English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sub-seasonal climate forecasting (SSF) is the prediction of key climatevariables such as temperature and precipitation on the 2-week to 2-month timehorizon. Skillful SSF would have substantial societal value in areas such asagricultural productivity, hydrology and water resource management, andemergency planning for extreme events such as droughts and wildfires. Despiteits societal importance, SSF has stayed a challenging problem compared to bothshort-term weather forecasting and long-term seasonal forecasting. Recentstudies have shown the potential of machine learning (ML) models to advanceSSF. In this paper, for the first time, we perform a fine-grained comparison ofa suite of modern ML models with start-of-the-art physics-based dynamicalmodels from the Subseasonal Experiment (SubX) project for SSF in the westerncontiguous United States. Additionally, we explore mechanisms to enhance the MLmodels by using forecasts from dynamical models. Empirical results illustratethat, on average, ML models outperform dynamical models while the ML modelstend to be conservatives in their forecasts compared to the SubX models.Further, we illustrate that ML models make forecasting errors under extremeweather conditions, e.g., cold waves due to the polar vortex, highlighting theneed for separate models for extreme events. Finally, we show that suitablyincorporating dynamical model forecasts as inputs to ML models cansubstantially improve the forecasting performance of the ML models. The SSFdataset constructed for the work, dynamical model predictions, and code for theML models are released along with the paper for the benefit of the broadermachine learning community.

Learning and Dynamical Models for Sub-seasonal Climate Forecasting: Comparison and Collaboration