Leveraging Machine Learning Models To Optimize Electrochemical CO 2 Capture from Treated Used Water

Machine learning holds the potential to be a powerful tool to aid in designing catalytic and sustainable chemical systems. However, it is important for experimental researchers to understand the capabilities of different machine learning models when trained on experimental data. In this work, we trained three different machine learning algorithms (decision tree, random forest, and multilayer perceptron) with a hand-curated dataset of 127 reaction conditions for electrocatalytic CO2 reduction on heterogeneous catalysts in aqueous electrolytes. The input to the machine learning models were the experimental conditions, and we posed four separate outputs to each of these machine learning algorithms: (1) if the number of proton-coupled electron transfer events was greater than two, (2) if carbon–carbon coupling occurred, (3) if ethylene was the major product, and (4) major product prediction. We observed that with a dataset of this size, all three machine learning models could achieve accuracies between 0.7 and 0.8 for the three binary classification problems (1, 2, and 3). Also, the shallow learning decision tree and random forest models performed equal to or better than the deep learning multilayer perceptron models. In the multiclass classification problem (i.e., predicting the product) the accuracy for all models decreased, with the random forest model producing the highest accuracy of 0.6. Analysis of the models showed that machine learning can independently arrive at conclusions that are well-known in the literature, e.g., that Cu is an important catalyst for producing high-carbon content products, and discern more-complicated patterns, with respect to feature importance.

Machine learning (ML) can be a powerful tool to expedite materials research, but the deployment for experimental research is often hindered by data scarcity and model uncertainty. An human‐in‐the‐loop procedure to tailor the implementation of ML for multicriteria optimization is described. The effectiveness of this procedure in the development of a nafion‐based membrane electrode assembly for electrochemical CO2 reduction reaction (CO2RR) into CO for two targets is demonstrated: energy efficiency (EE) and partial current density for CO2RR (). Model‐agnostic nonlinear correlation analyses identify the 11 features relevant to those targets. The three studied decision tree‐based ML models yield similar cross‐validation errors so an ad hoc feature analysis of the models is done with SHapley Additive exPlanations and nonlinear correlation techniques. The predicted EE‐ space and the functional dependency of the predictions are investigated to assess model plausibility. A genetic algorithm with CO production cost as the final target with subsequent validation experiments of candidate conditions is devised. The model chosen through ad hoc analysis yields the highest accuracy and the only one that can locate the Pareto front with a single round of experiments, demonstrating how appropriate model selection through careful inspection can greatly accelerate the research cycle.

Electrochemical CO2 reduction has attracted significant attention as a potential method to close the carbon cycle. In this study, we investigated the impact of the electrode fabrication and electrolysis conditions on the product selectivity of Ag electrocatalysts using a machine learning (ML) approach. Specifically, we explored the experimental conditions for obtaining the desired H2/CO mixture ratio with high CO efficiency. Notably, unlike previous ML‐based studies, we used experimental results as training data. This ML‐based approach allowed us to quantitatively assess the effect of experimental parameters on these targets with a reduced number of experimental trials (only 56 experiments). An inverse analysis based on the ML model suggested the optimal experimental conditions for achieving the desired characteristics of the electrolysis system, with the proposed conditions experimentally validated. This study constitutes the first demonstration of optimal experimental conditions for electrochemical CO2 reduction with desired characteristics using the experimental results as training data.

Evaluating Physician-AI Interaction for Multiple Myeloma Management: Paving the Path Towards Precision Oncology

Electrochemical reduction of CO2 is a promising method for converting a greenhouse gas into value-added products, utilizing renewable energy. Novel catalysts, electrode assemblies, and cell configurations are all necessary to achieve economically appealing performance. In my talk, I am going to present our most recent results on the electrochemical CO2 -to-CO and CO-to-ethylene conversion. I will show how proper cell components and operational conditions result in unprecedentedly high partial current densities in zero-gap cells. I will demonstrate the role of each component of the membrane electrode assembly, such as the catalysts, the porous transport layers, the membrane, and the ionomers. All these factors contribute to the local chemical environment, which builds-up during the electrolysis. I will show how proper electrolyte management is critically important in ensuring robust operation of the electrolyzer. In the second part of my talk, I will present our scale-up efforts carried out at eChemicles, resulting in an operational CO2 electrolyzer stack with 2500 cm2 single cell area, as well as a containerized prototype system. As an outlook, I will present the overview of a complex machine learning based approach, through which we aim to find the optimal operating conditions of such CO2 electrolyzer cells.

Accurate net load forecasting (NLF) is crucial in modern power systems and microgrids to ensure optimal operation and management. At the microgrid level, the increasing penetration of renewable energy sources requires more efficient methodologies for NLF, since statistical approaches fail to provide accurate forecasts. Performance limitations of existing statistical approaches can be overcome by leveraging machine learning (ML) models. The purpose of this work is to compare the forecasting performance of six ML models (artificial neural network, extreme gradient boosting, k-nearest neighbors, random forest, recurrent neural network and support vector regression) and identify the best-performing model for short-term net load forecasting (STNLF). The comparative analysis was carried out using historical net load and weather data from the renewable integrated microgrid of the University of Cyprus. The results demonstrated accuracies below 10% for all STNLF ML models. Random forest was the best performing model, achieving a normalized root mean square error of 4.32%. The findings illustrate the applicability of STNLF ML models in renewable integrated microgrids, which can benefit microgrid operators in managing and controlling their various assets.

A novel deep-learning technique for forecasting oil price volatility using historical prices of five precious metals in context of green financing – A comparison of deep learning, machine learning, and statistical models

Deep neural networks (DNNs) have shown success in image classification, with high accuracy in recognition of everyday objects. Performance of DNNs has traditionally been measured assuming human accuracy is perfect. In specific problem domains, however, human accuracy is less than perfect and a comparison between humans and machine learning (ML) models can be performed. In recognising everyday objects, humans have the advantage of a lifetime of experience, whereas DNN models are trained only with a limited image dataset. We have tried to compare performance of human learners and two DNN models on an image dataset which is novel to both, i.e. histological images. We thus aim to eliminate the advantage of prior experience that humans have over DNN models in image classification. Ten classes of tissues were randomly selected from the undergraduate first year histology curriculum of a Medical School in North India. Two machine learning (ML) models were developed based on the VGG16 (VML) and Inception V2 (IML) DNNs, using transfer learning, to produce a 10-class classifier. One thousand (1000) images belonging to the ten classes (i.e. 100 images from each class) were split into training (700) and validation (300) sets. After training, the VML and IML model achieved 85.67 and 89% accuracy on the validation set, respectively. The training set was also circulated to medical students (MS) of the college for a week. An online quiz, consisting of a random selection of 100 images from the validation set, was conducted on students (after obtaining informed consent) who volunteered for the study. 66 students participated in the quiz, providing 6557 responses. In addition, we prepared a set of 10 images which belonged to different classes of tissue, not present in training set (i.e. out of training scope or OTS images). A second quiz was conducted on medical students with OTS images, and the ML models were also run on these OTS images. The overall accuracy of MS in the first quiz was 55.14%. The two ML models were also run on the first quiz questionnaire, producing accuracy between 91 and 93%. The ML models scored more than 80% of medical students. Analysis of confusion matrices of both ML models and all medical students showed dissimilar error profiles. However, when comparing the subset of students who achieved similar accuracy as the ML models, the error profile was also similar. Recognition of ‘stomach’ proved difficult for both humans and ML models. In 04 images in the first quiz set, both VML model and medical students produced highly equivocal responses. Within these images, a pattern of bias was uncovered–the tendency of medical students to misclassify ‘liver’ tissue. The ‘stomach’ class proved most difficult for both MS and VML, producing 34.84% of all errors of MS, and 41.17% of all errors of VML model; however, the IML model committed most errors in recognising the ‘skin’ class (27.5% of all errors). Analysis of the convolution layers of the DNN outlined features in the original image which might have led to misclassification by the VML model. In OTS images, however, the medical students produced better overall score than both ML models, i.e. they successfully recognised patterns of similarity between tissues and could generalise their training to a novel dataset. Our findings suggest that within the scope of training, ML models perform better than 80% medical students with a distinct error profile. However, students who have reached accuracy close to the ML models, tend to replicate the error profile as that of the ML models. This suggests a degree of similarity between how machines and humans extract features from an image. If asked to recognise images outside the scope of training, humans perform better at recognising patterns and likeness between tissues. This suggests that ‘training’ is not the same as ‘learning’, and humans can extend their pattern-based learning to different domains outside of the training set.

Human-induced global warming, primarily attributed to the rise in atmospheric CO2, poses a substantial risk to the survival of humanity. While most research focuses on predicting annual CO2 emissions, which are crucial for setting long-term emission mitigation targets, the precise prediction of daily CO2 emissions is equally vital for setting short-term targets. This study examines the performance of 14 models in predicting daily CO2 emissions data from 1/1/2022 to 30/9/2023 across the top four polluting regions (China, India, the USA, and the EU27&UK). The 14 models used in the study include four statistical models (ARMA, ARIMA, SARMA, and SARIMA), three machine learning models (support vector machine (SVM), random forest (RF), and gradient boosting (GB)), and seven deep learning models (artificial neural network (ANN), recurrent neural network variations such as gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional-LSTM (BILSTM), and three hybrid combinations of CNN-RNN). Performance evaluation employs four metrics (R2, MAE, RMSE, and MAPE). The results show that the machine learning (ML) and deep learning (DL) models, with higher R2 (0.714–0.932) and lower RMSE (0.480–0.247) values, respectively, outperformed the statistical model, which had R2 (− 0.060–0.719) and RMSE (1.695–0.537) values, in predicting daily CO2 emissions across all four regions. The performance of the ML and DL models was further enhanced by differencing, a technique that improves accuracy by ensuring stationarity and creating additional features and patterns from which the model can learn. Additionally, applying ensemble techniques such as bagging and voting improved the performance of the ML models by approximately 9.6%, whereas hybrid combinations of CNN-RNN enhanced the performance of the RNN models. In summary, the performance of both the ML and DL models was relatively similar. However, due to the high computational requirements associated with DL models, the recommended models for daily CO2 emission prediction are ML models using the ensemble technique of voting and bagging. This model can assist in accurately forecasting daily emissions, aiding authorities in setting targets for CO2 emission reduction.

In modern distributed systems, load balancing plays a critical role in ensuring optimal performance and user experience. However, traditional static load balancing mechanisms often fail to adapt to dynamic traffic patterns, leading to performance degradation, increased latency, and inefficient resource utilization. This paper presents a novel approach that leverages machine learning (ML) models to enhance load balancing by predicting traffic fluctuations and intelligently distributing workloads in real time. By training ML models on historical traffic data and application performance metrics, we enable the system to make proactive decisions about resource allocation. This approach improves the ability to handle traffic surges during peak periods, minimizes latency, and optimizes infrastructure usage. The research outlines the implementation of various ML techniques, such as reinforcement learning and neural networks, into a microservices-based architecture, demonstrating how these models enhance both load balancing and auto-scaling capabilities. Empirical results from the study reveal that ML-driven load balancing reduces latency by up to 40%, improves resource efficiency, and lowers infrastructure costs by 30%, compared to traditional methods. The paper concludes by discussing the technical challenges, future possibilities of using more advanced ML algorithms, and the broader implications for cloud-native application performance.

For recent years, Machine Learning (ML) models have been proven to be useful in solving problems of a wide variety of fields such as medical, economic, manufacturing, transportation, energy, education, etc. With increased interest in ML models and advances in sensor technologies, ML models are being widely applied even in civil engineering domain. ML model enables analysis of large amounts of data, automation, improved decision making and provides more accurate prediction. While several state-of-the-art reviews have been conducted in each sub-domain (e.g., geotechnical engineering, structural engineering) of civil engineering or its specific application problems (e.g., structural damage detection, water quality evaluation), little effort has been devoted to comprehensive review on ML models applied in civil engineering and compare them across sub-domains. A systematic, but domain-specific literature review framework should be employed to effectively classify and compare the models. To that end, this study proposes a novel review approach based on the hierarchical classification tree “D-A-M-I-E (Domain-Application problem-ML models-Input data-Example case)”. “D-A-M-I-E” classification tree classifies the ML studies in civil engineering based on the (1) domain of the civil engineering, (2) application problem, (3) applied ML models and (4) data used in the problem. Moreover, data used for the ML models in each application examples are examined based on the specific characteristic of the domain and the application problem. For comprehensive review, five different domains (structural engineering, geotechnical engineering, water engineering, transportation engineering and energy engineering) are considered and the ML application problem is divided into five different problems (prediction, classification, detection, generation, optimization). Based on the “D-A-M-I-E” classification tree, about 300 ML studies in civil engineering are reviewed. For each domain, analysis and comparison on following questions has been conducted: (1) which problems are mainly solved based on ML models, (2) which ML models are mainly applied in each domain and problem, (3) how advanced the ML models are and (4) what kind of data are used and what processing of data is performed for application of ML models. This paper assessed the expansion and applicability of the proposed methodology to other areas (e.g., Earth system modeling, climate science). Furthermore, based on the identification of research gaps of ML models in each domain, this paper provides future direction of ML in civil engineering based on the approaches of dealing data (e.g., collection, handling, storage, and transmission) and hopes to help application of ML models in other fields.

Highlights Machine Learning (ML) models are identified, reviewed, and analyzed for HAB predictions. Data preprocessing is vital for efficient ML model development. ML models for toxin production and monitoring are limited. Abstract. Harmful algal blooms (HABs) are detrimental to livestock, humans, pets, the environment, and the global economy, which calls for a robust approach to their management. While process-based models can inform practitioners about HAB enabling conditions, they have inherent limitations in accurately predicting harmful algal blooms. To address these limitations, Machine Learning (ML) models can potentially leverage large volumes of IoT data to aid in near real-time predictions. ML models have evolved as efficient tools for understanding patterns and relationships between water quality parameters and HAB expansion. This review describes ML models currently used for predicting and forecasting HABs in freshwater ecosystems and presents model structures and their application for predicting algal parameters and related toxins. The review revealed that regression trees, random forest, Artificial Neural Network (ANN), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) are the most frequently used models for HABs monitoring. This review shows ML models' prowess in identifying significant variables influencing algal growth, HAB drivers, and multistep HAB prediction. Hybrid models also improve the prediction of algal-related parameters through improved optimization techniques and variable selection algorithms. While ML models often focus on algal biomass prediction, few studies apply ML models for toxin monitoring and prediction. This limitation can be associated with a lack of high-frequency toxin datasets for model development, and exploring this domain is encouraged. This review serves as a guide for policymakers and researchers to implement ML models for HAB prediction and reveals the potential of ML models for decision support and early prediction for HAB management. Keywords: Cyanobacteria, Freshwater, Harmful algal blooms, Machine learning, Water quality.

Machine learning (ML) and deep learning (DL) models can play an important role when it comes to modelling complicated processes. Such capability is necessary for hydrological and climate-related applications. Generally, ML models utilize precipitation and temperature time series of a basin as input to develop a lumped rainfall-runoff model to simulate streamflow at the basin outlet. However, when it is divided into several sub-basins, Graph Neural Networks (GNN) can consider each sub-basin as a node and link them together using a connectivity matrix to account for spatial variations of hydroclimatic variables. In this study, GNN and various ML models with different types of architecture, ranging from neural networks, tree-based structure, and gradient boosting, were exploited for daily streamflow simulation over different case studies. For each case study, the basin was divided into a few sub-basins for which daily precipitation and temperature data were aggregated and used as input. For training GNN, the connection matrix of sub-basins was also used as input. Basically, 75% of historical records were utilized to train GNN and different ML models, e.g., artificial neural networks, support vector machine, decision tree, random forest, eXtreme Gradient Boosting (XGBoost), Light Gradient-Boosting Machine (LightGBM), and Category Boosting (CatBoost), while the rest was used for testing. Streamflow simulation was conducted with/without considering seasonality impact and lag times. The obtained results clearly demonstrate that considering seasonality and time lags can enhance accuracy of streamflow predictions based on Kling–Gupta efficiency (KGE). Furthermore, GNN with seasonality impact and time lags achieved promising results across different case studies with KGE>0.85 for training and KGE>0.59 for testing data, respectively. Among ML models, boosting models, e.g., LightGBM and XGBoost, performed slightly better than other ML models. for Finally, this comparative analysis provides valuable insights for ML/DL applications in climate change impact assessments.Acknowledgements: This research work was carried out as part of the TRANSCEND project with funding received from the European Union Horizon Europe Research and Innovation Programme under Grant Agreement No. 10108411.

The electrochemical reduction of CO2 (CO2RR) using renewable electricity has the potential to reduce atmospheric CO2 levels while producing valuable chemicals and fuels. However, the practical implementation of this technology is limited by the activity, selectivity, and stability of catalyst materials. In this study, we employ high-throughput density functional theory (DFT) calculations to screen ∼800 transition metal nitrides and identify potential catalysts for CO2RR. The stability and activity of the screened materials were thoroughly evaluated via thermodynamic analysis, revealing Co, Cr, and Ti transition metal nitrides as the most promising candidates. Additionally, we conduct a feature importance analysis using machine learning (ML) regression models for binding energy prediction and determine the primary factors influencing the stability of catalysts. We show that the group number of metals has a significant impact on the binding energy of *OH and thus on the stability of the catalysts. We anticipate that this combined approach of high-throughput DFT screening and design strategy derived from ML regression analysis could effectively lead to the discovery of improved energy materials.

Development and internal validation of machine learning models for personalized survival predictions in spinal cord glioma patients