category container 1 (for first block of text)

Cyclone Idai, one of the deadliest storms ever in the Southern Hemisphere, struck Mozambique in March of this year.

Farmers in Mozambique may have time to move their livestock out of harm’s way ahead of catastrophic floods, like those that devastated that nation earlier this year.

Energy companies will be better able to predict when winds will die down enough to deploy line repair crews in a storm’s aftermath.

Airlines will be able to reroute flights earlier when threatened by bad weather, reducing airport-snarling delays.

We realize that there’s a gap globally in that only a small portion of the world really has access to it.
- Kevin Petty, The Weather Company

Around the globe, billions of smartphone users will have access to more accurate forecasts – like when a dangerous thunderstorm will hit their neighborhood – with the tap of a finger.

These are but a few of the far-reaching effects a new global weather forecasting system may bring. Known as IBM GRAF, the Global High-Resolution Atmospheric Forecasting System can predict conditions up to 12 hours in advance at previously unattainable resolution and detail. The system was developed by The Weather Company, an IBM business. It is set to begin operating this month.

Built on a new, advanced weather model first developed by the National Center for Atmospheric Research and the Los Alamos National Laboratory, IBM GRAF will provide much finer-grained predictions of the atmosphere and update its forecasts six to 12 times more frequently than conventional global modeling systems. Just as important, IBM GRAF provides much greater local accuracy. Current global weather models cover 10-15 square kilometers (6.2-9.3 miles) and are updated every 6-12 hours. By contrast, IBM GRAF forecasts down to 3 kilometers (1.9 miles).

IBM GRAF can give farmers in Kenya, like David Ngugi, the same weather forecast accuracy as farmers in the United States, like Roric Paulman.

That’s particularly important for developing nations, which are among the most vulnerable to the increasingly extreme weather resulting from climate change.

Executives at The Weather Company refer to the effort as “democratizing weather data” for the world to share.

“We are focused on bringing high-resolution modeling to the masses,” said Kevin Petty, head of science and forecast operations at The Weather Company. “We realized that there’s a gap globally. Only a small portion of the world really has had access to it.”


image 1 for slider

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. 

image 2 for slider

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. 

image 3
mobile only image 1
mobile 2
mobile only 3
image for slider mobile only 4
image for mobile only 5

The Growing Need for Predictive Prowess

As the world’s weather becomes more devastating and economically disruptive, it is affecting lives, businesses and institutions in ways both mundane and profound – whether gusty winds that send a delivery drone off-track or a tornado that flattens a town.

Climate change has overturned centuries-old wisdom about weather patterns, said Laura Harwig, who directs a program that helps bring new technology to farmers in developing nations.

In the United States, 2019 marks the fifth consecutive year with at least 10 weather or climate disaster events each causing losses of at least $1 billion, according to the National Oceanic and Atmospheric Administration. Over the last five years, the annual total U.S. losses from weather calamities have averaged $100 billion.

In California in autumn 2019, violent winds howling out of the mountains helped spread wildfires across tens of thousands of acres, displacing residents and leading to vast intentional blackouts as electric utilities struggled to prevent and contain the damage.

block of text after long image, gets stacked embedded images

Laura Harwig directs the Feed the Future Partnering for Innovation program, which is sponsored by USAID and managed by Fintrac.

And globally, between 1980 and 2016, flooding caused more than 225,000 deaths and economic damage in excess of $1.6 trillion, according to the World Bank.

“As we experience greater climate extremes, we need good forecasting coupled with early warning systems to help people get to safety,” said Alice Hill, a senior fellow at the Council on Foreign Relations and co-author of the climate-change book Building a Resilient Tomorrow. “We have greater predictive capabilities, but we’re not getting the predictions out to those who need to get them.”

IBM GRAF aims to change that in a number of ways, including through The Weather Channel app, the most downloaded weather app in the world.

In some parts of the developing world, where the best access to forecasts might be a weekly newspaper report covering a large region or an entire country, climate change has overturned centuries-old wisdom about weather patterns, said Laura Harwig. She directs the U.S. Agency for International Development's Feed the Future Partnering for Innovation program at Fintrac, which helps bring new technologies to agribusinesses in Africa, Asia and Latin America.

In regions like Northern Kenya, she said, there are traditionally fertile areas where generation after generation of livestock farmers would move their herds at certain times of the year to find water and forage. Now, many of those grazing grounds are often bone dry.

“Farmers have to make real-time decisions about what to do in response to that changing climate,” Harwig said. “Giving farmers access to the information they need to make those decisions is increasingly important.”

Earlier this year, a pair of cyclones hit Mozambique and caused massive, destructive flooding. With more notice about the torrential rains and the possibility of severe flooding, she said, farmers might have been able to move their livestock to safer places.

David Ngugi, who with his wife, Jacinta, raises livestock and crops in Kikuyu, Kenya, near Nairobi, sees an urgent need for better forecasts. Rainfall dictates not only when to plant but also reproductive and growth cycles for the family’s cows. The weather forecasts on local TV or newspapers, he said, sometimes “say the truth,” but are too often inaccurate, leaving him with little more than prayer and watching the clouds to judge when the rain will come.

Kenyan Farmers Would Welcome Weather Certainty

As climate change disrupts traditional weather patterns, the lack of reliable forecasting has presented a challenge for agriculture in East Africa.

image 5 (slider 2)
image 6 (for slider 2)
image 7 (for slider 2)

In Limuru, a central Kenyan town about an hour northwest of Nairobi, Gladys Mwangi grows food crops like kale, spinach, herbs and carrots to sell at her shop in the nation’s capital, along with flowers for export.

Planning is important, she and Samuel Thiongo, manager at her Rainbow Orchards farm said. They must decide precisely when to plant, when to mulch or apply pesticides, when to water—all of which revolve around the weather. When will it be wet or dry? When will it be mild or hot?

They have never been able to rely on the local weather forecasts to tell them any of that. The forecasts have never been timely or accurate. Rainbow Orchards has sometimes lost an entire crop to a surprise rainfall.

“There are times when spinach gets so affected, they rot and we throw them away and we start anew,” Ms. Mwangi said, standing in a verdant field as workers tended plants behind her. “That is a huge loss.”

And that’s why Ms. Mwangi and Mr. Thiongo will welcome the local accuracy that IBM GRAF will bring to weather forecasting in Kenya.

Especially as climate change has disrupted traditional weather patterns, the lack of reliable forecasting has presented a challenge for small farms like Rainbow Orchards. Other farmers and agricultural experts who work in the area say that in recent years planning has become even more difficult, turning each planting season into a gamble.

As Simon Ndungu Nahason, who grows coffee, strawberries, avocados, bananas and other crops in a village about two hours north of Nairobi, put it, “Whenever you don’t plan, then you’re planning to fail.”

For generations, Kenyan farmers have relied on a traditional crop calendar, planting around rains and dry spells that used to come mainly in certain months, said Amos Tabalia, a climate risk analyst at Acre Africa, an insurance surveyor and agent with operations in several countries on the continent. That calendar is no longer predictable.

“The seasons are either coming in very late or the rain is more or less variable,” Mr. Tabalia said. “So that becomes a problem.”

Farmers can end up planting too early or too late. Too often, these days, their seedlings either wither or wash away or mature plantings—like grains that must dry in the field—rot before harvest.

With Kenya’s population growing along with the rest of sub-Saharan Africa’s, the need for more efficient farming techniques is becoming increasingly acute. Current food production methods are falling short, Mr. Tabalia said, a gap that could create a crisis by 2050.

Most farmers have access to mobile phones, televisions and radio, so they could benefit greatly from improved forecast information delivered through television and radio reports or a smartphone app, Mr. Thiongo of Rainbow Orchards said.

“If they get an accurate type of service,” he said, “I think one can increase food production, and food shortage will be a thing of the past.”

How Businesses Can Benefit

Improving forecasts, even by small amounts, can help weather-dependent industries like agriculture, retail, construction, transportation and energy in the developed world as well.

last content block

“Weather drives every decision that we make,” said Roric Paulman, a third-generation farmer in southwest Nebraska. There, rainfall varies widely during the growing seasons – less than an inch some years, more than 20 in others.

With 6,500 acres of crops at Paulman Farms irrigated largely with groundwater, the ability to anticipate rainfall on a given day can mean not using the 1.2 megawatts of power it takes to run the farm’s well pumps. That saves money and avoids greenhouse gas emissions from the fossil fuels that are part of the local energy mix.

“The more accurate the data we can get in advance of a weather event, the more proactive we can be and attempt to inconvenience our passengers the least,” said Steve Abelman, manager of weather technology for American Airlines.

Other industries also recognize IBM GRAF’s potential. “The more accurate the data we can get in advance of a weather event, the more proactive we can be to attempt to inconvenience our passengers the least,” said Steve Abelman, manager of weather technology for American Airlines. That could mean extra notice to move aircraft out of harm’s way, devise new flight paths a day in advance of bad weather or have a better estimate of when the threat of lightning will end, so ground crews and baggage handlers can return to the runways.

Pilots flying long routes to destinations where advance weather data has been limited, like South America, will have a clearer picture of the conditions they’ll encounter upon landing eight or nine hours after takeoff. “With every integration of more sophisticated models and more global data in general, models are getting better and better,” Ableman said. “We are looking forward to seeing the results that the GRAF model will bring.”

The Power of Shared Data

IBM GRAF’s speed, accuracy and resolution depend on massive computing power, a new weather model and the use of a wide variety of data from traditional and new sources.

A powerful new supercomputer called Dyeus, in Raleigh, North Carolina, assimilates 10 terabytes worth of observations about conditions in the atmosphere each day—factors like humidity, air pressure, temperature and wind speed and direction. Then it performs roughly 2 trillion computations per second on that data.

All of that computing power is brought to bear on a new, advanced prediction model that resulted from a highly collaborative effort. Developed by the National Center for Atmospheric Research (NCAR) in concert with the climate modeling group at Los Alamos National Laboratory, it was later refined in collaboration with IBM and The Weather Company.

“This is a great example of basic research leading to private sector applications,” said Antonio Busalacchi, president of the University Corporation for Atmospheric Research, which manages NCAR for the National Science Foundation.

IBM GRAF’s predictive capabilities,  and global forecasting science as a whole, will continue to advance with improved data collection around the globe.  As weather models use increasingly fine resolutions, Busalacchi said, it’s even more important to pull in data from nontraditional sources. IBM GRAF will eventually use data from airplane sensors and individual smartphones, if people choose to share them. “That’s where IBM has a role in terms of its ability to take advantage of those observations” and improve the models, Busalacchi said.

Petty, of The Weather Company, considers the potential to advance weather science and modeling to be one of IBM GRAF’s many strengths. “GRAF,’’ he said, “is going to bring new capabilities that we haven’t seen before.’’