FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting. The approach is designed to respect spherical geometry and to accurately model the spatially correlated probabilistic nature of the problem, resulting in stable spectra and realistic dynamics across multiple scales. FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods, while producing forecasts 8 to 60 times faster than these approaches. In contrast to other ML approaches, FourCastNet 3 demonstrates excellent probabilistic calibration and retains realistic spectra, even at extended lead times of up to 60 days. All of these advances are realized using a purely convolutional neural network architecture tailored for spherical geometry. Scalable and efficient large-scale training on 1024 GPUs and more is enabled by a novel training paradigm for combined model- and data-parallelism, inspired by domain decomposition methods in classical numerical models. Additionally, FourCastNet 3 enables rapid inference on a single GPU, producing a 60-day global forecast at 0.25°, 6-hourly resolution in under 4 minutes. Its computational efficiency, medium-range probabilistic skill, spectral fidelity, and rollout stability at subseasonal timescales make it a strong candidate for improving meteorological forecasting and early warning systems through large ensemble predictions.

President Trump speaks to reporters outside the White House on July 15, 2025, in Washington, as Press Secretary Karoline Leavitt watches in reverence.. Manuel Balce Ceneta/AP This story was originally published by WIRED and is reproduced here as part of the Climate Desk collaboration. AI is "not my thing," President Donald Trump admitted during a speech in Pittsburgh on Tuesday. However, the president said during his remarks at the Energy and Innovation Summit, his advisers had told him just how important energy was to the future of AI. "You need double the electric of what we have right now, and maybe even more than that," Trump said, recalling a conversation with "David"--most likely White House AI czar David Sacks, a panelist at the summit. "I said, what, are you kidding? That's double the electric that we have. Take everything we have and double it."

The identification of Linear Time-V ariant (L TV) systems from input-output data is a fundamental yet challenging ill-posed inverse problem. This work introduces a unified Bayesian framework that models the system's impulse response, h( t,τ), as a stochastic process. We decompose the response into a posterior mean and a random fluctuation term, a formulation that provides a principled approach for quantifying uncertainty and naturally defines a new, useful system class we term Linear Time-Invariant in Expectation (L TIE). To perform inference, we leverage modern machine learning techniques, including Bayesian neural networks and Gaussian Processes, using scalable variational inference. We demonstrate through a series of experiments that our framework can robustly infer the properties of an L TI system from a single noisy observation, show superior data e fficiency compared to classical methods in a simulated ambient noise tomography problem, and successfully track a continuously varying L TV impulse response by using a structured Gaussian Process prior. This work provides a flexible and robust methodology for uncertainty-aware system identification in dynamic environments.1. Introduction Linear Time-V ariant (L TV) systems are fundamental to modeling dynamic processes in fields ranging from geophysics and communications to control theory (Kozachek et al., 2024; Lin et al., 2020). Unlike their time-invariant counterparts, an L TV system's behavior is described by an impulse response, h( t,τ), that changes over time, posing significant challenges for analysis and estimation (Kailath, 1962; Bello, 1963). The task of identifying h( t,τ) from input-output data is a severely ill-posed inverse problem, as one must infer a function of two variables from one-dimensional time series (Aubel and B olcskei, 2015). This work introduces a Bayesian framework for modeling such systems, where the inherent uncertainty and time-varying nature are captured probabilistically.

We propose an automatic approach for manifold nonlinear autoregressive with exogenous inputs (mNARX) modeling that leverages the feature-based structure of functional-NARX (F-NARX) modeling. This novel approach, termed mNARX+, preserves the key strength of the mNARX framework, which is its expressivity allowing it to model complex dynamical systems, while simultaneously addressing a key limitation: the heavy reliance on domain expertise to identify relevant auxiliary quantities and their causal ordering. Our method employs a data-driven, recursive algorithm that automates the construction of the mNARX model sequence. It operates by sequentially selecting temporal features based on their correlation with the model prediction residuals, thereby automatically identifying the most critical auxiliary quantities and the order in which they should be modeled. This procedure significantly reduces the need for prior system knowledge. We demonstrate the effectiveness of the mNARX+ algorithm on two case studies: a Bouc-Wen oscillator with strong hysteresis and a complex aero-servo-elastic wind turbine simulator. The results show that the algorithm provides a systematic, data-driven method for creating accurate and stable surrogate models for complex dynamical systems.

The evaluation of large language models is a complex task, in which several approaches have been proposed. The most common is the use of automated benchmarks in which LLMs have to answer multiple-choice questions of different topics. However, this method has certain limitations, being the most concerning, the poor correlation with the humans. An alternative approach, is to have humans evaluate the LLMs. This poses scalability issues as there is a large and growing number of models to evaluate making it impractical (and costly) to run traditional studies based on recruiting a number of evaluators and having them rank the responses of the models. An alternative approach is the use of public arenas, such as the popular LM arena, on which any user can freely evaluate models on any question and rank the responses of two models. The results are then elaborated into a model ranking. An increasingly important aspect of LLMs is their energy consumption and, therefore, evaluating how energy awareness influences the decisions of humans in selecting a model is of interest. In this paper, we present GEA, the Generative Energy Arena, an arena that incorporates information on the energy consumption of the model in the evaluation process. Preliminary results obtained with GEA are also presented, showing that for most questions, when users are aware of the energy consumption, they favor smaller and more energy efficient models. This suggests that for most user interactions, the extra cost and energy incurred by the more complex and top-performing models do not provide an increase in the perceived quality of the responses that justifies their use.

Protected natural areas play a vital role in ecological balance and ecosystem services. Monitoring these regions at scale using satellite imagery and machine learning is promising, but current methods often lack interpretability and uncertainty-awareness, and do not address how uncertainty affects naturalness assessment. In contrast, we propose Confidence-Filtered Relevance (CFR), a data-centric framework that combines LRP Attention Rollout with Deep Deterministic Uncertainty (DDU) estimation to analyze how model uncertainty influences the interpretability of relevance heatmaps. CFR partitions the dataset into subsets based on uncertainty thresholds, enabling systematic analysis of how uncertainty shapes the explanations of naturalness in satellite imagery. Applied to the AnthroProtect dataset, CFR assigned higher relevance to shrublands, forests, and wetlands, aligning with other research on naturalness assessment. Moreover, our analysis shows that as uncertainty increases, the interpretability of these relevance heatmaps declines and their entropy grows, indicating less selective and more ambiguous attributions. CFR provides a data-centric approach to assess the relevance of patterns to naturalness in satellite imagery based on their associated certainty.

-- Image captioning has emerged as a crucial task in the intersection of computer vision and natural language processing, enabling automated generation of descriptive text from visual content. In the context of remote sensing, image captioning plays a significant role in interpreting vast and complex satellite imagery, aiding applications such as environmental monitoring, disaster assessment, and urban planning. This motivates us, in this paper, to present a transformer based network architecture for remote sensing image captioning (RSIC) in which multiple techniques of Static Expansion, Memory-Augmented Self-Attention, Mesh Transformer are evaluated and integrated. We evaluate our proposed models using two benchmark remote sensing image datasets of UCM-Caption and NWPU-Caption. Our best model outperforms the state-of-the-art systems on most of evaluation metrics, which demonstrates potential to apply for real-life remote sensing image systems.

As the data volume of astronomical imaging surveys rapidly increases, traditional methods for image anomaly detection, such as visual inspection by human experts, are becoming impractical. We introduce a machine-learning-based approach to detect poor-quality exposures in large imaging surveys, with a focus on the DECam Legacy Survey (DECaLS) in regions of low extinction (i.e., $E(B-V)<0.04$). Our semi-supervised pipeline integrates a vision transformer (ViT), trained via self-supervised learning (SSL), with a k-Nearest Neighbor (kNN) classifier. We train and validate our pipeline using a small set of labeled exposures observed by surveys with the Dark Energy Camera (DECam). A clustering-space analysis of where our pipeline places images labeled in ``good'' and ``bad'' categories suggests that our approach can efficiently and accurately determine the quality of exposures. Applied to new imaging being reduced for DECaLS Data Release 11, our pipeline identifies 780 problematic exposures, which we subsequently verify through visual inspection. Being highly efficient and adaptable, our method offers a scalable solution for quality control in other large imaging surveys.

Spatial grounding, the process of associating natural language expressions with corresponding image regions, has rapidly advanced due to the introduction of transformer-based models, significantly enhancing multimodal representation and cross-modal alignment. Despite this progress, the field lacks a comprehensive synthesis of current methodologies, dataset usage, evaluation metrics, and industrial applicability. This paper presents a systematic literature review of transformer-based spatial grounding approaches from 2018 to 2025. Our analysis identifies dominant model architectures, prevalent datasets, and widely adopted evaluation metrics, alongside highlighting key methodological trends and best practices. This study provides essential insights and structured guidance for researchers and practitioners, facilitating the development of robust, reliable, and industry-ready transformer-based spatial grounding models.

-- Soil moisture is a quantity of interest in many application areas including agriculture and climate modeling. Existing methods are not suitable for scale applications due to large deployment costs in high-resolution sensing applications such as for variable irrigation. In this work, we design, build and field deploy an autonomous mobile robot, MoistureMapper, for soil moisture sensing. The robot is equipped with Time Domain Reflectometry (TDR) sensors and a direct push drill mechanism for deploying the sensor to measure volumetric water content in the soil. Additionally, we implement and evaluate multiple adaptive sampling strategies based on a Gaussian Process based modeling to build a spatial mapping of moisture distribution in the soil. The adaptive sampling approach outperforms a greedy benchmark approach and results in up to 30% reduction in travel distance and 5% reduction in variance in the reconstructed moisture maps. Link to video showing field experiments: https://youtu.be/S4bJ4tRzObg