Water managers in the western United States (U.S.) rely on longterm forecasts of temperature and precipitation to prepare for droughts and other wet weather extremes. To improve the accuracy of these longterm forecasts, the U.S. Bureau of Reclamation and the National Oceanic and Atmospheric Administration (NOAA) launched the Subseasonal Climate Forecast Rodeo, a year-long real-time forecasting challenge in which participants aimed to skillfully predict temperature and precipitation in the western U.S. two to four weeks and four to six weeks in advance. Here we present and evaluate our machine learning approach to the Rodeo and release our SubseasonalRodeo dataset, collected to train and evaluate our forecasting system.

During disaster response, key resources are supplied from a variety of channels including: government agencies, volunteer organizations, commercial businesses, educational institutions and others. While these entities have efficient internal methods of communication and coordination, interorganizational collaboration has often been hindered by political, social, and technological challenges. This paper examines the challenges to collaboration among responding entities and proposes a technology-enabled self-synchronization framework for sharing information using a distributed, highly scalable, web application based on the cloud computing technologies. The proposed design applies the unique benefits of cloud computing to the disaster response domain. This notional design facilitates communication among a broad range of public and private groups without requiring these organizations to compromise competitive advantage.