Data assimilation techniques are widely used to predict complex dynamical systems with uncertainties, based on time-series observation data. Error covariance matrices modelling is an important element in data assimilation algorithms which can considerably impact the forecasting accuracy. The estimation of these covariances, which usually relies on empirical assumptions and physical constraints, is often imprecise and computationally expensive especially for systems of large dimension. In this work, we propose a data-driven approach based on long short term memory (LSTM) recurrent neural networks (RNN) to improve both the accuracy and the efficiency of observation covariance specification in data assimilation for dynamical systems. Learning the covariance matrix from observed/simulated time-series data, the proposed approach does not require any knowledge or assumption about prior error distribution, unlike classical posterior tuning methods. We have compared the novel approach with two state-of-the-art covariance tuning algorithms, namely DI01 and D05, first in a Lorenz dynamical system and then in a 2D shallow water twin experiments framework with different covariance parameterization using ensemble assimilation. This novel method shows significant advantages in observation covariance specification, assimilation accuracy and computational efficiency.

The World Economic Forum has published a new study on how Artificial Intelligence (AI) can be used to accelerate a more equitable energy transition and build trust for the technology throughout the industry. As the impacts of climate change become more visible worldwide, governments and industry face the urgent challenge of transitioning to a low-carbon global energy system. Digital technologies – particularly AI – are key enablers for this transition and have the potential to deliver the energy sector's climate goals more rapidly and at lower cost. Written in collaboration with BloombergNEF and Deutsche Energie-Agentur (dena) – the German Energy Agency, Harnessing Artificial Intelligence to Accelerate the Energy Transition reviews the state of play of AI adoption in the energy sector, identifies high-priority applications of AI in the energy transition, and offers a road map and practical recommendations for the energy and AI industries to maximize AI's benefits. The report finds that AI has the potential to create substantial value for the global energy transition.

Differentiable programming techniques are widely used in the community and are responsible for the machine learning renaissance of the past several decades. While these methods are powerful, they have limits. In this short report, we discuss a common chaos based failure mode which appears in a variety of differentiable circumstances, ranging from recurrent neural networks and numerical physics simulation to training learned optimizers. We trace this failure to the spectrum of the Jacobian of the system under study, and provide criteria for when a practitioner might expect this failure to spoil their differentiation based optimization algorithms.

Our result is tight up to negligible terms when d n, and is the first to imply asymptotic consistency of noisy minimum-norm interpolation for isotropic features and sparse ground truths. Our work complements the literature on "benign overfitting" for minimum l

We present the PowerGridworld software package to provide users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). Although many frameworks exist for training multi-agent RL (MARL) policies, none can rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning MARL policies using both OpenAI's multi-agent deep deterministic policy gradient (MADDPG) and RLLib's proximal policy optimization (PPO) algorithms. In both cases, at least some subset of agents incorporates elements of the power flow solution at each time step as part of their reward (negative cost) structures.

Sustainable consumption aims to minimize the environmental and societal impact of the use of services and products. Over-consumption of services and products leads to potential natural resource exhaustion and societal inequalities, as access to goods and services becomes more challenging. In everyday life, a person can simply achieve more sustainable purchases by drastically changing their lifestyle choices and potentially going against their personal values or wishes. Conversely, achieving sustainable consumption while accounting for personal values is a more complex task, as potential trade-offs arise when trying to satisfy environmental and personal goals. This article focuses on value-sensitive design of recommender systems, which enable consumers to improve the sustainability of their purchases while respecting their personal values. Value-sensitive recommendations for sustainable consumption are formalized as a multi-objective optimization problem, where each objective represents different sustainability goals and personal values. Novel and existing multi-objective algorithms calculate solutions to this problem. The solutions are proposed as personalized sustainable basket recommendations to consumers. These recommendations are evaluated on a synthetic dataset, which comprises three established real-world datasets from relevant scientific and organizational reports. The synthetic dataset contains quantitative data on product prices, nutritional values and environmental impact metrics, such as greenhouse gas emissions and water footprint. The recommended baskets are highly similar to consumer purchased baskets and aligned with both sustainability goals and personal values relevant to health, expenditure and taste. Even when consumers would accept only a fraction of recommendations, a considerable reduction of environmental impact is observed.

Series expansions have been a cornerstone of applied mathematics and engineering for centuries. In this paper, we revisit the Taylor series expansion from a modern Machine Learning perspective. Specifically, we introduce the Fast Continuous Convolutional Taylor Transform (FC2T2), a variant of the Fast Multipole Method (FMM), that allows for the efficient approximation of low dimensional convolutional operators in continuous space. We build upon the FMM which is an approximate algorithm that reduces the computational complexity of N-body problems from O(NM) to O(N+M) and finds application in e.g. particle simulations. As an intermediary step, the FMM produces a series expansion for every cell on a grid and we introduce algorithms that act directly upon this representation. These algorithms analytically but approximately compute the quantities required for the forward and backward pass of the backpropagation algorithm and can therefore be employed as (implicit) layers in Neural Networks. Specifically, we introduce a root-implicit layer that outputs surface normals and object distances as well as an integral-implicit layer that outputs a rendering of a radiance field given a 3D pose. In the context of Machine Learning, $N$ and $M$ can be understood as the number of model parameters and model evaluations respectively which entails that, for applications that require repeated function evaluations which are prevalent in Computer Vision and Graphics, unlike regular Neural Networks, the techniques introduce in this paper scale gracefully with parameters. For some applications, this results in a 200x reduction in FLOPs compared to state-of-the-art approaches at a reasonable or non-existent loss in accuracy.

WIRE)--Imtiaz Adam joins Marktechpost as an Advisory Board Member. Imtiaz Adam (MBA, MSc) is a leading AI influencer and hybrid Data Science and business strategy specialist. Imtiaz is the founder of an AI startup, Deep Learn Strategies Limited (DLS). Imtiaz has been a speaker at major events such as during the WEF at Davos where he spoke at a panel on AI. He is a Sloan Fellow in Strategy from London Business School with an EMBA exchange at Columbia Business School.

The growth in solar photovoltaic systems (solar PV) capacity globally has been near exponential over the past 20 years. Solar PV is expected to be the fastest growing renewable energy source in the US until 2050. The ever increasing efficiency of solar panel technology, combined with improvements in manufacturing, installation, and maintenance mean that this vital renewable power resource is set to become a major component in our energy infrastructure. However, challenges remain, particular when it comes to overseeing and fixing faults across thousands of enormous solar PV farms. Machine learning for computer vision may be providing some of the answers to these problems by enabling automated, fault finding applications for solar farms.

Artificial intelligence will be important at every level of retail. When I talk to retailers about artificial intelligence, their eyes glaze over, like I'm speaking a foreign language and very few people want to talk about it. AI is going to pervade almost every aspect of retail, big and small. Here's a case in point: The EPA estimates that a supermarket of 50,000 square feet, that's a large store but not excessively so, uses about $200,000 worth of electricity and natural gas in the course of a year. According to the EPA, about half of that cost is in refrigeration and lighting.