Green Chemical Engineering最新文献

{"title":"Evaluating ionic liquid toxicity with machine learning and structural similarity methods","authors":"Rongli Shan ,&nbsp;Runqi Zhang ,&nbsp;Ying Gao ,&nbsp;Wenxin Wang ,&nbsp;Wenguang Zhu ,&nbsp;Leilei Xin ,&nbsp;Tianxiong Liu ,&nbsp;Yinglong Wang ,&nbsp;Peizhe Cui","doi":"10.1016/j.gce.2024.08.008","DOIUrl":"10.1016/j.gce.2024.08.008","url":null,"abstract":"<div><div>Ionic liquids (ILs) have garnered significant interest owing to their distinct physicochemical traits. Nonetheless, their extensive application is curtailed by ecotoxicity concerns. This study aimed to develop a quantitative structure-activity relationship (QSAR) model for predicting the toxicity of ILs in biological cells. Toxicity data of ILs on leukemia rat cell line IPC-81, <em>Escherichia coli</em> (<em>E. coli</em>), and acetylcholinesterase (AChE) were collected from open-source databases, and two integrated models, random forest (RF) and gradient boosted decision tree (GBDT), were used to train the data. The molecular structures of the ILs were represented by three different methods, namely molecular descriptor (MD), molecular fingerprint (MF), and molecular identifier (MI), respectively. The Tanimoto similarity coefficients indicate that MD has a stronger ability to recognize structural similarity. Statistical metrics of model performance showed that the two models (MD-RF and MD-GBDT) with MD as an input feature performed better in the three datasets. The application of the SHapley Additive exPlanations (SHAP) method explains the importance of different features. Specifically, reducing the carbon chain length and the number of fluorine atoms in the structure of ILs can effectively reduce their toxic effects on biological cells. This study employs machine learning to grasp better how the structure of ILs relates to inhibiting biotoxicity, offering insights for crafting safer, eco-friendly IL designs.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 249-262"},"PeriodicalIF":9.1,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594164","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":"Machine learning models coupled with ionic fragment σ-profiles to predict ammonia solubility in ionic liquids","authors":"Kaikai Li ,&nbsp;Yuesong Zhu ,&nbsp;Sensen Shi ,&nbsp;Yongzheng Song ,&nbsp;Haiyan Jiang ,&nbsp;Xiaochun Zhang ,&nbsp;Shaojuan Zeng ,&nbsp;Xiangping Zhang","doi":"10.1016/j.gce.2024.08.005","DOIUrl":"10.1016/j.gce.2024.08.005","url":null,"abstract":"<div><div>Emitting NH₃ into the atmosphere leads to significant air pollution, while NH₃ itself serves as an essential component for fertilizers and refrigerants in industry. Thus, recovering and reusing NH₃ is highly valuable. Ionic liquids (ILs) have shown great potential for NH₃ capture, where the accurate prediction of solubility is a critical point for selecting ILs and designing a separation process. This work combined the Ionic Fragment Contribution (IFC) strategy with machine learning (ML) to develop four models (IFC-ML) to predict NH₃ solubility in ILs. A dataset containing 785 solubility data points, covering 10 cations and 10 anions, was collected. From this dataset, the <em>S</em>1–<em>S</em>6 descriptors based on the IFC method were used as inputs for the ML models, together with temperature (<em>T</em>) and pressure (<em>P</em>). Among the models, the IFC-GBR model was recommended for predicting NH₃ solubility in ILs due to its higher coefficient of determination (R²) of 0.9945 and lower mean squared error (MSE) of 0.0003 than the others. Additionally, in comparison with previous conductor-like screening model for real solvents (COSMO-RS) and extreme learning machine (ELM) methods, the IFC-GBR (gradient boosting regressor) method showed a more accurate prediction of the NH₃ solubility in ILs over a wider range of temperatures and pressures, providing additional chemical insights into IL-NH₃ system that cations played a more important role for NH₃ solubility. These results highlighted the developed IFC-GBR model offered valuable insights for helping guide the process design of absorbing NH₃ through IL-based technology.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 223-232"},"PeriodicalIF":9.1,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594169","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":"Pressure swing adsorption process modeling using physics-informed machine learning with transfer learning and labeled data","authors":"Zhiqiang Wu ,&nbsp;Yunquan Chen ,&nbsp;Bingjian Zhang ,&nbsp;Jingzheng Ren ,&nbsp;Qinglin Chen ,&nbsp;Huan Wang ,&nbsp;Chang He","doi":"10.1016/j.gce.2024.08.004","DOIUrl":"10.1016/j.gce.2024.08.004","url":null,"abstract":"<div><div>Pressure swing adsorption (PSA) modeling remains a challenging task since it exhibits strong dynamic and cyclic behavior. This study presents a systematic physics-informed machine learning method that integrates transfer learning and labeled data to construct a spatiotemporal model of the PSA process. To approximate the latent solutions of partial differential equations (PDEs) in the specific steps of pressurization, adsorption, heavy reflux, counter-current depressurization, and light reflux, the system's network representation is decomposed into five lightweight sub-networks. On this basis, we propose a parameter-based transfer learning (TL) combined with domain decomposition to address the long-term integration of periodic PDEs and expedite the network training process. Moreover, to tackle challenges related to sharp adsorption fronts, our method allows for the inclusion of a specified amount of labeled data at the boundaries and/or within the system in the loss function. The results show that the proposed method closely matches the outcomes achieved through the conventional numerical method, effectively simulating all steps and cyclic behavior within the PSA processes.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 233-248"},"PeriodicalIF":9.1,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594163","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":"Deep learning-based prediction of velocity and temperature distributions in metal foam with hierarchical pore structure","authors":"Yixiong Lin ,&nbsp;Zhengqi Wu ,&nbsp;Shiqi You ,&nbsp;Chen Yang ,&nbsp;Qinglian Wang ,&nbsp;Wang Yin ,&nbsp;Ting Qiu","doi":"10.1016/j.gce.2024.08.003","DOIUrl":"10.1016/j.gce.2024.08.003","url":null,"abstract":"<div><div>Constrained by the substantial computational time required for numerical simulation, a deep learning technique is applied to investigate fluid flow and heat transfer processes in metal foam with a hierarchical pore structure. This work adopted a 3D convolutional neural network (CNN) combining U-Net architecture to predict velocity and temperature distributions, alongside corresponding permeability and overall heat transfer coefficient. This approach demonstrates excellent capability in intricate image segmentation. The training sets were acquired by lattice Boltzmann method (LBM) simulations. The CNN model, trained on a substantial amount of data, demonstrates remarkable precision, exhibiting mean relative errors of 0.57% for permeability prediction and 2.27% for overall heat transfer coefficient prediction. Moreover, in CNN prediction, a broader range of structure parameters and boundary conditions beyond those in the training set was used to evaluate the practicability of the trained CNN model. In contrast to numerical simulation, the CNN model economizes approximately 95.41% and 99.57% of computational time for velocity and temperature distribution prediction, respectively, providing a novel approach for exploring transport processes in metal foam with hierarchical pore structure.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 209-222"},"PeriodicalIF":9.1,"publicationDate":"2024-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594168","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":"Development of an interpretable QSPR model to predict the octanol-water partition coefficient based on three artificial intelligence algorithms","authors":"Ao Yang ,&nbsp;Shirui Sun ,&nbsp;Lu Qi ,&nbsp;Zong Yang Kong ,&nbsp;Jaka Sunarso ,&nbsp;Weifeng Shen","doi":"10.1016/j.gce.2024.07.003","DOIUrl":"10.1016/j.gce.2024.07.003","url":null,"abstract":"<div><div>This study aims to significantly improve existing quantitative structure-property relationship (QSPR) models for predicting the octanol-water partition coefficient (<em>K</em>_OW). This is because accurate predictions of <em>K</em>_OW are crucial for assessing the environmental behavior and bioaccumulation potential of chemicals. Previous models have reported determination coefficient (R²) values between 0.9451 and 0.9681, and this research seeks to exceed these benchmarks. Three machine learning (ML) models are explored, <em>i.e.</em>, feed-forward neural networks (FNN), extreme gradient boosting (XGBoost), and random forest (RF). Using a dataset of 14,610 solvents (14,580 after data cleaning) and 21 molecular descriptors derived from SMILES representations, we rigorously evaluate these models based on R², mean absolute error (MAE), root mean squared error (RMSE), and mean relative error (MRE). Notably, the best model developed, the XGBoost-based QSPR, demonstrated exceptional performance, exhibiting an impressive R² value of 0.9772, surpassing benchmarks set by prior research models. Additionally, shapley additive explanation (SHAP) analysis is also employed for model interpretation, and it is revealed that the top five influential input features include SMR_VSA8, SMR_VSA3, Kappa2, HeavyAtomCount, and fr_furan. This study not only sets a new benchmark for <em>K</em>_OW prediction accuracy but also enhances the interpretability of QSPR models.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 193-199"},"PeriodicalIF":9.1,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141849803","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":"Multi-criteria computational screening of [BMIM][DCA]@MOF composites for CO2 capture","authors":"Mengjia Sheng,&nbsp;Xiang Zhang,&nbsp;Hongye Cheng,&nbsp;Zhen Song,&nbsp;Zhiwen Qi","doi":"10.1016/j.gce.2024.07.002","DOIUrl":"10.1016/j.gce.2024.07.002","url":null,"abstract":"<div><div>Ionic liquid (IL) can be inserted into metal organic framework (MOF) to form IL@MOF composite with enhanced properties. In this work, hypothetical IL@MOFs were computationally constructed and screened by integrating molecular simulation and convolutional neural network (CNN) for CO₂ capture. First, the IL [BMIM][DCA] with a large CO₂ solubility was inserted into 1631 pre-selected Computational-Ready Experimental (CoRE) MOFs to create hypothetical IL@MOFs. Then, given the temperature and pressure of adsorption and desorption, the CO₂/N₂ selectivity and CO₂ working capacity of 700 representative IL@MOFs were assessed <em>via</em> molecular simulations. Based on the results, two CNN models were trained and used to predict the performance of other IL@MOFs, which reduces the computational costs effectively. By combining the simulation results and CNN model predictions, 22 IL@MOFs with top-ranked performance were identified. Three distinct ones IL@HABDAS, IL@GUBKUL, and IL@MARJAQ were chosen for explicit analysis. It was found that a desired balance between CO₂/N₂ selectivity and CO₂ working capacity can be obtained by inserting the optimal number of IL molecules. This helps guide a novel design of IL@MOF composites with advanced performance on carbon capture.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 200-208"},"PeriodicalIF":9.1,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141842912","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":"Outside Back Cover","authors":"","doi":"10.1016/S2666-9528(24)00028-1","DOIUrl":"10.1016/S2666-9528(24)00028-1","url":null,"abstract":"","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"5 3","pages":"Page OBC"},"PeriodicalIF":9.1,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666952824000281/pdfft?md5=4391d9d0b440e4bfc5bd8b0958109991&pid=1-s2.0-S2666952824000281-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141623777","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":"OFC: Outside Front Cover","authors":"","doi":"10.1016/S2666-9528(24)00020-7","DOIUrl":"10.1016/S2666-9528(24)00020-7","url":null,"abstract":"","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"5 3","pages":"Page OFC"},"PeriodicalIF":9.1,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666952824000207/pdfft?md5=2156f5cbc0bab54ec018a83503597fae&pid=1-s2.0-S2666952824000207-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141623778","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 comprehensive study of affordable “water-in-salt” electrolytes and their properties","authors":"Aritsa Bunpheng ,&nbsp;Panwad Chavalekvirat ,&nbsp;Kanokporn Tangthana-umrung ,&nbsp;Varisara Deerattrakul ,&nbsp;Khanin Nueangnoraj ,&nbsp;Wisit Hirunpinyopas ,&nbsp;Pawin Iamprasertkun","doi":"10.1016/j.gce.2024.06.004","DOIUrl":"10.1016/j.gce.2024.06.004","url":null,"abstract":"<div><div>The search for alternative electrolytes has been extremely topical in recent years with the “water-in-salt” electrolyte, especially, lithium bis(trifluoromethanesulfonyl) imide (LiTFSI) coming to the fore in the context of high-voltage electrolytes. However, “water-in-LiTFSI” exhibits ultra-high cost and low ionic transport when compared with the aqueous lithium-halide, -nitrate as well as -sulphate salts (quoted as LiX). This work rediscovered the properties of a “water-in-salt” (LiX electrolytes) made from a variety of concentration from 1 m to saturated conditions. The changes of physical properties <em>e.g.</em>, viscosity, pH, conductivity, density, and temperature during mixing were then reported. The electrochemical properties of electrolyte were tested using carbon-based materials (YEC-8A) as a model system (three electrode configuration), and the finding was then expanded to a coin cell supercapacitor for benchmarking the performance per cost unit. It has been found that the use of highly concentrated LiX electrolytes does not always enhance the potential window. LiBr and LiI shown the redox properties while increasing the concentration can speed up the redox process (voltage remains unchanged). Using superconcentrated LiCl can slightly expand the potential window; however, corrosion is the main task to be addressed. Besides, voltage expansion of LiNO₃ is found to be approximately 2.2 V, which is comparable to LiTFSI. The breakdown cost of the electrolyte also shows that LiTFSI exhibits the lowest energy density per cost unit (dollars), while LiNO₃ provides the most feasible cost in term of power density. We then marked that the electrolytes such as LiBr and LiI can be used as redox additive electrolytes. This work also shows the fundamental insight into the physical and electrochemical properties of LiX for possible alternative use as a cheap “water-in-salt” electrolyte in energy storage apart from LiTFSI.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 1","pages":"Pages 126-135"},"PeriodicalIF":9.1,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142704746","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":"Developing deep learning-based large-scale organic reaction classification model via sigma-profiles","authors":"Wenlong Wang ,&nbsp;Chenyang Xu ,&nbsp;Jian Du ,&nbsp;Lei Zhang","doi":"10.1016/j.gce.2024.06.003","DOIUrl":"10.1016/j.gce.2024.06.003","url":null,"abstract":"<div><div>Advanced technologies like deep learning have accelerated the discovery of novel chemical reactions, especially in the field of organic synthesis. With hundreds of thousands of reactions available for reference, one way to effectively leverage them is by classifying chemical reactions into different clusters based on their specific characteristics, which makes target-guided navigation in the vast chemical space possible. Although previous attempts that apply deep learning to reaction classification tasks have made substantial progress, developing a model with good interpretability as well as high accuracy for large-scale reaction classification tasks remains an open question. In this work, a deep learning-based model for a large-scale reaction classification task is first constructed by utilizing pre-trained BERT and autoencoder. Then, the model is trained under the open-source dataset USPTO_TPL which contains recorded reactions of up to 1000 different types. The multi-classification accuracy of the model on the testing dataset is 99.382%, showing its great potential for practical use. Besides, a reaction similarity map is presented to correlate the reactions in the USPTO_TPL dataset based on their sigma-profile-based statistical features. Finally, representative reactions from the testing dataset are provided to illustrate the model's effectiveness on the reaction classification task.</div></div>","PeriodicalId":66474,"journal":{"name":"Green Chemical Engineering","volume":"6 2","pages":"Pages 181-192"},"PeriodicalIF":9.1,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141410117","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}