The carbon footprint of a model can be complicated to determine and compare across modelling approaches and data centre infrastructures. A reasonable place to start may be by assessing the number of floating-point operations – that is, a discrete count of how many simple mathematical operations (for example, multiplication, division, addition, subtraction, and variable assignment) – that need to be performed to train a model. This factor and others can impact energy consumption along with the architecture of the model and the training resources, such as hardware like GPU or CPUs. Additionally, the physical considerations of the storage and cooling of the servers comes into play. As a final complication, it also matters where the energy is sourced from.

A transition to a low-carbon electricity supply is crucial to limit the impacts of climate change. Reducing carbon emissions could help prevent the world from reaching a tipping point, where runaway emissions are likely. Runaway emissions could lead to extremes in weather conditions around the world -- especially in problematic regions unable to cope with these conditions. However, the movement to a low-carbon energy supply can not happen instantaneously due to the existing fossil-fuel infrastructure and the requirement to maintain a reliable energy supply. Therefore, a low-carbon transition is required, however, the decisions various stakeholders should make over the coming decades to reduce these carbon emissions are not obvious. This is due to many long-term uncertainties, such as electricity, fuel and generation costs, human behaviour and the size of electricity demand. A well choreographed low-carbon transition is, therefore, required between all of the heterogenous actors in the system, as opposed to changing the behaviour of a single, centralised actor. The objective of this thesis is to create a novel, open-source agent-based model to better understand the manner in which the whole electricity market reacts to different factors using state-of-the-art machine learning and artificial intelligence methods. In contrast to other works, this thesis looks at both the long-term and short-term impact that different behaviours have on the electricity market by using these state-of-the-art methods.

Yellowstone Caldera Chronicles is a weekly column written by scientists and collaborators of the Yellowstone Volcano Observatory. This week's contribution is from Keith Koper, director of the University of Utah Seismograph Stations and professor at the University of Utah Department of Geology and Geophysics, and Alysha Armstrong, graduate student at the University of Utah Department of Geology and Geophysics. While the automated monitoring system currently in place for detecting and processing earthquakes in Yellowstone National Park works well most of the time, its solutions need to be reviewed and refined by a seismic analyst. This means that the larger earthquakes -- generally over M1-- get most of the attention, and smaller earthquakes, which are harder to locate, are not always processed. The current system can also struggle in situations like earthquake swarms, where there is a lot of seismicity close together in space and time.

The new artificial intelligence tool has already led to the discovery of four new materials. Researchers at the University of Liverpool have created a collaborative artificial intelligence tool that reduces the time and effort required to discover truly new materials. Reported in the journal Nature Communications, the new tool has already led to the discovery of four new materials including a new family of solid state materials that conduct lithium. Such solid electrolytes will be key to the development of solid state batteries offering longer range and increased safety for electric vehicles. Further promising materials are in development.

Volt-var control (VVC) is the problem of operating power distribution systems within healthy regimes by controlling actuators in power systems. Existing works have mostly adopted the conventional routine of representing the power systems (a graph with tree topology) as vectors to train deep reinforcement learning (RL) policies. We propose a framework that combines RL with graph neural networks and study the benefits and limitations of graph-based policy in the VVC setting. Our results show that graph-based policies converge to the same rewards asymptotically however at a slower rate when compared to vector representation counterpart. We conduct further analysis on the impact of both observations and actions: on the observation end, we examine the robustness of graph-based policy on two typical data acquisition errors in power systems, namely sensor communication failure and measurement misalignment. On the action end, we show that actuators have various impacts on the system, thus using a graph representation induced by power systems topology may not be the optimal choice. In the end, we conduct a case study to demonstrate that the choice of readout function architecture and graph augmentation can further improve training performance and robustness.

Multivariate Time Series Forecasting (TSF) focuses on the prediction of future values based on historical context. In these problems, dependent variables provide additional information or early warning signs of changes in future behavior. State-of-the-art forecasting models rely on neural attention between timesteps. This allows for temporal learning but fails to consider distinct spatial relationships between variables. This paper addresses the problem by translating multivariate TSF into a novel spatiotemporal sequence formulation where each input token represents the value of a single variable at a given timestep. Long-Range Transformers can then learn interactions between space, time, and value information jointly along this extended sequence. Our method, which we call Spacetimeformer, scales to high dimensional forecasting problems dominated by Graph Neural Networks that rely on predefined variable graphs. We achieve competitive results on benchmarks from traffic forecasting to electricity demand and weather prediction while learning spatial and temporal relationships purely from data.

Decision-making problems under uncertainty have broad applications in operations research, machine learning, engineering, and economics. When the data involves uncertainty due to measurement error, insufficient sample size, contamination, and anomalies, or model misspecification, distributionally robust optimization (DRO) is a promising approach to data-driven optimization, by seeking a minimax robust optimal decision that minimizes the expected loss under the most adverse distribution within a given set of relevant distributions, called ambiguity set. It provides a principled framework to produce a solution with more promising out-of-sample performance than the traditional sample average approximation (SAA) method for stochastic programming [86]. We refer to [81] for a recent survey on DRO. At the core of DRO is the choice of the ambiguity set. Ideally, a good ambiguity set should take account of the properties of practical applications while maintaining the computational tractability of resulted DRO formulation; and it should be rich enough to contain all distributions relevant to the decision-making but, at the same time, should not include unnecessary distributions that lead to overly conservative decisions. Various DRO formulations have been proposed in the literature. Among them, the ambiguity set based on Wasserstein distance has recently received much attention [104, 67, 17, 46]. The Wasserstein distance incorporates the geometry of sample space, and thereby is suitable for comparing distributions with non-overlapping supports and hedging against data perturbations [46].

Tesla, a company by Elon Musk, has changed the automobile market. Everyone should learn how to use technology correctly from Tesla. Today, we will discuss how Tesla uses Artificial Intelligence and will understand its benefits and challenges. Tesla Motors, established in 2003, owns a market value of more than $700 billion. Tesla USP is their electric vehicles, sustainable energy generation products, solar panels, and much more.

NASA's InSight lander has measured one of the biggest and longest marsquakes yet, which featured tremors of 4.2 magnitude lasting nearly an hour and a half, the space agency said. The robotic seismometre celebrated 1,000 days on the Red Planet on September 18, when it detected the largest tremor since it arrived at the Elysium Planitia in 2018. The 4.2 magnitude quake equals the largest detected so far on Mars, but on Earth that would be considered'light', with more than 10,000 earthquakes of that level detected every year, feeling like a light rumble that would make dishes shake. The lander was only able to make the measurement after efforts to clear dust from its solar panels earlier in the year - keeping the seismometre operating. The team took a counterintuitive approach to achieving this by sprinkling one solar panel with larger sand grains in the hope wind would blow it across the other panel and result in clearing enough of the dust to allow power to enter the device.

In the next ten years, the Netherlands aim to take major steps towards increasing the amount of renewable energy produced and the electrification of heat demand and mobility. This desire requires a complete and highly complex transformation of the energy system. The fossil, central energy system is changing into a decentralised system based on renewable energy. Algorithms and AI can make a significant difference in accelerating this transition and in achieving an efficient and sustainable energy system. When making decisions about the energy transition, such as investing in infrastructure or placing renewable sources, much depends on predictions, often based on limited data, and there are many different interests.