Disturbance Storm Time Index Prediction using Long Short-Term Memory Machine Learning

Wihayati,; Purnomo, Hindriyanto Dwi; Trihandaru, Suryasatriya

doi:10.1109/ic2ie53219.2021.9649119

Cited by 2 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, we present here a complete data analysis of the ACE solar wind and IMF measurements, an essential and largely used data when forecasting on-Earth events, even today (Myagkova et al (2020), Wintoft et al (2015), etc.). While we will not expand on this in this paper, it is interesting to notice that a lot of studies use the NASA's OMNIWeb dataset (see https://omniweb.gsfc.nasa.gov/html/ow_data.html) such as Wihayati et al (2021) or Gombosi et al (2018) for instance. High-Resolution OMNIWeb data are made of ACE, IMP 8, Wind and Geotail satellites data gathered and time-shifted to the Bow Shock Nose.…”

Section: Introductionmentioning

confidence: 99%

Towards an AI-based understanding of the solar wind: A critical data analysis of ACE data

Bouriat

Vandame

Barthélémy

et al. 2022

Front. Astron. Space Sci.

View full text Add to dashboard Cite

All artificial intelligence models today require preprocessed and cleaned data to work properly. This crucial step depends on the quality of the data analysis being done. The Space Weather community increased its use of AI in the past few years, but a thorough data analysis addressing all the potential issues is not always performed beforehand. Here is an analysis of a largely used dataset: Level-2 Advanced Composition Explorer’s SWEPAM and MAG measurements from 1998 to 2021 by the ACE Science Center. This work contains guidelines and highlights issues in the ACE data that are likely to be found in other space weather datasets: missing values, inconsistency in distributions, hidden information in statistics, etc. Amongst all specificities of this data, the following can seriously impact the use of algorithms: Histograms are not uniform distributions at all, but sometime Gaussian or Laplacian. Algorithms will be inconsistent in the learning samples as some rare cases will be underrepresented. Gaussian distributions could be overly brought by Gaussian noise from measurements and the signal-to-noise ratio is difficult to estimate. Models will not be reproducible from year to year due to high changes in histograms over time. This high dependence on the solar cycle suggests that one should have at least 11 consecutive years of data to train the algorithm. Rounding of ion temperatures values to different orders of magnitude throughout the data, (probably due to a fixed number of bits on which measurements are coded) will bias the model by wrongly over-representing or under-representing some values. There is an extensive number of missing values (e.g., 41.59% for ion density) that cannot be implemented without pre-processing. Each possible pre-processing is different and subjective depending on one’s underlying objectives A linear model will not be able to accurately model the data. Our linear analysis (e.g., PCA), struggles to explain the data and their relationships. However, non-linear relationships between data seem to exist. Data seem cyclic: we witness the apparition of the solar cycle and the synodic rotation period of the Sun when looking at autocorrelations.Some suggestions are given to address the issues described to enable usage of the dataset despite these challenges.

show abstract

Section: Introductionmentioning

confidence: 99%