Severe convective weather events, such as hail, tornadoes, and thunderstorms, often occur quickly yet cause significant damage, costing billions of dollars every year. This highlights the importance of forecasting severe weather threats hours in advance to better prepare meteorologists and residents in at-risk areas. Can modern large foundation models perform such forecasting? Existing weather benchmarks typically focus only on predicting time-series changes in certain weather parameters (e.g., temperature, moisture) with text-only features. In this work, we introduce WeatherQA, the first multimodal dataset designed for machines to reason about complex combinations of weather parameters (a.k.a., ingredients) and predict severe weather in real-world scenarios. The dataset includes over 8,000 (multi-images, text) pairs for diverse severe weather events. Each pair contains rich information crucial for forecasting -- the images describe the ingredients capturing environmental instability, surface observations, and radar reflectivity, and the text contains forecast analyses written by human experts. With WeatherQA, we evaluate state-of-the-art vision language models, including GPT4, Claude3.5, Gemini-1.5, and a fine-tuned Llama3-based VLM, by designing two challenging tasks: (1) multi-choice QA for predicting affected area and (2) classification of the development potential of severe convection. These tasks require deep understanding of domain knowledge (e.g., atmospheric dynamics) and complex reasoning over multimodal data (e.g., interactions between weather parameters). We show a substantial gap between the strongest VLM, GPT4o, and human reasoning. Our comprehensive case study with meteorologists further reveals the weaknesses of the models, suggesting that better training and data integration are necessary to bridge this gap. WeatherQA link: https://github.com/chengqianma/WeatherQA.

Generative AI, such as OpenAI's GPT-4V large-language model, has rapidly entered mainstream discourse. Novel capabilities in image processing and natural-language communication may augment existing forecasting methods. Large language models further display potential to better communicate weather hazards in a style honed for diverse communities and different languages. This study evaluates GPT-4V's ability to interpret meteorological charts and communicate weather hazards appropriately to the user, despite challenges of hallucinations, where generative AI delivers coherent, confident, but incorrect responses. We assess GPT-4V's competence via its web interface ChatGPT in two tasks: (1) generating a severe-weather outlook from weather-chart analysis and conducting self-evaluation, revealing an outlook that corresponds well with a Storm Prediction Center human-issued forecast; and (2) producing hazard summaries in Spanish and English from weather charts. Responses in Spanish, however, resemble direct (not idiomatic) translations from English to Spanish, yielding poorly translated summaries that lose critical idiomatic precision required for optimal communication. Our findings advocate for cautious integration of tools like GPT-4V in meteorology, underscoring the necessity of human oversight and development of trustworthy, explainable AI.

Weather radar data are critical for nowcasting and an integral component of numerical weather prediction models. While weather radar data provide valuable information at high resolution, their ground-based nature limits their availability, which impedes large-scale applications. In contrast, meteorological satellites cover larger domains but with coarser resolution. However, with the rapid advancements in data-driven methodologies and modern sensors aboard geostationary satellites, new opportunities are emerging to bridge the gap between ground- and space-based observations, ultimately leading to more skillful weather prediction with high accuracy. Here, we present a Transformer-based model for nowcasting ground-based radar image sequences using satellite data up to two hours lead time. Trained on a dataset reflecting severe weather conditions, the model predicts radar fields occurring under different weather phenomena and shows robustness against rapidly growing/decaying fields and complex field structures. Model interpretation reveals that the infrared channel centered at 10.3 $\mu m$ (C13) contains skillful information for all weather conditions, while lightning data have the highest relative feature importance in severe weather conditions, particularly in shorter lead times. The model can support precipitation nowcasting across large domains without an explicit need for radar towers, enhance numerical weather prediction and hydrological models, and provide radar proxy for data-scarce regions. Moreover, the open-source framework facilitates progress towards operational data-driven nowcasting.

Now, there is a computer model that can help forecasters recognize potential severe storms more quickly and accurately, thanks to a team of researchers at Penn State, AccuWeather, Inc., and the University of Almería in Spain. They have developed a framework based on machine learning linear classifiers -- a kind of artificial intelligence -- that detects rotational movements in clouds from satellite images that might have otherwise gone unnoticed. This AI solution ran on the Bridges supercomputer at the Pittsburgh Supercomputing Center. Steve Wistar, senior forensic meteorologist at AccuWeather, said that having this tool to point his eye toward potentially threatening formations could help him to make a better forecast. "The very best forecasting incorporates as much data as possible," he said.

No matter where in the country you live, chances are you get hit with severe weather every once in a while. In New England, it's nasty Nor'Easters and blizzards, while tornadoes are a greater threat in the Midwest and South. Plus, just about everyone is subject to heavy rainfall and thunderstorms from time to time. When severe weather is headed in your direction, you're generally forced to hunker down at home (unless you're supposed to evacuate, in which case, please do so). As long as your electricity and internet are still working, though, your Amazon Echo can help you weather the storm!

A new algorithm could enable quicker and more accurate detection of severe weather. When forecasting weather, meteorologists use a number of models and data sources to track shapes and movements of clouds that could indicate severe storms. However, with increasingly expanding weather data sets and looming deadlines, it is nearly impossible for them to monitor all storm formations -- especially smaller-scale ones -- in real time. Now, there is a computer model that can help recognize severe storms more quickly and accurately, thanks to a team of researchers partially funded by the National Science Foundation. The researchers from Penn State, AccuWeather, Inc. and the University of Almería in Spain developed a framework based on machine learning linear classifiers -- a kind of artificial intelligence -- that detects from satellite images rotational movements in clouds that might have otherwise gone unnoticed.

"Alexa, make the rain go away." If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA TODAY's newsroom and any business incentives. No matter where in the country you live, chances are you get hit with severe weather every once in a while. In New England, it's nasty Nor'Easters and blizzards, while tornadoes are a greater threat in the Midwest and South.

Verizon is working on getting service to you after a crazy storm or other emergencies. This week, the company announced it tested a large drone that could provide service during an emergency using a "flying cell site." The technical test took place at Woodbine Municipal Airport in Woodbine, New Jersey and was made to simulate an environment in which commercial power would be out completely after severe weather or other dangerous events that affect communications services. The drone is owned and piloted by American Aerospace Technologies, Inc. (AATI). The test follows a previous successful run in October in Cape May, New Jersey which delivered 4G LTE network from the drone.

During the summer of 1989, the Forecast Systems Laboratory of the National Oceanic and Atmospheric Administration sponsored an evaluation of artificial intelligence-based systems that forecast severe convective storms. The evaluation experiment, called Shootout-89, took place in Boulder, and focussed on storms over the northeastern Colorado foothills and plains (Moninger, et al., 1990). Six systems participated in Shootout-89. These included traditional expert systems, an analogy-based system, and a system developed using methods from the cognitive science/judgment analysis tradition. Each day of the exercise, the systems generated 2 to 9 hour forecasts of the probabilities of occurrence of: non significant weather, significant weather, and severe weather, in each of four regions in northeastern Colorado. A verification coordinator working at the Denver Weather Service Forecast Office gathered ground-truth data from a network of observers. Systems were evaluated on the basis of several measures of forecast skill, and on other metrics such as timeliness, ease of learning, and ease of use. Systems were generally easy to operate, however the various systems required substantially different levels of meteorological expertise on the part of their users--reflecting the various operational environments for which the systems had been designed. Systems varied in their statistical behavior, but on this difficult forecast problem, the systems generally showed a skill approximately equal to that of persistence forecasts and climatological (historical frequency) forecasts. The two systems that appeared best able to discriminate significant from non significant weather events were traditional expert systems. Both of these systems required the operator to make relatively sophisticated meteorological judgments. We are unable, based on only one summer's worth of data, to determine the extent to which the greater skill of the two systems was due to the content of their knowledge bases, or to the subjective judgments of the operator. A follow-on experiment, Shootout-91, is currently being planned. Interested potential participants are encouraged to contact the author at the address above.