Forecasting North America Winter Surface Air Temperature Using Machine Learning Methods
Bibliographic record
Abstract
Two machine learning (ML) models (Support Vector Regression and Extreme Gradient Boosting; SVR and XGBoost hereafter) have been developed to perform seasonal forecast for the winter (December–January–February, DJF) surface air temperature (SAT) in North America (NA) in this study. The seasonal forecast skills of the two ML models are evaluated in a cross-validated fashion. Forecast results from one Linear Regression (LR and hereafter) model and two Canadian dynamic climate models are used for the purpose of a comparison. In the take-one-out hindcast experiment, the two ML models and the LR model show reasonable seasonal forecast skills for the winter SAT in NA. Comparing to the two Canadian dynamic models, the two ML models and the LR model have better forecast skill for the winter SAT over the central NA which mainly get contribution of a skillful forecast of the second Empirical Orthogonal Function (EOF) mode of winter SAT over NA. In general, the SVR model and XGBoost model hindcasts show better forecast performances than LR model. However, the LR model shows less dependence on the size of the training dataset than SVR and XGBoost models. In the real forecast experiments during the period 2011-2017, compared to the two Canadian dynamic climate models, the two ML models clearly improve the forecast skill of winter SAT over northern and central NA. The results of this study suggest that ML models may provide real-time supplementary forecast tools to improve the forecast skill and may operationally facilitate the seasonal forecast of the winter climate of NA.
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 | 0.001 |
| 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 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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".