Professor Amir Behzadan joined an “invitation-only” group of experts from academia, government and the private sector to discuss the potential for artificial intelligence (AI) to transform weather prediction at the AI for Numerical Weather Prediction (AI4NWP) workshop in Washington, D.C. The event, held on May 6, was jointly hosted by the White House Office of Science and Technology Policy and the National Oceanic and Atmospheric Administration (NOAA). 

“We are witnessing an upward trend in the number and frequency of major climate events across the country and around the world,” said Behzadan, of CU Boulder’s Department of Civil, Environmental and Architectural Engineering and a faculty research fellow of the at the . “Storms are becoming more severe and moving far more inland. Tornadoes, intense rainfalls and flash floods are happening in places that were once deemed safe.” 

Behzaden said that early AI models demonstrate improved skill in forecasting events like hurricanes, winter storms and heat waves. These models are potentially valuable tools for alerting residents earlier, ultimately saving lives and property, he said.

During the event, Behzadan served on a scientific panel on building and maintaining trust in AI systems, where he shared his views on how human trust in AI-generated weather predictions can be formed, calibrated, measured and used to inform decision-making. 

Event participants, including Biden-Harris administration leaders, covered a wide range of topics pertaining to the benefits and challenges of AI for weather prediction, building and maintaining trust in AI systems and exploring scientific unknowns that pose the biggest challenges. 

Through the workshop, NOAA strengthened its commitment to working with partners from academia and the private sector to build the necessary infrastructure for trustworthy weather AI models that support decision-making. 

CU Boulder sat down with Professor Behzadan to ask a few questions about the use of AI in weather prediction. 

How can AI be used to improve weather prediction?

AI can enhance weather prediction in several ways. For example, AI algorithms can analyze large volumes of data from various sources, including weather satellites, ground stations, in-situ sensors and crowdsourced information. Machine learning (ML) techniques can be then applied to identify patterns and correlations in this data, leading to more accurate forecasts. 

Neural networks, a type of ML model inspired by the structure and function of the human brain, can analyze complex atmospheric dynamics and predict weather phenomena that are indicative of storms, hurricanes or droughts. 

AI can also improve our understanding of cloud formations or atmospheric pressure gradients, allowing meteorologists to generate more reliable forecasts, particularly in regions with limited data. AI models can analyze and learn from the available data, discern patterns and relationships within the data and adapt and improve over time as they receive more data. These capabilities allow the model to adapt to evolving weather patterns, increase the accuracy of long-term predictions and enhance our ability to mitigate risks due to climate disasters.

How can scientists increase public trust in AI for weather prediction?

To build and strengthen trust in AI for weather prediction, transparency and communication are key. For example, providing clear explanations of how AI algorithms work and their limitations can help build understanding and confidence among end users. 

Also, for an AI model to be fully adopted, it must demonstrate the underlying uncertainty and accuracy by comparing its forecasts with traditional methods. Collaborating with meteorologists and incorporating their expertise can reassure users that human oversight is integral to system design and deployment. Continuous validation against observed weather data and transparent communication of AI predictions’ successes and failures will further build trust in its capabilities. 

 Professor Amir Behzadan

Should we trust AI for weather forecasting?

As for whether humans should trust AI for weather prediction, this is a question of choice and weighing the evidence; after all, "trust" is a subjective willingness of individuals or communities to rely on each other or on a technology. 

While emerging AI systems have the potential to significantly improve forecast accuracy and lead to better preparedness for extreme weather events, it’s essential to recognize their limitations and the possibility of errors. 

To sustain user trust, potential users should have ample opportunities to safely interact with AI systems, with human oversight and interpretation remaining central to AI integration, especially in complex or unprecedented situations, such as rapidly intensifying storms, flash floods and wind storms. This is mainly because in those situations, the variability and uncertainty of data increases, potentially leading to unstable AI outcomes that need to be more closely scrutinized by a human expert. Ultimately, as with any high-stake application, a balanced approach that leverages both AI technology and human expertise is likely the most effective strategy for reliable weather prediction.

Off

Off

Caption: Participants of the Harnessing Artificial Intelligence (AI) for Disaster Management: Bridging Research, Practice, and Community Engagement workshop held on the CU Boulder campus.

In disaster and emergency management, rescue teams rely on simple tools, like drones and mobile devices connected to the internet, to take photos of damaged buildings and document the resulting destruction. First responders use this information to prioritize where help is needed immediately and in the long-term.

At the same time, many emergency response agencies have been slow to embrace advanced tools like artificial intelligence (AI) due to concerns of complexity, training needs, initial costs and the potential impact on their work, said Professor Amir H. Behzadan, of CU Boulder’s Department of Civil, Environmental and Architectural Engineering and a faculty research fellow of the at the . 

“This hesitation, along with a historical lack of diversity in the workforce, has contributed to delayed and unfair treatment of communities hit hardest by disasters,” Behzadan said. “Lower-income disaster survivor homeowners are not only less likely to receive assistance compared to wealthier counterparts, but also tend to receive substantially less aid.”

On April 19, Behzadan hosted a workshop titled “AI4DM - Harnessing Artificial Intelligence (AI) for Disaster Management: Bridging Research, Practice, and Community Engagement," with participants from academia, disaster management practitioners and disaster nonprofits. Attendees included representatives from CU Boulder, Texas A&M University, University of Florida, University of North Texas, University of Texas at Arlington, and University of Albany along with the Colorado Office of Emergency Management.

The workshop was supported by Behzadan’s NSF grant from the Future of Work: Human-Technology Frontier program, which aims to raise awareness of AI and related technologies in disaster management. Participants were introduced to human-centered AI applications in disaster management and encouraged to work toward ways to adopt AI-informed solutions.

“AI can be applied in disaster management for various purposes, such as generating instant disaster data visualizations; providing interview training and reskilling/upskilling for employees; assessing and mapping disaster damage; and enhancing disaster risk messaging and communication strategies,” Behzaden said.

Human-centered AI focuses on designing AI systems that prioritize human needs, values, expectations and experiences, aiming for beneficial, equitable, safe and ethical outcomes. In disaster and emergency management, this includes increased representation of data from marginalized groups, using inclusive communication strategies that resonate with at-risk communities, considering linguistic and cultural sensitivities and removing personal biases when assessing community needs during disasters.

“Human-centered AI leads to more effective disaster response and recovery practices by promoting collaboration, understanding and inclusivity among team members, survivors and stakeholders,” Behzadan said. ”It helps create equitable solutions that address the needs of all affected communities, regardless of their socioeconomic and cultural backgrounds.”

Behzaden and his team plan to pursue additional funding to sustain these efforts. While leveraging their existing partnerships in Texas and Florida, they are also forging new relationships with local communities as well as disaster and emergency management organizations in Colorado who will ultimately be the beneficiaries of these technologies.

“The success of any technology hinges on its adoption by the intended end users,” Behzadan said. “Understanding user needs and preferences, especially when working with vulnerable groups, is crucial for meaningful adoption and realizing the full potential of technological advancements.”

Off

The Department of Civil, Environmental and Architectural Engineering welcomed four new faculty members for 2023-2024. Meet the team and see why we're so excited about these talented individuals:

Off

Off

Off

Off

Off

Off