Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2510.23976 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913060916035584 |
|---|---|
| author | Berk, Richard |
| author_facet | Berk, Richard |
| contents | Using data from the Longyearbyen weather station, quantile gradient boosting ("small AI") is applied to forecast daily temperatures in Svalbard, Norway. Temperatures above 0 degrees Celsius are of special interest because of their impact on ice, snow, and tundra permafrost. To improve forecasting skill for warmer temperatures, the target quantile is 0.60; forecast underestimates are weighted 1.5 times more heavily than forecast overestimates when the quantile loss is computed. Predictors include eight routinely collected indicators of weather conditions, each lagged by 14 days, yielding temperature forecasts with a two-week lead time. Adaptive conformal prediction regions quantify forecasting uncertainty with provably valid coverage. Using a holdout sample, a forecast of 0 degrees Celsius is correct 14 days later at least 80% of the time. Implications for Arctic adaptation policy are discussed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Forecasting Arctic Temperatures With Quantile Machine Learning Berk, Richard Applications Using data from the Longyearbyen weather station, quantile gradient boosting ("small AI") is applied to forecast daily temperatures in Svalbard, Norway. Temperatures above 0 degrees Celsius are of special interest because of their impact on ice, snow, and tundra permafrost. To improve forecasting skill for warmer temperatures, the target quantile is 0.60; forecast underestimates are weighted 1.5 times more heavily than forecast overestimates when the quantile loss is computed. Predictors include eight routinely collected indicators of weather conditions, each lagged by 14 days, yielding temperature forecasts with a two-week lead time. Adaptive conformal prediction regions quantify forecasting uncertainty with provably valid coverage. Using a holdout sample, a forecast of 0 degrees Celsius is correct 14 days later at least 80% of the time. Implications for Arctic adaptation policy are discussed. |
| title | Forecasting Arctic Temperatures With Quantile Machine Learning |
| topic | Applications |
| url | https://arxiv.org/abs/2510.23976 |