Adhesive joints are increasingly used in industry for a wide variety of applications because of their favorable characteristics such as high strength-to-weight ratio, design flexibility, limited stress concentrations, planar force transfer, good damage tolerance, and fatigue resistance. Finding the optimal process parameters for an adhesive bonding process is challenging: the optimization is inherently multi-objective (aiming to maximize break strength while minimizing cost), constrained (the process should not result in any visual damage to the materials, and stress tests should not result in failures that are adhesion-related), and uncertain (testing the same process parameters several times may lead to different break strengths). Real-life physical experiments in the lab are expensive to perform. Traditional evolutionary approaches (such as genetic algorithms) are then ill-suited to solve the problem, due to the prohibitive amount of experiments required for evaluation. Although Bayesian optimization-based algorithms are preferred to solve such expensive problems, few methods consider the optimization of more than one (noisy) objective and several constraints at the same time. In this research, we successfully applied specific machine learning techniques (Gaussian Process Regression) to emulate the objective and constraint functions based on a limited amount of experimental data. The techniques are embedded in a Bayesian optimization algorithm, which succeeds in detecting Pareto-optimal process settings in a highly efficient way (i.e., requiring a limited number of physical experiments).

Microorganisms such as algae and bacteria move in a viscous environment with extremely low Reynolds ($Re$), where the viscous drag dominates the inertial forces. They have adapted to this environment by developing specialized features such as whole-body deformations and flexible structures such as flagella (with various shapes, sizes, and numbers) that break the symmetry during the motion. In this study, we hypothesize that the changes in the flexibility of the flagella during a cycle of movement impact locomotion dynamics of flagellated locomotion. To test our hypothesis, we developed an autonomous, self-propelled robot with four flexible, multi-segmented flagella actuated together by a single DC motor. The stiffness of the flagella during the locomotion is controlled via a cable-driven mechanism attached to the center of the robot. Experimental assessments of the robot's swimming demonstrate that increasing the flexibility of the flagella during recovery stroke and reducing the flexibility during power stroke improves the swimming performance of the robot. Our results give insight into how these microorganisms manipulate their biological features to propel themselves in low viscous media and are of great interest to biomedical and research applications.

Camera-based tactile sensors have shown great promise in enhancing a robot's ability to perform a variety of dexterous manipulation tasks. Advantages of their use can be attributed to the high resolution tactile data and 3D depth map reconstructions they can provide. Unfortunately, many of these tactile sensors use either a flat sensing surface, sense on only one side of the sensor's body, or have a bulky form-factor, making it difficult to integrate the sensors with a variety of robotic grippers. Of the camera-based sensors that do have all-around, curved sensing surfaces, many cannot provide 3D depth maps; those that do often require optical designs specified to a particular sensor geometry. In this work, we introduce GelSight360, a fingertip-like, omnidirectional, camera-based tactile sensor capable of producing depth maps of objects deforming the sensor's surface. In addition, we introduce a novel cross-LED lighting scheme that can be implemented in different all-around sensor geometries and sizes, allowing the sensor to easily be reconfigured and attached to different grippers of varying DOFs. With this work, we enable roboticists to quickly and easily customize high resolution tactile sensors to fit their robotic system's needs.

Crops are constantly challenged by different environmental conditions. Seed treatment by nanomaterials is a cost-effective and environmentally-friendly solution for environmental stress mitigation in crop plants. Here, 56 seed nanopriming treatments are used to alleviate environmental stresses in maize. Seven selected nanopriming treatments significantly increase the stress resistance index (SRI) by 13.9% and 12.6% under salinity stress and combined heat-drought stress, respectively. Metabolomics data reveals that ZnO nanopriming treatment, with the highest SRI value, mainly regulates the pathways of amino acid metabolism, secondary metabolite synthesis, carbohydrate metabolism, and translation. Understanding the mechanism of seed nanopriming is still difficult due to the variety of nanomaterials and the complexity of interactions between nanomaterials and plants. Using the nanopriming data, we present an interpretable structure-activity relationship (ISAR) approach based on interpretable machine learning for predicting and understanding its stress mitigation effects. The post hoc and model-based interpretation approaches of machine learning are combined to provide complementary benefits and give researchers or policymakers more illuminating or trustworthy results. The concentration, size, and zeta potential of nanoparticles are identified as dominant factors for correlating root dry weight under salinity stress, and their effects and interactions are explained. Additionally, a web-based interactive tool is developed for offering prediction-level interpretation and gathering more details about specific nanopriming treatments. This work offers a promising framework for accelerating the agricultural applications of nanomaterials and may profoundly contribute to nanosafety assessment.

In a Bayesian framework, we give a principled account of how domain(cid:173) specific prior knowledge such as imperfect analytic domain theories can be optimally incorporated into networks of locally-tuned units: by choosing a specific architecture and by applying a specific training regimen. Our method proved successful in overcoming the data deficiency problem in a large-scale application to devise a neural control for a hot line rolling mill. It achieves in this application significantly higher accuracy than optimally-tuned standard algorithms such as sigmoidal backpropagation, and outperforms the state-of-the-art solution.

Model Predictive Control (MPC), a control algorithm which uses an optimizer to solve for the optimal control moves over a future time horizon based upon a model of the process, has become a stan(cid:173) dard control technique in the process industries over the past two decades. In most industrial applications, a linear dynamic model developed using empirical data is used even though the process it(cid:173) self is often nonlinear. Linear models have been used because of the difficulty in developing a generic nonlinear model from empirical data and the computational expense often involved in using non(cid:173) linear models. In this paper, we present a generic neural network based technique for developing nonlinear dynamic models from em(cid:173) pirical data and show that these models can be efficiently used in a model predictive control framework. This nonlinear MPC based approach has been successfully implemented in a number of indus(cid:173) trial applications in the refining, petrochemical, paper and food industries.

Prediction of chemical shift in NMR using machine learning methods is typically done with the maximum amount of data available to achieve the best results. In some cases, such large amounts of data are not available, e.g. for heteronuclei. We demonstrate a novel machine learning model which is able to achieve good results with comparatively low amounts of data. We show this by predicting 19F and 13C NMR chemical shifts of small molecules in specific solvents.

Wood Mackenzie are the global research, analytics, and consultancy business powering the natural resources industry. For 50 years, we have been providing the quality data, analytics, and insights our customers rely on to inspire their decision making. Our dedicated oil, gas & LNG, power & renewables, chemicals, metals & mining sector teams are located around the world and deliver a variety of projects based on our assessment and valuation of thousands of individual assets, companies, and economic indicators such as market supply, demand, and price trends. We have over 1,900 employees in 30 locations, serving customers in nearly 80 countries. Together, we inspire and innovate the markets we serve – providing invaluable intelligence to help our customers overcome the toughest challenges, and make strategic decisions that will, ultimately, accelerate the world's transition to a more sustainable future.

The chemical space for designing materials is practically infinite. This makes disruptive progress by traditional physics-based modeling alone challenging. Yet, training data for identifying composition–structure–property relations by artificial intelligence are sparse. We discuss opportunities to discover new chemically complex materials by hybrid methods where physics laws are combined with artificial intelligence. Machine learning models have been widely applied to boost the computational efficiency of searching vast chemical space of compositionally complex materials. This Perspective summarizes the recent developments and proposes future opportunities, such as the physics-informed machine learning models.

End-to-end relation extraction (E2ERE) is an important task in information extraction, more so for biomedicine as scientific literature continues to grow exponentially. E2ERE typically involves identifying entities (or named entity recognition (NER)) and associated relations, while most RE tasks simply assume that the entities are provided upfront and end up performing relation classification. E2ERE is inherently more difficult than RE alone given the potential snowball effect of errors from NER leading to more errors in RE. A complex dataset in biomedical E2ERE is the ChemProt dataset (BioCreative VI, 2017) that identifies relations between chemical compounds and genes/proteins in scientific literature. ChemProt is included in all recent biomedical natural language processing benchmarks including BLUE, BLURB, and BigBio. However, its treatment in these benchmarks and in other separate efforts is typically not end-to-end, with few exceptions. In this effort, we employ a span-based pipeline approach to produce a new state-of-the-art E2ERE performance on the ChemProt dataset, resulting in $> 4\%$ improvement in F1-score over the prior best effort. Our results indicate that a straightforward fine-grained tokenization scheme helps span-based approaches excel in E2ERE, especially with regards to handling complex named entities. Our error analysis also identifies a few key failure modes in E2ERE for ChemProt.