Digital discovery最新文献

{"title":"Automated structural analysis of small angle scattering data from common nanoparticles via machine learning","authors":"Graham Roberts, Mu-Ping Nieh, Anson W. K. Ma and Qian Yang","doi":"10.1039/D5DD00059A","DOIUrl":"https://doi.org/10.1039/D5DD00059A","url":null,"abstract":"<p >Billions of dollars have been invested in recent years to build up national scattering facilities around the world with more advanced configurations and faster data collection for small angle scattering (SAS), a technique that enables <em>in situ</em> structural analysis of nanoparticles (NP) under stringent sample environments. However, the interpretation of experimental SAS data is typically a slow process that requires significant domain expertise, leading to high-throughput scattering facilities such as synchrotron scattering centers collecting large quantities of data that may potentially be left unanalyzed. Here, we present a fast and data-efficient machine learning (ML) framework for identifying basic NP morphologies (spherical, cylindrical and discoidal geometries) and their corresponding structural parameters. The trained models take as input scattering curves with minimal pre-processing, and are able to identify morphology and structural dimensions from experimental curves with comparable accuracy to human experts. Critically, design choices that facilitate the practical application of ML models in scattering facilities are discussed, including ease of training, extrapolability outside of the parameter range of training data, and verifiability of predictions. The enhanced data analysis efficiency enabled by applying ML models to real-time <em>in situ</em> analysis of SAS data has the potential to revolutionize the utilization of synchrotron and neutron scattering facilities for probing nanostructures.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1467-1477"},"PeriodicalIF":6.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00059a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the transferability of machine-learning models for analyzing XRD data of shocked microstructures: from single crystal to polycrystals†","authors":"Daniel Vizoso, Phillip Tsurkan, Ke Ma, Avinash M. Dongare and Rémi Dingreville","doi":"10.1039/D4DD00400K","DOIUrl":"https://doi.org/10.1039/D4DD00400K","url":null,"abstract":"<p >This study explores the transferability of machine-learning models to analyze X-ray diffraction (XRD) profiles of shock-loaded single-crystal and polycrystalline data. Transferability in this context refers to the ability of these models to accurately predict microstructural descriptors for crystal orientations and structures not included in its training data. Supervised machine-learning models were trained on XRD profiles and microstructural descriptors from atomistic simulations to extract properties like pressure, temperature, phase fractions, and dislocation density. We assessed two aspects of transferability: (1) the ability of models trained on specific single crystal orientations to predict microstructural descriptors for other orientations, and (2) the capacity of models trained on single crystal data to analyze polycrystalline structures. Results show promising accuracy in predicting certain descriptors within the same orientation and improved transferability to new orientations and polycrystalline systems when trained on multiple orientations. However, the accuracy of these predictions depends on the microstructural descriptor being targeted and the specific crystal orientations included in the training dataset. This work highlights the potential and limitations of machine learning for analyzing XRD data of shock-loaded materials and emphasizes the need for diverse training data to enhance model transferability and robustness.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1457-1466"},"PeriodicalIF":6.2,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00400k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A self-driving fluidic lab for data-driven synthesis of lead-free perovskite nanocrystals†","authors":"Sina Sadeghi, Karl Mattsson, Joshua Glasheen, Victoria Lee, Christine Stark, Pragyan Jha, Nikolai Mukhin, Junbin Li, Arup Ghorai, Negin Orouji, Christopher H. J. Moran, Alireza Velayati, Jeffrey A. Bennett, Richard B. Canty, Kristofer G. Reyes and Milad Abolhasani","doi":"10.1039/D5DD00062A","DOIUrl":"https://doi.org/10.1039/D5DD00062A","url":null,"abstract":"<p >Copper (Cu)-based metal halide perovskite (MHP) nanocrystals (NCs) have recently gained attention as promising Pb-free and environmentally sustainable alternatives to traditional Pb-based MHPs, offering wide bandgaps, large Stokes shifts, and high emission stability. Despite these advantages, achieving high photoluminescence quantum yields (PLQYs) in Cu-based MHP NCs remains challenging, which impedes their widespread deployment in advanced optoelectronic and energy-related devices. Introducing a metal halide additive in the precursor chemistry can enhance the optical performance of Cu-based MHP NCs, but this approach substantially expands the experimental parameter space, rendering conventional batch-based, trial-and-error methods both time- and resource-intensive. Here, we present a self-driving fluidic lab (SDFL) that combines a modular microfluidic reactor, real-time <em>in situ</em> characterization, and machine-learning-guided decision-making to autonomously explore and optimize high-dimensional Cu-based MHP NC syntheses in the presence of a metal halide additive. Leveraging droplet-based flow chemistry and ensemble neural network-enabled Bayesian optimization, our SDFL rapidly navigates complex precursor formulations and reaction conditions of Cu-based MHP NCs, thus minimizing waste and accelerating discovery. We utilize the SDFL with three distinct precursor chemistries to synthesize Cs<small>₃</small>Cu<small>₂</small>I<small>₅</small> NCs, with zinc iodide (ZnI<small>₂</small>) serving as the metal halide additive. The high-fidelity data generated <em>in situ</em> allow for the creation of predictive digital twin models that yield mechanistic insights into additive-assisted NC formation. By iteratively refining synthesis parameters within the SDFL, we achieve Cs<small>₃</small>Cu<small>₂</small>I<small>₅</small> NCs with post-purification PLQYs of approximately 61%, marking a significant improvement over conventional Cu-based MHP NCs. The resulting high-performance, Pb-free NCs underscore the potential of sustainable materials acceleration platforms to speed-up the development of next-generation photonic and energy technologies.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 7","pages":" 1722-1733"},"PeriodicalIF":6.2,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00062a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144589456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large chemical language models for property prediction and high-throughput screening of ionic liquids†","authors":"Yuxin Qiu, Zhen Song, Guzhong Chen, Wenyao Chen, Long Chen, Kake Zhu, Zhiwen Qi, Xuezhi Duan and De Chen","doi":"10.1039/D5DD00035A","DOIUrl":"https://doi.org/10.1039/D5DD00035A","url":null,"abstract":"<p >Ionic liquids (ILs) possess unique physicochemical properties and exceptional tunability, making them versatile materials for a wide range of applications. However, their immense design flexibility also poses significant challenges in efficiently identifying outstanding ILs for specific tasks within the vast chemical space. In this study, we introduce ILBERT, a large-scale chemical language model designed to predict twelve key physicochemical and thermodynamic properties of ILs. By leveraging pre-training on over 31 million unlabeled IL-like molecules and employing data augmentation techniques, ILBERT achieves superior performance compared to existing machine learning methods across all twelve benchmark datasets. As a case study, we highlight ILBERT's ability to screen ILs as potential electrolytes from a database of 8 333 096 synthetically feasible ILs, demonstrating its reliability and computational efficiency. With its robust performance, ILBERT serves as a powerful tool for guiding the rational discovery of ILs, driving innovation in their practical applications.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1505-1517"},"PeriodicalIF":6.2,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00035a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Building workflows for an interactive human-in-the-loop automated experiment (hAE) in STEM-EELS†","authors":"Utkarsh Pratiush, Kevin M. Roccapriore, Yongtao Liu, Gerd Duscher, Maxim Ziatdinov and Sergei V. Kalinin","doi":"10.1039/D5DD00033E","DOIUrl":"https://doi.org/10.1039/D5DD00033E","url":null,"abstract":"<p >Exploring the structural, chemical, and physical properties of matter on the nano- and atomic scales has become possible with the recent advances in aberration-corrected electron energy-loss spectroscopy (EELS) in scanning transmission electron microscopy (STEM). However, the current paradigm of STEM-EELS relies on the classical rectangular grid sampling, in which all surface regions are assumed to be of equal <em>a priori</em> interest. However, this is typically not the case for real-world scenarios, where phenomena of interest are concentrated in a small number of spatial locations, such as interfaces, structural and topological defects, and multi-phase inclusions. One of the foundational problems is the discovery of nanometer- or atomic-scale structures having specific signatures in EELS spectra. Herein, we systematically explore the hyperparameters controlling deep kernel learning (DKL) discovery workflows for STEM-EELS and identify the role of the local structural descriptors and acquisition functions in experiment progression. In agreement with the actual experiment, we observe that for certain parameter combinations the experiment path can be trapped in the local minima. We demonstrate the approaches for monitoring the automated experiment in the real and feature space of the system and knowledge acquisition of the DKL model. Based on these, we construct intervention strategies defining the human-in-the-loop automated experiment (hAE). This approach can be further extended to other techniques including 4D STEM and other forms of spectroscopic imaging. The hAE library is available on Github at https://github.com/utkarshp1161/hAE/tree/main/hAE.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 1323-1338"},"PeriodicalIF":6.2,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00033e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143944056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Excited-state nonadiabatic dynamics in explicit solvent using machine learned interatomic potentials†","authors":"Maximilian X. Tiefenbacher, Brigitta Bachmair, Cheng Giuseppe Chen, Julia Westermayr, Philipp Marquetand, Johannes C. B. Dietschreit and Leticia González","doi":"10.1039/D5DD00044K","DOIUrl":"10.1039/D5DD00044K","url":null,"abstract":"<p >Excited-state nonadiabatic simulations with quantum mechanics/molecular mechanics (QM/MM) are essential to understand photoinduced processes in explicit environments. However, the high computational cost of the underlying quantum chemical calculations limits its application in combination with trajectory surface hopping methods. Here, we use FieldSchNet, a machine-learned interatomic potential capable of incorporating electric field effects into the electronic states, to replace traditional QM/MM electrostatic embedding with its ML/MM counterpart for nonadiabatic excited state trajectories. The developed method is applied to furan in water, including five coupled singlet states. Our results demonstrate that with sufficiently curated training data, the ML/MM model reproduces the electronic kinetics and structural rearrangements of QM/MM surface hopping reference simulations. Furthermore, we identify performance metrics that provide robust and interpretable validation of model accuracy.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1478-1491"},"PeriodicalIF":6.2,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12060776/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144059995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Citizen Data Science program at Dow†","authors":"Kyle Andrews, Steven Arturo, Matt Benedict, Birgit Braun, Brian Clark, Simon Cook, Jaime Curtis-Fisk, Fabio D’Ottaviano, Tim Licquia, Peter Margl, Jonathan Moore, Lynette Naler, Parth Singh, Alix Schmidt, Anatoliy Sokolov, John Talbert and James Wade","doi":"10.1039/D5DD00002E","DOIUrl":"https://doi.org/10.1039/D5DD00002E","url":null,"abstract":"<p >We present the Citizen Data Science (CDS) program, a data literacy program aimed at a Research and Development (R&amp;D)/Technical Service and Development (TS&amp;D) population from a heterogeneous background of traditional disciplines such as chemistry, materials science, engineering and others. The CDS program aims to facilitate the culture change required for maximizing researcher productivity and wellbeing by equipping every researcher with the skills to best manage, analyze, and communicate their data, enabling them to thrive in R&amp;D/TS&amp;D organizations that themselves are going through profound structural transformation induced by the pressures of digitalization. The Dow CDS program is going through its fourth year of implementation and improvement; we share the program and our learnings in the hope that they may be useful to other researchers in the materials development and adjacent spaces.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 1124-1133"},"PeriodicalIF":6.2,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00002e?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncovering ion transport mechanisms in ionic liquids using data science†","authors":"J. E. Umaña, Ryan K. Cashen, Victor M. Zavala and Matthew A. Gebbie","doi":"10.1039/D4DD00378K","DOIUrl":"https://doi.org/10.1039/D4DD00378K","url":null,"abstract":"<p >Batteries play a key role in the energy transition but suffer from safety concerns arising from the electrochemical instability of organic electrolytes. Ionic liquids are emerging as promising, non-flammable electrolytes for next-generation batteries. Yet, designing ionic liquids to facilitate redox ion transport has proven challenging, because ionic liquids are concentrated electrolytes where ion–ion interactions cause pronounced deviation from classical electrolyte scaling theories which assume viscosity governs mobility. Machine learning studies show that ionic liquid transport properties are challenging to predict from molecular descriptors, preventing rational design. Here, we pursue a broader data-centric approach to provide insight into ionic liquid design by merging databases of experimental properties and computational molecular features for 218 ionic liquids across 127 publications. We find that ionic liquids are well-described by a modified Arrhenius model that captures structure-driven ion transport in correlated electrolytes, yielding energy barriers of around 20–30 kJ mol<small>⁻¹</small>. This exhibits remarkable agreement with the approximately 25 kJ mol<small>⁻¹</small> screened ion pair interaction energy derived from surface forces measurements, suggesting links between mechanisms of ion transport and interfacial screening. We also use machine learning models to find that molecular features can predict some properties, such as density, while failing to predict properties that rely on long-range correlations, such as viscous dissipation. Our study reveals that data science tools can be leveraged to reveal non-classical transport scaling relationships and alternative materials descriptors that promise to be transformative for designing ionic liquids and other correlated electrolytes for next-generation batteries. All data and models are shared as open-source code.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1423-1436"},"PeriodicalIF":6.2,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00378k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A classification-based methodology for the estimation of binary surfactant critical micelle concentrations","authors":"Chetan R. Chilkunda, John R. Kitchin and Robert D. Tilton","doi":"10.1039/D5DD00058K","DOIUrl":"https://doi.org/10.1039/D5DD00058K","url":null,"abstract":"<p >The commercial formulation development for multicomponent complex fluids is time-intensive and data-intensive. There is a need for tools to expedite this process. This work develops an experimental and analytical high-throughput methodology to quantify binary surfactant mixture micellization in a 96-well plate. The novelty of this work lies in (1) employing model-driven design of experiments for efficient experimentation and (2) using physics-informed classification to quantify the mixture critical micelle concentration. This work employs a novel classification-based approach to map the binary critical micelle concentration as a function of the surfactant mixture ratio. Regular solution theory is used as the physics basis for modeling the binary interactions between surfactants (quantifying the <em>β</em> interaction parameter). Other, more complex surfactant interaction models exist; however, this simple model is used to demonstrate the efficacy of this methodology as a high-throughput screening tool for binary surfactant mixtures. Using regular solution theory as a guide to map the critical micelle concentration against the surfactant ratio, the SDS-C<small>₈</small>E<small>₄</small> surfactant system was determined to have a <em>β</em> = −3.6 ± 0.5, a 14.9% difference from the literature reference of <em>β</em> = −3.1. We demonstrate the utility of the method on the SDS-C<small>₈</small>E<small>₄</small> system in 0.5 M NaCl which was determined to have a <em>β</em> = −3.1 ± 0.4, which is a 17.5% difference from a similar literature system of SDS-C<small>₁₂</small>E<small>₈</small> in 0.5 M NaCl with <em>β</em> = −2.6. These two systems support the efficacy and generalizability of this high-throughput methodology to any binary surfactant mixture and future work involves extending this methodology to ternary surfactant mixtures.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 6","pages":" 1449-1456"},"PeriodicalIF":6.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d5dd00058k?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"High-throughput robotic colourimetric titrations using computer vision†","authors":"Yuan Li, Biplab Dutta, Qi Jie Yeow, Rob Clowes, Charlotte E. Boott and Andrew I. Cooper","doi":"10.1039/D4DD00334A","DOIUrl":"https://doi.org/10.1039/D4DD00334A","url":null,"abstract":"<p >A high-throughput (HTE) robotic colourimetric titration workstation was developed using a commercial liquid handling robot (Opentrons OT-2) and computer vision-based analysis. While designed for multiple titration applications, hydrogen peroxide (H<small>₂</small>O<small>₂</small>) determination serves as the most elaborate and well-characterized demonstration of its capabilities. Specifically, potassium permanganate (KMnO<small>₄</small>) redox titration was employed to quantify the hydrogen peroxide (H<small>₂</small>O<small>₂</small>) concentration, leveraging the distinct colourimetric transition from colourless to pale pink at the titration endpoint. To monitor this colour change, a webcam was installed on the OT-2 pipette mount, capturing real-time titration progress. Image analysis was enhanced through VGG-augmented UNet for segmentation and the CIELab colour model, ensuring robust and reproducible detection of subtle colour changes. The sensitivity test of the computer vision-aided colour analysis was strongly correlated to UV-vis spectroscopy (<em>R</em><small>²</small> = 0.9996), with a good linear dynamic range at low concentrations. The analytical accuracy of this workstation was ±11.9% in a 95% confidence interval and its corresponding absolute concentration difference was only 0.50 mM. To validate its real-world applicability, this workstation was first deployed to monitor the photoproduction of H<small>₂</small>O<small>₂</small> over a conjugated polymer photocatalyst, DE7. In addition to performing redox titrations, we demonstrated that this workstation can also be used for acid–base titration and complexometric titration, capturing a diverse range of colour changes.</p>","PeriodicalId":72816,"journal":{"name":"Digital discovery","volume":" 5","pages":" 1276-1283"},"PeriodicalIF":6.2,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://pubs.rsc.org/en/content/articlepdf/2025/dd/d4dd00334a?page=search","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143944052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}