Large-scale detectors consisting of a liquid scintillator target surrounded by an array of photo-multiplier tubes (PMTs) are widely used in the modern neutrino experiments: Borexino, KamLAND, Daya Bay, Double Chooz, RENO, and the upcoming JUNO with its satellite detector TAO. Such apparatuses are able to measure neutrino energy which can be derived from the amount of light and its spatial and temporal distribution over PMT channels. However, achieving a fine energy resolution in large-scale detectors is challenging. In this work, we present machine learning methods for energy reconstruction in the JUNO detector, the most advanced of its type. We focus on positron events in the energy range of 0-10 MeV which corresponds to the main signal in JUNO -- neutrinos originated from nuclear reactor cores and detected via the inverse beta decay channel. We consider the following models: Boosted Decision Trees and Fully Connected Deep Neural Network, trained on aggregated features, calculated using the information collected by PMTs. We describe the details of our feature engineering procedure and show that machine learning models can provide the energy resolution $\sigma = 3\%$ at 1 MeV using subsets of engineered features. The dataset for model training and testing is generated by the Monte Carlo method with the official JUNO software.

Authors in (Rajapaksha and The growth in the deployment of Internet of Things (IoT) Bergmeir 2022) focused on providing rule based explanations sensors across different industries has opened several opportunities for a particular forecast, considering the global forecasting for the economy. One of them is the collection of IoT model as a black-box model trained across multivariate data that companies can use to build smarter solutions.

In the mobile-edge-cloud continuum, a plethora of heterogeneous data sources and computation-capable nodes are available. Such nodes can cooperate to perform a distributed learning task, aided by a learning controller (often located at the network edge). The controller is required to make decisions concerning (i) data selection, i.e., which data sources to use; (ii) model selection, i.e., which machine learning model to adopt, and (iii) matching between the layers of the model and the available physical nodes. All these decisions influence each other, to a significant extent and often in counter-intuitive ways. In this paper, we formulate a problem addressing all of the above aspects and present a solution concept called RightTrain, aiming at making the aforementioned decisions in a joint manner, minimizing energy consumption subject to learning quality and latency constraints. RightTrain leverages an expanded-graph representation of the system and a delay-aware Steiner tree to obtain a provably near-optimal solution while keeping the time complexity low. Specifically, it runs in polynomial time and its decisions exhibit a competitive ratio of $2(1+\epsilon)$, outperforming state-of-the-art solutions by over 50%. Our approach is also validated through a real-world implementation.

Modern power systems are experiencing the challenge of high uncertainty with the increasing penetration of renewable energy resources and the electrification of heating systems. In this paradigm shift, understanding electricity users' demand is of utmost value to retailers, aggregators, and policymakers. However, behind-the-meter (BTM) equipment and appliances at the household level are unknown to the other stakeholders mainly due to privacy concerns and tight regulations. In this paper, we seek to identify residential consumers based on their BTM equipment, mainly rooftop photovoltaic (PV) systems and electric heating, using imported/purchased energy data from utility meters. To solve this problem with an interpretable, fast, secure, and maintainable solution, we propose an integrated method called Interpretable Refined Motifs And binary Classification (IRMAC). The proposed method comprises a novel shape-based pattern extraction technique, called Refined Motif (RM) discovery, and a single-neuron classifier. The first part extracts a sub-pattern from the long time series considering the frequency of occurrences, average dissimilarity, and time dynamics while emphasising specific times with annotated distances. The second part identifies users' types with linear complexity while preserving the transparency of the algorithms. With the real data from Australia and Denmark, the proposed method is tested and verified in identifying PV owners and electrical heating system users.

Physical reservoir computing is a computational framework that implements spatiotemporal information processing directly within physical systems. By exciting nonlinear dynamical systems and creating linear models from their state, we can create highly energy-efficient devices capable of solving machine learning tasks without building a modular system consisting of millions of neurons interconnected by synapses. To act as an effective reservoir, the chosen dynamical system must have two desirable properties: nonlinearity and memory. We present task agnostic spatial measures to locally measure both of these properties and exemplify them for a specific physical reservoir based upon magnetic skyrmion textures. In contrast to typical reservoir computing metrics, these metrics can be resolved spatially and in parallel from a single input signal, allowing for efficient parameter search to design efficient and high-performance reservoirs. Additionally, we show the natural trade-off between memory capacity and nonlinearity in our reservoir's behaviour, both locally and globally. Finally, by balancing the memory and nonlinearity in a reservoir, we can improve its performance for specific tasks.

The computer chip shortage has prompted Dr Geert van Kollenburg and his colleagues at Eindhoven University of Technology, the Netherlands, to find data-driven methods to optimise chip manufacturing processes. As part of the MadeIn4 project, they have developed a predictive discarding framework in which quality predictions from artificial intelligence (AI) algorithms are used to decide on whether to discard an unfinished product. This approach can improve both the profitability and sustainability of manufacturing processes. In line with Industry 5.0 goals, predictive discarding offers a way for humans and AI to work together to achieve sustainable manufacturing. Our digital society relies on computer chips, but these chips are currently in short supply.

Mapping and exploration of a Martian terrain with an aerial vehicle has become an emerging research direction, since the successful flight demonstration of the Mars helicopter Ingenuity. Although the autonomy and navigation capability of the state of the art Mars helicopter has proven to be efficient in an open environment, the next area of interest for exploration on Mars are caves or ancient lava tube like environments, especially towards the never-ending search of life on other planets. This article presents an autonomous exploration mission based on a modified frontier approach along with a risk aware planning and integrated collision avoidance scheme with a special focus on energy aspects of a custom designed Mars Coaxial Quadrotor (MCQ) in a Martian simulated lava tube. One of the biggest novelties of the article stems from addressing the exploration capability, while rapidly exploring in local areas and intelligently global re-positioning of the MCQ when reaching dead ends in order to to efficiently use the battery based consumed energy, while increasing the volume of the exploration. The proposed novel algorithm for the Martian exploration is able to select the next way point of interest, such that the MCQ keeps its heading towards the local exploration direction where it will find maximum information about the surroundings. The proposed three layer cost based global re-position point selection assists in rapidly redirecting the MCQ to previously partially seen areas that could lead to more unexplored part of the lava tube. The Martian fully simulated mission presented in this article takes into consideration the fidelity of physics of Mars condition in terms of thin atmosphere, low surface pressure and low gravity of the planet, while proves the efficiency of the proposed scheme in exploring an area that is particularly challenging due to the subterranean-like environment. The proposed exploration-planning framework is also validated in simulation by comparing it against the graph based exploration planner. Intensive simulations with true Mars conditions are carried out in order to validate and benchmark our approach in a utmost realistic Mars lava tube exploration scenario using a Mars Coaxial Quadrotor.

Nowadays, it is broadly recognized in the power system community that to meet the ever expanding energy sector's needs, it is no longer possible to rely solely on physics-based models and that reliable, timely and sustainable operation of energy systems is impossible without systematic integration of artificial intelligence (AI) tools. Nevertheless, the adoption of AI in power systems is still limited, while integration of AI particularly into distribution grid investment planning is still an uncharted territory. We make the first step forward to bridge this gap by showing how graph convolutional networks coupled with the hyperstructures representation learning framework can be employed for accurate, reliable, and computationally efficient distribution grid planning with resilience objectives. We further propose a Hyperstructures Graph Convolutional Neural Networks (Hyper-GCNNs) to capture hidden higher order representations of distribution networks with attention mechanism. Our numerical experiments show that the proposed Hyper-GCNNs approach yields substantial gains in computational efficiency compared to the prevailing methodology in distribution grid planning and also noticeably outperforms seven state-of-the-art models from deep learning (DL) community.

Influenced by the advances in data and computing, the scientific practice increasingly involves machine learning and artificial intelligence driven methods which requires specialized capabilities at the system-, science- and service-level in addition to the conventional large-capacity supercomputing approaches. The latest distributed architectures built around the composability of data-centric applications led to the emergence of a new ecosystem for container coordination and integration. However, there is still a divide between the application development pipelines of existing supercomputing environments, and these new dynamic environments that disaggregate fluid resource pools through accessible, portable and re-programmable interfaces. New approaches for dynamic composability of heterogeneous systems are needed to further advance the data-driven scientific practice for the purpose of more efficient computing and usable tools for specific scientific domains. In this paper, we present a novel approach for using composable systems in the intersection between scientific computing, artificial intelligence (AI), and remote sensing domain. We describe the architecture of a first working example of a composable infrastructure that federates Expanse, an NSF-funded supercomputer, with Nautilus, a Kubernetes-based GPU geo-distributed cluster. We also summarize a case study in wildfire modeling, that demonstrates the application of this new infrastructure in scientific workflows: a composed system that bridges the insights from edge sensing, AI and computing capabilities with a physics-driven simulation.

As one of Ireland's leading renewable energy developers and suppliers of green electricity, Energia Group proudly employs numerous scientists working across various fields, from marine biology to data science. Ahead of Science Week, which runs from the 13th to the 20th of November, Energia Group is celebrating the infinite possibilities and the role of science in the energy sector and how that contributes to Ireland's climate goals. Neil Mc Caul, Gregory Balogh and Anchit Bhagat are working together on an innovative artificial intelligence solution that can support energy traders in the decisions they make. Neil Mc Caul, Energy Trading Development Manager with Energia Group has more than 15 years energy trading experience. He has seen first-hand how the rapid increase in digitalization plus the added complexity of many additional energy sources such as solar, increased levels of wind (both onshore & offshore) and battery storage has changed the energy trading industry.