Leveraging Deterministic Weather Forecasts for In Situ Probabilistic Temperature Predictions via Deep Learning
Bibliographic record
Abstract
Abstract We propose a neural network approach to produce probabilistic weather forecasts from a deterministic numerical weather prediction. Our approach is applied to operational surface temperature outputs from the Global Deterministic Prediction System up to 10-day lead times, targeting METAR observations in Canada and the United States. We show how postprocessing performance is improved by training a single model for multiple lead times. Multiple strategies to condition the network for the lead time are studied, including a supplementary predictor and an embedding. The proposed model is evaluated for accuracy, spread, distribution calibration, and its behavior under extremes. The neural network approach decreases the continuous ranked probability score (CRPS) by 15% and has improved distribution calibration compared to a naive probabilistic model based on past forecast errors. Our approach increases the value of a deterministic forecast by adding information about the uncertainty, without incurring the cost of simulating multiple trajectories. It applies to any gridded forecast including the recent machine learning–based weather prediction models. It requires no information regarding forecast spread and can be trained to generate probabilistic predictions from any deterministic forecast. Significance Statement Weather is difficult to predict a long time in advance because we cannot measure the state of the atmosphere precisely enough. Consequently, it is common practice to run forecasts several times and look at the differences to evaluate how uncertain the prediction is. This process of running ensemble forecasts is expensive and consequently not always feasible. We propose a middle ground where we add uncertainty information to forecasts that were run only once, using artificial intelligence. Our method increases the value of these forecasts by adding information about the uncertainty without incurring the cost of multiple full simulations.
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 | 0.001 | 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) | 0.001 | 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 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".