Ontologies are formal representations of knowledge in specific domains that provide a structured framework for organizing and understanding complex information. Creating ontologies, however, is a complex and time-consuming endeavor. ChEBI is a well-known ontology in the field of chemistry, which provides a comprehensive resource for defining chemical entities and their properties. However, it covers only a small fraction of the rapidly growing knowledge in chemistry and does not provide references to the scientific literature. To address this, we propose a methodology that involves augmenting existing annotated text corpora with knowledge from Chebi and fine-tuning a large language model (LLM) to recognize chemical entities and their roles in scientific text. Our experiments demonstrate the effectiveness of our approach. By combining ontological knowledge and the language understanding capabilities of LLMs, we achieve high precision and recall rates in identifying both the chemical entities and roles in scientific literature. Furthermore, we extract them from a set of 8,000 ChemRxiv articles, and apply a second LLM to create a knowledge graph (KG) of chemical entities and roles (CEAR), which provides complementary information to ChEBI, and can help to extend it.

Literature research, vital for scientific advancement, is overwhelmed by the vast ocean of available information. Addressing this, we propose an automated review generation method based on Large Language Models (LLMs) to streamline literature processing and reduce cognitive load. In case study on propane dehydrogenation (PDH) catalysts, our method swiftly generated comprehensive reviews from 343 articles, averaging seconds per article per LLM account. Extended analysis of 1041 articles provided deep insights into catalysts' composition, structure, and performance. Recognizing LLMs' hallucinations, we employed a multi-layered quality control strategy, ensuring our method's reliability and effective hallucination mitigation. Expert verification confirms the accuracy and citation integrity of generated reviews, demonstrating LLM hallucination risks reduced to below 0.5% with over 95% confidence. Released Windows application enables one-click review generation, aiding researchers in tracking advancements and recommending literature. This approach showcases LLMs' role in enhancing scientific research productivity and sets the stage for further exploration.

Using "soft" targets to improve model performance has been shown to be effective in classification settings, but the usage of soft targets for regression is a much less studied topic in machine learning. The existing literature on the usage of soft targets for regression fails to properly assess the method's limitations, and empirical evaluation is quite limited. In this work, we assess the strengths and drawbacks of existing methods when applied to molecular property regression tasks. Our assessment outlines key biases present in existing methods and proposes methods to address them, evaluated through careful ablation studies. We leverage these insights to propose Distributional Mixture of Experts (DMoE): A model-independent, and data-independent method for regression which trains a model to predict probability distributions of its targets. Our proposed loss function combines the cross entropy between predicted and target distributions and the L1 distance between their expected values to produce a loss function that is robust to the outlined biases. We evaluate the performance of DMoE on different molecular property prediction datasets -- Open Catalyst (OC20), MD17, and QM9 -- across different backbone model architectures -- SchNet, GemNet, and Graphormer. Our results demonstrate that the proposed method is a promising alternative to classical regression for molecular property prediction tasks, showing improvements over baselines on all datasets and architectures.

When objects are packed in a cluster, physical interactions are unavoidable. Such interactions emerge because of the objects geometric features; some of these features promote entanglement, while others create repulsion. When entanglement occurs, the cluster exhibits a global, complex behaviour, which arises from the stochastic interactions between objects. We hereby refer to such a cluster as an entangled granular metamaterial. We investigate the geometrical features of the objects which make up the cluster, henceforth referred to as grains, that maximise entanglement. We hypothesise that a cluster composed from grains with high propensity to tangle, will also show propensity to interact with a second cluster of tangled objects. To demonstrate this, we use the entangled granular metamaterials to perform complex robotic picking tasks, where conventional grippers struggle. We employ an electromagnet to attract the metamaterial (ferromagnetic) and drop it onto a second cluster of objects (targets, non-ferromagnetic). When the electromagnet is re-activated, the entanglement ensures that both the metamaterial and the targets are picked, with varying degrees of physical engagement that strongly depend on geometric features. Interestingly, although the metamaterials structural arrangement is random, it creates repeatable and consistent interactions with a second tangled media, enabling robust picking of the latter.

A spatiotemporal deep learning framework is proposed that is capable of 2D full-field prediction of fracture in concrete mesostructures. This framework not only predicts fractures but also captures the entire history of the fracture process, from the crack initiation in the interfacial transition zone to the subsequent propagation of the cracks in the mortar matrix. In addition, a convolutional neural network is developed which can predict the averaged stress-strain curve of the mesostructures. The UNet modeling framework, which comprises an encoder-decoder section with skip connections, is used as the deep learning surrogate model. Training and test data are generated from high-fidelity fracture simulations of randomly generated concrete mesostructures. These mesostructures include geometric variabilities such as different aggregate particle geometrical features, spatial distribution, and the total volume fraction of aggregates. The fracture simulations are carried out in Abaqus, utilizing the cohesive phase-field fracture modeling technique as the fracture modeling approach. In this work, to reduce the number of training datasets, the spatial distribution of three sets of material properties for three-phase concrete mesostructures, along with the spatial phase-field damage index, are fed to the UNet to predict the corresponding stress and spatial damage index at the subsequent step. It is shown that after the training process using this methodology, the UNet model is capable of accurately predicting damage on the unseen test dataset by using 470 datasets. Moreover, another novel aspect of this work is the conversion of irregular finite element data into regular grids using a developed pipeline. This approach allows for the implementation of less complex UNet architecture and facilitates the integration of phase-field fracture equations into surrogate models for future developments.

To reduce the experimental validation workload for chemical researchers and accelerate the design and optimization of high-energy-density lithium metal batteries, we aim to leverage models to automatically predict Coulombic Efficiency (CE) based on the composition of liquid electrolytes. There are mainly two representative paradigms in existing methods: machine learning and deep learning. However, the former requires intelligent input feature selection and reliable computational methods, leading to error propagation from feature estimation to model prediction, while the latter (e.g. MultiModal-MoLFormer) faces challenges of poor predictive performance and overfitting due to limited diversity in augmented data. To tackle these issues, we propose a novel method COEFF (COlumbic EFficiency prediction via Fine-tuned models), which consists of two stages: pre-training a chemical general model and fine-tuning on downstream domain data. Firstly, we adopt the publicly available MoLFormer model to obtain feature vectors for each solvent and salt in the electrolyte. Then, we perform a weighted average of embeddings for each token across all molecules, with weights determined by the respective electrolyte component ratios. Finally, we input the obtained electrolyte features into a Multi-layer Perceptron or Kolmogorov-Arnold Network to predict CE. Experimental results on a real-world dataset demonstrate that our method achieves SOTA for predicting CE compared to all baselines. Data and code used in this work will be made publicly available after the paper is published.

A robot dog equipped with a flamethrower could be used to stop weeds growing on farms, potentially offering a replacement for harmful herbicides. Even highly targeted herbicides can cause environmental problems, affecting local wildlife, and "superweeds" are quickly evolving resistance to the most common weed-killers like glyphosate. In search of an alternative solution, Dezhen Song at Texas A&M University and his colleagues have developed a weed control system that uses a brief burst of heat from a propane-powered flamethrower controlled by a robotic arm, attached to a Spot robot manufactured by Boston Dynamics. Rather than incinerate the weeds, the robot is designed to identify and heat up the centre of the plant, which can stop it growing for several weeks, says Song. "The weeds don't die – you just suppress their growth so it gives your crop a chance to fight the weed." Song and his team first tested the flame nozzle to make sure they could accurately target the weeds' centre.

A robot dog equipped with a blowtorch could be used to stop weeds growing on farms, potentially offering a replacement for harmful herbicides. Even highly targeted herbicides can cause environmental problems, affecting local wildlife, and "superweeds" are quickly evolving resistance to the most common weed-killers like glyphosate. In search of an alternative solution, Dezhen Song at Texas A&M University and his colleagues have developed a weed control system that uses a brief burst of heat from a propane-powered torch controlled by a robotic arm, attached to a Spot robot manufactured by Boston Dynamics. Rather than incinerate the weeds, the robot is designed to identify and heat up the centre of the plant, which can stop it growing for several weeks, says Song. "The weeds don't die – you just suppress their growth so it gives your crop a chance to fight the weed." The latest science news delivered to your inbox, every day.

Fish locomotion is enabled by fin rays-actively deformable boney rods, which manipulate the fin to facilitate complex interaction with surrounding water and enable propulsion. Replicating the performance and kinematics of the biological fin ray from an engineering perspective is a challenging task and has not been realised thus far. This work introduces a prototype of a fin ray-inspired origami electromagnetic tendon-driven (FOLD) actuator, designed to emulate the functional dynamics of fish fin rays. Constructed in minutes using origami/kirigami and paper joinery techniques from flat laser-cut polypropylene film, this actuator is low-cost at {\pounds}0.80 (\$1), simple to assemble, and durable for over one million cycles. We leverage its small size to embed eight into two fin membranes of a 135 mm long cuttlefish robot capable of four degrees of freedom swimming. We present an extensive kinematic and swimming parametric study with 1015 data points from 7.6 hours of video, which has been used to determine optimal kinematic parameters and validate theoretical constants observed in aquatic animals. Notably, the study explores the nuanced interplay between undulation patterns, power distribution, and locomotion efficiency, underscoring the potential of the actuator as a model system for the investigation of energy-efficient propulsion and control of bioinspired systems. The versatility of the actuator is further demonstrated by its integration into a fish and a jellyfish.

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform well leading to degraded results. Previous approaches to this problem have largely focused on broadening the training observation distribution, employing techniques like data augmentation and domain randomization. However, given the sequential nature of the RL decision-making problem, it is often the case that residual errors are propagated by the learned policy model and accumulate throughout the trajectory, resulting in highly degraded performance. In this paper, we leverage the observation that predicted rewards under domain shift, even though imperfect, can still be a useful signal to guide fine-tuning. We exploit this property to fine-tune a policy using reward prediction in the target domain. We have found that, even under significant domain shift, the predicted reward can still provide meaningful signal and fine-tuning substantially improves the original policy. Our approach, termed Predicted Reward Fine-tuning (PRFT), improves performance across diverse tasks in both simulated benchmarks and real-world experiments. More information is available at project web page: https://sites.google.com/view/prft.