Understanding the robustness of a weather forecasting model with respect to input noise or different uncertainties is important in assessing its output reliability, particularly for extreme weather events like hurricanes. In this paper, we test sensitivity and robustness of an artificial intelligence (AI) weather forecasting model: NVIDIAs FourCastNetv2 (FCNv2). We conduct two experiments designed to assess model output under different levels of injected noise in the models initial condition. First, we perturb the initial condition of Hurricane Florence from the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5) dataset (September 13-16, 2018) with varying amounts of Gaussian noise and examine the impact on predicted trajectories and forecasted storm intensity. Second, we start FCNv2 with fully random initial conditions and observe how the model responds to nonsensical inputs. Our results indicate that FCNv2 accurately preserves hurricane features under low to moderate noise injection. Even under high levels of noise, the model maintains the general storm trajectory and structure, although positional accuracy begins to degrade. FCNv2 consistently underestimates storm intensity and persistence across all levels of injected noise. With full random initial conditions, the model generates smooth and cohesive forecasts after a few timesteps, implying the models tendency towards stable, smoothed outputs. Our approach is simple and portable to other data-driven AI weather forecasting models.

Big Tech has lost its way. At WIRED's Big Interview event, Techdirt editor Mike Masnick and Common Tools CEO Alex Komoroske announced a manifesto designed to help the industry get back on track. Alex Komoroske has always been at odds with Big Tech's darker side. Though he cut his product-management teeth at Google and Stripe, he was never comfortable with the industry's increasing prioritization of profits over people. Once during his time at Google, he extolled the societal benefits of a project only to be met with, "Oh Alex, you'd be a VP by now if you just stopped thinking through the implications of your actions."

By how much, if at all, will AI boost the U.S. economy? New research by Anthropic, seen exclusively by TIME in advance of its release today, offers at least a partial answer to that question. By studying aggregated data about how people use Claude in the course of their work, Anthropic researchers came up with an estimate for how much AI could contribute to annual labor productivity growth--an important contributor to the total level of growth in the overall economy--as the technology becomes more widely used. Their answer: current-generation AI models could increase the U.S. annual labor productivity growth rate by 1.8%--doubling the average rate of growth since 2019. Assuming that labor makes up 60% of total productivity in the economy, and that AI reaches full diffusion in a decade's time, "this implies an overall total factor productivity increase of 1.1% per year," the researchers write.

Bureau of Meteorology, Australia ABSTRACT: Artificial Intelligence (AI) weather models are now reaching operational-grade performance for some variables, but like traditional Numerical Weather Prediction (NWP) models, they exhibit systematic biases and reliability issues. We test the application of the Bureau of Meteorology's existing statistical post-processing system, IMPROVER, to ECMWF's deterministic Artificial Intelligence Forecasting System (AIFS), and compare results against post-processed outputs from the ECMWF HRES and ENS models. Without any modification to processing workflows, post-processing yields comparable accuracy improvements for AIFS as for traditional NWP forecasts, in both expected value and probabilistic outputs. We show that blending AIFS with NWP models improves overall forecast skill, even when AIFS alone is not the most accurate component. These findings show that statistical post-processing methods developed for NWP are directly applicable to AI models, enabling national meteorological centres to incorporate AI forecasts into existing workflows in a low-risk, incremental fashion. Notice This Work has been accepted by Artificial Intelligence for the Earth Systems. The AMS does not guarantee that the copy provided here is an accurate copy of the Version of Record (VoR).

Deep learning (DL)-based general circulation models (GCMs) are emerging as fast simulators, yet their ability to replicate extreme events outside their training range remains unknown. Here, we evaluate two such models -- the hybrid Neural General Circulation Model (NGCM) and purely data-driven Deep Learning Earth System Model (DL\textit{ESy}M) -- against a conventional high-resolution land-atmosphere model (HiRAM) in simulating land heatwaves and coldwaves. All models are forced with observed sea surface temperatures and sea ice over 1900-2020, focusing on the out-of-sample early-20th-century period (1900-1960). Both DL models generalize successfully to unseen climate conditions, broadly reproducing the frequency and spatial patterns of heatwave and cold wave events during 1900-1960 with skill comparable to HiRAM. An exception is over portions of North Asia and North America, where all models perform poorly during 1940-1960. Due to excessive temperature autocorrelation, DL\textit{ESy}M tends to overestimate heatwave and cold wave frequencies, whereas the physics-DL hybrid NGCM exhibits persistence more similar to HiRAM.

Extreme heat is the deadliest weather-related hazard in the United States. Furthermore, it is increasing in intensity, frequency, and duration, making skillful forecasts vital to protecting life and property. Traditional numerical weather prediction (NWP) models struggle with extreme heat for medium-range and subseasonal-to-seasonal (S2S) timescales. Meanwhile, artificial intelligence-based weather prediction (AIWP) models are progressing rapidly. However, it is largely unknown how well AIWP models forecast extremes, especially for medium-range and S2S timescales. This study investigates 2-m temperature forecasts for 60 heat waves across the four boreal seasons and over four CONUS regions at lead times up to 20 days, using two AIWP models (Google GraphCast and Pangu-Weather) and one traditional NWP model (NOAA United Forecast System Global Ensemble Forecast System (UFS GEFS)). First, case study analyses show that both AIWP models and the UFS GEFS exhibit consistent cold biases on regional scales in the 5-10 days of lead time before heat wave onset. GraphCast is the more skillful AIWP model, outperforming UFS GEFS and Pangu-Weather in most locations. Next, the two AIWP models are isolated and analyzed across all heat waves and seasons, with events split among the model's testing (2018-2023) and training (1979-2017) periods. There are cold biases before and during the heat waves in both models and all seasons, except Pangu-Weather in winter, which exhibits a mean warm bias before heat wave onset. Overall, results offer encouragement that AIWP models may be useful for medium-range and S2S predictability of extreme heat.

To improve the trustworthiness of an AI model, finding consistent, understandable representations of its inference process is essential. This understanding is particularly important in high-stakes operations such as weather forecasting, where the identification of underlying meteorological mechanisms is as critical as the accuracy of the predictions. Despite the growing literature that addresses this issue through explainable AI, the applicability of their solutions is often limited due to their AI-centric development. To fill this gap, we follow a user-centric process to develop an example-based concept analysis framework, which identifies cases that follow a similar inference process as the target instance in a target model and presents them in a user-comprehensible format. Our framework provides the users with visually and conceptually analogous examples, including the probability of concept assignment to resolve ambiguities in weather mechanisms. To bridge the gap between vector representations identified from models and human-understandable explanations, we compile a human-annotated concept dataset and implement a user interface to assist domain experts involved in the the framework development.

The original version of this story appeared in Quanta Magazine. Sometime in the fall of 2021, Andrew Krapivin, an undergraduate at Rutgers University, encountered a paper that would change his life. At the time, Krapivin didn't give it much thought. But two years later, when he finally set aside time to go through the paper ("just for fun," as he put it), his efforts would lead to a rethinking of a widely used tool in computer science. The paper's title, "Tiny Pointers," referred to arrowlike entities that can direct you to a piece of information, or element, in a computer's memory. Krapivin soon came up with a potential way to further miniaturize the pointers so they consumed less memory.

This paper presents a physics-constrained neural differential equation framework for parameterization, and employs it to model the time evolution of seasonal snow depth given hydrometeorological forcings. When trained on data from multiple SNOTEL sites, the parameterization predicts daily snow depth with under 9% median error and Nash Sutcliffe Efficiencies over 0.94 across a wide variety of snow climates. The parameterization also generalizes to new sites not seen during training, which is not often true for calibrated snow models. Requiring the parameterization to predict snow water equivalent in addition to snow depth only increases error to ~12%. The structure of the approach guarantees the satisfaction of physical constraints, enables these constraints during model training, and allows modeling at different temporal resolutions without additional retraining of the parameterization. These benefits hold potential in climate modeling, and could extend to other dynamical systems with physical constraints.

In this study, we present the integration of a neural network-based parameterization into the global atmospheric model ARP-GEM1, leveraging the Python interface of the OASIS coupler. This approach facilitates the exchange of fields between the Fortran-based ARP-GEM1 model and a Python component responsible for neural network inference. As a proof-of-concept experiment, we trained a neural network to emulate the deep convection parameterization of ARP-GEM1. Using the flexible Fortran/Python interface, we have successfully replaced ARP-GEM1's deep convection scheme with a neural network emulator. To assess the performance of the neural network deep convection scheme, we have run a 5-years ARP-GEM1 simulation using the neural network emulator. The evaluation of averaged fields showed good agreement with output from an ARP-GEM1 simulation using the physics-based deep convection scheme. The Python component was deployed on a separate partition from the general circulation model, using GPUs to increase inference speed of the neural network.