This paper explores the effectiveness of data-driven models to predict voltage excursion events in power systems using simple categorical labels. By treating the prediction as a categorical classification task, the workflow is characterized by a low computational and data burden. A proof-of-concept case study on a real portion of the Italian 150 kV sub-transmission network, which hosts a significant amount of wind power generation, demonstrates the general validity of the proposal and offers insight into the strengths and weaknesses of several widely utilized prediction models for this application.

We identify effective stochastic differential equations (SDE) for coarse observables of fine-grained particle- or agent-based simulations; these SDE then provide useful coarse surrogate models of the fine scale dynamics. We approximate the drift and diffusivity functions in these effective SDE through neural networks, which can be thought of as effective stochastic ResNets. The loss function is inspired by, and embodies, the structure of established stochastic numerical integrators (here, Euler-Maruyama and Milstein); our approximations can thus benefit from backward error analysis of these underlying numerical schemes. They also lend themselves naturally to "physics-informed" gray-box identification when approximate coarse models, such as mean field equations, are available. Existing numerical integration schemes for Langevin-type equations and for stochastic partial differential equations (SPDE) can also be used for training; we demonstrate this on a stochastically forced oscillator and the stochastic wave equation. Our approach does not require long trajectories, works on scattered snapshot data, and is designed to naturally handle different time steps per snapshot. We consider both the case where the coarse collective observables are known in advance, as well as the case where they must be found in a data-driven manner.

A 20% savings in fuel efficiency for a two-day retrofit is nothing to sneeze at, and that explains why the leading cargo shipper Kawasaki Kisen Kaisha, Ltd. is adding more wind power punch to its existing roster of cargo ships. The company has just ordered another three Seawing sails from the company Airseas on top of a previous order. Better yet, from a carbon-cutting perspective, "K" Line also expects to leverage artificial intelligence to squeeze even more clean power from centuries-old seagoing technology. If the name Airseas rings a bell, that's probably because of the connection to the well known aircraft maker Airbus. Airseas sailed across the CleanTechnica radar last fall, when we noted that it was founded by former engineers at Airbus (for the record, it is also funded and supported by Airbus, the EU, and other partners).

We study policy gradient (PG) for reinforcement learning in continuous time and space under the regularized exploratory formulation developed by Wang et al. (2020). We represent the gradient of the value function with respect to a given parameterized stochastic policy as the expected integration of an auxiliary running reward function that can be evaluated using samples and the current value function. This representation effectively turns PG into a policy evaluation (PE) problem, enabling us to apply the martingale approach recently developed by Jia and Zhou (2022a) for PE to solve our PG problem. Based on this analysis, we propose two types of actor-critic algorithms for RL, where we learn and update value functions and policies simultaneously and alternatingly. The first type is based directly on the aforementioned representation, which involves future trajectories and is offline. The second type, designed for online learning, employs the first-order condition of the policy gradient and turns it into martingale orthogonality conditions. These conditions are then incorporated using stochastic approximation when updating policies. Finally, we demonstrate the algorithms by simulations in two concrete examples.

Direct-to-satellite (DtS) communication has gained importance recently to support globally connected Internet of things (IoT) networks. However, relatively long distances of densely deployed satellite networks around the Earth cause a high path loss. In addition, since high complexity operations such as beamforming, tracking and equalization have to be performed in IoT devices partially, both the hardware complexity and the need for high-capacity batteries of IoT devices increase. The reconfigurable intelligent surfaces (RISs) have the potential to increase the energy-efficiency and to perform complex signal processing over the transmission environment instead of IoT devices. But, RISs need the information of the cascaded channel in order to change the phase of the incident signal. This study evaluates the pilot signal as a graph and incorporates this information into the graph attention networks (GATs) to track the phase relation through pilot signaling. The proposed GAT-based channel estimation method examines the performance of the DtS IoT networks for different RIS configurations to solve the challenging channel estimation problem. It is shown that the proposed GAT both demonstrates a higher performance with increased robustness under changing conditions and has lower computational complexity compared to conventional deep learning methods. Moreover, bit error rate performance is investigated for RIS designs with discrete and non-uniform phase shifts under channel estimation based on the proposed method. One of the findings in this study is that the channel models of the operating environment and the performance of the channel estimation method must be considered during RIS design to exploit performance improvement as far as possible.

Numerical simulations in climate, chemistry, or astrophysics are computationally too expensive for uncertainty quantification or parameter-exploration at high-resolution. Reduced-order or surrogate models are multiple orders of magnitude faster, but traditional surrogates are inflexible or inaccurate and pure machine learning (ML)-based surrogates too data-hungry. We propose a hybrid, flexible surrogate model that exploits known physics for simulating large-scale dynamics and limits learning to the hard-to-model term, which is called parametrization or closure and captures the effect of fine- onto large-scale dynamics. Leveraging neural operators, we are the first to learn grid-independent, non-local, and flexible parametrizations. Our \textit{multiscale neural operator} is motivated by a rich literature in multiscale modeling, has quasilinear runtime complexity, is more accurate or flexible than state-of-the-art parametrizations and demonstrated on the chaotic equation multiscale Lorenz96.

Santiago Miret is a deep learning researcher at Intel Labs, where he focuses on developing artificial intelligence (AI) solutions and exploring the intersection of AI and the physical sciences. The successful design and deployment of novel material technologies in the last couple of decades has enabled tremendous innovations across various industries. Building today's smartphones, for example, would have cost about 100 million dollars in the 1980s and yielded a 14 meters tall device, both of which would be very impractical. Furthermore, materials innovations surrounding silicon have enabled advances in microelectronics and computer technologies that build the foundation of a technology-enabled world, including the recent proliferation of artificial intelligence (AI). Similar, albeit different advances, in silicon technology and perovskites, a class of semiconductor materials that transport the electric charge of light, have provided the basis for solar photovoltaic cells which enable the harvesting of renewable solar energy thereby driving a redesign of the energy industry to a more sustainable and less carbon-heavy system.

What role will machine learning, a subset of AI, play in Australia's transition to a zero carbon energy future, and what are some of the implications and trade-offs that come with its increased use in our energy infrastructure? Over the past decade, renewable energy consumption has grown globally at an average annual rate of 13.7%. In Australia, 2020 saw more than a quarter of the country's total electricity generation coming from renewable sources for the first time. Tasmania, the Australian island state, currently runs on 100% renewable energy. This is good news for climate change.

Machine learning (ML) often mimics how human brains operate by attaching virtual neurons with virtual synapses. Deep learning (DL) is a subset of ML putting steroids into the virtual brain and growing it orders of magnitude larger. This neuron count has skyrocketed hand-in-hand with the advances in computational power. Most headlines about ML solving hard problems like self-driving cars or facial recognition use DL, but the steroids come with a cost. Global warming is arguably the most critical problem our generation has to solve in the following years.

First, it must be shown that Ai can imitate human behavior. This can be done by showing that Ai can pass the Turing Test. Second, it must be demonstrated that Ai can understand human emotions. This can be done by showing that Ai can identify human emotions from facial expressions. Third, it must be demonstrated that Ai can generate its own emotions.