Predicting Direction of Supernova Events Through the Use of Convolutional Neural Networks
Bibliographic record
Abstract
Manual supernova direction prediction is time-consuming and often does not allow enough time for telescopes to catch the supernova event. Using machine learning, it is possible to develop an algorithm that can quickly determine the supernova direction. In this paper, a machine learning approach to predicting the direction of supernova events are applied with promising results. Neutrinos are subatomic particles that are at least six orders of magnitudes smaller than the mass of an electron. Following Colgate and White's theory of supernova neutrino production, neutrinos emitted by supernovas can be detected before the first electromagnetic emissions can be detected. However, neutrino interactions with matter are minimal and feeble. They have no electric charge. This makes them difficult to detect. As part of this research project, we are using simulated data representing detected neutrino events from the Super-K observatory. We used 80% of the data as a training set and 20% was a testing set. Both feature and label values were normalized into the range between 0 and 1. We used a Convolutional Neural Network to process inputs from a 1D array representing the image containing event data. The overall results of the model (67% of the time, model prediction is within 5 degrees of the actual event, and 99% of the time, model prediction is within 10 degrees of the actual event) were similar to the currently used prediction methods. However, once the models are trained, the detection can be much faster, as the results can be obtained within seconds.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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".