Explainable AI Applied to the Analysis of the Climatic Behavior of 11 Years of Meteosat Water Vapor Images
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
Large stocks of meteorological satellite images contain important climatic information of the last decades. This paper explores the capabilities of three Explainable AI procedures (Occlusion, XRAI and SHAP) as tools to analyze and uncover patterns in the mid to upper troposphere Water Vapor dynamics, and their relationships with yearly seasons. The data consisted of 4140 daily Meteosat satellite images on the WV6.2 band between 2010 to 2020 and the base model was a convolutional neural network targeting season prediction. The results show that each explanation procedure highlights different aspects of the atmospheric processes and are appropriate for different purposes: Occlusion for studying the general traits of the 11 years time period covered by the images, XRAI for detecting and following dynamic patterns for short spans of time, and SHAP for detailed geographical expressions of atmospheric processes. All together Explainable AI exhibits an important potential for the study of atmospheric and climate change, which should be further investigated.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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