ◽  
Fabio Gastaldello ◽  
Stein Haaland ◽  
Artem Smirnov ◽  
Max Berrendorf ◽  
...  
Keyword(s):  
Magnetic Field ◽  
Machine Learning ◽  
Solar Wind ◽  
Southern Hemisphere ◽  
Solar Wind Speed ◽  
Flank Region ◽  
Learning Approach ◽  
X Ray ◽  
Machine Learning Approach ◽  
Field Lines

<p>One of the major and unfortunately unforeseen sources of background for the current generation of X-ray telescopes flying mainly in the magnetosphere are soft protons with few tens to hundreds of keV concentrated. One such telescope is the X-ray Multi-Mirror Mission (XMM-Newton) by ESA. Its observing time lost due to the contamination is  about 40%. This affects all the major broad science goals of XMM, ranging from cosmology to astrophysics of neutron stars and black holes. The soft proton background could dramatically impact future X-ray missions such Athena and SMILE missions. Magnetopsheric processes that trigger this background are still poorly understood. We use a machine learning approach to delineate related important parameters and to develop a model to predict the background contamination using 12 years of XMM observations. As predictors we use the location of XMM, solar and geomagnetic activity parameters. We revealed that the contamination is most strongly related to the distance in southern direction, ZGSE, (XMM observations were in the southern hemisphere), the solar wind velocity and the location on the magnetospheric magnetic field lines. We derived simple empirical models for the best two individual predictors and a machine learning model which utilizes an ensemble of the predictors (Extra Trees Regressor) and gives better performance. Based on our analysis, future X-Ray missions in the magnetosphere should minimize observations during  times  associated with high solar wind speed  and avoid closed magnetic field lines, especially at the dusk flank region at least in the southern hemisphere. </p>

scholarly journals Timing of the solar wind propagation delay between L1 and Earth based on machine learning

2021 ◽  
Author(s):  
Carsten Baumann ◽  
Aoife E. McCloskey
Keyword(s):  
Machine Learning ◽  
Solar Wind ◽  
Wind Speed ◽  
Space Weather ◽  
Solar Wind Speed ◽  
Propagation Delay ◽  
Learning Approach ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Gb Model

Erroneous GNSS positioning, failures in spacecraft operations and power outages due to geomagnetically induced currents  are severe threats originating from space weather. Having knowledge of potential impacts on modern society in advance is key for many end-user applications. This covers not only the timing of severe geomagnetic storms but also predictions of substorm onsets at polar latitudes. In this study we aim at contributing to the timing problem of space weather impacts and propose a new method to predict the solar wind propagation delay between Lagrangian point L1 and the Earth based on machine learning, specifically decision tree models. The propagation delay is measured from the identification of interplanetary discontinuities detected by the Advanced Composition Explorer (ACE) and their subsequent sudden commencements in the magnetosphere recorded by ground-based magnetometers. A database of the propagation delay has been constructed on this principle including 380 interplanetary shocks with data ranging from 1998 to 2018. The feature set of the machine learning approach consists of six features, namely the three components of each the solar wind speed and position of ACE around L1. The performance assessment of the machine learning model is examined on the basis of a 10-fold cross-validation. The machine learning results are compared to physics-based models, i.e., the flat propagation delay and the more sophisticated method based on the normal vector of solar wind discontinuities (vector delay). After hyperparameter optimization, the trained gradient boosting (GB) model is the best machine learning model among the tested ones. The GB model achieves an RMSE of 4.5 min with respect to the measured solar wind propagation delay and also outperforms the physical flat and vector delay models by 50 % and 15 % respectively. To increase the confidence in the predictions of the trained GB model, we perform a operational validation, provide drop-column feature importance and analyse the feature impact on the model output with Shapley values. The major advantage of the machine learning approach is its simplicity when it comes to its application. After training, values for the solar wind speed and spacecraft position from only one datapoint have to be fed into the algorithm for a good prediction.

PFSS-Based Solar Wind Forecast and the Radius of the Source-Surface

2017 ◽  
Vol 13 (S335) ◽  
pp. 307-309
Author(s):  
Ljubomir Nikolić
Keyword(s):  
Magnetic Field ◽  
Solar Wind ◽  
Spherical Surface ◽  
Solar Wind Speed ◽  
Coronal Holes ◽  
Coronal Magnetic Field ◽  
Source Surface ◽  
Field Source ◽  
Forecast Models ◽  
Field Lines

AbstractThe potential-field source-surface (PFSS) model of the solar corona is a widely used tool in the space weather research and operations. In particular, the PFSS model is used in solar wind forecast models which empirically associate solar wind properties with the numerically derived coronal magnetic field. In the PFSS model, the spherical surface where magnetic field lines are forced to open is typically placed at 2.5 solar radii. However, the results presented here suggest that setting this surface (the source-surface) to lower heights can provide a better agreement between observed and modelled coronal holes during the current solar cycle. Furthermore, the lower heights of the source-surface provide a better match between observed and forecasted solar wind speed.

scholarly journals Machine Learning Approach for Solar Wind Categorization

2020 ◽  
Vol 7 (5) ◽  
Author(s):  
Hui Li ◽  
Chi Wang ◽  
Cui Tu ◽  
Fei Xu
Keyword(s):  
Machine Learning ◽  
Solar Wind ◽  
Learning Approach ◽  
Machine Learning Approach

scholarly journals A Prediction of Corona Disease Transmission Using A Traditional Machine Learning Approach

2020 ◽  
pp. 447-452
Author(s):  
Chandran Venkatesan ◽  
Elakkiya Balan ◽  
Sumithra M G ◽  
Karthick A ◽  
Jayarajan V ◽  
...  
Keyword(s):  
Machine Learning ◽  
Disease Transmission ◽  
Transition Process ◽  
Machine Learning Algorithms ◽  
Learning Approach ◽  
X Ray ◽  
Machine Learning Approach ◽  
Current Scenario ◽  
Chest X Ray ◽  
Bayes Algorithm

In this current scenario, covid pandemic breaks analysis is becoming popular among the researchers. The various data sources from the different countries analyzed to predict the possibility of coronavirus transition from one person to another person. The datasets are not providing more information about the causes of the corona. Many authors provided the solution by using chest X-ray and CT images to predict the corona. In this paper, the covid pandemic transition process from one person to another person was classified using traditional machine learning algorithms. The input labels are encoded and transformed, utilizing the label encoder technique. The XG boost algorithm was outperformed all the other algorithms with overall accuracy and F1-measure of 99%. The Naive Bayes algorithm provides 100% accuracy, precision, recall, and F1-Score due to its improved ability to handle lower datasets.

Sign in / Sign up

Export Citation Format

Share Document