Data-driven Machine Learning Approach Research Articles

Random forest classification as a tool in epidemiological modelling: Identification of farm-specific characteristics relevant for the occurrence of Fasciola hepatica on German dairy farms.

Fasciola hepatica is an internal parasite of both human and veterinary relevance. In order to control fasciolosis, a multitude of attempts to predict the risk of infection such as risk maps or forecasting models have been developed. These attempts mainly focused on the influence of geo-climatic and meteorological features. Predicting bovine fasciolosis on farm level taking into account farm-specific settings yet remains challenging. In the present study, a new methodology for this purpose, a data-driven machine learning approach using a random forest classification algorithm was applied to a cross-sectional data set of farm characteristics, management regimes, and farmer aspects within two structurally different dairying regions in Germany in order to identify factors relevant for the occurrence of F. hepatica that could predict farm-level bulk tank milk positivity. The resulting models identified farm-specific key aspects in regard to the presence of F. hepatica. In study region North, farm-level production parameters (farm-level milk yield, farm-level milk fat, farm-level milk protein), leg hygiene, body condition (prevalence of overconditioned and underconditioned cows, respectively) and pasture access were identified as features relevant in regard to farm-level F. hepatica positivity. In study region South, pasture access together with farm-level lameness prevalence, farm-level prevalence of hock lesions, herd size, parity, and farm-level milk fat appeared to be important covariates. The stratification of the analysis by study region allows for the extrapolation of the results to similar settings of dairy husbandry. The local, region-specific modelling of F. hepatica presence in this work contributes to the understanding of on-farm aspects of F. hepatica appearance. The applied technique represents a novel approach in this context to model epidemiological data on fasciolosis which allows for the identification of farms at risk and together with additional findings in regard to the epidemiology of fasciolosis, can facilitate risk assessment and deepen our understanding of on-farm drivers of the occurrence of F. hepatica.

Unlocking Insights: Analysing COVID-19 Lockdown Policies and Mobility Data in Victoria, Australia, through a Data-Driven Machine Learning Approach

The state of Victoria, Australia, implemented one of the world’s most prolonged cumulative lockdowns in 2020 and 2021. Although lockdowns have proven effective in managing COVID-19 worldwide, this approach faced challenges in containing the rising infection in Victoria. This study evaluates the effects of short-term (less than 60 days) and long-term (more than 60 days) lockdowns on public mobility and the effectiveness of various social restriction measures within these periods. The aim is to understand the complexities of pandemic management by examining various measures over different lockdown durations, thereby contributing to more effective COVID-19 containment methods. Using restriction policy, community mobility, and COVID-19 data, a machine-learning-based simulation model was proposed, incorporating analysis of correlation, infection doubling time, and effective lockdown date. The model result highlights the significant impact of public event cancellations in preventing COVID-19 infection during short- and long-term lockdowns and the importance of international travel controls in long-term lockdowns. The effectiveness of social restriction was found to decrease significantly with the transition from short to long lockdowns, characterised by increased visits to public places and increased use of public transport, which may be associated with an increase in the effective reproduction number (Rt) and infected cases.

Integrated machine learning methods with oversampling technique for regional suitability prediction of waste-to-energy incineration projects

China's tiered strategy to enhance county-level waste incineration for energy aligns with the sustainable development goals (SDGs), emphasizing the need for comprehensive assessments of waste-to-energy (WtE) plant suitability. Traditional assessment methodologies face challenges, particularly in suggesting innovative site alternatives, adapting to new data sets, and their dependence on strict assumptions. This study introduced enhancements in three pivotal dimensions. Methodologically, it leverages data-driven machine learning (ML) approaches to capture the complex relationships essential for site selection, reducing dependency on strict assumptions. In terms of predictive performance, the integration of oversampling with stacked ensemble models enhances the diversity and generalizability of ML models. The area under curve (AUC) scores from four ML models, enhanced by the oversampled dataset, demonstrated significant improvements compared to the original dataset. The stacking model excelled, achieving a score of 92%. It also led in overall Precision and Recall, reaching 85.2% and 85.08% respectively. Nevertheless, a noticeable discrepancy existed in Precision and Recall for positive classes. The stacking model topped Precision scores at 83.1%, followed by eXtreme Gradient Boosting (XGBoost) (82.61%). In terms of Recall, XGBoost recorded the lowest at 85.07%, while the other three classifiers all marked 88.06%. From an industry applicability standpoint, the stacking model provides innovative location alternatives and demonstrates adaptability in Hunan province, offering a reusable tool for WtE location. In conclusion, this study not only enhances the methodological aspects of WtE site selection but also provides practical and adaptable solutions, contributing positively to sustainable waste management practices.

Early Prediction of Impending Exertional Heat Stroke With Wearable Multimodal Sensing and Anomaly Detection.

We employed wearable multimodal sensing (heart rate and triaxial accelerometry) with machine learning to enable early prediction of impending exertional heat stroke (EHS). US Army Rangers and Combat Engineers (N = 2,102) were instrumented while participating in rigorous 7-mile and 12-mile loaded rucksack timed marches. There were three EHS cases, and data from 478 Rangers were analyzed for model building and controls. The data-driven machine learning approach incorporated estimates of physiological strain (heart rate) and physical stress (estimated metabolic rate) trajectories, followed by reconstruction to obtain compressed representations which then fed into anomaly detection for EHS prediction. Impending EHS was predicted from 33 to 69 min before collapse. These findings demonstrate that low dimensional physiological stress to strain patterns with machine learning anomaly detection enables early prediction of impending EHS which will allow interventions that minimize or avoid pathophysiological sequelae. We describe how our approach can be expanded to other physical activities and enhanced with novel sensors.

A data-driven ensemble machine learning approach for predicting the mechanical strength of 3D printed orthopaedic bone screws

The mechanical strength of three-dimensional (3D) printed orthopaedic bone screws plays a major role in load-bearing bone fractures and deformities. Orthopaedic screws need to have enough mechanical strength to support and rehabilitate fracture sites under loads. Several process parameters are used in 3D printing technology for part fabrication; monitoring the mechanical strength of fabricated parts is a difficult and tedious task. The prediction of mechanical strength by a data-driven machine learning (ML) approach can be the solution. The present work leverages ensemble ML algorithms for predicting the mechanical strength of 3D-printed orthopaedic screws. Fused deposition modelling-based technology is utilised for orthopaedic cortical screw fabrication. Different process parameters were varied at different levels for the fabrication of orthopaedic screws. Ensemble ML techniques such as XGBoost, AdaBoost and GradientBoost are employed. The robustness and performance of predictive models were compared at different error metrics to offer an adequate predictive ML model. The XGBoost ensemble model was observed to be the most accurate with the least error metrics. Honeycomb-patterned with 100% infill percentage, layer height of 0.06 mm, and wall thickness of 1 mm may be selected for the maximum strength of a 3D-printed cortical screw. Moreover, the ensemble ML model's predictive performance and adequacy were higher than the base learning models.

Urban building energy performance prediction and retrofit analysis using data-driven machine learning approach

Stakeholders such as urban planners and energy policymakers use building energy performance modeling and analysis to develop strategic sustainable energy plans with the aim of reducing energy consumption and emissions from the built environment. However, inconsistent energy data and the lack of scalable building models create a gap between building energy modeling and traditional planning practices. An alternative approach is to conduct a large-scale energy usage survey, which is time-consuming. Similarly, existing studies rely on traditional machine learning or statistical approaches for calculating large-scale energy performance. This paper proposes a solution that employs a data-driven machine learning approach to predict the energy performance of urban residential buildings, using both ensemble-based machine learning and end-use demand segregation methods. The proposed methodology consists of five steps: data collection, archetype development, physics-based parametric modeling, machine learning modeling, and urban building energy performance analysis. The devised methodology is tested on the Irish residential building stock and generates a synthetic building dataset of one million buildings through the parametric modeling of 19 identified vital variables for four residential building archetypes. As a part of the machine learning modeling process, the study implemented an end-use demand segregation method, including heating, lighting, equipment, photovoltaic, and hot water, to predict the energy performance of buildings at an urban scale. Furthermore, the model's performance is enhanced by employing an ensemble-based machine learning approach, achieving 91% accuracy compared to the traditional approach's 76%. Accurate prediction of building energy performance enables stakeholders, including energy policymakers and urban planners, to make informed decisions when planning large-scale retrofit measures.

Predicting the solubility of hydrogen in hydrocarbon fractions: Advanced data-driven machine learning approach and equation of state

BackgroundHydrogen is a free carbon source for energy that attracts massive interest to be utilized during energy transition period in the near future. Molecular hydrogen soon will be a key component in fuels productions. It can be produced through catalytic steam and natural gas. For such processes the accurate estimation of solubility of hydrogen in many alkanes’ solution can have a major impact on the design and optimization of such petrochemical processes. MethodsIn this study, advanced data-driven scheme consisting in a committee machine intelligent system (CMIS) model was proposed for predicting the solubility of hydrogen in many hydrocarbon liquids raging from light n-alkanes C1 to heavy n-alkanes of C46. The CMIS was gained by combining multilayer perceptron (MLP) and cascaded forward neural network (CFNN) beneath a sole model using gene expression programming (GEP). A wide range database of hydrogen solubility in a binary system of hydrogen and various n-alkanes types was considered for developing the intelligent model. Besides, the reliability of the physics-based models, namely the Peng–Robinson equations of state (PR EOS) was checked for predicting the solubility of H2 in n-alkanes. Significant findingsThe main results demonstrated that the developed CMIS scheme can estimate the solubility of hydrogen in n-alkanes with a quite low computational cost and excellent performance, where the yielded overall RMSE and R2 values were 0.0033 and 0.9972, respectively. Besides, the established machine learning based model is capable of providing a good match against a wide range of experiment data. Furthermore, it is found that the implemented CMIS paradigm is superior to the existing intelligent and physics-based models in terms of accuracy. Lastly, the result of this work is vital for increasing the accuracy of hydrogen solubility in various hydrocarbon solvents required for process optimization of the hydrogen production units.

Abstract 14337: Identification of New Clinical Phenotypes of Sudden Cardiac Death Using Artificial Intelligence

Introduction: Current classifications of Sudden Cardiac Death (SCD) are based on cardiovascular (CV) conditions and risk factors, and frequently fail to explain numerous SCD cases. Hypothesis: a data-driven machine learning approach could identify new clinical phenotypes of SCD in the general population, using a wide range of CV and non-CV variables. Methods: All case of SCD over 18y that occurred between 2011-15 in Paris and suburbs were included in the Paris Sudden Death Expertise Center. Data from the French National Health Insurance database that occurred up to 10y before SCD were collected (drugs, examinations,diagnosis). We performed a non-supervised statistical approach to identify relevant clinical phenotypes of SCD, using clustering and dimension reduction methods. A validation was performed between 2016-20. Results: 12,651 SCD subjects were included. Mean age was 68y, and 61% were men. The clustering analysis identified 8 distinct clusters of SCD, with homogeneous characteristics. 3 clusters were already well known: a group mainly composed of aged women (3,307, 38% men, 81y), one with mainly CV diseases (3,638, 74% men, 74y) and one of young subjects with very few comorbidities (2,645, 65%men, 54 y). 4 non-CV clusters were identified: a group with psychiatric and/or neurologic disorders (862), a group with chronic or acute pulmonary diseases (688) and a group with malignant neoplasms of different sites and related drugs (518), and a group with kidney diseases (279). The last group was composed of subjects with characteristics related to social deprivation (alcohol related disorder, hepatitis, HIV, etc) (252).The same 8 clusters were identified in the validation cohort (11,485). Conclusions: By extending far beyond CV pathology, our approach provides for the first time a global picture of SCD, revealing the involvement of extra CV medical fields that might eventually lead to discover new pathways and help identifying high risk subjects.

Effect of pulsed current cathodic protection on pipeline steel API 5L X65 corrosion mitigation: An investigation and machine learning-assisted modeling

Pulsed current cathodic protection (PCCP) could be more effective than direct current cathodic protection (DCCP) for mitigating corrosion in buried structures in the oil and gas industries if appropriate pulsed parameters are chosen. The purpose of this research is to present the corrosion prevention mechanism of the PCCP technique by taking into account the effects of duty cycle as well as frequency, modeling the relationships between pulse parameters (frequency and duty cycle) and system outputs (corrosion rate, protective current and pipe-to-soil potential) and finally identifying the most effective protection conditions over a wide range of frequency (2–10 kHz) and duty cycle (25%-75%). For this, pipe-to-soil potential, pH, current and power consumption, corrosion rate, surface deposits and investigation of pitting corrosion were taken into account. To model the input-output relationship in the PCCP method, a data-driven machine learning approach was used by training an artificial neural network (ANN). The results revealed that the PCCP system could yield the best protection conditions at 10 kHz frequency and 50% duty cycle, resulting in the longest protection length with the lowest corrosion rate at a consumption current 0.3 time that of the DCCP method. In the frequency range of 6–10 kHz and duty cycles of 50%-75%, SEM images indicated a uniform distribution of calcite deposits and no pits on cathode surface.

Model and Data Driven Machine Learning Approach for Analyzing the Vulnerability to Cascading Outages With Random Initial States in Power Systems

In this paper, a hybrid machine learning model is applied to evaluate the relationship between random initial states and the power system’s vulnerability to cascading outages. A cascading outage simulator (CS), which uses off-line AC power flows, is proposed for generating training data. The initial states are randomly selected and the CS model is deployed for each initial state, where power system generation and loads are adjusted dynamically and power flows are redistributed to quantify the vulnerability metric. Furthermore, the proposed hybrid machine learning model deploys a combined Support Vector Machine (SVM) classification and Gradient Boosting Regression (GBR) to improve the learning precision. The classification model is trained by SVM, which divides the data into two categories with and without load shedding. Then, GBR is adopted only for the data with load shedding to determine the relationship between input power outage states and the vulnerability metric. The proposed vulnerability analysis approach is applied to several test systems and the results are analyzed. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The power system vulnerability can be quantified by cascading outage simulations. However, there are two challenges: i) there are a huge number of possible initial states and we cannot enumerate all these initial states for the cascading outage simulation. Neither can we precisely quantify the bus vulnerability. ii) The cascading outage simulation may be time-consuming for large-scale power systems, which is challenging for the online application. To address the above challenges, we expect to design a machine learning technique to predict the power system vulnerability, which can train the model in an offline way and then use it for the online application. Firstly, since there is not enough operation data from practical power systems, we develop a cascading outage simulator, using off-line AC power flows, for generating synthetic training data. Secondly, we observe that the training precision by directly applying the regression model may be very poor because the output of the machine learning model may take on an uneven distribution concerning input parameters. Thus, we propose a hybrid machine learning model with a combined classification and regression method, where the classification model is employed to remove the data without the load shedding, and the regression model then determines the relationship between input power outage states and the vulnerability metric. The proposed model and method have been tested on several systems including a practical large-scale Polish power system to show the effectiveness.

Machine learning prediction of structural dynamic responses using graph neural networks

Prediction of structural responses is essential for the analysis of structural behaviour subjected to dynamic loads. Existing approaches are limited in different ways. Experimental tests are expensive due to the requirement of intensive labour hours and specialised equipment. Numerical models can provide high-fidelity and labour-effective simulation of impact tests after proper validation, but it comes with high computational costs, which prohibit the usage of numerical methods for intensive and large-scale simulations in a design office. Data-driven machine learning approaches are also applied to structural response predictions, but they often exploit direct input–output mapping schemes that predict static field variables without capturing the dynamic response process. To close these gaps, we propose a novel machine learning approach based on graph neural networks (GNN) for full-field structural dynamics prediction. Our approach adopts a discretised representation of structures with an iterative rollout prediction scheme, and therefore it can simulate comprehensive spatiotemporal structural dynamics, providing the full potential for structural dynamics analysis. With several benchmark tests, it is demonstrated that our approach can generate accurate predictions of related field variables, e.g., displacement, strain, and stress, for different structures with a wide range of input parameters, such as structure geometry, impact speed and location. Additional interpolation and extrapolation tests are also conducted to show that our approach enjoys inherent generalisability and can produce satisfactory prediction even when all inputs are sampled outside of the training distribution. Our approach is also efficient and runs an order of magnitude faster than the commonly used numerical competitors. As the first attempt of using GNN for structural dynamics prediction and the result is promising, it is believed that GNN is well-suited for effective and efficient prediction of dynamic structural responses.

Tailoring the microstructure and mechanical properties of (CrMnFeCoNi)100-xCx high-entropy alloys: Machine learning, experimental validation, and mathematical modeling

As a common thermomechanical treatment route, “cold rolling and annealing” is widely used for the processing and grain refinement of interstitial-containing high-entropy alloys (HEAs). The interrelationship between the parameters of this process, the content of interstitial elements, and their interactions are outstanding challenges and areas of open discussion. Accordingly, the data-driven machine learning approach is a favorable choice for tuning the microstructure and mechanical properties, which needs to be systematically investigated. In the present work, these subjects were addressed in terms of correlating the thermomechanical processing parameters and chemical composition with the recrystallization and grain growth behaviors, grain size, carbide precipitation, and the resulting tensile yield stress for the model (CrMnFeCoNi)100-xCx HEAs. For this purpose, machine learning models based on adaptive neuro-fuzzy inference system (ANFIS), backpropagation artificial neural network (BP-ANN), and support network machine (SVM), as well as mathematical relationships and equations for the contribution of each strengthening mechanism were proposed and verified by extensive experimental work, which shed light on the design and prediction of the microstructure and properties of HEAs.

Incorporating physics to overcome data scarcity in predictive modeling of protein function: A case study of BK channels.

Machine learning has played transformative roles in numerous chemical and biophysical problems such as protein folding where large amount of data exists. Nonetheless, many important problems remain challenging for data-driven machine learning approaches due to the limitation of data scarcity. One approach to overcome data scarcity is to incorporate physical principles such as through molecular modeling and simulation. Here, we focus on the big potassium (BK) channels that play important roles in cardiovascular and neural systems. Many mutants of BK channel are associated with various neurological and cardiovascular diseases, but the molecular effects are unknown. The voltage gating properties of BK channels have been characterized for 473 site-specific mutations experimentally over the last three decades; yet, these functional data by themselves remain far too sparse to derive a predictive model of BK channel voltage gating. Using physics-based modeling, we quantify the energetic effects of all single mutations on both open and closed states of the channel. Together with dynamic properties derived from atomistic simulations, these physical descriptors allow the training of random forest models that could reproduce unseen experimentally measured shifts in gating voltage, ∆V1/2, with a RMSE ~ 32 mV and correlation coefficient of R ~ 0.7. Importantly, the model appears capable of uncovering nontrivial physical principles underlying the gating of the channel, including a central role of hydrophobic gating. The model was further evaluated using four novel mutations of L235 and V236 on the S5 helix, mutations of which are predicted to have opposing effects on V1/2 and suggest a key role of S5 in mediating voltage sensor-pore coupling. The measured ∆V1/2 agree quantitatively with prediction for all four mutations, with a high correlation of R = 0.92 and RMSE = 18 mV. Therefore, the model can capture nontrivial voltage gating properties in regions where few mutations are known. The success of predictive modeling of BK voltage gating demonstrates the potential of combining physics and statistical learning for overcoming data scarcity in nontrivial protein function prediction.

A data-driven machine learning approach for yaw control applications of wind farms

This study proposes a cost-effective machine-learning based model for predicting velocity and turbulence kinetic energy fields in the wake of wind turbines for yaw control applications. The model consists of an auto-encoder convolutional neural network (ACNN) trained to extract the features of turbine wakes using instantaneous data from large-eddy simulation (LES). The proposed framework is demonstrated by applying it to the Sandia National Laboratory Scaled Wind Farm Technology facility consisting of three 225 kW turbines. LES of this site is performed for different wind speeds and yaw angles to generate datasets for training and validating the proposed ACNN. It is shown that the ACNN accurately predicts turbine wake characteristics for cases with turbine yaw angle and wind speed that were not part of the training process. Specifically, the ACNN is shown to reproduce the wake redirection of the upstream turbine and the secondary wake steering of the downstream turbine accurately. Compared to the brute-force LES, the ACNN developed herein is shown to reduce the overall computational cost required to obtain the steady state first and second-order statistics of the wind farm by about 85%.

A data-driven machine learning approach for discovering potent LasR inhibitors

ABSTRACTThe rampant spread of multidrug-resistant Pseudomonas aeruginosa strains severely threatens global health. This severity is compounded against the backdrop of a stagnating antibiotics development pipeline. Moreover, with many promising therapeutics falling short of expectations in clinical trials, targeting the las quorum sensing (QS) system remains an attractive therapeutic strategy to combat P. aeruginosa infection. Thus, our primary goal was to develop a drug prediction algorithm using machine learning to identify potent LasR inhibitors. In this work, we demonstrated using a Multilayer Perceptron (MLP) algorithm boosted with AdaBoostM1 to discriminate between active and inactive LasR inhibitors. The optimal model performance was evaluated using 5-fold cross-validation and test sets. Our best model achieved a 90.7% accuracy in distinguishing active from inactive LasR inhibitors, an area under the Receiver Operating Characteristic Curve value of 0.95, and a Matthews correlation coefficient value of 0.81 when evaluated using test sets. Subsequently, we deployed the model against the Enamine database. The top-ranked compounds were further evaluated for their target engagement activity using molecular docking studies, Molecular Dynamics simulations, MM-GBSA analysis, and Free Energy Landscape analysis. Our data indicate that several of our chosen top hits showed better ligand-binding affinities than naringenin, a competitive LasR inhibitor. Among the six top hits, five of these compounds were predicted to be LasR inhibitors that could be used to treat P. aeruginosa-associated infections. To our knowledge, this study provides the first assessment of using an MLP-based QSAR model for discovering potent LasR inhibitors to attenuate P. aeruginosa infections.

A model for identifying the feeder-transformer relationship in distribution grids using a data-driven machine-learning algorithm

With the increasing demand for reliable power supply and the widespread integration of distributed energy sources, the topology of distribution networks is subject to frequent changes. Consequently, the dynamic alterations in the connection relationships between distribution transformers and feeders occur frequently, and these changes are not accurately monitored by grid companies in real-time. In this paper, we present a data-driven machine learning approach for identifying the feeder-transformer relationship in distribution networks. Initially, we preprocess the collected three-phase voltage magnitude data of distribution transformers, addressing data quality and enhancing usability through three-phase voltage normalization. Subsequently, we derive the correlation coefficient calculations between distribution transformers, as well as between distribution transformers and feeders. To tackle the challenging task of determining the correlation coefficient threshold, we propose a multi-feature fusion approach. We extracted additional features from the feeders and combined them with the correlation coefficients to create a feature matrix. Machine learning algorithms were then applied to calculate the results. Through experimentation on a real distribution network in Jiangxi province, we demonstrated the effectiveness of the proposed method. When compared to other approaches, our method achieved outstanding results with an F1 score of 0.977, indicating high precision and recall. The precision value was 0.973 and the recall value was 0.981. Importantly, our method eliminates the need for additional measurement installations, as the required data can be obtained using existing collection devices. This significantly reduces the application cost associated with implementing our approach.

Sea ice surface type classification of ICESat-2 ATL07 data by using data-driven machine learning model: Ross Sea, Antarctic as an example

The ICESat-2 (IS2) ATL07 sea ice height product provides precise and accurate measurements of sea ice height for the polar regions. Although the original ATL07 product classifies the sea ice surface into snow-covered ice and open water (dark leads and specular leads), it has two critical issues: (1) it does not distinguish thin ice (gray ice) from thick/snow-covered ice or open water and (2) it involves uncertainties in the dark lead determination. To address these issues and obtain more accurate lead fraction and freeboard estimation, in this study, we assess a data-driven machine learning approach for sea ice surface type classification from the ATL07 product. A total of 17 IS2 tracks covering the Ross Sea in February, March, September, October, and November 2019 are used in this study. For training and testing the neural network (NN) models, we label the ATL07 data into three surface types: thick/snow-covered sea ice, thin/gray sea ice, and open water based on the coincident Sentinel-2 optical images. We use six variables from the ATL07 data: background rate, photon rate, relative surface height, width of height distribution, number of laser pulses, and difference in mean and median height, with the first three variables found to be the most significant in determining surface types. Our spatiotemporal test shows that the NN models can be applied to the ATL07 dataset with ∼99% accuracy in the Ross Sea, and the beam test shows that the difference in the accuracy for three beams is negligible. While the current ATL07 product captures only ∼5% of thin ice and ∼ 81% of open water correctly, our NN models capture ∼90% of both open water and thin ice leads successfully. When we qualitatively assess the surface classification of the NN models by using the coincident optical and radar images, our NN models do not show significant misclassification issues both in the daytime and nighttime and both in the winter and summer seasons. Compared to the IS2 ATL10 sea ice freeboard product, the ability of our NN model to separate thin ice and open water from snow-covered/thick ice is significant in freeboard estimation, especially for winter and highly packed sea ice areas. Open water and thin ice classes also improve mapping lead fraction and floe size distribution.

Exploiting machine learning for controlled synthesis of carbon dots-based corrosion inhibitors

Benefitting from their prominent corrosion inhibition properties, excellent water solubility and benign environmental friendliness, carbon dots (CDs) have functioned as an ideal candidate for next-generation green corrosion inhibitors. However, the extensive adoption of the trial-and-error route driven by artificial experience in the preparation of CDs-based corrosion inhibitors leads to resource waste and environmental implications, detrimental to their sustainable development. It is still a considerable challenge to controllably prepare CDs-based corrosion inhibitors with the predictable inhibition efficiency. Herein, firstly exploiting a data-driven machine learning (ML) approach, this study aims to precisely predict the inhibition efficiency of CDs and optimize their synthesis route, resulting in the controlled synthesis of CDs-based corrosion inhibitors. Specifically, the dataset is constructed by combining 102 data points on CDs synthesis and inhibition efficiency from numerous published studies and our own experiments. After training and evaluation of different ML models, the Random Forest (RF) ML regression model is chosen with the lowest root-mean-square error and mean absolute error as well as the highest coefficient of determination. The results show that this RF model can comprehensively reveal the relationship between various hydrothermal synthesis parameters and the inhibition efficiency. Guided by the RF model, the inhibition efficiencies of CDs-based corrosion inhibitors are accurately predicted with an error less than 10%, and based on the genetic algorithm, their synthesis route is intelligently optimized. This work demonstrates the feasibility of ML techniques in guiding the optimization of synthesis conditions for CDs-based corrosion inhibitors. This optimization process results in reduced development time and cost, contributing to the sustainability and cleaner production of inhibitors.

Review of Challenges and Opportunities in Turbulence Modeling: A Comparative Analysis of Data-Driven Machine Learning Approaches

Engineering and scientific applications are frequently affected by turbulent phenomena, which are associated with a great deal of uncertainty and complexity. Therefore, proper modeling and simulation studies are required. Traditional modeling methods, however, pose certain difficulties. As computer technology continues to improve, machine learning has proven to be a useful solution to some of these problems. The purpose of this paper is to further promote the development of turbulence modeling using data-driven machine learning; it begins by reviewing the development of turbulence modeling techniques, as well as the development of turbulence modeling for machine learning applications using a time-tracking approach. Afterwards, it examines the application of different algorithms to turbulent flows. In addition, this paper discusses some methods for the assimilation of data. As a result of the review, analysis, and discussion presented in this paper, some limitations in the development process are identified, and related developments are suggested. There are some limitations identified and recommendations made in this paper, as well as development goals, which are useful for the development of this field to some extent. In some respects, this paper may serve as a guide for development.

Need for strategic planning of electric vehicle charging locations in Windsor, Ontario

The paper evaluates the impact of the new additional electric vehicle (EV) charging stations on accessibility to charging in the city of Windsor Ontario. It uses locations and coordinates information of electric vehicle charging stations extracted from the Environmental Canada database combined with details of the new additions by the city, manually abstracted from publications and google. These were spatially aggregated into the city’s Ward along with demographic and stations-per-Ward determined.Point-in-polygon, floating catchment area - FCA, and network level (travel-time) methods were used to understand variations in accessibility across Wards of the city, considering the existing and a combination of existing and new stations. The study found that the point-in-polygon method tends to overestimate the accessibility of Wards with a low population where kinetic (affluents) resides and could lead to improper identification of Wards highly accessible to charging. Findings from FCA and network accessibility methods highlights caution with the use of the point-in-polygon method which favors low-populated areas. Accessibility analysis using FCA, and network level (travel-time) technique revealed that the addition of new stations in the city does not significantly change accessibility levels. The study found that only a few Wards in the city of Windsor will be benefited from the addition of new stations as the median travel times from Wards to stations did not reduce significantly and larger variations exist around the median times suggesting that the new stations are randomly introduced rather than planned. Multicriteria analysis however aided in ranking of Wards based on available charging infrastructures, EV owned, travel time to stations and population density per Ward. The paper recommends data-driven machine learning approach in measuring accessibility and locating charging infrastructures in the city.