Using a Coevolutionary Postprocessor to Improve Skill for Both Forecasts of Surface Temperature and Nowcasts of Convection Occurrence
Bibliographic record
Abstract
Abstract An evolutionary programming postprocessor, using coevolution in a predator–prey ecosystem model, is developed and applied both to 72-h, 2-m temperature forecasts for the conterminous United States and southern Canada and to 60-min nowcasts of convection occurrence for the United States east of 94°W. The new approach improves deterministic and probabilistic forecasts of surface temperature relative to bias-corrected numerical weather prediction forecasts and to an earlier version of evolutionary programming forecasts for these same data. The new method also improves deterministic performance for an artificial neural network trained and evaluated for these same data. Additionally, the new approach substantially improves these forecasts’ reliability, as evidenced by reductions in the occurrence of excessive outliers in the rank histogram. The coevolutionary postprocessor also improves deterministic nowcasts of convection occurrence when compared to those produced by the National Weather Service’s AutoNowCaster system and to those obtained using multiple logistic regression. Notably, the degree of improvement relative to traditional methods appears to be problem dependent, while the training and implementation of such a system requires additional effort. However, the coevolutionary system is shown to be robust to imbalances between the frequency of positive and null events in the training data, unlike many postprocessing methods; to be implementable and effective in an adaptive mode, removing the need for retraining as inputs (such as numerical weather prediction model data) change; and to provide a useful, alternative perspective on the likelihood of event occurrence when used in combination with other methods.
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 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 | 0.000 |
| 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) | 0.002 | 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 teacher head, 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".