What We Know About the Winter Storm About to Hit the US--and What We Don't A huge portion of the United States is going to be hit with snow or freezing rain this weekend. Exactly where, what, and how much remains uncertain. Over the past weekend, when weather models first started forecasting a winter storm that would sweep over large parts of the country, Sean Sublette, a meteorologist living in Virginia, started telling people in his area to prepare for snow . At the time, Sublette says, "a lot of the data started to point to a substantial snow storm for the mid-Atlantic and the Northeast, with significant ice farther southward into Carolina's Tennessee Valley." Then, Sublette woke up Wednesday morning.

Efficient LLM pre-training requires well-tuned hyperparameters (HPs), including learning rate $η$ and weight decay $λ$. We study scaling laws for HPs: formulas for how to scale HPs as we scale model size N, dataset size D, and batch size B. Recent work suggests the AdamW timescale, $τ= B/(ηλD)$, should remain constant across training settings, and we verify the implication that optimal $λ$ scales linearly with B, for a fixed N and D. However, as N and D scale, we show optimal $τ$ obeys a precise power law in the tokens-per-parameter ratio, D/N. This law thus provides a method to accurately predict $λ$opt in advance of large-scale training. We also study scaling laws for optimal batch size Bopt (the B enabling lowest loss at a given N,D) and critical batch size Bcrit (the B beyond which further data parallelism becomes ineffective). In contrast to prior work, we find both Bopt and Bcrit scale as power laws in D, independent of model size, N. Finally, we analyze how these findings inform the real-world selection of Pareto-optimal N and D under dual training time and compute objectives. All experiments were run on Cerebras CS-3 systems.

The necessary integration of renewable energy sources, combined with the expanding scale of power networks, presents significant challenges in controlling modern power grids. Traditional control systems, which are human and optimization-based, struggle to adapt and to scale in such an evolving context, motivating the exploration of more dynamic and distributed control strategies. This work advances a graph-based distributed reinforcement learning framework for real-time, scalable grid management. The proposed architecture consists of a network of distributed low-level agents acting on individual power lines and coordinated by a high-level manager agent. A Graph Neural Network (GNN) is employed to encode the network's topological information within the single low-level agent's observation. To accelerate convergence and enhance learning stability, the framework integrates imitation learning and potential-based reward shaping. In contrast to conventional decentralized approaches that decompose only the action space while relying on global observations, this method also decomposes the observation space. Each low-level agent acts based on a structured and informative local view of the environment constructed through the GNN. Experiments on the Grid2Op simulation environment show the effectiveness of the approach, which consistently outperforms the standard baseline commonly adopted in the field. Additionally, the proposed model proves to be much more computationally efficient than the simulation-based Expert method.

Drones can inspect overhead power lines while they remain energized, significantly simplifying the inspection process. However, localizing a drone relative to all conductors using an onboard LiDAR sensor presents several challenges: (1) conductors provide minimal surface for LiDAR beams limiting the number of conductor points in a scan, (2) not all conductors are consistently detected, and (3) distinguishing LiDAR points corresponding to conductors from other objects, such as trees and pylons, is difficult. This paper proposes an estimation approach that minimizes the error between LiDAR measurements and a single geometric model representing the entire conductor array, rather than tracking individual conductors separately. Experimental results, using data from a power line drone inspection, demonstrate that this method achieves accurate tracking, with a solver converging under 50 ms per frame, even in the presence of partial observations, noise, and outliers. A sensitivity analysis shows that the estimation approach can tolerate up to twice as many outlier points as valid conductors measurements.

This story originally appeared on Grist and is part of the Climate Desk collaboration. What's shaping up to be one of the worst wildfire disasters in US history had many causes. Before the blazes raged across Los Angeles last week, eight months with hardly any rain had left the brush-covered landscape bone-dry. Santa Ana winds blew through the mountains, their gusts turning small fires into infernos and sending embers flying miles ahead. As many as 12,000 buildings have burned down, some hundred thousand people have fled their homes, and at least two dozen people have died.

Battery life has long been a key limiting factor in drone use. Although there are commercial models that can stay aloft for 45 minutes or longer on a single charge, being able to keep drones in the air for longer would be helpful for many purposes. Researchers at the University of Southern Denmark have been working on that issue for several years by developing drones that can recharge directly from power lines. This time around, the scientists attached a gripper system to a Tarot 650 Sport drone, which they customized with a electric quadcopter propulsion system, an autopilot module and other components. When the drone's systems detect that the battery is running low, the device employs its camera and millimeter-wave radar system to pinpoint the closest power line, as New Atlas notes.

We present a fully autonomous self-recharging drone system capable of long-duration sustained operations near powerlines. The drone is equipped with a robust onboard perception and navigation system that enables it to locate powerlines and approach them for landing. A passively actuated gripping mechanism grasps the powerline cable during landing after which a control circuit regulates the magnetic field inside a split-core current transformer to provide sufficient holding force as well as battery recharging. The system is evaluated in an active outdoor three-phase powerline environment. We demonstrate multiple contiguous hours of fully autonomous uninterrupted drone operations composed of several cycles of flying, landing, recharging, and takeoff, validating the capability of extended, essentially unlimited, operational endurance.

Chilling rain, swirling gray clouds and blustery winds rolled into Southern California on Sunday as the strongest winter storm of the season geared up to deliver near-record rainfall and life-threatening flash flooding in the region through Tuesday. The slow-moving atmospheric river was gathering strength Sunday afternoon, with the National Weather Service in Oxnard warning that "all systems are go for one of the most dramatic weather days in recent memory." Forecasters said the brunt of the storm appeared focused on the Los Angeles area, where the system could park itself for an extended time over the next few days. The storm could drop up to 8 inches of rainfall on the coast and valleys, and up to 14 inches in the foothills and mountains. Snowfall totals of 2 to 5 feet are likely at elevations above 7,000 feet.

Large-scale infrastructures are prone to deterioration due to age, environmental influences, and heavy usage. Ensuring their safety through regular inspections and maintenance is crucial to prevent incidents that can significantly affect public safety and the environment. This is especially pertinent in the context of electrical power networks, which, while essential for energy provision, can also be sources of forest fires. Intelligent drones have the potential to revolutionize inspection and maintenance, eliminating the risks for human operators, increasing productivity, reducing inspection time, and improving data collection quality. However, most of the current methods and technologies in aerial robotics have been trialed primarily in indoor testbeds or outdoor settings under strictly controlled conditions, always within the line of sight of human operators. Additionally, these methods and technologies have typically been evaluated in isolation, lacking comprehensive integration. This paper introduces the first autonomous system that combines various innovative aerial robots. This system is designed for extended-range inspections beyond the visual line of sight, features aerial manipulators for maintenance tasks, and includes support mechanisms for human operators working at elevated heights. The paper further discusses the successful validation of this system on numerous electrical power lines, with aerial robots executing flights over 10 kilometers away from their ground control stations.

In recent years, the use of inspection drones has become increasingly popular for high-voltage electric cable inspections due to their efficiency, cost-effectiveness, and ability to access hard-to-reach areas. However, safely landing drones on power lines, especially under windy conditions, remains a significant challenge. This study introduces a semi-autonomous control scheme for landing on an electrical line with the NADILE drone (an experimental drone based on original LineDrone key features for inspection of power lines) and assesses the operating envelope under various wind conditions. A Monte Carlo method is employed to analyze the success probability of landing given initial drone states. The performance of the system is evaluated for two landing strategies, variously controllers parameters and four level of wind intensities. The results show that a two-stage landing strategies offers higher probabilities of landing success and give insight regarding the best controller parameters and the maximum wind level for which the system is robust. Lastly, an experimental demonstration of the system landing autonomously on a power line is presented.