IBM Watson cognitive system can work physician , chef , information security specialist and scientist Now Watson has also become a forecaster. More precisely, previously the system was already able to make forecasts, but now, if I may say so, Watson has gone up.
Our company has concluded a cooperation agreement with Weather Underground, which compiles its weather forecasts based on data from 200, 000 weather stations. These stations are distributed all over the world, including Asia, South America, and Africa. Now it is planned to analyze this data with IBM Watson to make even more accurate forecasts.
When IBM acquired The Weather Company/WU (this happened last October), it immediately announced its intention to integrate all 200, 000 weather stations obtained with The Weather into the Internet of Things. This meant that the data from the stations’ sensors would be analyzed immediately. And the goal of the project is not to forecast the weather on TV. The main goal is to help businesses.
Only in the U.S. the losses of various companies due to adverse weather conditions amount to $500 billion annually. But you don’t have to lose money if you know where and how the weather will change. The best option is a long-term forecast. Airlines, insurance companies, and farmers all lose a lot of money to the vagaries of the weather. But if you know where to expect trouble, you can avoid problems and major losses.
"All of The Weather Company’s data can be accessed through the API, " says John Cohn, one of the contributors to the project. Watson has access to the API. This cognitive system analyzes all weather station data, makes a forecast, and provides information to partners.
The first project is called EZ Buddy and is being implemented in Kenya. EZ Buddy provides data on the dynamics of local weather conditions to local farmland owners. Farmers are aware of the weather changes, they know what to do in any given case, and act accordingly. Any farmer in the region, by sending an SMS to a specific phone number, can ask: "When should I water my field?" or "When will it rain and replenish my fresh water supply?"
The system answers questions in a reply message. Farmers in Kenya are now actively using this feature, and not just to know when to water the field. They consult with IBMWatson about the timing of fertilizer application, the planting season, and the optimal time to use pesticides.
Airlines are also collaborating with TheWeatherCompany (recall, now a division of IBM). Dispatchers and pilots need to know about turbulence zones in order to plan the best route, which not only does not endanger the lives and health of passengers, but also saves fuel. Every year, airlines lose about $5 million a year due to having to repair planes that get caught in an area with adverse weather conditions.
Even more, about $35mn, is spent on medical treatment for pilots and compensation for passengers injured during flights. Now our company collects data on turbulence zones and provides it to airlines. Pilots can bypass the danger zones, and the airlines’ computer systems adjust their flight arrival and departure times accordingly.
Insurance companies, receiving information from IBM, will be able to warn their customers of an approaching hurricane or flood. People will then try to do everything possible to minimize damage to their property. The benefits are there for both companies and customers. Power companies usually lose millions of dollars after weather disasters – because the power system is damaged, and the average repair cost for just one damage is about $500, 000.
The examples given do not only apply to airlines, farmers, and insurers. All of this applies to other representatives of a number of business sectors, as well as to government agencies that are responsible for the state of various infrastructures of human settlements. IBM Watson, using data from weather stations, can give a detailed weather forecast for about two weeks ahead. And it’s a very accurate forecast.
Fifty years ago, a weather forecast was more like reading coffee grounds. Nowadays, a weather forecast is the result of a sophisticated analysis of vast amounts of data. And the accuracy of such a forecast in most cases is very high.