Convolutional Neural Networks (CNN) possess many positive qualities when it comes to spatial raster data. Translation invariance enables CNNs to detect features regardless of their position in the scene. However, in some domains, like geospatial, not all locations are exactly equal. In this work, we propose localized convolutional neural networks that enable convolutional architectures to learn local features in addition to the global ones. We investigate their instantiations in the form of learnable inputs, local weights, and a more general form. They can be added to any convolutional layers, easily end-to-end trained, introduce minimal additional complexity, and let CNNs retain most of their benefits to the extent that they are needed. In this work we address spatio-temporal prediction: test the effectiveness of our methods on a synthetic benchmark dataset and tackle three real-world wind prediction datasets. For one of them, we propose a method to spatially order the unordered data. We compare the recent state-of-the-art spatio-temporal prediction models on the same data. Models that use convolutional layers can be and are extended with our localizations. In all these cases our extensions improve the results, and thus often the state-of-the-art. We share all the code at a public repository.

Extreme waves in the Arctic typically occur every 20 years, but as climate change continues to plague the region these events could happen every two to five years, a new study reveals. Much of this area is frozen for a majority of the year, but rising temperatures have increased periods of open water that could result in catastrophic waves. Using computer models, researchers found the area hit the hardest was in the Greenland Sea, which could experience maximum annual wave heights of more than 19 feet. The team also warns coastal flooding might increase by a factor of four to 10 by the end of this century. Extreme waves in the Arctic typically occur every 20 years, but as climate change continues to plague the region these events could happen every two to five years, a new study reveals.

The long-awaited sequel to Top Gun is due to hit cinemas in December, but the virtuoso fighter pilots at its heart could soon be a thing of the past. The trustworthy wingman will soon be replaced by artificial intelligence, built into a drone, or an existing fighter jet with no one in the cockpit. Since 2010, the US Air Force and Boeing's QF-16 programme has been converting old F-16 fighter jets into unmanned drones, which can fly preset routes without a pilot. This year, 32 of these autonomous planes – rescued from retirement in the "boneyard" at an Air Force base near Arizona – will be used as targets in weapons testing over the Gulf of Mexico. In the future, self-flying fighter jets such as these could transform aerial combat. The Air Force's Skyborg programme, which could be in operation as soon as 2023, is developing AI systems for its unmanned Valkyrie drones which would enable them to communicate with and operate in tandem with a manned F-35 jet.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Maybe it will take out missiles beyond the earth's atmosphere, incinerate targets well beyond the horizon with high-powered laser weapons and instantly stop a multi-faceted series of incoming attacks all at the same time? Perhaps it will use AI-empowered algorithms to launch a large fleet of networked surface, air and undersea drones, able to launch coordinated attacks at long ranges? All of these capabilities, advanced well beyond the current state-of-the-art into a new generation of maritime warfare weapons, are likely to figure prominently in the Navy's current conceptual work on a new generation of destroyers to emerge more than a decade from now – the Future Surface Combatant.

Sub-seasonal climate forecasting (SSF) focuses on predicting key climate variables such as temperature and precipitation in the 2-week to 2-month time scales. Skillful SSF would have immense societal value, in areas such as agricultural productivity, water resource management, transportation and aviation systems, and emergency planning for extreme weather events. However, SSF is considered more challenging than either weather prediction or even seasonal prediction. In this paper, we carefully study a variety of machine learning (ML) approaches for SSF over the US mainland. While atmosphere-land-ocean couplings and the limited amount of good quality data makes it hard to apply black-box ML naively, we show that with carefully constructed feature representations, even linear regression models, e.g., Lasso, can be made to perform well. Among a broad suite of 10 ML approaches considered, gradient boosting performs the best, and deep learning (DL) methods show some promise with careful architecture choices. Overall, suitable ML methods are able to outperform the climatological baseline, i.e., predictions based on the 30-year average at a given location and time. Further, based on studying feature importance, ocean (especially indices based on climatic oscillations such as El Nino) and land (soil moisture) covariates are found to be predictive, whereas atmospheric covariates are not considered helpful.

A 30ft-long whale that died after it became stranded in a Welsh estuary was a one-year-old male calf that was struggling to find food, an autopsy has revealed. The fin whale, named Henry by rescuers, is thought to have been recently weaned by his mother and started to live independently - as they stop receiving milk at around six to seven months old - before becoming beached. The young male died on the sands of the Dee Estuary, North Wales, on June 14. He had beached at least twice over the previous two days. A post-mortem was carried out by the Cetacean Strandings Investigation Programme (CSIP) to identify the cause of death and find out why the whale ended up out of the sea.

After years of development, Boston Dynamics' four-legged robot'dog' will be sold to companies for the first time ever. 'Spot', as the bot is called, will retail for $74,500 and comes with some restrictions as to when and where it can be deployed. Specifically, Boston Dynamics says all of its sales will be subject to terms and conditions that dictate the'beneficial use' of its robots. The company sees'Spot' applying most directly to'commercial and industrial use' and in particular, to bolster safety in jobs where humans could be harmed. 'The combination of Spot's sophisticated software and high performance mechanical design enables the robot to augment difficult or dangerous human work,' aid Marc Raibert, chairman and founder of Boston Dynamics in a statement. 'Now you can use Spot to increase human safety in environments and tasks where traditional automation hasn't been successful.'

Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading to a vast number of proposed approaches. However, they have mostly been treated as separate problems, and have typically relied on non-linear first-principles models with parameters that can only be determined experimentally. The rise of Deep Reinforcement Learning (DRL) in recent years suggests an alternative approach: end-to-end learning of the optimal guidance policy from scratch by means of a trial-and-error based approach. In this article, we explore the potential of Proximal Policy Optimization (PPO), a DRL algorithm with demonstrated state-of-the-art performance on Continuous Control tasks, when applied to the dual-objective problem of controlling an underactuated Autonomous Surface Vehicle in a COLREGs compliant manner such that it follows an a priori known desired path while avoiding collisions with other vessels along the way. Based on high-fidelity elevation and AIS tracking data from the Trondheim Fjord, an inlet of the Norwegian sea, we evaluate the trained agent's performance in challenging, dynamic real-world scenarios where the ultimate success of the agent rests upon its ability to navigate non-uniform marine terrain while handling challenging, but realistic vessel encounters.

We use a conditional deep convolutional generative adversarial network to predict the geopotential height of the 500 hPa pressure level, the two-meter temperature and the total precipitation for the next 24 hours over Europe. The proposed models are trained on 4 years of ERA5 reanalysis data from 2015-2018 with the goal to predict the associated meteorological fields in 2019. The forecasts show a good qualitative and quantitative agreement with the true reanalysis data for the geopotential height and two-meter temperature, while failing for total precipitation, thus indicating that weather forecasts based on data alone may be possible for specific meteorological parameters. We further use Monte-Carlo dropout to develop an ensemble weather prediction system based purely on deep learning strategies, which is computationally cheap and further improves the skill of the forecasting model, by allowing to quantify the uncertainty in the current weather forecast as learned by the model.

One main obstacle for the wide use of deep learning in medical and engineering sciences is its interpretability. While neural network models are strong tools for making predictions, they often provide little information about which features play significant roles in influencing the prediction accuracy. To overcome this issue, many regularization procedures for learning with neural networks have been proposed for dropping non-significant features. Unfortunately, the lack of theoretical results casts doubt on the applicability of such pipelines. In this work, we propose and establish a theoretical guarantee for the use of the adaptive group lasso for selecting important features of neural networks. Specifically, we show that our feature selection method is consistent for single-output feed-forward neural networks with one hidden layer and hyperbolic tangent activation function. We demonstrate its applicability using both simulation and data analysis.