Using Gradient Boosting Regressors to forecast the ambient solar wind from coronal magnetic models

2021 ◽  
Author(s):  
Rachel Bailey ◽  
Martin A. Reiss ◽  
Christian Möstl ◽  
C. Nick Arge ◽  
Carl Henney ◽  
...  
Keyword(s):  
Solar Wind ◽  
Interplanetary Space ◽  
Gradient Boosting ◽  
Final Model ◽  
Machine Learning Approach ◽  
Solar Wind Flow ◽  
Solar Storms ◽  
Input Variables ◽  
Almost All ◽  
Ambient Solar Wind

<p>In this study we present a method for forecasting the ambient solar wind at L1 from coronal magnetic models. Ambient solar wind flows in interplanetary space determine how solar storms evolve through the heliosphere before reaching Earth, and accurately modelling and forecasting the ambient solar wind flow is therefore imperative to space weather awareness. We describe a novel machine learning approach in which solutions from models of the solar corona based on 12 different ADAPT magnetic maps are used to output the solar wind conditions some days later at the Earth. A feature analysis is carried out to determine which input variables are most important. The results of the forecasting model are compared to observations and existing models for one whole solar cycle in a comprehensive validation analysis. We find that the new model outperforms existing models and 27-day persistence in almost all metrics. The final model discussed here represents an extremely fast, well-validated and open-source approach to the forecasting of ambient solar wind at Earth, and is specifically well-suited for ensemble modelling or for application with other coronal models.</p>

scholarly journals Using gradient boosting regression to improve ambient solar wind model predictions

Space Weather ◽  
2021 ◽  
Author(s):  
R. L. Bailey ◽  
M. A. Reiss ◽  
C. N. Arge ◽  
C. Möstl ◽  
C. J. Henney ◽  
...  
Keyword(s):  
Solar Wind ◽  
Gradient Boosting ◽  
Wind Model ◽  
Solar Wind Model ◽  
Model Predictions ◽  
Ambient Solar Wind

CME arrival time predictions with a deformable front

2021 ◽  
Author(s):  
Jürgen Hinterreiter ◽  
Tanja Amerstorfer ◽  
Martin A. Reiss ◽  
Andreas J. Weiss ◽  
Christian Möstl ◽  
...  
Keyword(s):  
Solar Wind ◽  
Large Scale ◽  
Arrival Time ◽  
Interplanetary Space ◽  
Solar Wind Speed ◽  
Model Combination ◽  
First Results ◽  
Good Agreement ◽  
Ambient Solar Wind

<p>We present the first results of our newly developed CME arrival prediction model, which allows the CME front to deform and adapt to the changing solar wind conditions. Our model is based on ELEvoHI and makes use of the WSA/HUX (Wang-Sheeley-Arge/Heliospheric Upwind eXtrapolation) model combination, which computes large-scale ambient solar wind conditions in the interplanetary space. With an estimate of the solar wind speed and density, we are able to account for the drag exerted on different parts of the CME front. Initially, our model relies on heliospheric imager observations to confine an elliptical CME front and to obtain an initial speed and drag parameter for the CME. After a certain distance, each point of the CME front is propagating based on the conditions in the heliosphere. In this case study, we compare our results to previous arrival time predictions using ELEvoHI with a rigid CME front. We find that the actual arrival time at Earth and the arrival time predicted by the new model are in very good agreement.</p>

scholarly journals INFLUENCE OF THE AMBIENT SOLAR WIND FLOW ON THE PROPAGATION BEHAVIOR OF INTERPLANETARY CORONAL MASS EJECTIONS

2011 ◽  
Vol 743 (2) ◽  
pp. 101 ◽  
Author(s):  
Manuela Temmer ◽  
Tanja Rollett ◽  
Christian Möstl ◽  
Astrid M. Veronig ◽  
Bojan Vršnak ◽  
...  
Keyword(s):  
Solar Wind ◽  
Coronal Mass Ejections ◽  
Wind Flow ◽  
Interplanetary Coronal Mass Ejections ◽  
Propagation Behavior ◽  
Solar Wind Flow ◽  
Ambient Solar Wind

Estimating Family Income from Administrative Banking Data: A Machine Learning Approach

2020 ◽  
Vol 110 ◽  
pp. 36-41
Author(s):  
Diana Farrell ◽  
Fiona Greig ◽  
Erica Deadman
Keyword(s):  
Credit Card ◽  
Family Income ◽  
Gradient Boosting ◽  
Reliable Estimate ◽  
Learning Approach ◽  
Final Model ◽  
Machine Learning Approach ◽  
Application Data ◽  
Public Datasets ◽  
Zip Code

The JPMorgan Chase Institute uses administrative banking data for research. In order to address representativeness in our data, we seek a reliable estimate of gross family income for population segmenting and reweighting purposes. JPMC Institute Income Estimate (JPMC IIE) version 1.0 uses gradient boosting machines (GBM) to estimate gross family income based on a truth set drawn from credit card and mortgage application data. The estimation relies on administrative banking data in combination with zip code-level characteristics available through public datasets. The final model yielded a significantly more accurate prediction of income than checking account inflows alone.

Modelling the evolution of CMEs and their shocks through different solar wind structures

2020 ◽  
Author(s):  
Erika Palmerio ◽  
Christina Lee ◽  
Leila Mays ◽  
Dusan Odstrcil
Keyword(s):  
Magnetic Field ◽  
Solar Wind ◽  
Vantage Point ◽  
Angular Width ◽  
Wind Flow ◽  
The Sun ◽  
Ambient Wind ◽  
Fast Wind ◽  
Solar Wind Flow ◽  
Ambient Solar Wind

<p>The evolution of coronal mass ejections (CMEs) as they travel away from the Sun is one of the major issues in heliophysics and space weather. After erupting, CMEs propagate outwards through the background solar wind flow, which in turn may significantly affect CME evolution by means of e.g. acceleration, deflection, and/or rotation. In order to determine to which extent the ambient wind can alter the speed, trajectory, and orientation of a CME, we run a series of 3D magnetohydrodynamics simulations (using the coupled solar–heliospheric WSA–Enlil model) to conduct a multi-vantage point study of the radial and longitudinal evolution of CME structures as they propagate up to Earth’s (1 AU) and Mars’ (1.5 AU) orbits. We explore a broad range of input CME parameters (initial radial speed, angular width) and ambient solar wind conditions (slow versus fast wind) to investigate the different evolutionary behaviours of CMEs and their driven shocks and sheath regions. To study the radial and longitudinal evolution for the modelled CME ejecta and shock events, we examine the resulting magnetic field and plasma time series at different heliocentric distances (0.5 AU, 1 AU, and 1.5 AU) and heliolongitudes (in 30° increments). This work will help establish a set of expected CME behaviours at Earth’s and Mars’ radial distances, which can be used for analysing real CME events.</p>

Effect of the ambient solar wind speed on drag-based CME prediction accuracy

2021 ◽  
Author(s):  
Tanja Amerstorfer ◽  
Jürgen Hinterreiter ◽  
Martin A. Reiss ◽  
Jackie A. Davies ◽  
Christian Möstl ◽  
...  
Keyword(s):  
Solar Wind ◽  
Wind Speed ◽  
Frequency Distribution ◽  
Prediction Accuracy ◽  
Arrival Time ◽  
Interplanetary Space ◽  
Solar Wind Speed ◽  
Ecliptic Plane ◽  
Arrival Probability ◽  
Ambient Solar Wind

<p>In the last years, many kinds of CME models, based on a drag-based evolution through interplanetary space, have been developed and are now widely used by the community. The unbeatable advantage of those methods is that they are computationally cheap and are therefore suitable to be used as ensemble models. Additionally, their prediction accuracy is absolutely comparable to more sophisticated models.</p><p>The ELlipse Evolution model based on heliospheric imager (HI) observations (ELEvoHI) assumes an elliptic frontal shape within the ecliptic plane and allows the CME to adjust to the ambient solar wind speed, i.e. it is drag-based. ELEvoHI is used as an ensemble simulation by varying the CME frontal shape within given boundary values. The results include a frequency distribution of predicted arrival time and arrival speed and an estimation of the arrival probability.</p><p>In this study, we investigate the possibility of not only varying the parameters related to the CME's ecliptic extent but also the ambient solar wind speed for each CME ensemle member. Although we have used a range of +/-100 km/s for possible values of the solar wind speed in the past, only the best candidate was in the end used to contribute to the prediction. We present the results of this approach by applying it to a CME propagating in a highly structured solar wind and compare the frequency distribution of the arrival time and speed predictions to those of the usual ELEvoHI approach.</p>

scholarly journals Assessing the Relation between Mud Components and Rheology for Loss Circulation Prevention Using Polymeric Gels: A Machine Learning Approach

Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1377
Author(s):  
Musaab I. Magzoub ◽  
Raj Kiran ◽  
Saeed Salehi ◽  
Ibnelwaleed A. Hussein ◽  
Mustafa S. Nasser
Keyword(s):  
Machine Learning ◽  
Rheological Properties ◽  
Nearest Neighbor ◽  
Drilling Fluid ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
Wide Range ◽  
Machine Learning Approach ◽  
Drilling Operations

The traditional way to mitigate loss circulation in drilling operations is to use preventative and curative materials. However, it is difficult to quantify the amount of materials from every possible combination to produce customized rheological properties. In this study, machine learning (ML) is used to develop a framework to identify material composition for loss circulation applications based on the desired rheological characteristics. The relation between the rheological properties and the mud components for polyacrylamide/polyethyleneimine (PAM/PEI)-based mud is assessed experimentally. Four different ML algorithms were implemented to model the rheological data for various mud components at different concentrations and testing conditions. These four algorithms include (a) k-Nearest Neighbor, (b) Random Forest, (c) Gradient Boosting, and (d) AdaBoosting. The Gradient Boosting model showed the highest accuracy (91 and 74% for plastic and apparent viscosity, respectively), which can be further used for hydraulic calculations. Overall, the experimental study presented in this paper, together with the proposed ML-based framework, adds valuable information to the design of PAM/PEI-based mud. The ML models allowed a wide range of rheology assessments for various drilling fluid formulations with a mean accuracy of up to 91%. The case study has shown that with the appropriate combination of materials, reasonable rheological properties could be achieved to prevent loss circulation by managing the equivalent circulating density (ECD).

scholarly journals A review of the SCOSTEP’s 5-year scientific program VarSITI—Variability of the Sun and Its Terrestrial Impact

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Kazuo Shiokawa ◽  
Katya Georgieva
Keyword(s):  
Solar Wind ◽  
Interplanetary Space ◽  
Solar Wind Plasma ◽  
The Sun ◽  
Scientific Program ◽  
Solar Cycles ◽  
Grand Minimum ◽  
The Earth ◽  
Earth Connection ◽  
Near Future

AbstractThe Sun is a variable active-dynamo star, emitting radiation in all wavelengths and solar-wind plasma to the interplanetary space. The Earth is immersed in this radiation and solar wind, showing various responses in geospace and atmosphere. This Sun–Earth connection variates in time scales from milli-seconds to millennia and beyond. The solar activity, which has a ~11-year periodicity, is gradually declining in recent three solar cycles, suggesting a possibility of a grand minimum in near future. VarSITI—variability of the Sun and its terrestrial impact—was the 5-year program of the scientific committee on solar-terrestrial physics (SCOSTEP) in 2014–2018, focusing on this variability of the Sun and its consequences on the Earth. This paper reviews some background of SCOSTEP and its past programs, achievements of the 5-year VarSITI program, and remaining outstanding questions after VarSITI.

Sign in / Sign up

Export Citation Format

Share Document