m-NLP inference models using simulation and regression techniques

Liu, Guangdong; Marholm, Sigvald; Eklund, Anders; Clausen, L. B. N.; Marchand, R.

doi:10.1002/essoar.10510978.1

Cited by 1 publication

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RMSRE and PCC between inferred data and ground truth IRI data is assessed for different levels of noise. As a consistency check, the currents calculated from the synthetic data are compared to currents which are again calculated from the inferred parameters using the finite-length/finite-radius models, as suggested by (G. Liu et al, 2022). This verifies the results of the inference model, as the back-inferred currents should agree with the currents from the synthetic data.…”

Section: Evaluation and Robustness Of The Modelmentioning

confidence: 58%

Electron Temperature Inference from Multiple Fixed Bias Langmuir Probes

Enengl

Marholm

Adhikari

et al. 2022

Preprint

View full text Add to dashboard Cite

We show the first achievement of inferring the electron temperature in ionospheric conditions from synthetic data using fixedbias Langmuir probes operating in the electron saturation region. This was done by using machine learning and altering the probe geometry. The electron temperature is inferred at the same rate as the currents are sampled by the probes. For inferring the electron temperature along with the electron density and the floating potential, a minimum number of three probes is required. Furthermore does one probe geometry need to be distinct from the other two, since otherwise the probe setup may be insensitive to temperature. This can be achieved by having either one shorter probe or a probe of a different geometry, e.g. two longer and a shorter cylindrical probe or two cylindrical probes and a spherical probe. We use synthetic plasma parameter data and calculate the synthetic collected probe currents to train a neural network and verify the results with a test set. We additionally verify the validity of the inferred temperature in altitudes ranging from about 100 km-500 km, using data from the International Reference Ionosphere model. Even minor changes in the probe sizing enable the temperature inference and result in root mean square relative errors between inferred and ground truth data of under 3%. When limiting the temperature inference to 120-450 km altitude an RMSRE of under 0.7% is achieved for all probe setups. In future, the multi-needle Langmuir Probe instrument dimensions can be adapted for higher temperature inference accuracy.

show abstract

Section: Evaluation and Robustness Of The Modelmentioning

confidence: 58%