Application of Artificial Neural Networks for Catalysis: A Review

Enhancing Molecular Energy Predictions with Physically Constrained Modifications to the Neural Network Potential

Exclusively prioritizing the precision of energy prediction frequently proves inadequate in satisfying multifaceted requirements. A heightened focus is warranted on assessing the rationality of potential energy curves predicted by machine learning-based force fields (MLFFs), alongside evaluating the pragmatic utility of these MLFFs. This study introduces SWANI, an optimized neural network potential stemming from the ANI framework. Through the incorporation of supplementary physical constraints, SWANI aligns more cohesively with chemical expectations, yielding rational potential energy profiles. It also exhibits superior predictive precision compared with that of the ANI model. Additionally, a comprehensive comparison is conducted between SWANI and a prominent graph neural network-based model. The findings indicate that SWANI outperforms the latter, particularly for molecules exceeding the dimensions of the training set. This outcome underscores SWANI's exceptional capacity for generalization and its proficiency in handling larger molecular systems.

Explainable machine-learning predictions for catalysts in CO2-assisted propane oxidative dehydrogenation

Propylene is an important raw material in the chemical industry that needs new routes for its production to meet the demand. The CO2-assisted oxidative dehydrogenation of propane (CO2-ODHP) represents an ideal way to produce propylene and uses the greenhouse gas CO2. The design of catalysts with high efficiency is crucial in CO2-ODHP research. Data-driven machine learning is currently of great interest and gaining popularity in the heterogeneous catalysis field for guiding catalyst development. In this study, the reaction results of CO2-ODHP reported in the literature are combined and analyzed with varied machine learning algorithms such as artificial neural network (ANN), k-nearest neighbors (KNN), support vector regression (SVR) and random forest regression (RF)and were used to predict the propylene space-time yield. Specifically, the RF method serves as a superior performing algorithm for propane conversion and propylene selectivity prediction, and SHapley Additive exPlanations (SHAP) based on the Shapley value performs fine model interpretation. Reaction conditions and chemical components show different impacts on catalytic performance. The work provides a valuable perspective for the machine learning in light alkane conversion, and helps us to design catalyst by catalytic performance hidden in the data of literatures.

Feed-Forward Neural Network for Predicting Enantioselectivity of the Asymmetric Negishi Reaction

Density functional theory (DFT) is a powerful tool to model transition state (TS) energies to predict selectivity in chemical synthesis. However, a successful multistep synthesis campaign must navigate energetically narrow differences in pathways that create some limits to rapid and unambiguous application of DFT to these problems. While powerful data science techniques may provide a complementary approach to overcome this problem, doing so with the relatively small data sets that are widespread in organic synthesis presents a significant challenge. Herein, we show that a small data set can be labeled with features from DFT TS calculations to train a feed-forward neural network for predicting enantioselectivity of a Negishi cross-coupling reaction with P-chiral hindered phosphines. This approach to modeling enantioselectivity is compared with conventional approaches, including exclusive use of DFT energies and data science approaches, using features from ligands or ground states with neural network architectures.

Accelerating explicit solvent models of heterogeneous catalysts with machine learning interatomic potentials

Realistically modelling how solvents affect catalytic reactions is a longstanding challenge due to its prohibitive computational cost. Typically, an explicit atomistic treatment of the solvent molecules is needed together with molecular dynamics (MD) simulations and enhanced sampling methods. Here, we demonstrate the utility of machine learning interatomic potentials (MLIPs), coupled with active learning, to enable fast and accurate explicit solvent modelling of adsorption and reactions on heterogeneous catalysts. MLIPs trained on-the-fly were able to accelerate ab initio MD simulations by up to 4 orders of magnitude while reproducing with high fidelity the geometrical features of water in the bulk and at metal-water interfaces. Using these ML-accelerated simulations, we accurately predicted key catalytic quantities such as the adsorption energies of CO*, OH*, COH*, HCO*, and OCCHO* on Cu surfaces and the free energy barriers of C-H scission of ethylene glycol over Cu and Pd surfaces, as validated with ab initio calculations. We envision that such simulations will pave the way towards detailed and realistic studies of solvated catalysts at large time- and length-scales.

Artificial intelligence-aided preparation of perovskite SrFexZr1-xO3-δ catalysts for ozonation degradation of organic pollutant concentrated water after membrane treatment

Membrane technology has been widely used to treat wastewater from a variety of industries, but it also results in a large amount of concentrated wastewater containing organic pollutants after membrane treatment, which is challenging to decompose. Here in this work, a series of perovskite SrFe_xZr_1-xO_3-δ catalysts were prepared via a modified co-precipitation method and evaluated for catalytic ozone oxidative degradation of m-cresol. An artificial neural intelligence networks (ANN) model was employed to train the experimental data to optimize the preparation parameters of catalysts, with SrFe_0.13Zr_0.87O_3-δ being the optimal catalysts. The resultant catalysts before and after reduction were then thoroughly characterized and tested for m-cresol degradation. It was found that the co-doping of Fe and Zr at the B-site and the improvement of oxygen vacancies and oxygen active species by reduction dramatically increased TOC removal rates up to 5 times compared with ozone alone, with the conversion rate of m-cresol reaching 100%. We also proposed a possible mechanism for m-cresol degradation via investigating the intermediates using GC-MS, and confirmed the good versatility of the reduced SrFe_0.13Zr_0.87O_3-δ catalyst to remove other common organic pollutants in concentrated wastewater. This work demonstrates new prospects for the use of perovskite materials in wastewater treatment.

Ultraprecise Controller for Piezoelectric Actuators Based on Deep Learning and Model Predictive Control

Piezoelectric actuators (PEA) are high-precision devices used in applications requiring micrometric displacements. However, PEAs present non-linearity phenomena that introduce drawbacks at high precision applications. One of these phenomena is hysteresis, which considerably reduces their performance. The introduction of appropriate control strategies may improve the accuracy of the PEAs. This paper presents a high precision control scheme to be used at PEAs based on the model-based predictive control (MPC) scheme. In this work, the model used to feed the MPC controller has been achieved by means of artificial neural networks (ANN). This approach simplifies the obtaining of the model, since the achievement of a precise mathematical model that reproduces the dynamics of the PEA is a complex task. The presented approach has been embedded over the dSPACE control platform and has been tested over a commercial PEA, supplied by Thorlabs, conducting experiments to demonstrate improvements of the MPC. In addition, the results of the MPC controller have been compared with a proportional-integral-derivative (PID) controller. The experimental results show that the MPC control strategy achieves higher accuracy at high precision PEA applications such as tracking periodic reference signals and sudden reference change.

Process schemes of ethanol coupling to C4 olefins based on a genetic algorithm for back propagation neural network optimization

C4 olefin is an important feedstock for the chemical industry. Designing an effective and stable industrial process for preparing C4 olefin from renewable ethanol is crucial for further sustainable chemical production. In this study, a comprehensive evaluation system of an experimental scheme was constructed based on the Analytic Hierarchy Process/Entropy Weight Method-Technique for Order Preference by Similarity to Ideal Solution (AHP/EWM-TOPSIS) and Chemical production indicators. Using this evaluation system, a Back Propagation Neural Network (BPNN) based on a Genetic Algorithm (GA) was constructed after simulating C4 olefin production conditions using the Improved Mixed Congruential method. Subsequently, the production scheme with the highest evaluation score was determined when the temperature was not limited and when the temperature was lower than 350°C through a series of mathematical models. Overall, our mathematical models provide guidance for the commercial production of ethanol to butene and effectively reduce the risk of scaling up the chemical process to pilot or industrial scale.

Artificial intelligence techniques in electrochemical processes for water and wastewater treatment: a review

In recent years, artificial intelligence (AI) techniques have been recognized as powerful techniques. In this work, AI techniques such as artificial neural networks (ANNs), support vector machines (SVM), adaptive neuro-fuzzy inference system (ANFIS), genetic algorithms (GA), and particle swarm optimization (PSO), used in water and wastewater treatment processes, are reviewed. This paper describes applications of the mentioned AI techniques for the modelling and optimization of electrochemical processes for water and wastewater treatment processes. Most research in the mentioned scope of study consists of electrooxidation, electrocoagulation, electro-Fenton, and electrodialysis. Also, ANNs have been the most frequent technique used for modelling and optimization of these processes. It was shown that most of the AI models have been built with a relatively low number of samples (< 150) in data sets. This points out the importance of reliability and robustness of the AI models derived from these techniques. We show how to improve the performance and reduce the uncertainty of these developed black-box data-driven models. From the perspectives of both experiment and theory, this review demonstrates how AI techniques can be effectively adapted to electrochemical processes for water and wastewater treatment to model and optimize these processes.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40201-022-00835-w.

Computational Analysis of a Multi-Layered Skin and Cardiac Pacemaker Model Based on Neural Network Approach

The presented study discusses the possible disturbing effects of the electromagnetic field of antennas used in mobile phones or WiFi technologies on the pacemaker in the patient's body. This study aims to obtain information on how the thickness of skin layers (such as the thickness of the hypodermis) can affect the activity of a pacemaker exposed to a high-frequency electromagnetic field. This study describes the computational mathematical analysis and modeling of the heart pacemaker inserted under the skin exposed to various electromagnetic field sources, such as a PIFA antenna and a tuned dipole antenna. The finite integration technique (FIT) for a pacemaker model was implemented within the commercially available CST Microwave simulation software studio. Likewise, the equations that describe the mathematical relationship between the subcutaneous layer thickness and electric field according to different exposures of a tuned dipole and a PIFA antenna are used and applied for training a neural network. The main output of this study is the creation of a mathematical model and a multilayer feedforward neural network, which can show the dependence of the thickness of the hypodermis on the size of the electromagnetic field, from the simulated data from CST Studio.

Design of an artificial neural network to predict mortality among COVID-19 patients

Introduction

The fast pandemic of coronavirus disease 2019 (COVID-19) has challenged clinicians with many uncertainties and ambiguities regarding disease outcomes and complications. To deal with these uncertainties, our study aimed to develop and evaluate several artificial neural networks (ANNs) to predict the mortality risk in hospitalized COVID-19 patients.

Material and methods

The data of 1710 hospitalized COVID-19 patients were used in this retrospective and developmental study. First, a Chi-square test (P < 0.05), Eta coefficient (η > 0.4), and binary logistics regression (BLR) analysis were performed to determine the factors affecting COVID-19 mortality. Then, using the selected variables, two types of feed-forward (FF) models, including the back-propagation (BP) and distributed time delay (DTD) were trained. The models' performance was assessed using mean squared error (MSE), error histogram (EH), and area under the ROC curve (AUC-ROC) metrics.

Results

After applying the univariate and multivariate analysis, 13 variables were selected as important features in predicting COVID-19 mortality at P < 0.05. A comparison of the two ANN architectures using the MSE showed that the BP-ANN (validation error: 0.067, most of the classified samples having 0.049 and 0.05 error rates, and AUC-ROC: 0.888) was the best model.

Conclusions

Our findings show the acceptable performance of ANN for predicting the risk of mortality in hospitalized COVID-19 patients. Application of the developed ANN-based CDSS in a real clinical environment will improve patient safety and reduce disease severity and mortality.

Applications of Machine Learning in Alloy Catalysts: Rational Selection and Future Development of Descriptors

At present, alloys have broad application prospects in heterogeneous catalysis, due to their various catalytic active sites produced by their vast element combinations and complex geometric structures. However, it is the diverse variables of alloys that lead to the difficulty in understanding the structure-property relationship for conventional experimental and theoretical methods. Fortunately, machine learning methods are helpful to address the issue. Machine learning can not only deal with a large number of data rapidly, but also help establish the physical picture of reactions in multidimensional heterogeneous catalysis. The key challenge in machine learning is the exploration of suitable general descriptors to accurately describe various types of alloy catalysts, which help reasonably design catalysts and efficiently screen candidates. In this review, several kinds of machine learning methods commonly used in the design of alloy catalysts is introduced, and the applications of various reactivity descriptors corresponding to different alloy systems is summarized. Importantly, this work clarifies the existing understanding of physical picture of heterogeneous catalysis, and emphasize the significance of rational selection of universal descriptors. Finally, the development of heterogeneous catalytic descriptors for machine learning are presented.

Kinetics of the Direct DME Synthesis: State of the Art and Comprehensive Comparison of Semi-Mechanistic, Data-Based and Hybrid Modeling Approaches

Hybrid kinetic models represent a promising alternative to describe and evaluate the effect of multiple variables in the performance of complex chemical processes, since they combine system knowledge and extrapolability of the (semi-)mechanistic models in a wide range of reaction conditions with the adaptability and fast convergence of data-based approaches (e.g., artificial neural networks—ANNs). For the first time, a hybrid kinetic model for the direct DME synthesis was developed consisting of a reactor model, i.e., balance equations, and an ANN for the reaction kinetics. The accuracy, computational time, interpolation and extrapolation ability of the new hybrid model were compared to those of aumped and a data-based model with the same validity range, using both simulations and experiments. The convergence of parameter estimation and simulations with the hybrid model is much faster than with theumped model, and the predictions show a greater degree of accuracy within the models’ validity range. A satisfactory dimension and range extrapolation was reached when the extrapolated variable was included in the knowledge module of the model. This feature is particularly dependent on the network architecture and phenomena covered by the underlying model, andess on the experimental conditions evaluated during model development.

Application of computational approach in plastic pyrolysis kinetic modelling: a review

During the past decade, pyrolysis routes have been identified as one of the most promising solutions for plastic waste management. However, the industrial adoption of such technologies has been limited and several unresolved blind spots hamper the commercial application of pyrolysis. Despite many years and efforts to explain pyrolysis models based on global kinetic approaches, recent advances in computational modelling such as machine learning and quantum mechanics offer new insights. For example, the kinetic and mechanistic information about plastic pyrolysis reactions necessary for scaling up processes is unravelling. This selective literature review reveals some of the foundational knowledge and accurate views on the reaction pathways, product yields, and other features of pyrolysis created by these new tools. Pyrolysis routes mapped by machine learning and quantum mechanics will gain more relevance in the coming years, especially studies that combine computational models with different time and scale resolutions governed by “first principles.” Existing research suggests that, as machine learning is further coupled to quantum mechanics, scientists and engineers will better predict products, yields, and compositions, as well as more complicated features such as ideal reactor design.

Demodulation of EM Telemetry Data Using Fuzzy Wavelet Neural Network with Logistic Response

Data telemetry is a critical element of successful unconventional well drilling operations, involving the transmission of information about the well-surrounding geology to the surface in real-time to serve as the basis for geosteering and well planning. However, the data extraction and code recovery (demodulation) process can be a complicated system due to the non-linear and time-varying characteristics of high amplitude surface noise. In this work, a novel model fuzzy wavelet neural network (FWNN) that combines the advantages of the sigmoidal logistic function, fuzzy logic, a neural network, and wavelet transform was established for the prediction of the transmitted signal code from borehole to surface with effluent quality. Moreover, the complete workflow involved the pre-processing of the dataset via an adaptive processing technique before training the network and a logistic response algorithm for acquiring the optimal parameters for the prediction of signal codes. A data reduction and subtractive scheme are employed as a pre-processing technique to better characterize the signals as eight attributes and, ultimately, reduce the computation cost. Furthermore, the frequency-time characteristics of the predicted signal are controlled by selecting an appropriate number of wavelet bases “N” and the pre-selected range for pij3 to be used prior to the training of the FWNN system. The results, leading to the prediction of the BPSK characteristics, indicate that the pre-selection of the N value and pij3 range provides a significantly accurate prediction. We validate its prediction on both synthetic and pseudo-synthetic datasets. The results indicated that the fuzzy wavelet neural network with logistic response had a high operation speed and good quality prediction, and the correspondingly trained model was more advantageous than the traditional backward propagation network in prediction accuracy. The proposed model can be used for analyzing signals with a signal-to-noise ratio lower than 1 dB effectively, which plays an important role in the electromagnetic telemetry system.

Machine Learning in Screening High Performance Electrocatalysts for CO2 Reduction

Converting CO₂ into carbon-based fuels is promising for relieving the greenhouse gas effect and the energy crisis. However, the selectivity and efficiency of current electrocatalysts for CO₂ reductions are still not satisfactory. In this paper, the development of machine learning methods in screening CO₂ reduction electrocatalysts over the recent years is reviewed. Through high-throughput calculation of some key descriptors such as adsorption energies, d-band center, and coordination number by well-constructed machine learning models, the catalytic activity, optimal composition, active sites, and CO₂ reduction reaction pathway over various possible materials can be predicted and understood. Machine learning is now realized as a fast and low-cost method to effectively explore high performance electrocatalysts for CO₂ reduction.

Artificial Neural Networks in Modeling of Dewaterability of Sewage Sludge

Mechanical dewatering is a key process in the management of sewage sludge. However, the drainage efficiency depends on a number of factors, from the type and dose of the conditioning agent to the parameters of the drainage device. The selection of appropriate methods and parameters of conditioning and dewatering of sewage sludge is the task of laboratory work. This work can be accelerated through the use of artificial neural network (ANNs). The paper discusses the possibilities of using ANNs in predicting the dewatering efficiency of physically conditioned sludge. The input variables were only four parameters characterizing the conditioning methods and the dewatering method by centrifugation. These were the dose of the sludge skeleton builders (cement, gypsum, fly ash, and liquid glass), sonication parameters (sonication amplitude and time), and relative centrifugal force. Dewatering efficiency parameters such as sludge hydration and separation factor were output variables. Due to the nature of the research problem, two nonlinear networks were selected: a multilayer perceptron and a radial neural network. Based on the results of the prediction of artificial neural networks, it was found that these networks can be used to forecast the effectiveness of municipal sludge dewatering. The prediction error did not exceed 1.0% of the real value. ANN can therefore be useful in optimizing the dewatering process. In the case of the conducted research, it was the optimization of the sludge dewatering efficiency as a function of the type and parameters of conditioning factors. Therefore, it is possible to predict the dewatering efficiency of sludge that has not been tested in the laboratory, for example, with the use of other doses of physical conditioner. However, the condition for correct prediction and optimization was the use of a large dataset in the neural network training process.

Early Warning Method for Public Health Emergency Under Artificial Neural Network in the Context of Deep Learning

The purpose is to minimize the substantial losses caused by public health emergencies to people’s health and daily life and the national economy. The tuberculosis data from June 2017 to 2019 in a city are collected. The Structural Equation Model (SEM) is constructed to determine the relationship between hidden and explicit variables by determining the relevant indicators and parameter estimation. The prediction model based on Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) is constructed. The method’s effectiveness is verified by comparing the prediction model’s loss value and accuracy in training and testing. Meanwhile, 50 pieces of actual cases are tested, and the warning level is determined according to the T-value. The results show that comparing and analyzing ANN, CNN, and the hybrid network of ANN and CNN, the hybrid network’s accuracy (95.1%) is higher than the other two algorithms, 89.1 and 90.1%. Also, the hybrid network has sound prediction effects and accuracy when predicting actual cases. Therefore, the early warning method based on ANN in deep learning has better performance in public health emergencies’ early warning, which is significant for improving early warning capabilities.

High-Performance Tracking for Piezoelectric Actuators Using Super-Twisting Algorithm Based on Artificial Neural Networks

Piezoelectric actuators (PEA) are frequently employed in applications where nano-Micr-odisplacement is required because of their high-precision performance. However, the positioning is affected substantially by the hysteresis which resembles in an nonlinear effect. In addition, hysteresis mathematical models own deficiencies that can influence on the reference following performance. The objective of this study was to enhance the tracking accuracy of a commercial PEA stack actuator with the implementation of a novel approach which consists in the use of a Super-Twisting Algorithm (STA) combined with artificial neural networks (ANN). A Lyapunov stability proof is bestowed to explain the theoretical solution. Experimental results of the proposed method were compared with a proportional-integral-derivative (PID) controller. The outcomes in a real PEA reported that the novel structure is stable as it was proved theoretically, and the experiments provided a significant error reduction in contrast with the PID.

Prediction of Active Microwave Backscatter Over Snow-Covered Terrain Across Western Colorado Using a Land Surface Model and Support Vector Machine Regression

The main objective of this article is to develop a physically constrained support vector machine (SVM) to predict C-band backscatter over snow-covered terrain as a function of geophysical inputs that reasonably represent the relevant characteristics of the snowpack. Sentinel-1 observations, in conjunction with geophysical variables from the Noah-MP land surface model, were used as training targets and input datasets, respectively. Robustness of the SVM prediction was analyzed in terms of training targets, training windows, and physical constraints related to snow liquid water content. The results showed that a combination of ascending and descending overpasses yielded the highest coverage of prediction (15.2%) while root mean square error (RMSE) ranged from 2.06 to 2.54 dB and unbiased RMSE ranged from 1.54 to 2.08 dB, but that the combined overpasses were degraded compared with ascending-only and descending-only training target sets due to the mixture of distinctive microwave signals during different times of the day (i.e., 6 A.M. versus 6 P.M. local time). Elongation of the training window length also increased the spatial coverage of prediction (given the sparsity of the training sets), but resulted in introducing more random errors. Finally, delineation of dry versus wet snow pixels for SVM training resulted in improving the accuracy of predicted backscatter relative to training on a mixture of dry and wet snow conditions. The overall results suggest that the prediction accuracy of the SVM was strongly linked with the first-order physics of the electromagnetic response of different snow conditions.

Increasing the Efficiency of Optimized V-SBA-15 Catalysts in the Selective Oxidation of Methane to Formaldehyde by Artificial Neural Network Modelling

The present study investigates the possibility of improving the selective oxidation of methane to formaldehyde over V-SBA-15 catalysts in two different ways. In a classical approach of catalyst optimization, the in situ synthesis of V-SBA-15 catalysts was optimized with regard to the applied pH value. Among the set of catalysts synthesized, a higher amount of incorporated vanadium, a higher content of polymeric VOx species as well as a less ordered structure of the support material were observed by increasing the pH values from 2.0 to 3.0. An optimum in performance during the selective oxidation of methane to formaldehyde with respect to activity and selectivity was found over V-SBA-15 prepared at a pH value of 2.5. With this knowledge, we have now evaluated the possibilities of reaction control using this catalyst. Specifically, artificial neural network modelling was applied after the collection of 232 training samples for obtaining insight into the influence of different reaction parameters (temperature; gas hourly space velocity (GHSV); and concentration of O2, N2 and H2O) onto methane conversion and selectivity towards formaldehyde. This optimization of reaction conditions resulted in an outstanding high space-time yield of 13.6 kgCH2O∙kgcat∙h−1.

Modeling of Mechanical Properties of Clay-Reinforced Polymer Nanocomposites Using Deep Neural Network

Due to the non-linear characteristics of the processing parameters, predicting the desired properties of nanocomposites using the conventional regression approach is often unsatisfactory. Thus, it is essential to use a machine learning approach to determine the optimum processing parameters. In this study, a backpropagation deep neural network (DNN) with nanoclay and compatibilizer content, and processing parameters as input, was developed to predict the mechanical properties, including tensile modulus and tensile strength, of clay-reinforced polyethylene nanocomposites. The high accuracy of the developed model proves that DNN can be used as an efficient tool for predicting mechanical properties of the nanocomposites in terms of four independent parameters.

Response surface methodology and artificial neural network for remediation of acid orange 7 using TiO2-P25: optimization and modeling approach

The primary responsibility for continuously discharging toxic organic pollutants into water bodies and open environments is the increase in industrial and agricultural activities. Developing economical and suitable methods to continuously remove organic pollutants from wastewater is highly essential. The aim of the present research was to apply response surface methodology (RSM) and artificial neural networks (ANNs) for optimization and modeling of photocatalytic degradation of acid orange 7 (AO7) by commercial TiO2-P25 nanoparticles (TNPs). Dose of TNPs, pH, and AO7 concentration were selected as investigated parameters. RSM results reveal the reflective rate of AO7 removal of ~ 94.974% was obtained at pH 7.599, TNP dose of 0.748 g/L, and AO7 concentration of 28.483 mg/L. The resulting quadratic model is satisfactory with the highest coefficient of determination (R2) between the predicted and experimental data (R2 = 0.98 and adjusted R2 = 0.954). On the other hand, ANNs were successfully employed for modeling of AO7 degradation process. The proposed ANN model was absolutely fitted with experimental results producing the highest R2. Furthermore, root mean square error (RMSE), mean average deviation (MAD), absolute average relative error (AARE), and mean square error (MSE) were examined more to compare the predictive capabilities of ANN and RSM models. The experimental data was well fitted into pseudo-first-order and pseudo-second-order kinetics with more accuracy. Thermodynamic parameters, namely enthalpy, entropy, Gibbs' free energy, and activation energy, were also evaluated to suggest the nature of the degradation process. The increase of temperature was analyzed to be more suitable for the fast removal of AO7 over TNPs. Graphical abstract.

Predicting Absenteeism and Temporary Disability Using Machine Learning: a Systematic Review and Analysis

The main objective of this paper is to present a systematic analysis and review of the state of the art regarding the prediction of absenteeism and temporary incapacity using machine learning techniques. Moreover, the main contribution of this research is to reveal the most successful prediction models available in the literature. A systematic review of research papers published from 2010 to the present, related to the prediction of temporary disability and absenteeism in available in different research databases, is presented in this paper. The review focuses primarily on scientific databases such as Google Scholar, Science Direct, IEEE Xplore, Web of Science, and ResearchGate. A total of 58 articles were obtained from which, after removing duplicates and applying the search criteria, 18 have been included in the review. In total, 44% of the articles were published in 2019, representing a significant growth in scientific work regarding these indicators. This study also evidenced the interest of several countries. In addition, 56% of the articles were found to base their study on regression methods, 33% in classification, and 11% in grouping. After this systematic review, the efficiency and usefulness of artificial neural networks in predicting absenteeism and temporary incapacity are demonstrated. The studies regarding absenteeism and temporary disability at work are mainly conducted in Brazil and India, which are responsible for 44% of the analyzed papers followed by Saudi Arabia, and Australia which represented 22%. ANNs are the most used method in both classification and regression models representing 83% and 80% of the analyzed works, respectively. Only 10% of the literature use SVM, which is the less used method in regression models. Moreover, Naïve Bayes is the less used method in classification models representing 17%.

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

A machine learning exploration of the chemical space surrounding Vaska's complex.

Homogeneous catalysis using transition metal complexes is ubiquitously used for organic synthesis, as well as technologically relevant in applications such as water splitting and CO₂ reduction. The key steps underlying homogeneous catalysis require a specific combination of electronic and steric effects from the ligands bound to the metal center. Finding the optimal combination of ligands is a challenging task due to the exceedingly large number of possibilities and the non-trivial ligand–ligand interactions. The classic example of Vaska's complex, trans-[Ir(PPh₃)₂(CO)(Cl)], illustrates this scenario. The ligands of this species activate iridium for the oxidative addition of hydrogen, yielding the dihydride cis-[Ir(H)₂(PPh₃)₂(CO)(Cl)] complex. Despite the simplicity of this system, thousands of derivatives can be formulated for the activation of H₂, with a limited number of ligands belonging to the same general categories found in the original complex. In this work, we show how DFT and machine learning (ML) methods can be combined to enable the prediction of reactivity within large chemical spaces containing thousands of complexes. In a space of 2574 species derived from Vaska's complex, data from DFT calculations are used to train and test ML models that predict the H₂-activation barrier. In contrast to experiments and calculations requiring several days to be completed, the ML models were trained and used on a laptop on a time-scale of minutes. As a first approach, we combined Bayesian-optimized artificial neural networks (ANN) with features derived from autocorrelation and deltametric functions. The resulting ANNs achieved high accuracies, with mean absolute errors (MAE) between 1 and 2 kcal mol^–1, depending on the size of the training set. By using a Gaussian process (GP) model trained with a set of selected features, including fingerprints, accuracy was further enhanced. Remarkably, this GP model minimized the MAE below 1 kcal mol^–1, by using only 20% or less of the data available for training. The gradient boosting (GB) method was also used to assess the relevance of the features, which was used for both feature selection and model interpretation purposes. Features accounting for chemical composition, atom size and electronegativity were found to be the most determinant in the predictions. Further, the ligand fragments with the strongest influence on the H₂-activation barrier were identified.

A Design-to-Device Pipeline for Data-Driven Materials Discovery

The world needs new materials to stimulate the chemical industry in key sectors of our economy: environment and sustainability, information storage, optical telecommunications, and catalysis. Yet, nearly all functional materials are still discovered by "trial-and-error", of which the lack of predictability affords a major materials bottleneck to technological innovation. The average "molecule-to-market" lead time for materials discovery is currently 20 years. This is far too long for industrial needs, as highlighted by the Materials Genome Initiative, which has ambitious targets of up to 4-fold reductions in average molecule-to-market lead times. Such a large step change in progress can only be realistically achieved if one adopts an entirely new approach to materials discovery. Fortunately, a fundamentally new approach to materials discovery has been emerging, whereby data science with artificial intelligence offers a prospective solution to speed up these average molecule-to-market lead times.This approach is known as data-driven materials discovery. Its broad prospects have only recently become a reality, given the timely and major advances in "big data", artificial intelligence, and high-performance computing (HPC). Access to massive data sets has been stimulated by government-regulated open-access requirements for data and literature. Natural-language processing (NLP) and machine-learning (ML) tools that can mine data and find patterns therein are becoming mainstream. Exascale HPC capabilities that can aid data mining and pattern recognition and also generate their own data from calculations are now within our grasp. These timely advances present an ideal opportunity to develop data-driven materials-discovery strategies to systematically design and predict new chemicals for a given device application.This Account shows how data science can afford materials discovery via a four-step "design-to-device" pipeline that entails (1) data extraction, (2) data enrichment, (3) material prediction, and (4) experimental validation. Massive databases of cognate chemical and property information are first forged from "chemistry-aware" natural-language-processing tools, such as ChemDataExtractor, and enriched using machine-learning methods and high-throughput quantum-chemical calculations. New materials for a bespoke application can then be predicted by mining these databases with algorithmic encodings of relationships between chemical structures and physical properties that are known to deliver functional materials. These may take the form of classification, enumeration, or machine-learning algorithms. A data-mining workflow short-lists these predictions to a handful of lead candidate materials that go forward to experimental validation. This design-to-device approach is being developed to offer a roadmap for the accelerated discovery of new chemicals for functional applications. Case studies presented demonstrate its utility for photovoltaic, optical, and catalytic applications. While this Account is focused on applications in the physical sciences, the generic pipeline discussed is readily transferable to other scientific disciplines such as biology and medicine.

Understanding the ML black box with simple descriptors to predict cluster–adsorbate interaction energy

Density functional theory (DFT) is currently one of the most accurate and yet practical theories used to gain insight into the properties of materials.

The CSD and knowledge databases: from answers to questions

We develop tools for extracting new information on crystal structures from crystallographic databases and show how to use these tools in the design of coordination compounds.

Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns

Computational Chemistry is currently a synergistic assembly between ab initio calculations, simulation, machine learning (ML) and optimization strategies for describing, solving and predicting chemical data and related phenomena. These include accelerated literature searches, analysis and prediction of physical and quantum chemical properties, transition states, chemical structures, chemical reactions, and also new catalysts and drug candidates. The generalization of scalability to larger chemical problems, rather than specialization, is now the main principle for transforming chemical tasks in multiple fronts, for which systematic and cost-effective solutions have benefited from ML approaches, including those based on deep learning (e.g. quantum chemistry, molecular screening, synthetic route design, catalysis, drug discovery). The latter class of ML algorithms is capable of combining raw input into layers of intermediate features, enabling bench-to-bytes designs with the potential to transform several chemical domains. In this review, the most exciting developments concerning the use of ML in a range of different chemical scenarios are described. A range of different chemical problems and respective rationalization, that have hitherto been inaccessible due to the lack of suitable analysis tools, is thus detailed, evidencing the breadth of potential applications of these emerging multidimensional approaches. Focus is given to the models, algorithms and methods proposed to facilitate research on compound design and synthesis, materials design, prediction of binding, molecular activity, and soft matter behavior. The information produced by pairing Chemistry and ML, through data-driven analyses, neural network predictions and monitoring of chemical systems, allows (i) prompting the ability to understand the complexity of chemical data, (ii) streamlining and designing experiments, (ii) discovering new molecular targets and materials, and also (iv) planning or rethinking forthcoming chemical challenges. In fact, optimization engulfs all these tasks directly.

Modeling and optimization of fixed mode dual effect (photocatalysis and photo-Fenton) assisted Metronidazole degradation using ANN coupled with genetic algorithm

The study presents the novel concept of application of fixed bed-batch mode in-situ dual effect of degradation of photo-Fenton and photocatalysis using composite material composed of fuller's earth and foundry sand for the removal of antibiotic Metronidazole. The composite material was involved in the subsequent leaching of iron prompting to in-situ photo-Fenton reactions while TiO₂ layer immobilized upon the support involved in photocatalysis. Dual process facilitated the significant reduction in treatment time as 80% of the compound degraded with 30 min of the reaction. Both the processes almost took 180 min for 50% degradation, when applied individually. No doubt, there was an astonishing increase in the rate constant. An artificial neural network model coupled with the genetic algorithm was employed for the optimization of various parameters like H₂O₂ dose, treatment time, number of beads, pH, etc. Various characterizations have been performed to confirm the novelty of the process. Extended recyclability up to 70 recycles of these composite beads really confirmed the feasibility of this technology for field-scale applications.

Artificial Intelligence Modelling Approach for the Prediction of CO-Rich Hydrogen Production Rate from Methane Dry Reforming

This study investigates the applicability of the Leven–Marquardt algorithm, Bayesian regularization, and a scaled conjugate gradient algorithm as training algorithms for an artificial neural network (ANN) predictively modeling the rate of CO and H2 production by methane dry reforming over a Co/Pr2O3 catalyst. The dataset employed for the ANN modeling was obtained using a central composite experimental design. The input parameters consisted of CH4 partial pressure, CO2 partial pressure, and reaction temperature, while the target parameters included the rate of CO and H2 production. A neural network architecture of 3 13 2, 3 15 2, and 3 15 2 representing the input layer, hidden neuron layer, and target (output) layer were employed for the Leven–Marquardt, Bayesian regularization, and scaled conjugate gradient training algorithms, respectively. The ANN training with each of the algorithms resulted in an accurate prediction of the rate of CO and H2 production. The best prediction was, however, obtained using the Bayesian regularization algorithm with the lowest standard error of estimates (SEE). The high values of coefficient of determination (R2 > 0.9) obtained from the parity plots are an indication that the predicted rates of CO and H2 production were strongly correlated with the observed values.