ORCID Profile
0000-0002-6929-2158
Current Organisations
RMIT University
,
Cooperative Institute for Research in Environmental Sciences
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Related Links
Publications
Multi‐Hour‐Ahead Dst Index Prediction Using Multi‐Fidelity Boosted Neural Networks
Publisher: American Geophysical Union (AGU)
Date: 30-03-2023
DOI: 10.1029/2022SW003286
Abstract: The Disturbance storm time (Dst) index has been widely used as a proxy for the ring current intensity, and therefore as a measure of geomagnetic activity. It is derived by measurements from four ground magnetometers in the geomagnetic equatorial region. We present a new model for predicting Dst with a lead time between 1 and 6 hr. The model is first developed using a Gated Recurrent Unit (GRU) network that is trained using solar wind parameters. The uncertainty of the Dst model is then estimated by using the Accurate and Reliable Uncertainty Estimate method (C oreale & Carè, 2021, 0.1615/int.j.uncertaintyquantification.2021034623 ). Finally, a multi‐fidelity boosting method is developed in order to enhance the accuracy of the model and reduce its associated uncertainty. It is shown that the developed model can predict Dst 6 hr ahead with a root‐mean‐square‐error of 13.54 nT. This is significantly better than a persistence model or a single GRU model.
Impact of Thermospheric Mass Density on the Orbit Prediction of LEO Satellites
Publisher: American Geophysical Union (AGU)
Date: 2020
DOI: 10.1029/2019SW002336
Abstract: Many thermospheric mass density (TMD) variations have been recognized in observations and physical simulations however, their impact on the low‐Earth‐orbit satellites has not been fully evaluated. The present study investigates the quantitative impact of periodic spatiotemporal TMD variations modulated by the empirical DTM2013 model. Also considered are two small‐scale variations, that is, the equatorial mass anomaly and the midnight density maximum, which are reproduced by the Thermosphere‐Ionosphere‐Electrodynamics General Circulation Model. This investigation is performed through a 1‐day orbit prediction (OP) simulation for a 400‐km circular orbit. The results show that the impact of TMD variations during solar maximum is 1 order of magnitude larger than that during solar minimum. The dominant impact has been found in the along‐track direction. Semiannual and semidiurnal variations in TMD exert the most significant impact on OP among the intra‐annual and intradiurnal variations, respectively. The zero mean periodic variations in TMD may not significantly affect the predicted orbit but increase the orbital uncertainty if their periods are shorter than the time span of OP. Additionally, the equatorial mass anomaly creates a mean orbit difference of 50 m (5 m) with a standard deviation of 30 m (3 m) in 1‐day OP during high (low) solar activity. The midnight density maximum exhibits a stronger impact in the order of 150±30 and 15±6 m during solar maximum and solar minimum, respectively. This study makes clear that careful selection of TMD variations is of great importance to balance the trade‐off between efficiency and accuracy in OP problems.
Physics-informed Machine Learning prediction of ambient solar wind speed
Publisher: Copernicus GmbH
Date: 15-05-2023
DOI: 10.5194/EGUSPHERE-EGU23-4005
Abstract: Forecasting the ambient solar wind several days in advance still proves extremely difficult. In fact, state-of-the-art models (either physics-based or based on machine learning) do not consistently outperform simple baseline predictions based on 1-day persistence or 27-day recurrence. In turn, our inability to precisely forecast the ambient solar wind impacts both the accuracy and the lead-time of every Geospace and Magnetosphere-Ionosphere-Thermosphere model used for space weather purposes. Here, we present preliminary results about a physics-informed machine learning model that aims to predict the ambient solar wind up to 5 days ahead, by combining Global Oscillation Network Group (GONG) observations and a simplified solar wind propagation model, known as HUX (Heliospheric Upwind eXtrapolation). In essence the model learns a coronal model in a completely data-driven fashion, by using ACE observations as its target.
Modeling TEC Maps Over China Using Particle Swarm Optimization Neural Networks and Long‐Term Ground‐Based GPS, COSMIC, and Fengyun Data
Publisher: American Geophysical Union (AGU)
Date: 04-2023
DOI: 10.1029/2022SW003357
Abstract: This paper presents a new model for ionospheric total electron content (TEC) over China. The new model is developed using a hybrid method composed of the particle swarm optimization (PSO) and artificial neural network and long‐term observations from 257 ground‐based global navigation satellite systems (GNSS) stations and space‐borne GNSS radio occultation systems (COSMIC and Fengyun) during the 14‐year period of 2008–2021. The PSO algorithm is used to optimize the traditional back‐propagation neural network (BP‐NN) model by reducing the effects of the local minimum problem. The new model is validated using out‐of‐s le data, and its results are compared to the BP‐NN, IRI‐2016 model, and global ionospheric maps provided by the International GNSS Service. Results show that TEC predicted from the new model agrees better with the reference TEC than the BP‐NN and IRI‐2016 models. The improvements made by the new model over the BP‐NN and IRI‐2016 models in the equinox, summer, and winter seasons of the solar maximum year (2015) are 4%–20%/20%–36%, 9%–21%/26%–42%, and 6%–22%/21%–43%, respectively, and their corresponding results in the solar minimum year (2019) are 12%–24%/41%–59%, 9%–24%/28%–56%, and 10%–26%/53%–72%. Furthermore, the new model well captures the diurnal evolution, seasonal variation, and variations in the ionospheric TEC under different solar activity levels. It also well captures the mid‐latitude summer nighttime anomaly over China, and the diurnal anomaly is more pronounced in the solar minimum year (2019) than in the solar maximum year (2015) in terms of the nighttime‐to‐noontime ratio and the range of months it lasts in a year.
A Deep Neural Network Model of Global Topside Electron Temperature Using Incoherent Scatter Radars and Its Application to GNSS Radio Occultation
Publisher: American Geophysical Union (AGU)
Date: 02-2020
DOI: 10.1029/2019JA027263
Helmert-VCE-aided fast-WTLS approach for global ionospheric VTEC modelling using data from GNSS, satellite altimetry and radio occultation
Publisher: Springer Science and Business Media LLC
Date: 14-11-2018
Ionospheric and Thermospheric Responses to the Recent Strong Solar Flares on 6 September 2017
Publisher: American Geophysical Union (AGU)
Date: 10-2018
DOI: 10.1029/2018JA025700
Correction: Hu, A. Using Bidirectional Long Short-Term Memory Method for the Height of F2 Peak Forecasting from Ionosonde Measurements in the Australian Region. Remote Sens. 2018, 10, 1658
Publisher: MDPI AG
Date: 21-11-2018
DOI: 10.3390/RS10111857
Abstract: After publication of the research paper [...]
Application of a Multi‐Layer Artificial Neural Network in a 3‐D Global Electron Density Model Using the Long‐Term Observations of COSMIC, Fengyun‐3C, and Digisonde
Publisher: American Geophysical Union (AGU)
Date: 03-2021
DOI: 10.1029/2020SW002605
Abstract: The ionosphere plays an important role in satellite navigation, radio communication, and space weather prediction. However, it is still a challenging mission to develop a model with high predictability that captures the horizontal‐vertical features of ionospheric electrodynamics. In this study, multiple observations during 2005–2019 from space‐borne global navigation satellite system (GNSS) radio occultation (RO) systems (COSMIC and FY‐3C) and the Digisonde Global Ionosphere Radio Observatory are utilized to develop a completely global ionospheric three‐dimensional electron density model based on an artificial neural network, namely ANN‐TDD. The correlation coefficients of the predicted profiles all exceed 0.96 for the training, validation and test datasets, and the minimum root‐mean‐square error of the predicted residuals is 7.8 × 10 4 el/cm 3 . Under quiet space weather, the predicted accuracy of the ANN‐TDD is 30%–60% higher than the IRI‐2016 at the Millstone Hill and Jicamarca incoherent scatter radars. However, the ANN‐TDD is less capable of predicting ionospheric dynamic evolution under severe geomagnetic storms compared to the IRI‐2016 with the STORM option activated. Additionally, the ANN‐TDD successfully reproduces the large‐scale horizontal‐vertical ionospheric electrodynamic features, including seasonal variation and hemispheric asymmetries. These features agree well with the structure revealed by the RO profiles derived from the FORMOSAT/COSMIC‐2 mission. Furthermore, the ANN‐TDD successfully captures the prominent regional ionospheric patterns, including the equatorial ionization anomaly, Weddell Sea anomaly and mid‐latitude summer nighttime anomaly. The new model is expected to play an important role in the application of GNSS navigation and in the explanation of the physical mechanisms involved.
Using machine learning to identify magnetic reconnection in two-dimensional simulations
Publisher: Copernicus GmbH
Date: 23-03-2020
DOI: 10.5194/EGUSPHERE-EGU2020-12160
Abstract: & & The understanding of fundamental processes at play in a collisionless plasmas such as the solar wind, is a frontier problem in space physics. We investigate here the occurrence of magnetic reconnection in a plasma with parameters corresponding to solar wind plasma and its interplay with a fully-developed turbulent state. Ongoing magnetic reconnection can, at the moment, be accurately identified only by humans. Therefore, as a first step, the goal of this study is to present a new method to automatically recognise reconnection events in the output of two-dimensional HVM (Hybrid Vlasov Maxwell)& simulations& where ions evolve by solving the Vlasov equation and the electrons are treated as a fluid with mass. A large dataset with labelled reconnection events was prepared, including parameters such as the magnetic field, the electron velocity field and the current density. We consider two types of machine learning models: classical approaches using on physics-based features, and convolutional neural networks (CNNs). We will investigate which approach performs better, and which input variables are most relevant. In addition, we will try to categorize magnetic reconnection regions (current sheets). This work has received funding from the European Union& #8217 s Horizon 2020 research and innovation programme under grant agreement No 776262 (AIDA, www.aida-space.eu).& / &
Probabilistic Prediction of Dst Storms One‐Day‐Ahead Using Full‐Disk SoHO Images
Publisher: American Geophysical Union (AGU)
Date: 08-2022
DOI: 10.1029/2022SW003064
Abstract: We present a new model for the probability that the disturbance storm time ( Dst ) index exceeds −100 nT, with a lead time between 1 and 3 days. Dst provides essential information about the strength of the ring current around the Earth caused by the protons and electrons from the solar wind, and it is routinely used as a proxy for geomagnetic storms. The model is developed using an ensemble of Convolutional Neural Networks that are trained using Solar and Heliospheric Observatory (SoHO) images (Michelson Doppler Imager, Extreme ultraviolet Imaging Telescope, and Large Angle and Spectrometric Coronagraph). The relationship between the SoHO images and the solar wind has been investigated by many researchers, but these studies have not explicitly considered using SoHO images to predict the Dst index. This work presents a novel methodology to train the in idual models and to learn the optimal ensemble weights iteratively, by using a customized class‐balanced mean square error (CB‐MSE) loss function tied to a least‐squares based ensemble. The proposed model can predict the probability that Dst −100 nT 24 hr ahead with a True Skill Statistic (TSS) of 0.62 and Matthews Correlation Coefficient (MCC) of 0.37. The weighted TSS and MCC is 0.68 and 0.47, respectively. An additional validation during non‐Earth‐directed CME periods is also conducted which yields a good TSS and MCC score.
A new voxel-based model for the determination of atmospheric weighted mean temperature in GPS atmospheric sounding
Publisher: Copernicus GmbH
Date: 07-06-2017
Abstract: Abstract. The Global Positioning System (GPS) is a powerful atmospheric observing system for determining precipitable water vapour (PWV). In the detection of PWV using GPS, the atmospheric weighted mean temperature (Tm) is a crucial parameter for the conversion of zenith tropospheric delay (ZTD) to PWV since the quality of PWV is affected by the accuracy of Tm. In this study, an improved voxel-based Tm model, named GWMT-D, was developed using global reanalysis data over a 4-year period from 2010 to 2013 provided by the United States National Centers for Environmental Prediction (NCEP). The performance of GWMT-D was assessed against three existing empirical Tm models – GTm-III, GWMT-IV, and GTm_N – using different data sources in 2014 – the NCEP reanalysis data, surface Tm data provided by Global Geodetic Observing System and radiosonde measurements. The results show that the new GWMT-D model outperforms all the other three models with a root-mean-square error of less than 5.0 K at different altitudes over the globe. The new GWMT-D model can provide a practical alternative Tm determination method in real-time GPS-PWV remote sensing systems.
Modeling of Topside Ionospheric Vertical Scale Height Based on Ionospheric Radio Occultation Measurements
Publisher: American Geophysical Union (AGU)
Date: 06-2019
DOI: 10.1029/2018JA026280
A new voxel-based model for the determination of atmospheric-weighted-mean temperature in GPS atmospheric sounding
Publisher: Copernicus GmbH
Date: 12-2016
DOI: 10.5194/AMT-2016-338
Abstract: Abstract. The Global Positioning System (GPS) has been regarded as a powerful atmospheric observing system for determining precipitable water vapour (PWV) nowadays. One of the most critical variables in PWV remote sensing using GPS technique is the zenith tropospheric delay (ZTD). The conversion from ZTD to PWV requires a good knowledge of the atmospheric-weighted-mean temperature (Tm) over the station. Thus the quality of PWV is affected by the accuracy of both ZTD and Tm. In this study, an improved voxel-based Tm model, named GWMT−D, was developed and validated using global reanalysis data from 2010 to 2014 provided by NCEP-DOE Reanalysis 2 data (NCEP2). The performance of GWMT−D, along with other three selected empirical Tm models, GTm−III, GWMT−IV and GTm_N, was assessed with reference Tm derived from different sources – the NCEP2, Global Geodetic Observing System (GGOS) data and radiosonde measurements. The results showed that the new GWMT−D model outperformed all the other three models with a root-mean-square error of less than 5.0 K at different altitudes over the globe. The new GWMT−D model can provide an alternative Tm determination method in real-time/near real-time GPS-PWV remote sensing system.
Improvement of Reflection Detection Success Rate of GNSS RO Measurements Using Artificial Neural Network
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2018
Identifying Magnetic Reconnection in 2D Hybrid Vlasov Maxwell Simulations with Convolutional Neural Networks
Publisher: American Astronomical Society
Date: 03-09-2020
Using Bidirectional Long Short-Term Memory Method for the Height of F2 Peak Forecasting from Ionosonde Measurements in the Australian Region
Publisher: MDPI AG
Date: 19-10-2018
DOI: 10.3390/RS10101658
Abstract: The height of F2 peak (hmF2) is an essential ionospheric parameter and its variations can reflect both the earth magnetic and solar activities. Therefore, reliable prediction of hmF2 is important for the study of space, such as solar wind and extreme weather events. However, most current models are unable to forecast the variation of the ionosphere effectively since real-time measurements are required as model inputs. In this study, a new Australian regional hmF2 forecast model was developed by using ionosonde measurements and the bidirectional Long Short-Term Memory (bi-LSTM) method. The hmF2 value in the next hour can be predicted using the data from the past five hours at the same location. The inputs chosen from a location of interest include month of the year, local time (LT), K p , F 10 . 7 and hmF2 as an independent variable vector. The independent variable vectors in the immediate past five hours are considered as an independent variable set, which is used as an input of the new Australian regional hmF2 forecast model developed for the prediction of hmF2 in the hour to come. The performance of the new model developed is evaluated by comparing with those from other popular models, such as the AMTB, Shubin, ANN and LSTM models. Results showed that: (1) the new model can substantially outperform all the other four models. (2) Compared to the LSTM model, the new model is proven to be more robust and rapidly convergent. The mew model also outperforms that of the ANN model by around 30%. (3) the minimum s le number for the bi-LSTM method (i.e., 2000) to converge is about 50% less than that is required for the LSTM method (i.e., 3000). (4) Compared to the Shubin model, the bi-LSTM method can effectively forecast the hmF2 values up to 5 h. This research is a first attempt at using the deep learning-based method for the application of the ionospheric prediction.
Related Organisations
Nanjing University Of Information Science And Technology
Location: China
Cooperative Institute For Research In Environmental Sciences
Location: United States of America
Related Funding Activities
No related grants have been discovered for Andong Hu.