This summer, three college students set out to answer the same question: How can AI help build better weather applications?
During their internships at Wet Dog Weather, Alicia Skiver-Palmer, Lex Hudson, and Antonio McElfresh each developed unique AI weather applications using AI and real weather data. While every project focused on a different audience, all three demonstrated how artificial intelligence can accelerate software development while still relying on human creativity, scientific knowledge, and thoughtful design.
Throughout the summer, each intern documented their progress in our weekly AI Journal, sharing the prompts, challenges, breakthroughs, and lessons they encountered as they built their applications.
Last week, that journey culminated in our Summer AI Intern Showcase, where the interns presented their completed projects and demonstrated their work. Watch their presentations below, then explore their AI Journal entries to see how each application evolved from the first idea to the final demonstration.
Storm Pointer: An AI Storm Chasing Dashboard
Alicia Skiver-Palmer, a graduate student at Mississippi State University, developed Storm Pointer, an AI storm chasing dashboard designed to bring together the forecasting and decision-support tools storm chasers and meteorologists rely on during severe weather.
Rather than switching between multiple websites, Storm Pointer combines radar, SPC outlooks, mesoanalysis, atmospheric soundings, model data, route planning, and other forecasting resources into a single interface. One of Alicia’s favorite features was developing the atmospheric sounding system, allowing users to generate Skew-T diagrams, hodographs, and severe weather parameters directly from HRRR model data.
As development progressed, Alicia realized that building weather software is about much more than displaying data. She focused on creating an intuitive workflow that helps users spend less time searching for information and more time analyzing the atmosphere. Along the way, she learned that successful weather applications require scientific accuracy as much as technical skill, and she validated her results against trusted meteorological sources rather than assuming that working software was necessarily correct.
FishCast: An AI Fishing Weather App
Lex Hudson, a meteorology student at Central Michigan University, built FishCast. This AI fishing weather app helps anglers better understand how changing weather conditions influence fishing success.
Inspired by conversations with her father before fishing trips, Lex wanted to create more than an app that recommends the best lakes in Michigan to fish. FishCast combines Wet Dog Weather data with additional datasets to calculate a Fishing Index based on variables such as atmospheric pressure and water temperature, and to explain why those conditions influence fish behavior.
One of Lex’s biggest takeaways was that building software isn’t just about creating an attractive interface. Integrating live weather data, prioritizing features, and writing clear AI prompts became some of her greatest lessons. Her goal was to make complex meteorology easier for anglers to understand without sacrificing the science behind the forecast.
RuffRide: An AI Aviation Weather App
Antonio McElfresh, a meteorology student at the University of Oklahoma, created RuffRide, an AI aviation weather app designed to help pilots better understand turbulence and flying conditions.
RuffRide brings together aviation weather information for pilots with a focus on turbulence, while a companion application aims to answer a simple question for airline passengers: How turbulent will my flight be? Antonio chose the project because of his passion for aviation meteorology and his interest in exploring how AI can accelerate software development.
For Antonio, the project reinforced that successful AI-assisted development depends on providing the right context, managing AI efficiently, and validating results. He also came away with a deeper appreciation for the amount of weather data available and the importance of communicating that information in ways pilots and passengers can quickly understand.
What the Interns Learned About Building AI Weather Applications
Although each intern built a different project, they reached many of the same conclusions about developing AI weather applications.
AI dramatically accelerated development, enabling ideas to become working prototypes much faster than traditional software development alone could. At the same time, they discovered that successful AI-assisted development still requires careful planning, detailed prompts, validation, and subject-matter expertise.
Throughout the summer, the interns also learned that building weather applications is about much more than displaying data. Creating useful tools requires understanding the people who will use them, organizing information effectively, and communicating complex weather concepts in ways that support better decisions.
The Future of AI Weather Applications
The Summer AI Intern Showcase highlighted more than three impressive software projects. It demonstrated how the next generation of meteorologists is using AI to create innovative AI weather applications for aviation, fishing, storm chasing, and beyond.
We’re incredibly proud of everything Alicia, Lex, and Antonio accomplished during the internship and look forward to seeing where their careers take them next.
Want to learn more? Watch each intern’s final presentation above, read their individual spotlight articles, and explore their weekly AI Journal entries to see how each project evolved throughout the summer. The journals provide a behind-the-scenes look at the challenges, breakthroughs, and lessons learned while building these AI weather applications.
As AI continues to evolve, it’s exciting to imagine what the next generation of AI weather applications will look like and the role these young meteorologists will play in building them.