“Climate Forecast Applications Network (CFAN) develops innovative weather and climate forecast tools to help clients manage weather and climate risks. CFAN’s scientific team members are world leaders in research on extended-range prediction of weather and extreme weather events. A true synergy between research, forecasts, and decision support have produced a culture of innovation and client support that is unique among weather and climate forecast providers,” says Judith Curry, President, and Co-founder. To deliver more precise probabilistic weather forecasts with longer lead periods, CFAN applies the latest in ensemble forecast methodologies, machine learning, and artificial intelligence.
Academia to Private Sector: Challenges & Growth
Judith had a prominent academic career, most recently as Chair of the School of Earth and Atmospheric Sciences at the Georgia Institute of Technology. While at Georgia Tech, she and her colleague Peter Webster were encouraged to launch a company of Georgia Tech’s Venture Lab program, which became CFAN. However, Judith feels, “There is a striking difference between succeeding in academia versus the private sector. In academia, there are no consequences for being wrong once a paper is published, preferably with attendant publicity. In the private sector, if you make a highly confident forecast that turns out to be wrong, your company’s reputation will suffer, and you will lose clients.”
She has come to realize the difficulty of different decisions that depend, at least in part, on weather and climate information. She’s come to realize how crucial it is to carefully identify and communicate the uncertainty around scientific knowledge, especially when making forecasts. The worst consequence for decision-makers, in her experience, is a scientific conclusion or prognosis that was made with a high degree of confidence and turns out to be inaccurate. Judith shares, “The toughest challenge for CFAN has been making a transition from a university-based research focus to a customer-oriented focus. We have succeeded by not just providing superior forecasts, but by providing services to our clients and working with them to customize and integrate our forecasts into their risk assessment models.”
"The need for better solutions to an ever-broadening range of weather and climate impacts will continue to drive the economic prospects in this sector."
Building Blocks: Innovations & Opportunities
Centrally located in Reno, Nevada CFAN was established in 2006 by Judith Curry and Peter Webster. Since the company’s founding, she has served as its president. CFAN was founded to translate cutting-edge weather and climate research into forecast products that support the mitigation of weather and climate risk, on timescales from days to decades. The company leverages ensemble forecast methods, machine learning, and artificial intelligence to provide more accurate probabilistic forecasts at longer lead times. Moreover, CFAN provides the most critical information about forecast accuracy and uncertainty that helps its clients improve outcomes as they manage weather and climate risks. CFAN continuously works with clients to develop new products and address their most challenging problems and lucrative opportunities.
Client demands for better weather and climate predictions and newly emerging concepts from research and technological advancements are what drive CFAN’s product improvements. The initial motivation for the creation of CFAN was to more effectively coordinate their USAID and CARE-funded humanitarian work on flood forecasting in Bangladesh. As Judith shares, “An important opportunity for CFAN occurred following the destruction caused by Hurricane Katrina (2005) in the oil-producing and refining region of the Gulf of Mexico. A major company in the petroleum industry challenged CFAN to develop extended-range, better-than-market hurricane forecasts. They sought improved hurricane forecasts to anticipate disruptions to energy supply, drilling, refining, and transport activities, in support of energy trading and sales. CFAN responded to this challenge by translating its tropical cyclone research into an innovative forecast product for North Atlantic Hurricanes, which became operational in 2007. CFAN’s forecast models quickly proved their worth when forecasting Hurricane Dean’s 2007 landfall in Mexico, allowing the client to profit from the natural gas trading market that anticipated a Texas landfall. In 2008, CFAN’s early forecast of Hurricane Ike’s landfall in Houston also enabled the company to plan for emergency management and business continuity.”
CFAN built upon the success of its hurricane forecasts to develop OmniCast, a platform for energy traders that expanded the product suite to include daily, weekly, and seasonal forecasts for the major energy markets across the U.S. and Europe. Along with surface temperature, wind, and solar forecasts, CFAN developed probabilistic forecasts of streamflow and hydropower for the Columbia River basin. OmniCast uses machine learning to calibrate the ensemble forecasts from global weather models and advanced ensemble interpretation techniques, which are key elements in CFAN’s superior forecast accuracy. CFAN has recently developed innovative weather forecast products for the insurance sector, including extended-range forecasts of hurricane landfall impacts, fire weather, and severe convective weather. These forecast products are at the forefront of incorporating artificial intelligence techniques into forecast modules driven by ensemble weather forecast models.
Traits & Habits: Experiences of a Leader
Judith feels that there is a fundamental difference between being a leader versus a manager. Differentiators for a leader include courage and learning agility. There are also important differentiators between leaders who move a field or industry forward, versus fast followers. A leader looks beyond the obvious and what everyone else is doing, with vision, inspiration, creativity, and strategic thinking. As Judith shares, “I read extensively, and find social media (mainly Twitter @curryja) to be invaluable in pointing me towards new research and trends, as well as networking with a broad range of researchers and decision-makers. I have developed communication skills through engaging with the public via my blog Climate Etc. (judithcurry.com), which provides a forum for climate researchers, academics and technical experts from other fields, citizen scientists, and the interested public to engage in a discussion on topics related to climate science and the science-policy interface.”
For Judith, an important part of her legacy is her book “Climate Uncertainty and Risk.” Her book helps us rethink the climate change problem, the risks we are facing, and our response. It helps us strategize on how we can best engage with our environment and support human well-being while responding to climate change. The book provides a comprehensive framework for understanding the climate change debate. It shows how both the climate change problem and its solution have been oversimplified. It explains how understanding uncertainty helps us to better assess the risks. It describes how uncertainty and disagreement can be part of the decision-making process. It provides a road map for formulating pragmatic solutions that can improve our well-being in the 21st century.
Values & Culture: The CFAN Way Forward
The workplace culture at CFAN consists of two key components. The first is an employee-centric strategy that develops each employee’s capabilities within the framework of project teams, career advancement, and a flexible workplace that encourages work-life balance. The second important aspect is a culture of client service and engagement that supports client needs that go beyond their “off the shelf” products. Apart from providing a high level of service to their clients, this engagement directly connects CFAN employees with client needs in a collaborative relationship that spawns ideas for new products.
Judith feels, “The weather and climate services sector is booming, owing to the growing realization of the socioeconomic impacts of extreme weather and climate change. The need for better solutions to an ever-broadening range of weather and climate impacts will continue to drive the economic prospects in this sector.” CFAN has recently launched a new weather forecast platform to support precision agriculture in India and Pakistan. The company is working with a team of crop scientists as well as local farmers to optimize its forecasts to support decision-making on cropping, planting, irrigation, and harvesting. CFAN’s forecasts, along with critical crop-specific information, are communicated to the farmers by cell phone. CFAN is also working with several companies in the risk management sector to develop innovative risk management strategies, tools, and information systems.
Looking forward, Judith sees several trends. There is a growing need for weather forecasts on sub-seasonal time scales (weeks), particularly in the energy, agricultural and retail sectors. There is a growing need for more realistic scenarios for regional climate change that can be provided by climate models Incorporation of Machine Learning and AI into operational weather forecast products and climate scenarios provides tremendous opportunities for weather and climate services.
Judith signs off with these inspiring lines, “Be a leader, not a fast follower. Carve out your niche using new technologies and insights for new applications.”
