Photo by Simon Hurry on Unsplash
According to a recent survey by The Economist, more than 99 percent of executives report that their supply chain has been negatively impacted by extreme weather. The areas most impacted include downstream transportation, supplier production, and manufacturing. Transportation is particularly noteworthy, as weather is the cause of 23 percent of all road delays in the United States, costing transportation companies upwards of 3.5 billion dollars each year.
With these numbers in mind, businesses need to brace for more frequent and severe weather-related supply chain disruptions in the near future. In 2023, the Intergovernmental Panel on Climate Change (IPCC) warned that climate change was strengthening “extreme weather” events such as heat waves and hurricanes and that some consequences had become “irreversible.”
Ultimately, the question is not whether businesses must adapt to extreme weather but how they will do so, facing a future of destructive and escalating weather disruptions.
Businesses struggle to counter extreme weather’s variety and spontaneity. Extreme weather manifests in many forms, from flash floods to wildfires, with no one-size-fits-all solution. Furthermore, it is difficult to predict. The National Oceanic and Atmospheric Administration (NOAA) states, “[...] a 10-day—or longer—forecast is only right about half the time.”
A myriad of constantly changing and interacting meteorological variables make long-term weather forecasts costly and imprecise. Consequently, businesses must ‘fight’ extreme weather on multiple fronts and on short notice — a formidable task.
Artificial Intelligence (AI) empowers businesses to better counter the disruptive qualities of extreme weather. Industry innovators, such as tomorrow.io, along with established giants like Google, are employing AI to better predict and address extreme weather.
Researchers from the Chinese technology company Huawei were the first to introduce AI to weather forecasting in 2023, with the meteorology community immediately recognizing its promise. However, it wasn’t until Google introduced its Scalable Ensemble Envelope Diffusion Sampler (SEEDS) model in March 2024 that further performance gains were realized through the use of generative AI.
Generative AI models are trained on large datasets, typically with data that is freely available on the web, and are used to create new text, image, and video outputs by recognizing patterns in the training data. Similar to how ChatGPT is able to produce an essay in seconds, SEEDS is able to produce a robust weather forecast in minutes. Using historical weather data, SEEDS generates upwards of 100 possible weather outcomes per minute, giving meteorologists a complete picture of future weather events quickly and at a computing cost that has been described as “negligible” by industry experts.
Given these recent advances, AI can play an important role in helping businesses anticipate weather-related disruptions in their supply chains, potentially days, weeks, or even months in advance. However, businesses must begin integrating AI-enabled weather forecasting solutions into their supply chain now if they want to remain competitive in the future.
Government agencies such as the National Weather Service (NWS) and NOAA have been experimenting with AI models for weather forecasting since 2022, sending a clear signal to private enterprises that AI-enabled weather forecasting systems are the future.
Government interest in AI-enabled weather solutions validates the efficacy of these new tools and will likely lead to increased funding, research, and developments in the coming years — simultaneously driving down costs and increasing the capabilities of the underlying models.
Given this outlook, businesses should consider implementing AI-enabled weather prediction and mitigation systems now, in order to foster greater resilience, reduce operational risks, and maintain a competitive edge in a rapidly changing climate landscape.
With today's models taking minutes as opposed to hours to make forecasts, costing much less than supercomputers, and being up to 90 percent more accurate than existing methods, the transition to these systems is inevitable. The question is: when will your business begin to take advantage of AI?
In 2021, Synaptiq helped a client use AI to develop a satellite-based system for early wildfire detection. Our client developed and launched stratospheric balloons carrying long-range sensory equipment to gather live data on key wildfire indicators (such as temperature). We developed computer vision software that rapidly analyzes this data, conducts a risk assessment, and decides whether to alert local fire departments.
Synaptiq's work in leveraging AI for early detection and predictive analysis is a testament to how AI can make extreme weather more predictable and manageable, benefiting communities and ecosystems.
Synaptiq is an AI and data science consultancy based in Portland, Oregon. We collaborate with our clients to develop human-centered products and solutions. We uphold a strong commitment to ethics and innovation.
Contact us if you have a problem to solve, a process to refine, or a question to ask.
You can learn more about our story through our past projects, blog, or podcast.