In the era of big data, there has been a surge in the availability of data containing rich spatial and temporal information, offering valuable insights into dynamic systems and processes for applications such as weather forecasting, natural disaster management, intelligent transport systems, and precision agriculture. Graph neural networks (GNNs) have emerged as a powerful tool for modeling and understanding data with dependencies to each other such as spatial and temporal dependencies. There is a large amount of existing work that focuses on addressing the complex spatial and temporal dependencies in spatiotemporal data using GNNs. However, the strong interdisciplinary nature of spatiotemporal data has created numerous GNNs variants specifically designed for distinct application domains. Although the techniques are generally applicable across various domains, cross-referencing these methods remains essential yet challenging due to the absence of a comprehensive literature review on GNNs for spatiotemporal data. This article aims to provide a systematic and comprehensive overview of the technologies and applications of GNNs in the spatiotemporal domain. First, the ways of constructing graphs from spatiotemporal data are summarized to help domain experts understand how to generate graphs from various types of spatiotemporal data. Then, a systematic categorization and summary of existing spatiotemporal GNNs are presented to enable domain experts to identify suitable techniques and to support model developers in advancing their research. Moreover, a comprehensive overview of significant applications in the spatiotemporal domain is offered to introduce a broader range of applications to model developers and domain experts, assisting them in exploring potential research topics and enhancing the impact of their work. Finally, open challenges and future directions are discussed.

This paper proposes an anticipative transformer-based model for short-term solar irradiance forecasting. Given a sequence of sky images, our proposed vision transformer encodes features of consecutive images, feeding into a transformer decoder to predict irradiance values associated with future unseen sky images. We show that our model effectively learns to attend only to relevant features in images in order to forecast irradiance. Moreover, the proposed anticipative transformer captures long-range dependencies between sky images to achieve a forecasting skill of 21.45 % on a 15 minute ahead prediction for a newly introduced dataset of all-sky images when compared to a smart persistence model.

Technologies such as robotics, 3D printing and artificial intelligence are poised to reshape where we live in the coming years. Augmented reality could beam a'holographic' Gordon Ramsay into your kitchen, to offer cooking tips as you fire up the induction hob. Every surface in the home could be transformed into a touchscreen that operates different tasks, walls can turn into windows on demand and your house could double as a food-growing farm. Augmented reality could put a virtual chef in your kitchen, talking you through meal plans. Walls, floors and ceilings might be able to transform themselves in response to voice commands, with nanotechnology turning walls solid or translucent or into a giant TV screen.

Symbolic regression is a machine learning technique that can learn the governing formulas of data and thus has the potential to transform scientific discovery. However, symbolic regression is still limited in the complexity and dimensionality of the systems that it can analyze. Deep learning on the other hand has transformed machine learning in its ability to analyze extremely complex and high-dimensional datasets. We propose a neural network architecture to extend symbolic regression to parametric systems where some coefficient may vary but the structure of the underlying governing equation remains constant. We demonstrate our method on various analytic expressions, ODEs, and PDEs with varying coefficients and show that it extrapolates well outside of the training domain. The neural network-based architecture can also integrate with other deep learning architectures so that it can analyze high-dimensional data while being trained end-to-end. To this end we integrate our architecture with convolutional neural networks to analyze 1D images of varying spring systems.

In recent years, learning-based control in robotics has gained significant attention due to its capability to address complex tasks in real-world environments. With the advances in machine learning algorithms and computational capabilities, this approach is becoming increasingly important for solving challenging control problems in robotics by learning unknown or partially known robot dynamics. Active exploration, in which a robot directs itself to states that yield the highest information gain, is essential for efficient data collection and minimizing human supervision. Similarly, uncertainty-aware deployment has been a growing concern in robotic control, as uncertain actions informed by the learned model can lead to unstable motions or failure. However, active exploration and uncertainty-aware deployment have been studied independently, and there is limited literature that seamlessly integrates them. This paper presents a unified model-based reinforcement learning framework that bridges these two tasks in the robotics control domain. Our framework uses a probabilistic ensemble neural network for dynamics learning, allowing the quantification of epistemic uncertainty via Jensen-Renyi Divergence. The two opposing tasks of exploration and deployment are optimized through state-of-the-art sampling-based MPC, resulting in efficient collection of training data and successful avoidance of uncertain state-action spaces. We conduct experiments on both autonomous vehicles and wheeled robots, showing promising results for both exploration and deployment.

Electrical conductivity is of fundamental importance in electric arc furnaces (EAF) and the interaction of this phenomenon with the process slag results in energy losses and low optimization. As mathematical modeling helps in understanding the behavior of phenomena and it was used to predict the electrical conductivity of EAF slags through artificial neural networks. The best artificial neural network had 100 neurons in the hidden layer, with 6 predictor variables and the predicted variable, electrical conductivity. Mean absolute error and standard deviation of absolute error were calculated, and sensitivity analysis was performed to correlate the effect of each predictor variable with the predicted variable.

Digital technologies have dramatically accelerated the digital transformation in process industries, boosted new industrial applications, upgraded the production system, and enhanced operational efficiency. In contrast, the challenges and gaps between human and artificial intelligence (AI) have become more and more prominent, whereas the digital divide in process safety is aggregating. The study attempts to address the following questions: (i)What is AI in the process safety context? (ii)What is the difference between AI and humans in process safety? (iii)How do AI and humans collaborate in process safety? (iv)What are the challenges and gaps in human-AI collaboration? (v)How to quantify the risk of human-AI collaboration in process safety? Qualitative risk analysis based on brainstorming and literature review, and quantitative risk analysis based on layer of protection analysis (LOPA) and Bayesian network (BN), were applied to explore and model. The importance of human reliability should be stressed in the digital age, not usually to increase the reliability of AI, and human-centered AI design in process safety needs to be propagated.

In the realm of computational fluid dynamics (CFD), accurate prediction of aerodynamic behaviour plays a pivotal role in aerofoil design and optimization. This study proposes a novel approach that synergistically combines autoencoders and Generative Adversarial Networks (GANs) for the purpose of generating CFD results. Our innovative framework harnesses the intrinsic capabilities of autoencoders to encode aerofoil geometries into a compressed and informative 20-length vector representation. Subsequently, a conditional GAN network adeptly translates this vector into precise pressure-distribution plots, accounting for fixed wind velocity, angle of attack, and turbulence level specifications. The training process utilizes a meticulously curated dataset acquired from JavaFoil software, encompassing a comprehensive range of aerofoil geometries. The proposed approach exhibits profound potential in reducing the time and costs associated with aerodynamic prediction, enabling efficient evaluation of aerofoil performance. The findings contribute to the advancement of computational techniques in fluid dynamics and pave the way for enhanced design and optimization processes in aerodynamics.

The accurate prediction of the two-phase heat transfer coefficient (HTC) as a function of working fluids, channel geometries and process conditions is key to the optimal design and operation of compact heat exchangers. Advances in artificial intelligence research have recently boosted the application of machine learning (ML) algorithms to obtain data-driven surrogate models for the HTC. For most supervised learning algorithms, the task is that of a nonlinear regression problem. Despite the fact that these models have been proven capable of outperforming traditional empirical correlations, they have key limitations such as overfitting the data, the lack of uncertainty estimation, and interpretability of the results. To address these limitations, in this paper, we use a multi-output Gaussian process regression (GPR) to estimate the HTC in microchannels as a function of the mass flow rate, heat flux, system pressure and channel diameter and length. The model is trained using the Brunel Two-Phase Flow database of high-fidelity experimental data. The advantages of GPR are data efficiency, the small number of hyperparameters to be trained (typically of the same order of the number of input dimensions), and the automatic trade-off between data fit and model complexity guaranteed by the maximization of the marginal likelihood (Bayesian approach). Our paper proposes research directions to improve the performance of the GPR-based model in extrapolation.

Early detection of power outages is crucial for maintaining a reliable power distribution system. This research investigates the use of transfer learning and language models in detecting outages with limited labeled data. By leveraging pretraining and transfer learning, models can generalize to unseen classes. Using a curated balanced dataset of social media tweets related to power outages, we conducted experiments using zero-shot and few-shot learning. Our hypothesis is that Language Models pretrained with limited data could achieve high performance in outage detection tasks over baseline models. Results show that while classical models outperform zero-shot Language Models, few-shot fine-tuning significantly improves their performance. For example, with 10% fine-tuning, BERT achieves 81.3% accuracy (+15.3%), and GPT achieves 74.5% accuracy (+8.5%). This has practical implications for analyzing and localizing outages in scenarios with limited data availability. Our evaluation provides insights into the potential of few-shot fine-tuning with Language Models for power outage detection, highlighting their strengths and limitations. This research contributes to the knowledge base of leveraging advanced natural language processing techniques for managing critical infrastructure.