Long-lead Forecast of Heatwaves in the Eastern United States using Artificial Intelligence
Abstract
Heat events have various negative impacts on public health, agriculture, and economy, that can be minimized with advance warnings and preparations for such events. Despite the gradual progress over the past several decades, seasonal to sub-seasonal forecast models exhibit minimal skills in forecasting heat events over the United States. In this study, various machine learning techniques are used for long-lead prediction of heat events in the Eastern United States using sea surface temperatures anomalies in the Pacific Ocean. Using historical measurements for the eastern United States and sea surface temperature from reanalysis, the machine learning models were trained to predict heat events in the eastern United States 20, 30, 40, and 50 days in advance. Results of cross-validation show that the machine learning models have significant statistical skill in forecasting extreme heat for binary forecasts. Relative Operating Characteristic (ROC) score was used for accessing the models' skills due to its applicability to both binary and unique events. Furthermore, the machine learning models were evaluated using hot days in 2016, 2017, and 2018.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2018
- Bibcode:
- 2018AGUFM.T31E0362S
- Keywords:
-
- 3399 General or miscellaneous;
- ATMOSPHERIC PROCESSESDE: 1699 General or miscellaneous;
- GLOBAL CHANGEDE: 3099 General or miscellaneous;
- MARINE GEOLOGY AND GEOPHYSICSDE: 8099 General or miscellaneous;
- STRUCTURAL GEOLOGY