Using a convolutional neural network with all sky infrared images to classify sky regions as clear or cloudy
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Atmospheric visibility is a major factor in the quality of data produced by ground-based instruments in astronomy. Two instruments Canada France Hawaii Telescope uses to address this issue are ASIVA and SkyProbe. ASIVA produces all-sky infrared and visible light images to identify clouds, and SkyProbe produces an attenuation measurement for the atmosphere in between the telescope and its observation target. A Convolutional Neural Network is used to detect clouds on Mauna Kea using ASIVA archival data. A full-sky model was able to determine clear skies with 100% accuracy and cloudy skies with 96% accuracy. A separate heatmap generator model used a small kernel passed over an input image to determine the likelihood of cloud coverage at each location, producing an AUC of 0.987. Further work is being done to incorporate SkyProbe data by correlating measurements to locations in ASIVA images. Preliminary results show a strong ability to differentiate clear from cloudy kernels. However, dataset limitations inhibit a strong correlation between predicted and actual attenuation values. Additional work is needed to tune the model architecture and find more data in ASIVA archives.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it