VAMPIRE: Using a Random Forest to Forecast Earth's Outer Van Allen Radiation Belt
Bibliographic record
Abstract
Abstract The outer Van Allen radiation belt is highly dynamic in both strength and location, being driven by several distinct physical processes, making it difficult to predict for spacecraft operators. Forecasting models exist, in part, to minimise potential damage caused by this natural hazard. Both physics‐based and machine learning models exist; generally, physics‐based models allow for a deeper understanding of the system, while machine learning models offer a computationally cheap way to make a forecast, but do not always provide physical insight. We present VAMPIRE (Van Allen belt Multi‐day Predictions by Implementing a Random forest for Electrons), a pair of simple machine learning models, along with an analysis of model feature importance, to both forecast and understand the physical drivers of the outer radiation belt. We use a random forest methodology to predict whether the daily maximum ∼2 MeV electron flux and daily fluence across the entirety of the outer belt crosses the alert levels, similar to the approach used by the UK Met Office. Both models show high levels of accuracy at both nowcasting and forecasting up to a week in advance. We use feature importance to determine the most important elements of each model, and demonstrate that these models also give an insight into the major drivers of the radiation belts, and the timescales on which they have an impact.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".