Prediction of Solar Wind Speed at 1 AU Using an Artificial Neural Network

Yang, Yi; Shen, Fang; Yang, Zhongshan; Feng, Xueshang

doi:10.1029/2018sw001955

Cited by 47 publications

(50 citation statements)

References 116 publications

(144 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the difference is relatively large or unsatisfactory, the error between the network output and the expected output is returned, and repeated training is learned by adjusting the weight of each connection until it can produce an output that approximates the true answer. NN technology has been widely used in ground-based and space-based remote sensing retrieval [41][42][43][44].…”

Section: Bp Nn-based Inversion Of Atmospheric Temperature and Humidity Algorithmmentioning

confidence: 99%

Temperature and Relative Humidity Profile Retrieval from Fengyun-3D/HIRAS in the Arctic Region

Bao

Liu

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The acquisition of real-time temperature and relative humidity (RH) profiles in the Arctic is of great significance for the study of the Arctic’s climate and Arctic scientific research. However, the operational algorithm of Fengyun-3D only takes into account areas within 60°N, the innovation of this work is that a new technique based on Neural Network (NN) algorithm was proposed, which can retrieve these parameters in real time from the Fengyun-3D Hyperspectral Infrared Radiation Atmospheric Sounding (HIRAS) observations in the Arctic region. Considering the difficulty of obtaining a large amount of actual observation (such as radiosonde) in the Arctic region, collocated ERA5 data from European Centre for Medium-Range Weather Forecasts (ECMWF) and HIRAS observations were used to train the neural networks (NNs). Brightness temperature and training targets were classified using two variables: season (warm season and cold season) and surface type (ocean and land). NNs-based retrievals were compared with ERA5 data and radiosonde observations (RAOBs) independent of the NN training sets. Results showed that (1) the NNs retrievals accuracy is generally higher on warm season and ocean; (2) the root-mean-square error (RMSE) of retrieved profiles is generally slightly higher in the RAOB comparisons than in the ERA5 comparisons, but the variation trend of errors with height is consistent; (3) the retrieved profiles by the NN method are closer to ERA5, comparing with the AIRS products. All the results demonstrated the potential value in time and space of NN algorithm in retrieving temperature and relative humidity profiles of the Arctic region from HIRAS observations under clear-sky conditions. As such, the proposed NN algorithm provides a valuable pathway for retrieving reliably temperature and RH profiles from HIRAS observations in the Arctic region, providing information of practical value in a wide spectrum of practical applications and research investigations alike.All in all, our work has important implications in broadening Fengyun-3D’s operational implementation range from within 60°N to the Arctic region.

show abstract

Section: Bp Nn-based Inversion Of Atmospheric Temperature and Humidity Algorithmmentioning

confidence: 99%

Temperature and Relative Humidity Profile Retrieval from Fengyun-3D/HIRAS in the Arctic Region

Bao

Liu

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Within the class of semiempirical models, models purely based on statistics of past events, past data, and pattern recognition (e.g., Camporeale et al, ; Owens, Riley, et al ; Riley et al, ) or neural networks (e.g., Y. Yang et al, ) have been proposed or are currently being developed. These models have shown promising results for the prediction of the solar wind speed or density at 1 AU, but their appropriateness for forecasting the magnetic field inside CMEs and CME‐driven shocks/sheaths is yet unproven.…”

Section: Modeling the Evolution Of Cmesmentioning

confidence: 99%

Forecasting the Structure and Orientation of Earthbound Coronal Mass Ejections

et al. 2019

View full text Add to dashboard Cite

Coronal Mass Ejections (CMEs) are the key drivers of strong to extreme space weather storms at the Earth that can have drastic consequences for technological systems in space and on ground. The ability of a CME to drive geomagnetic disturbances depends crucially on the magnetic structure of the embedded flux rope, which is thus essential to predict. The current capabilities in forecasting in advance (at least half a day before) the geoeffectiveness of a given CME is however severely hampered by the lack of remote-sensing measurements of the magnetic field in the corona and adequate tools to predict how CMEs deform, rotate, and deflect during their travel through the coronal and interplanetary space as they interact with the ambient solar wind and other CMEs. These problems can lead not only to overestimation or underestimation of the severity of a storm, but also to forecasting "misses" and "false alarms" that are particularly difficult for the end-users. In this paper, we discuss the current status and future challenges and prospects related to forecasting of the magnetic structure and orientation of CMEs. We focus both on observational-and modeling-based (first principle and semiempirical) approaches and discuss the space-and ground-based observations that would be the most optimal for making accurate space weather predictions. We also cover the gaps in our current understanding related to the formation and eruption of the CME flux rope and physical processes that govern its evolution in the variable ambient solar wind background that complicate the forecasting.

show abstract

“…A MLP neural network functions like a biological neural network and is an interconnected assembly of simple processing elements, units, or neurons that is based on the neural configuration of the brain. MLP can handle large data sets and has the ability to capture nonlinear and complex underlying relationships of any physical process with plenty of data (Yang, Shen, et al, 2018). The architectural design of a neural network in this study consists of five layers: an input layer, three hidden layers, and an output layer.…”

Section: Mlp Neural Network and Lstm Algorithmsmentioning

confidence: 99%

Deep Learning Models for Estimation of the SuperDARN Cross Polar Cap Potential

Liu

et al. 2020

Earth and Space Science

View full text Add to dashboard Cite

We present deep learning models for cross polar cap potential (CPCP) by applying multilayer perceptron (MLP) and long short‐term memory (LSTM) networks to estimate CPCP based on Super Dual Auroral Radar Network (SuperDARN) measurements. Three statistical parameters are proposed, which are root‐mean‐square error (RMSE), mean absolute error and linear correlation coefficient (LC), to validate and test the models by measuring their performance on an independent data set that was withheld from the training data set. In addition, we compare the models with previous work. The results show that the deep learning models can successfully reproduce the CPCP values with much lower RMSE (8.41 kV for MLP and 7.20 kV for LSTM) and mean absolute error (7.22 kV for MLP and 6.28 kV for LSTM) and higher LC (0.84 for MLP and 0.90 for LSTM) than do the other models, which have RMSE larger than 10 kV and LC lower than 0.75. The deep learning models can also express the CPCP nonlinear properties (saturation effect) accurately. This study demonstrates that deep learning techniques can enhance the ability to predict CPCP.

show abstract

Prediction of Solar Wind Speed at 1 AU Using an Artificial Neural Network

Cited by 47 publications

References 116 publications

Temperature and Relative Humidity Profile Retrieval from Fengyun-3D/HIRAS in the Arctic Region

Temperature and Relative Humidity Profile Retrieval from Fengyun-3D/HIRAS in the Arctic Region

Forecasting the Structure and Orientation of Earthbound Coronal Mass Ejections

Deep Learning Models for Estimation of the SuperDARN Cross Polar Cap Potential

Contact Info

Product

Resources

About