Building loads consume roughly 40% of the energy produced in developed countries, a significant part of which is invested towards building temperature-control infrastructure. Therein, renewable resource-based microgrids offer a greener and cheaper alternative. This communication explores the possible co-design of microgrid power dispatch and building HVAC (heating, ventilation and air conditioning system) actuations with the objective of effective temperature control under minimised operating cost. For this, we attempt control designs with various levels of abstractions based on information available about microgrid and HVAC system models using the Deep Reinforcement Learning (DRL) technique. We provide control architectures that consider model information ranging from completely determined system models to systems with fully unknown parameter settings and illustrate the advantages of DRL for the design prescriptions.

Kim Custeau, senior vice president of asset performance management and manufacturing execution systems at AVEVA, explains why performance intelligence will be critical in a post-pandemic industrial world that demands organisations develop a high level of agility, sustainability and resilience. Why is performance intelligence a critical focus today? The global big data and analytics market is growing at lightening pace and projected to be worth $274 billion by 2022. Staying ahead of the curve requires a new understanding of the scope and scale of industrial information to leverage that data effectively. Insight into industrial information from edge to enterprise reduces downtime, production costs and energy consumption, allowing organisations to optimise resources and drive sustainability.

Probabilistic graphical models are a fundamental tool in probabilistic modeling, machine learning and artificial intelligence. They allow us to integrate in a natural way expert knowledge, physical modeling, heterogeneous and correlated data and quantities of interest. For exactly this reason, multiple sources of model uncertainty are inherent within the modular structure of the graphical model. In this paper we develop information-theoretic, robust uncertainty quantification methods and non-parametric stress tests for directed graphical models to assess the effect and the propagation through the graph of multi-sourced model uncertainties to quantities of interest. These methods allow us to rank the different sources of uncertainty and correct the graphical model by targeting its most impactful components with respect to the quantities of interest. Thus, from a machine learning perspective, we provide a mathematically rigorous approach to correctability that guarantees a systematic selection for improvement of components of a graphical model while controlling potential new errors created in the process in other parts of the model. We demonstrate our methods in two physico-chemical examples, namely quantum scale-informed chemical kinetics and materials screening to improve the efficiency of fuel cells.

Skoltech researchers and their colleagues from the U.S. and Singapore have created a neural network that can help tweak semiconductor crystals in a controlled fashion to achieve superior properties for electronics. This enables a new direction of development of next-generation chips and solar cells by exploiting a controllable deformation that may change the properties of a material on the fly. The paper was published in the journal npj Computational Materials. Materials at the nanoscale can withstand major deformation. In what's called the strained state, they can exhibit remarkable optical, thermal, electronic, and other properties due to a change in interatomic distances.

Scientists hunting for elusive gravitational waves across the universe may be able to supercharge their discoveries with a new tool: artificial intelligence. Gravitational waves are ripples in spacetime, created when a massive object is accelerated or disturbed, such as when a black hole and a neutron star collide. Theorized by Albert Einstein, their existence was confirmed in 2015 with the first gravitational wave discovery by researchers using LIGO (the advanced Laser Interferometer Gravitational-Wave Observatory). Now, just six years later, there have been at least 50 gravitational wave events detected. However, while scientists continue to detect gravitational waves, some think that, by using artificial intelligence (AI), researchers could spot these signals much faster and, therefore, more often.

ABS has issued New Technology Qualification (NTQ) to SBM Offshore's artificial intelligence (AI) powered Intelligent Agent Mooring Line Integrity Tool, allowing the technology to be integrated into offshore systems for the first time. The novel tool collects data such as wind speed, FPSO heading, and GPS information and couples this with machine learning approaches to provide the asset owner with continuous feedback on the integrity of their mooring system. The tool has the ability to detect potential mooring line failure and location without reliance on a traditional tension monitoring system, thanks to the potential for deeper insight offered by AI techniques. "This technology enables the continuous monitoring of the integrity of mooring lines and has significant potential to advance safety in the offshore industry. This is just the latest example of how ABS is supporting the application of advanced technology to drive forward safety outcomes in the marine and offshore industries. Our industry leadership in offshore, as well as smart and artificial intelligence applications at sea means we are uniquely placed to support SBM Offshore with the development of this tool," said Matt Tremblay, ABS Senior Vice President, Global Offshore.

I spent years, during my master's studies in engineering, trying to model energy systems. In most cases, only the simplest problems can be modelled directly (analytical resolution of the governing differential equations of the system studied), for particularly simple and convenient geometries and boundary conditions. More complex problems are tackled using various mathematical/numerical or procedural techniques to simplify their nature so that reasonably accurate, albeit approximate, calculation models can be developed. One of the most interesting aspects of my recent experience with the integration of Deep Learning and engineering in the broadest sense (structural analysis, fluid dynamics, energy systems…) is the possibility of approaching the problems studied in completely different ways. The abundance and complexity of data is no longer a problem, but an advantage, allowing more accurate and sophisticated forecasting models to be developed.

Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural network to obey safety constraints. Most existing safety-related methods only seek to verify that already-trained networks obey constraints, requiring alternating training and verification. Instead, this work proposes a constrained method to simultaneously train and verify a feedforward neural network with rectified linear unit (ReLU) nonlinearities. Constraints are enforced by computing the network's output-space reachable set and ensuring that it does not intersect with unsafe sets; training is achieved by formulating a novel collision-check loss function between the reachable set and unsafe portions of the output space. The reachable and unsafe sets are represented by constrained zonotopes, a convex polytope representation that enables differentiable collision checking. The proposed method is demonstrated successfully on a network with one nonlinearity layer and approximately 50 parameters.

Uncertainty quantification in Artificial Intelligence (AI)-based predictions of material properties is of immense importance for the success and reliability of AI applications in material science. While confidence intervals are commonly reported for machine learning (ML) models, prediction intervals, i.e., the evaluation of the uncertainty on each prediction, are seldomly available. In this work we compare 3 different approaches to obtain such individual uncertainty, testing them on 12 ML-physical properties. Specifically, we investigated using the Quantile loss function, machine learning the prediction intervals directly and using Gaussian Processes. We identify each approachs advantages and disadvantages and end up slightly favoring the modeling of the individual uncertainties directly, as it is the easiest to fit and, in most cases, minimizes over-and under-estimation of the predicted errors. All data for training and testing were taken from the publicly available JARVIS-DFT database, and the codes developed for computing the prediction intervals are available through JARVIS-Tools.

Labeled data is essential in modern systems that rely on Machine Learning (ML) for predictive modelling. Such systems may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even worse in imbalanced data scenarios. Online financial fraud detection is an example where labeling is: i) expensive, or ii) it suffers from long delays, if relying on victims filing complaints. The latter may not be viable if a model has to be in place immediately, so an option is to ask analysts to label events while minimizing the number of annotations to control costs. We propose an Active Learning (AL) annotation system for datasets with orders of magnitude of class imbalance, in a cold start streaming scenario. We present a computationally efficient Outlier-based Discriminative AL approach (ODAL) and design a novel 3-stage sequence of AL labeling policies where it is used as warm-up. Then, we perform empirical studies in four real world datasets, with various magnitudes of class imbalance. The results show that our method can more quickly reach a high performance model than standard AL policies. Its observed gains over random sampling can reach 80% and be competitive with policies with an unlimited annotation budget or additional historical data (with 1/10 to 1/50 of the labels).