Machine Learning Ensemble Approach for Ionosphere and Space Weather Forecasting with Uncertainty Quantification

Natraš, Randa; Soja, Benedikt; Schmidt, Michaël

doi:10.23919/at-ap-rasc54737.2022.9814334

Cited by 4 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current state of research is mostly related to short-time forecasting from 1 h forecasting, such as in [15], to 1-day, such as in [24,33], and 2 day forecasting [31].…”

Section: Introductionmentioning

confidence: 99%

Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting

2022

Self Cite

View full text Add to dashboard Cite

Space weather describes varying conditions between the Sun and Earth that can degrade Global Navigation Satellite Systems (GNSS) operations. Thus, these effects should be precisely and timely corrected for accurate and reliable GNSS applications. That can be modeled with the Vertical Total Electron Content (VTEC) in the Earth’s ionosphere. This study investigates different learning algorithms to approximate nonlinear space weather processes and forecast VTEC for 1 h and 24 h in the future for low-, mid- and high-latitude ionospheric grid points along the same longitude. VTEC models are developed using learning algorithms of Decision Tree and ensemble learning of Random Forest, Adaptive Boosting (AdaBoost), and eXtreme Gradient Boosting (XGBoost). Furthermore, ensemble models are combined into a single meta-model Voting Regressor. Models were trained, optimized, and validated with the time series cross-validation technique. Moreover, the relative importance of input variables to the VTEC forecast is estimated. The results show that the developed models perform well in both quiet and storm conditions, where multi-tree ensemble learning outperforms the single Decision Tree. In particular, the meta-estimator Voting Regressor provides mostly the lowest RMSE and the highest correlation coefficients as it averages predictions from different well-performing models. Furthermore, expanding the input dataset with time derivatives, moving averages, and daily differences, as well as modifying data, such as differencing, enhances the learning of space weather features, especially over a longer forecast horizon.

show abstract

“…Current state of research is mostly related to short-time forecasting from 1 h forecasting, such as in [15], to 1-day, such as in [24,33], and 2 day forecasting [31].…”

Section: Introductionmentioning

confidence: 99%

Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ensemble modeling combines multiple diverse models to predict an outcome using either different algorithms or different data sets. The ensemble model, called Super‐Ensemble (SE) (Natras et al., 2022b), aggregates the mean result across all base models to produce a final prediction with reduced generalization error. This approach improves the prediction compared to the single base model within the ensemble by averaging the results over a set of functions of well‐performing models (Natras et al., 2022b).…”

Section: Methodsmentioning

confidence: 99%

“…The ensemble model, called Super‐Ensemble (SE) (Natras et al., 2022b), aggregates the mean result across all base models to produce a final prediction with reduced generalization error. This approach improves the prediction compared to the single base model within the ensemble by averaging the results over a set of functions of well‐performing models (Natras et al., 2022b). In this study, ensemble modeling combines three learning algorithms, namely Random Forest (Breiman, 2001), Adaptive Boosting (AdaBoost) (Freund & Schapire, 1997) and Gradient Boosting (Friedman, 2001) on three data sets consisting of different versions of input features and output.…”

Section: Methodsmentioning

confidence: 99%

“…The initial study of an ML ensemble approach to VTEC forecast in Natras et al. (2022b) showed higher accuracy and improved generalization compared to a single‐model approach, with uncertainties estimated as ensemble spread. Other studies on ML‐based VTEC modeling and forecasting, such as Y. Han et al.…”

Section: Introductionmentioning

confidence: 99%

“…The least squares inclusion of both input and output data uncertainties with Bayesian learning using a Long Short-Term Memory neural network resulted in better generalization when applied to the prediction of Earth orientation parameters and Global Navigation Satellite Systems station coordinates (Kiani Shahvandi & Soja, 2022). The initial study of an ML ensemble approach to VTEC forecast in Natras et al (2022b) showed higher accuracy and improved generalization compared to a single-model approach, with uncertainties estimated as ensemble spread. Other studies on ML-based VTEC modeling and forecasting, such as Y.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Uncertainty Quantification for Machine Learning‐Based Ionosphere and Space Weather Forecasting: Ensemble, Bayesian Neural Network, and Quantile Gradient Boosting

Natras,

Soja,

Schmidt

2023

Space Weather

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) has been increasingly applied to space weather and ionosphere problems in recent years, with the goal of improving modeling and forecasting capabilities through a data‐driven modeling approach of nonlinear relationships. However, little work has been done to quantify the uncertainty of the results, lacking an indication of how confident and reliable the results of an ML system are. In this paper, we implement and analyze several uncertainty quantification approaches for an ML‐based model to forecast Vertical Total Electron Content (VTEC) 1‐day ahead and corresponding uncertainties with 95% confidence intervals (CI): (a) Super‐Ensemble of ML‐based VTEC models (SE), (b) Gradient Tree Boosting with quantile loss function (Quantile Gradient Boosting, QGB), (c) Bayesian neural network (BNN), and (d) BNN including data uncertainty (BNN + D). Techniques that consider only model parameter uncertainties (a and c) predict narrow CI and over‐optimistic results, whereas accounting for both model parameter and data uncertainties with the BNN + D approach leads to a wider CI and the most realistic uncertainties quantification of VTEC forecast. However, the BNN + D approach suffers from a high computational burden, while the QGB approach is the most computationally efficient solution with slightly less realistic uncertainties. The QGB CI are determined to a large extent from space weather indices, as revealed by the feature analysis. They exhibit variations related to daytime/nightime, solar irradiance, geomagnetic activity, and post‐sunset low‐latitude ionosphere enhancement.

show abstract

Global ionospheric total electron content short-term forecast based on Light Gradient Boosting Machine, Extreme Gradient Boosting, and Gradient Boost Regression

Emmela,

Rama Lahari,

Anusha

et al. 2024

Advances in Space Research

View full text Add to dashboard Cite

Machine Learning Ensemble Approach for Ionosphere and Space Weather Forecasting with Uncertainty Quantification

Cited by 4 publications

References 6 publications

Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting

Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting

Uncertainty Quantification for Machine Learning‐Based Ionosphere and Space Weather Forecasting: Ensemble, Bayesian Neural Network, and Quantile Gradient Boosting

Global ionospheric total electron content short-term forecast based on Light Gradient Boosting Machine, Extreme Gradient Boosting, and Gradient Boost Regression

Contact Info

Product

Resources

About