Salient Predictions has developed a new – and more accurate – scheme for forecasting the weather that is much more focused on the ocean (rather than the atmosphere). The logic is simple: the ocean contains over 1,000 times the heat capacity of the atmosphere, and 100,000 times as much water. If you want to make long-range forecasts, it makes more sense to look to the ocean as the memory of the climate system than to the chaotic atmosphere. Yet nearly all existing forecasts are based on forward integration of the physical laws governing the atmosphere, a process that decays into chaos after about 10 days out, due to the sensitivity to initial conditions.
At Salient, we take a different approach to develop more accurate forecasts based on the patterns of ocean temperature and salinity, and by using new machine learning tools. We believe that the oceanic “dog” waves the atmospheric “tail” – not the other way around – and that belief continues to pay off.
An example of our success can be seen in our long-range winter outlook that we put out last fall. We correctly forecast a mild December and January, and a cold February. And recently, in January our forecast for February picked up the extreme cold in the Midwest and East, whereas the conventional forecasts based on the atmospheric tail were calling for quite the opposite pattern.
Figure 1: February forecasts put out in January by Salient (left), NOAA (center), and The Weather Company (right).
Our core forecast engine’s superior accuracy enables us to also build industry-specific forecast products (e.g. our solutions for energy and agriculture customers, among others) that vastly outperform market alternatives.
Can your company use more accurate weather forecasts? Yes. Yes, they can. Contact Salient Predictions at email@example.com