Frontiers in Astronomy and Space Sciences

7 papers15 directions
Frontiers in Astronomy and Space Sciences serves as a venue for research at the intersection of space science and computational methodology. Between 2021 and 2024, the journal has published work focusing on the application of machine learning and statistical methods to complex astrophysical phenomena. Research often centers on solar flare prediction, space weather modeling, and the classification of celestial bodies, such as asteroids, using feature-based analysis. The venue is characterized by its focus on time series forecasting and anomaly detection within non-stationary environments. Published papers explore global conditioning for local forecasting, symbolic discovery of governing physical equations, and the use of mixture models to address heterogeneity in solar flare mechanisms. Additionally, the journal features research on outlier ranking algorithms and interpretable anomaly detection, which are used to facilitate discovery in large scientific datasets and localize root causes in complex systems. Contributions to the machine learning community include unified benchmarking for neural architectures and the development of modular, decoupled systems. The venue also addresses practical challenges such as training data contamination and the resolution of micro-scale features in remote sensing. Prolific contributors include Enrico Camporeale, W. B. Manchester, and Shane A. Maloney, whose work emphasizes the integration of polar field data and interplanetary observations into predictive models for geomagnetic and solar events.

Papers by Year

2024 1
2023 2
2022 2
2021 2

Top Research Directions

Research directions most represented by papers from this venue.

Linear Aggregation Bottlenecks for Inherent Model Interpretability 1
Eliminating Pattern Redundancy via Iterative Model Updates 1
Integrating Non-Visible Spectral Bands for Robust Visual Representations 1
Spectral Signal Conditioning for Robust Quantitative Analysis 1
Bridging the Temporal Generalization Gap in Predictive Models 1
Automated Model Selection for Anomaly Detection 1
Unified Evaluation Frameworks for Reproducible Machine Learning 1
Contamination Resistant Unsupervised Anomaly Detection 1
Spatial Resolution Constraints in Environmental Remote Sensing 1
Nonparametric Bayesian Methods for Adaptive Clustering 1
Resolving Spectral Signature Confusion in Sensor Data 1
Chronological Data Partitioning for Realistic Model Evaluation 1
Greedy Incremental Feature Selection 1
Interpretable Anomaly Detection 1
Spectral Band Selection for Hyperspectral Dimensionality Reduction 1

Top Authors

AuthorPapers
Alfred O. Hero1
Hannah Kerner1
Yang Chen1
Zeyu Sun1

Papers

TitleYear
Uncovering the heterogeneity of a solar flare mechanism with mixture models2024
Editorial: Machine learning and statistical methods for solar flare prediction2023
Interplanetary scintillation observation and space weather modelling2023
Domain-Agnostic Outlier Ranking Algorithms—A Configurable Pipeline for Facilitating Outlier Detection in Scientific Datasets2022
Incorporating polar field data for improved solar flare prediction2022
Impact of Storm-Enhanced Density (SED) on Ion Upflow Fluxes During Geomagnetic Storm2021
Predicting Asteroid Types: Importance of Individual and Combined Features2021