We present a new method to create spatial data using a generative adversarial network (GAN). Our contribution uses coarse and widely available geospatial data to create maps of less available features at the finer scale in the built environment, bypassing their traditional acquisition techniques (e.g. satellite imagery or land surveying). In the work, we employ land use data and road networks as input to generate building footprints, and conduct experiments in 9 cities around the world. The method, which we implement in a tool we release openly, enables generating approximate maps of the urban form, and it is generalisable to augment other types of geoinformation, enhancing the completeness and quality of spatial data infrastructure. It may be especially useful in locations missing detailed and high-resolution data and those that are mapped with uncertain or heterogeneous quality, such as much of OpenStreetMap. The quality of the results is influenced by the urban form and scale. In most cases, experiments suggest promising performance as the method tends to truthfully indicate the locations, amount, and shape of buildings. The work has the potential to support several applications, such as energy, climate, and urban morphology studies in areas previously lacking required data.

The US Navy is developing a pilotless solar-powered plane that can fly for 90 days at a time to help keep a watchful eye on naval ships below or act as a communications relay platform. The plane, dubbed'Skydweller' and developed by Skydweller Aero, builds on the manned Solar Impulse 2 aircraft that flew around the world in 2015 and 2016, but had to stop every five days. The upgraded version will eliminate the cockpit, allowing space for hardware that allows for autonomous abilities. Skydweller Aero CEO Robert Miller told New Scientist: 'When we remove the cockpit, we are enabling true persistence and providing the opportunity to install up to about 400 kilograms of payload capacity.' The pilotless craft will feature 236-foot long wings that are blanked in solar cells, but its makers may add hydrogen fuel cells for an additional boost.

Google is refreshing its Nest lineup with three new products and a refresh for the wired indoor Nest Cam. Among the newcomers are Google's first battery-powered Nest Cam and Doorbell, as a recent leak indicated. You'll be able to install them just about anywhere around your home, and connect them to a wired power source, if you prefer. The battery life depends on how many recorded events the devices detect and factors like the temperature and settings. Google says the Doorbell's battery will run for up to six months on a single charge, while the Nest Cam can run for up to seven months before you need to juice it up.

More than six months after its original line of aging Nest cameras began running out of stock, Google has taken the wraps off a quartet of new Nest cams, including a floodlight cam and a successor to the Nest Hello video doorbell. Boasting smaller designs, updated features, and more affordable price tags, all four of the revamped Nest devices also come with a killer feature: on-device, AI-powered detection of people, animals, vehicles, and (for the doorbell) packages, all without a subscription. Among the new devices is the $99.99 Nest Cam, a wired camera that marks the first Nest camera to be priced less than $100 (well, a penny under, anyway), while the $180 Nest Doorbell boasts a head-to-toe field of view and runs on either battery or low-voltage wired power. Also coming soon is a $180 wireless Nest Cam, which can run on either battery or wired power and can be installed either outdoors or inside, plus the $280 Nest Cam with floodlight. Two of the new Nest products--the Nest Doorbell and the battery-powered Nest Cam--will arrive on August 24, while the wired Nest Cam and the Nest Cam with floodlight are coming "at a later date," Google said.

Marshall Worth, senior project manager AI at PowerSecure, discusses artificial intelligence and a practical approach that microgrid customers can take today to achieve their energy goals of the future. "Alexa, reduce my energy costs!" With as fast as technology has progressed over the last decade, and with the promise of self-driving cars on the horizon and the electrification of everything, it's only natural to question when this is all going to filter into our everyday, energy consuming lives. In this device-driven age, shouldn't we already have the artificial intelligence (AI) capabilities to reduce our carbon footprint today and our energy bill tomorrow? Those of us who work in the energy industry are fortunate; we are naturally driven to innovate and build the future of energy.

While the forward and backward modeling of the process-structure-property chain has received a lot of attention from the materials community, fewer efforts have taken into consideration uncertainties. Those arise from a multitude of sources and their quantification and integration in the inversion process are essential in meeting the materials design objectives. The first contribution of this paper is a flexible, fully probabilistic formulation of such optimization problems that accounts for the uncertainty in the process-structure and structure-property linkages and enables the identification of optimal, high-dimensional, process parameters. We employ a probabilistic, data-driven surrogate for the structure-property link which expedites computations and enables handling of non-differential objectives. We couple this with a novel active learning strategy, i.e. a self-supervised collection of data, which significantly improves accuracy while requiring small amounts of training data. We demonstrate its efficacy in optimizing the mechanical and thermal properties of two-phase, random media but envision its applicability encompasses a wide variety of microstructure-sensitive design problems.

The United States said Wednesday it suspected Iranian involvement in the alleged hijacking of a ship in the Gulf of Oman as it vowed to work with Britain to respond to an earlier deadly attack it blamed on Tehran. Oman said that the Asphalt Princess, an asphalt and bitumen tanker, was involved in "a hijacking incident in international waters" and that it deployed aircraft and naval ships. The United States and Britain said that the murky incident in the Gulf of Oman concluded after one day, with the alleged hijackers leaving the Panamanian-flagged vessel. "We believe that these personnel were Iranian, but we're not in a position to confirm this at this time," State Department spokesman Ned Price told reporters in Washington. "Iran has undertaken a pattern of belligerence in terms of proxy attacks in the region and of course, these maritime attacks," Price said, while adding that circumstances in the latest incident were "still emerging".

Random reconstruction of three-dimensional (3D) digital rocks from two-dimensional (2D) slices is crucial for elucidating the microstructure of rocks and its effects on pore-scale flow in terms of numerical modeling, since massive samples are usually required to handle intrinsic uncertainties. Despite remarkable advances achieved by traditional process-based methods, statistical approaches and recently famous deep learning-based models, few works have focused on producing several kinds of rocks with one trained model and allowing the reconstructed samples to satisfy certain given properties, such as porosity. To fill this gap, we propose a new framework, named RockGPT, which is composed of VQ-VAE and conditional GPT, to synthesize 3D samples based on a single 2D slice from the perspective of video generation. The VQ-VAE is utilized to compress high-dimensional input video, i.e., the sequence of continuous rock slices, to discrete latent codes and reconstruct them. In order to obtain diverse reconstructions, the discrete latent codes are modeled using conditional GPT in an autoregressive manner, while incorporating conditional information from a given slice, rock type, and porosity. We conduct two experiments on five kinds of rocks, and the results demonstrate that RockGPT can produce different kinds of rocks with the same model, and the reconstructed samples can successfully meet certain specified porosities. In a broader sense, through leveraging the proposed conditioning scheme, RockGPT constitutes an effective way to build a general model to produce multiple kinds of rocks simultaneously that also satisfy user-defined properties.

This paper presents a novel method for attitude estimation of an object in 3D space by incremental learning of the Long-Short Term Memory (LSTM) network. Gyroscope, accelerometer, and magnetometer are few widely used sensors in attitude estimation applications. Traditionally, multi-sensor fusion methods such as the Extended Kalman Filter and Complementary Filter are employed to fuse the measurements from these sensors. However, these methods exhibit limitations in accounting for the uncertainty, unpredictability, and dynamic nature of the motion in real-world situations. In this paper, the inertial sensors data are fed to the LSTM network which are then updated incrementally to incorporate the dynamic changes in motion occurring in the run time. The robustness and efficiency of the proposed framework is demonstrated on the dataset collected from a commercially available inertial measurement unit. The proposed framework offers a significant improvement in the results compared to the traditional method, even in the case of a highly dynamic environment. The LSTM framework-based attitude estimation approach can be deployed on a standard AI-supported processing module for real-time applications.

In this paper, we study zeroth-order algorithms for nonconvex-concave minimax problems, which have attracted widely attention in machine learning, signal processing and many other fields in recent years. We propose a zeroth-order alternating randomized gradient projection (ZO-AGP) algorithm for smooth nonconvex-concave minimax problems, and its iteration complexity to obtain an $\varepsilon$-stationary point is bounded by $\mathcal{O}(\varepsilon^{-4})$, and the number of function value estimation is bounded by $\mathcal{O}(d_{x}\varepsilon^{-4}+d_{y}\varepsilon^{-6})$ per iteration. Moreover, we propose a zeroth-order block alternating randomized proximal gradient algorithm (ZO-BAPG) for solving block-wise nonsmooth nonconvex-concave minimax optimization problems, and the iteration complexity to obtain an $\varepsilon$-stationary point is bounded by $\mathcal{O}(\varepsilon^{-4})$ and the number of function value estimation per iteration is bounded by $\mathcal{O}(K d_{x}\varepsilon^{-4}+d_{y}\varepsilon^{-6})$. To the best of our knowledge, this is the first time that zeroth-order algorithms with iteration complexity gurantee are developed for solving both general smooth and block-wise nonsmooth nonconvex-concave minimax problems. Numerical results on data poisoning attack problem validate the efficiency of the proposed algorithms.