Machine learning (ML)-based solutions are rapidly changing the landscape of many fields, including structural engineering. Despite their promising performance, these approaches are usually only demonstrated as proof-of-concept in structural engineering, and are rarely deployed for real-world applications. This paper aims to illustrate the challenges of developing ML models suitable for deployment through two illustrative examples. Among various pitfalls, the presented discussion focuses on model overfitting and underspecification, training data representativeness, variable omission bias, and cross-validation.

Common crops, like wheat or maize, could be genetically altered to be brightly coloured to make it easier for weeding robots to do their job, suggest researchers. Weeding reduces the need for herbicides, but the artificial intelligence models that power weeding robots can struggle to differentiate between crops and weeds that are a similar shape and colour. To get round this problem, Pedro Correia at the University of Copenhagen in Denmark and his colleagues have suggested that crop genomes could be adapted to express pigments such as anthocyanins, which make blueberries blue, or carotenoids, which make carrots orange. Crops could also be grown to have unusually shaped leaves or to have characteristics that are invisible to the naked eye but detectable by sensors, such as in the infrared spectrum, they say. Correia says AI's struggles with weeding could be exacerbated as wild species are adapted for agriculture to capitalise on their abilities to cope with a changing climate.

Quantum chemical simulations can be greatly accelerated by constructing machine learning potentials, which is often done using active learning (AL). The usefulness of the constructed potentials is often limited by the high effort required and their insufficient robustness in the simulations. Here we introduce the end-to-end AL for constructing robust data-efficient potentials with affordable investment of time and resources and minimum human interference. Our AL protocol is based on the physics-informed sampling of training points, automatic selection of initial data, uncertainty quantification, and convergence monitoring. The versatility of this protocol is shown in our implementation of quasi-classical molecular dynamics for simulating vibrational spectra, conformer search of a key biochemical molecule, and timeresolved mechanism of the Diels-Alder reactions. These investigations took us days instead of weeks of pure quantum chemical calculations on a high-performance computing cluster. Introduction The introduction of machine learning potentials (MLPs) pushed the boundaries of what was previously possible in molecular dynamics (MD). MLPs enable simulations of longer time scales and larger systems with higher accuracy.

Molecular relaxation, finding the equilibrium state of a non-equilibrium structure, is an essential component of computational chemistry to understand reactivity. Classical force field methods often rely on insufficient local energy minimization, while neural network force field models require large labeled datasets encompassing both equilibrium and non-equilibrium structures. As a remedy, we propose MoreRed, molecular relaxation by reverse diffusion, a conceptually novel and purely statistical approach where non-equilibrium structures are treated as noisy instances of their corresponding equilibrium states. To enable the denoising of arbitrarily noisy inputs via a generative diffusion model, we further introduce a novel diffusion time step predictor. Notably, MoreRed learns a simpler pseudo potential energy surface instead of the complex physical potential energy surface. It is trained on a significantly smaller, and thus computationally cheaper, dataset consisting of solely unlabeled equilibrium structures, avoiding the computation of non-equilibrium structures altogether. We compare MoreRed to classical force fields, equivariant neural network force fields trained on a large dataset of equilibrium and non-equilibrium data, as well as a semi-empirical tight-binding model. To assess this quantitatively, we evaluate the root-mean-square deviation between the found equilibrium structures and the reference equilibrium structures as well as their DFT energies.

In April 2021 Stava bridge, a main bridge on E6 in Norway, was abruptly closed for traffic. A structural defect had seriously compromised the bridge structural integrity. The Norwegian Public Roads Administration (NPRA) closed it, made a temporary solution and reopened with severe traffic restrictions. The incident was alerted through what constitutes the bridge Digital Twin processing data from Internet of Things sensors. The solution was crucial in online and offline diagnostics, the case demonstrating the value of technologies to tackle emerging dangerous situations as well as acting preventively. A critical and rapidly developing damage was detected in time to stop the development, but not in time to avoid the incident altogether. The paper puts risk in a broader perspective for an organization responsible for highway infrastructure. It positions online monitoring and Digital Twins in the context of Risk- and Condition-Based Maintenance. The situation that arose at Stava bridge, and how it was detected, analyzed, and diagnosed during virtual inspection, is described. The case demonstrates how combining physics-based methods with Machine Learning can facilitate damage detection and diagnostics. A summary of lessons learnt, both from technical and organizational perspectives, as well as plans of future work, is presented.

Large Language Models (LLMs) such as BERT [6] (Bidirectional Encoder Representations from Transformers) by Devlin et al. and GPT [11] (Generative Pre-trained Transformer) by Radford et al., have revolutionized the field of Natural Language Processing (NLP) with their exceptional capabilities, setting new standards in performance across various tasks. Due to their superb generative capability, LLMs are widely deployed as the backend for various real-world applications, referred to as LLM-Integrated Applications. For instance, Microsoft utilizes GPT-4 as the service backend for the new Bing Search [1]; OpenAI has developed various applications--such as ChatWithPDF and AskTheCode--that utilize GPT-4 for different tasks such as text processing, code interpretation, and product recommendation [2, 3]; Google deploys the search engine Bard, powered by PaLM 2. In general, to accomplish a task, an LLM-Integrated Application requires an instruction prompt, which aims to instruct the backend LLM to perform the task, and a data prompt, which is the data to be processed by the LLM in the task. The instruction prompt can be provided by a user or the LLM-Integrated Application itself; and the data prompt is often obtained from external resources such as emails and webpages on the Internet. An LLM-Integrated Application queries the backend LLM using the instruction prompt and data prompt to accomplish the task and returns the response from the LLM to the user. Recently, several types of vulnerabilities have been identified in LLMs to deceive models or mislead users. Among these, prompt injection attacks and jailbreak attacks stand out as prevalent vulnerabilities.

The rapid growth of the Industry 4.0 paradigm is increasing the pressure to develop effective automated monitoring systems. Artificial Intelligence (AI) is a convenient tool to improve the efficiency of industrial processes while reducing errors and waste. In fact, it allows the use of real-time data to increase the effectiveness of monitoring systems, minimize errors, make the production process more sustainable, and save costs. In this paper, a novel automatic monitoring system is proposed in the context of production process of plastic consumables used in analysis laboratories, with the aim to increase the effectiveness of the control process currently performed by a human operator. In particular, we considered the problem of classifying the presence or absence of a transparent anticoagulant substance inside test tubes. Specifically, a hand-designed deep network model is used and compared with some state-of-the-art models for its ability to categorize different images of vials that can be either filled with the anticoagulant or empty. Collected results indicate that the proposed approach is competitive with state-of-the-art models in terms of accuracy. Furthermore, we increased the complexity of the task by training the models on the ability to discriminate not only the presence or absence of the anticoagulant inside the vial, but also the size of the test tube. The analysis performed in the latter scenario confirms the competitiveness of our approach. Moreover, our model is remarkably superior in terms of its generalization ability and requires significantly fewer resources. These results suggest the possibility of successfully implementing such a model in the production process of a plastic consumables company.

Bayesian optimization has been successfully applied throughout Chemical Engineering for the optimization of functions that are expensive-to-evaluate, or where gradients are not easily obtainable. However, domain experts often possess valuable physical insights that are overlooked in fully automated decision-making approaches, necessitating the inclusion of human input. In this article we re-introduce the human back into the data-driven decision making loop by outlining an approach for collaborative Bayesian optimization. Our methodology exploits the hypothesis that humans are more efficient at making discrete choices rather than continuous ones and enables experts to influence critical early decisions. We apply high-throughput (batch) Bayesian optimization alongside discrete decision theory to enable domain experts to influence the selection of experiments. At every iteration we apply a multi-objective approach that results in a set of alternate solutions that have both high utility and are reasonably distinct. The expert then selects the desired solution for evaluation from this set, allowing for the inclusion of expert knowledge and improving accountability, whilst maintaining the advantages of Bayesian optimization. We demonstrate our approach across a number of applied and numerical case studies including bioprocess optimization and reactor geometry design, demonstrating that even in the case of an uninformed practitioner our algorithm recovers the regret of standard Bayesian optimization. Through the inclusion of continuous expert opinion, our approach enables faster convergence, and improved accountability for Bayesian optimization in engineering systems.

Abstract--Through the implementation of reconfigurability to achieve flexibility and adaptation to tasks by morphology changes rather than by increasing the number of joints, malleable robots present advantages over traditional serial robot arms in regards to reduced weight, size, and cost. While limited in degrees of freedom (DOF), malleable robots still provide versatility across operations typically served by systems using higher DOF than required by the tasks. In this paper, we present the creation of a 2-DOF malleable robot, detailing the design of joints and malleable link, along with its modelling through forward and inverse kinematics, and a reconfiguration methodology that informs morphology changes based on end effector location-- determining how the user should reshape the robot to enable a task previously unattainable. The recalibration and motion planning for making robot motion possible after reconfiguration are also discussed, and thorough experiments with the prototype to evaluate accuracy and reliability of the system are presented. ECONFIGURABLE robot systems provide several key potential advantages over traditional robots, including of the robot (such as locomotion), albeit with a decrease in increased task versatility by adapting to better suit tasks, the performance for a specific task compared to a specialised and reduced robot cost due to a smaller total number of robot. While the majority of reconfigurable robots are modular, modules, such as links and joints. As such, there has been reconfiguration can also be achieved by locking aspects of significant research into the development of reconfigurable the robot. Examples include directly locking revolute joints to robots, with the most popular approach utilising modularity reduce the DOF of the robot [11], and locking passive cylindrical as the method of reconfiguration, as this allows for the joints carefully positioned to directly vary the Denavit-interchangeability of parts, leading to self-repair [1], [2].

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose $200+$ concrete research questions.