Accurate interatomic force field for molecular dynamics simulation by hybridizing classical and machine learning potentials

<sec><p indent="0mm">Catalysis, the science of accelerating chemical reactions and regulating the selectivity of reaction products, lies in the heart of modern chemical industry. Typically, catalysis can be categorized into heterogeneous catalysis and homogeneous catalysis. Over the past century, heterogeneous catalytic processes such as ammonia synthesis and Fischer-Tropsch synthesis have become an indispensable part of the chemical industry. In recent years, the rational design of catalysts has gained a lot of attention due to both economic and environmental concerns, which has raised new demands for a deep understanding of the mechanism of catalytic reactions. Machine learning methods as one of the most important areas of artificial intelligence (AI) are becoming more and more popular in practices of theoretical simulations. This review gives an overview on various machine learning methods and their applications in theoretical heterogeneous catalysis. </sec><sec> Starting with statistical learning models on small datasets based on specific physical descriptors, which play an important role in early theoretical heterogeneous research, this review analyzes how they connect linear scaling relationship and catalytic experiments. However, due to the complexity of heterogeneous catalytic systems, sometimes nonlinear models can be essential. In this way, the exact form of equations should be obtained before fitting, which is extremely challenging. This problem can be solved by methods based on symbolic regression like SISSO to obtain a set of expressions, and the researchers can select one by their domain knowledge. This review also shows the applications of some popular machine learning methods (such as SVM, PCA, RF, etc.) in research, most of which are based on specific descriptors, simple but have difficulty transferring to other systems. </sec><sec> First-principle calculations like DFT are crucial in catalysis rational design by computational simulations for surface structure determination and reaction channel exploration, but they are impractical for simulations on large and complex catalytic systems due to high computational costs. In recent years, machine learning potentials (MLPs), as tools to bridge the gap between first-principle accuracy and computational efficiency, have pushed forward the frontier of theoretical heterogeneous catalysis. Popular MLPs (LASP, EANN, DP, GemNet-OC, MACE, DPA, etc.) have numerous applications in this field, from global optimization and molecular dynamics of active surfaces under reaction conditions to automatic reaction network exploration. Recently, universal machine learning potentials have gained much attention and are very promising in heterogeneous catalysis simulations, for their promising capability to encapsulate huge chemical space of the whole periodic table in one pre-trained model, which is easy to fine-tune on a specific chemical system, efficiently deploying a specific MLP with high accuracy and transferability. </sec><sec> Recent advances in generative models have shown considerable promise for heterogeneous catalysis research, and the dramatic emergence of large language models like ChatGPT is especially important in this case. LLMs can incorporate information from massive natural language data, having a huge ability to push forward the understanding of topics in catalytic science. Furthermore, the concept of generative models themselves has much potential in generating novel catalytic information directly without natural language as the intermediate, but their application in heterogeneous catalysis is under limitation due to the lack of large datasets with high quality. </sec><sec> In a nutshell, machine learning methods play a key role in theoretical understanding of heterogeneous catalytic systems. Challenges remain due to the complexity of heterogeneous catalytic systems and lack of high-quality dataset, but the era of AI-driven rational design of surface catalysts is truly coming. </sec>

Investigating the potential of Machine Learning for fault location on Inverter-Based Resource interconnection lines: Insights and recommendations

GPx4 is bound to peroxidized membranes by a hydrophobic anchor.

In this study, we trained a deep potential (DP) for H2O, an accurate machine learning (ML) potential. We performed molecular dynamics (MD) simulations of liquid water using the DP model (or DeePMD simulations). Our results showed that the DP model exhibits DFT-level accuracy, and the DeePMD simulation is a promising approach for modeling the structural properties of liquid water. Based on the DeePMD simulation trajectories, we calculated the isotropic Raman spectra of the O-H stretching mode using the surface-specific velocity-velocity correlation function (ssVVCF), showing that the DeePMD/ssVVCF approach can correctly capture the bimodal characteristics of the experimental Raman spectra, with one peak located near 3400 cm-1 and the other near 3250 cm-1. The success of the DeePMD/ssVVCF approach should be credited to (1) the DFT-level accuracy of the DP model for H2O, (2) the ssVVCF formulation considering the coupling between vibrational modes, and (3) non-Condon effects. Furthermore, the DeePMD simulations revealed that the anharmonic interactions between the coupled water molecules in the first and second hydration shells should play an essential role in the strong mixing of the H-O-H bending mode and the O-H stretching mode, leading to the delocalization of the O-H stretching band. In particular, increasing the strength of hydrogen bonds would enhance the bend-stretch coupling, leading to the red-shifting of the O-H vibrational spectra and the increase in the intensity of the shoulder around 3250 cm-1.

By adding machine learning (ML) into predictive analytics, the area of personalised healthcare computing has evolved and new approaches to enhance patient outcomes via tailored treatment plans have been generated. This paper examines how healthcare treatments could be tailored and predicted using machine learning methods. It underlines how crucial sophisticated analytics are for enhancing patient care and guiding clinical choices. Treatment is more accurate, more efficient, and better generally when one can predict how a condition will worsen, choose the best course of action for taking drugs, and observe any issues. Like controlled and unstructured learning algorithms, machine learning models have proved to be able to efficiently examine large and complex clinical datasets including electronic health records (EHR) and genetic data. These models identify hidden trends, relationships, and patterns that enable us to forecast individual health paths, identify those at risk, and simplify preventive action. ML also makes it feasible to merge many kinds of data, therefore providing clinicians with a more complete picture of every patient's health and, ultimately, facilitates the provision of more individualised, better treatment. Many facets of healthcare, including management of chronic illnesses, cancer detection, mental health analysis, and new medication discovery, employ predictive models. By helping clinicians make decisions based on data, ML models assist to reduce errors and enhance the flow of treatment. Still, there are issues including concerns about data security, model understanding, and the necessity of consistent frameworks to ensure models are robust and dependable in real-life clinical environments. This work also addresses the moral issues raised by using machine learning algorithms in tailored healthcare. It addresses issues like prejudice, justice, and patient agreement. It emphasises the need of cooperation among legislators, data scientists, and healthcare professionals to maintain developing models so that the whole potential of machine learning in healthcare may be fulfilled.

Background:A common and persistent inflammatory condition impacting the supportive structures of teeth, periodontal disease presents notable challenges in dental healthcare. It leads to various clinical issues, including the loss of clinical attachment, increased pocket depth, and tooth mobility. The global prevalence of periodontitis is substantial, with an estimated 20%–50% of the world’s population affected, particularly in developing countries. Furthermore, periodontitis often culminates in tooth loss, affecting overall health and the quality of life, particularly in aging populations. Early intervention and accurate prediction of tooth loss are crucial for improving oral health outcomes. Conventional prognostic models have their constraints in sensitivity, prompting the exploration of alternative approaches. Machine learning, an evolving field in artificial intelligence, has gained prominence in various domains, including healthcare. In this study, we examined the potential of machine learning to predict tooth loss based on diverse parameters, including age, systemic diseases (such as diabetes and hypertension), grades of tooth mobility, oral hygiene habits, and more.Materials and Methods:Data from 200 patients were collected, categorized by gender, age, and mobility grades, with 45 having diabetes, 36 with hypertension, and the remaining free of these systemic diseases. The Orange machine learning tool was employed to analyze these data. The free and open-source data visualization and machine learning platform offers user-friendly visual programming for predictive modeling and data analysis.Results:This study showed that machine learning models produced highly accurate predictions, with an area under the curve of 1.000 for several algorithms, such as Naive Bayes, AdaBoost, Random Forest, and Neural Network. Accuracy, precision, recall, and specificity values consistently exceeded 95%, demonstrating the potential of machine learning in predicting tooth loss.Conclusion:By analyzing comprehensive datasets, machine learning models can enhance the accuracy and objectivity of tooth loss prediction. While challenges remain, such as data quality and privacy concerns, integrating machine learning algorithms in dentistry can revolutionize dental healthcare, improve patient outcomes, and reshape the future of periodontics.

Stroke is a leading cause of disability and mortality worldwide, necessitating the development of advanced technologies to improve its diagnosis, treatment, and patient outcomes. In recent years, machine learning techniques have emerged as promising tools in stroke medicine, enabling efficient analysis of large-scale datasets and facilitating personalized and precision medicine approaches. This abstract provides a comprehensive overview of machine learning's applications, challenges, and future directions in stroke medicine. Recently introduced machine learning algorithms have been extensively employed in all the fields of stroke medicine. Machine learning models have demonstrated remarkable accuracy in imaging analysis, diagnosing stroke subtypes, risk stratifications, guiding medical treatment, and predicting patient prognosis. Despite the tremendous potential of machine learning in stroke medicine, several challenges must be addressed. These include the need for standardized and interoperable data collection, robust model validation and generalization, and the ethical considerations surrounding privacy and bias. In addition, integrating machine learning models into clinical workflows and establishing regulatory frameworks are critical for ensuring their widespread adoption and impact in routine stroke care. Machine learning promises to revolutionize stroke medicine by enabling precise diagnosis, tailored treatment selection, and improved prognostication. Continued research and collaboration among clinicians, researchers, and technologists are essential for overcoming challenges and realizing the full potential of machine learning in stroke care, ultimately leading to enhanced patient outcomes and quality of life. This review aims to summarize all the current implications of machine learning in stroke diagnosis, treatment, and prognostic evaluation. At the same time, another purpose of this paper is to explore all the future perspectives these techniques can provide in combating this disabling disease.

Machine learning detecting aggression among mood disorder patients visited in psychiatric emergency departments.

Detailed long-term climate scenarios over cities are needed for reliable future urban risk assessment and for designing climate resilient cities. For many cities, only coarse model information is however available. A small portion of mainly large cities in the global North possesses (sub-)kilometer long-term climate information, often acquired in the context of dedicated modelling case studies. Producing intra-urban climate projections for the multitude of medium to small cities is impossible using traditional downscaling techniques due to the high computational cost.Therefore, we explored the potential of machine learning to simulate high-resolution near-surface air temperature over European cities. The European Random Forest Urban Climate Emulator (Eu-RaFUCE) framework was built and tested on hectometer-scale 2 m-air temperature of the urban climate model UrbClim for which data for 100 European cities is available (Lauwaet et al., 2024). Feature importance analysis showed that both temporal, such as surface net solar radiation, and spatial, such as land cover, inputs are important for the machine learning model to capture the urban heat island (UHI) effect. By applying Eu-RaFUCE, hourly ERA5 reanalysis data can be directly downscaled to (sub-)kilometer 2 m-temperature. Eu-RaFUCE captures the spatial and temporal UHI characteristics of multiple test cities well, resulting in high model accuracy over cities and years that were not included during the training. Out of all test cities Madrid has the largest root mean square error (RMSE), amounting 1.82 K, while the lowest RMSE of 0.85 K was found for Tallin. This proof of concept paves the way for the application of Eu-RaFUCE in downscaling 2 m-temperature projections to hectometer resolution over many cities, showing the potential of machine learning for urban climate studies.Reference: Lauwaet et al. (2024). High resolution modelling of the urban heat island of 100 European cities. Urban Climate, 54, 101850.

We introduce weighted atom-centered symmetry functions (wACSFs) as descriptors of a chemical system's geometry for use in the prediction of chemical properties such as enthalpies or potential energies via machine learning. The wACSFs are based on conventional atom-centered symmetry functions (ACSFs) but overcome the undesirable scaling of the latter with an increasing number of different elements in a chemical system. The performance of these two descriptors is compared using them as inputs in high-dimensional neural network potentials (HDNNPs), employing the molecular structures and associated enthalpies of the 133 855 molecules containing up to five different elements reported in the QM9 database as reference data. A substantially smaller number of wACSFs than ACSFs is needed to obtain a comparable spatial resolution of the molecular structures. At the same time, this smaller set of wACSFs leads to a significantly better generalization performance in the machine learning potential than the large set of conventional ACSFs. Furthermore, we show that the intrinsic parameters of the descriptors can in principle be optimized with a genetic algorithm in a highly automated manner. For the wACSFs employed here, we find however that using a simple empirical parametrization scheme is sufficient in order to obtain HDNNPs with high accuracy.

A thorough exploration of the effects of a given minute’s currency exchange rates on subsequent 1, 5, 10, 15, 30, 45, and 60 minutes’ currency exchange rates is presented in this article, with machine learning and ensemble methods being applied. The focus is on twelve currency pairs, including EUR/AUD, EUR/GBP, and EUR/PLN, with a data set of per-minute logs of these pairs’ exchange rates from 2022 being leveraged. A stacked ensemble of Random Forest and Support Vector Regression (SVR) is used to predict future exchange rates. A comparison of this model is also made with the single RF, single SVR, and an average ensemble of RF and SVR models. The research method is further fortified by the use of k-fold cross-validation and ANOVA tests. The findings of the study reveal significant predictive accuracy of the stacked ensemble model, emphasizing the intricate interconnections of currency exchange rates. The potential of machine learning and ensemble techniques in predicting short-term currency exchange rates is underlined, thereby augmenting financial forecasting research.

Background: Conjunctivitis, often referred to as "pink eye" is a highly prevalent inflammation of the conjunctiva, a thin, transparent membrane lining the white part of your eye and the inner surface of your eyelids. This inflammation triggers a cascade of symptoms that can range from mild annoyance to significant discomfort, affecting people of all ages worldwide. The three main types of conjunctivitis are viral, bacterial, and allergy. Some common symptoms include redness of the white part of the eye, ranging from watery to thick and pus-like, discharge from the eye, itching or burning sensation, and a Gritty feeling in the eye. Methods: Several deep-learning techniques for conjunctivitis detection have been developed due to their simplicity of use and their affordability. This systematic review delves into the burgeoning field of machine learning within healthcare, specifically seeking viable approaches for detecting conjunctivitis. We embark on a comparative analysis of the most successful ML algorithms currently in use regarding machine learning, including evaluation metrics, image augmentation, and the origin and size of the dataset used. Results: The results of this study provide compelling evidence for the feasibility and potential benefits of using DL algorithms for conjunctivitis detection. Conclusion: This review sheds light on the potential of machine learning in detecting Conjunctivitis, providing scientific evidence for its feasibility. By analyzing images, diagnoses, and clinical data within the medical field, the review explores how machine and deep learning algorithms can offer a wide-ranging approach to conjunctivitis detection.

Interatomic potentials are essential for studying fundamental mechanisms of deformation and failure in metals and alloys because the relevant defects (dislocations, cracks, etc.) are far above the scales accessible to first-principles studies. Existing potentials for non-fcc metals and nearly all alloys are, however, not sufficiently quantitative for many crucial phenomena. Here machine learning in the Behler-Parrinello neural-network framework is used to create a broadly applicable potential for pure hcp magnesium (Mg). Lightweight Mg and its alloys are technologically important while presenting a diverse range of slip systems and crystal surfaces relevant to both plasticity and fracture that present a significant challenge for any potential. The machine learning potential is trained on first-principles density-functional theory (DFT) computable metallurgically relevant properties and is then shown to well predict metallurgically crucial dislocation and crack structures and competing phenomena. Extensive comparisons to an existing very good modified embedded atom method potential are made. These results demonstrate that a single machine learning potential can represent the wide scope of phenomena required for metallurgical studies. The DFT database is openly available for use in any other machine learning method. The method is naturally extendable to alloys, which are necessary for engineering applications but where ductility and fracture are controlled by complex atomic-scale mechanisms that are not well predicted by existing potentials.

The pursuit of understanding Mars, our neighboring planet, is rife with challenges that range from treacherous conditions for potential human astronauts to the vast distances that complicate communication. However, a beacon of hope emerges in the form of machine learning, a technological frontier that promises to transform the landscape of Martian exploration. As we embark on this interplanetary journey, the recognition of machine learning's potential is growing. It offers innovative solutions to some of the most pressing challenges, ushering in a new era of autonomous exploration. Imagine rovers and orbiter spacecraft equipped with the ability to analyze Martian data on-site, reducing the need for slow communications with Earth. This revolutionary approach is already in action with rovers like Curiosity, where machine learning enables self-directed exploration and continuous data analysis on the Martian surface. The applications of machine learning extend beyond mere autonomy. They hold the promise of addressing communication limitations, providing greater operational autonomy, and unlocking the mysteries that shroud the Red Planet. From identifying sources of atmospheric gases, such as oxygen and methane, to interpreting geological features like cloud distributions and weather patterns, machine learning is proving itself to be a versatile and indispensable tool in unraveling the complexities of Mars. Venturing deeper into the Martian climate, machine learning becomes a powerful ally. By leveraging this technology to analyze climate data, we have the potential to generate predictive models crucial for planning future surface missions and assessing the habitability of Mars. Additionally, the application of machine learning on Earth offers a unique opportunity to decode uncertainties related to Martian atmospheric interactions, the dynamics of dust storms, and conditions beneath the surface. Anticipating the wealth of data that future Mars missions will yield, the integration of machine learning emerges as a game-changer. Its efficiency in discerning intricate patterns within extensive datasets has the potential to revolutionize our scientific understanding of Mars. As we delve deeper into the mysteries of the Red Planet, machine learning stands as a pivotal catalyst, promising not just incremental but transformative discoveries. It becomes the linchpin in our ongoing quest to answer the age-old question: Did life ever exist on Mars? In the realm of Martian exploration, machine learning is proving to be the technological cornerstone that propels us towards unprecedented scientific revelations.

Metabolomics, leveraging techniques like NMR and MS, is crucial for understanding biochemical processes in pathophysiological states. This field, however, faces challenges in metabolite sensitivity, data complexity, and omics data integration. Recent machine learning advancements have enhanced data analysis and disease classification in metabolomics. This study explores machine learning integration with metabolomics to improve metabolite identification, data efficiency, and diagnostic methods. Using deep learning and traditional machine learning, it presents advancements in metabolic data analysis, including novel algorithms for accurate peak identification, robust disease classification from metabolic profiles, and improved metabolite annotation. It also highlights multiomics integration, demonstrating machine learning's potential in elucidating biological phenomena and advancing disease diagnostics. This work contributes significantly to metabolomics by merging it with machine learning, offering innovative solutions to analytical challenges and setting new standards for omics data analysis.