Gaussian Process Regression Model Research Articles

Hybrid real-time wave forecasting model combining Gaussian process regression and neural networks

To safely and effectively conduct offshore operations, a real-time wave forecast model that can accurately and rapidly forecast waves hours or days in advance is highly valuable. Recent studies have investigated models with neural networks (NNs) and have demonstrated their advantages in terms of forecasting speed and accuracy. However, NNs are limited by their requirement for a large training dataset, which can hinder the construction of the model if sufficient training data are unavailable. Therefore, this study constructed a hybrid real-time wave forecast model by combining an NN model and Gaussian process regression (GPR) model. The objective was to obtain reasonably accurate forecasts that were more accurate than those from individual NN models even when sufficient training data for the NN model was unavailable. To derive an optimal prediction, the values predicted by the NN and GPR models were combined by utilizing the standard deviation of the latter and considering the accuracy of each model. Consequently, predictions that were more accurate compared to those of the individual models for an entire year were obtained. This improvement was particularly significant for predicting relatively large wave heights, as indicated by the daily maximum wave heights. Additionally, various accuracy evaluation metrics demonstrated that despite using a small training dataset, the optimal prediction of the hybrid model was still superior to those of the individual models for predicting the daily maximum wave heights.

Stacking BSRG-PLS: A physical and data-driven real-time stability safety analysis of arch dams during operation

Anti-sliding stability is the foundation for the normal operation of arch dams. In recent years, extreme weather has occurred frequently. It is important to grasp the anti-slide stability of arch dam (ASSAD) under complex load conditions in time. Currently, the ASSAD safety factor is primarily analyzed through the finite element method (FEM), which are time-consuming, labor-intensive, and lack timeliness. To address this, this paper proposes a real-time ASSAD analysis method during operation based on the Stacking BSRG-PLS model, which integrates a Bidirectional long short-term memory network, Residual neural network, Support vector machine, Gaussian process regression model and Partial Least Squares regression method. Firstly, based on the Stacking BSRG-PLS model and measured temperature combing with FEM, the transient temperature field of arch dam is established. Subsequently, a sample dataset containing the load data and the corresponding ASSAD safety factors calculated by FEM is constructed. Whereafter, using the Stacking BSRG-PLS model again, the real-time ASSAD safety factor is obtained based on the sample dataset. Case studies indicate that this method is effective and feasible, and has high analysis precision. It provides an effective way to quickly evaluate the ASSAD safety based on the measured data.

A machine-learned kinetic energy model for light weight metals and compounds of group III-V elements

Abstract We present a machine-learned (ML) model of kinetic energy for orbital-free density functional theory (OF-DFT) suitable for bulk light weight metals and compounds made of group III–V elements. The functional is machine-learned with Gaussian process regression (GPR) from data computed with Kohn-Sham DFT with plane wave bases and local pseudopotentials. The dataset includes multiple phases of unary, binary, and ternary compounds containing Li, Al, Mg, Si, As, Ga, Sb, Na, Sn, P, and In. A total of 433 materials were used for training, and 18 strained structures were used for each material. Averaged (over the unit cell) kinetic energy density is fitted as a function of averaged terms of the 4th order gradient expansion and the product of the density and effective potential. The kinetic energy predicted by the model allows reproducing energy-volume curves around equilibrium geometry with good accuracy. We show that the GPR model beats linear and polynomial regressions. We also find that unary compounds sample a wider region of the descriptor space than binary and ternary compounds, and it is therefore important to include them in the training set; a GPR model trained on a small number of unary compounds is able to extrapolate relatively well to binary and ternary compounds but not vice versa.

Computationally efficient and error aware surrogate construction for numerical solutions of subsurface flow through porous media

Limiting the injection rate to restrict the pressure below a threshold at a critical location can be an important goal of simulations that model the subsurface pressure between injection and extraction wells. The pressure is approximated by the solution of Darcy’s partial differential equation for a given permeability field. The subsurface permeability is modeled as a random field since it is known only up to statistical properties. This induces uncertainty in the computed pressure. Solving the partial differential equation for an ensemble of random permeability simulations enables estimating a probability distribution for the pressure at the critical location. These simulations are computationally expensive, and practitioners often need rapid online guidance for real-time pressure management. An ensemble of numerical partial differential equation solutions is used to construct a Gaussian process regression model that can quickly predict the pressure at the critical location as a function of the extraction rate and permeability realization. The Gaussian process surrogate analyzes the ensemble of numerical pressure solutions at the critical location as noisy observations of the true pressure solution, enabling robust inference using the conditional Gaussian process distribution.Our first novel contribution is to identify a sampling methodology for the random environment and matching kernel technology for which fitting the Gaussian process regression model scales as O(nlogn) instead of the typical O(n3) rate in the number of samples n used to fit the surrogate. The surrogate model allows almost instantaneous predictions for the pressure at the critical location as a function of the extraction rate and permeability realization. Our second contribution is a novel algorithm to calibrate the uncertainty in the surrogate model to the discrepancy between the true pressure solution of Darcy’s equation and the numerical solution. Although our method is derived for building a surrogate for the solution of Darcy’s equation with a random permeability field, the framework broadly applies to solutions of other partial differential equations with random coefficients.

Optimization of Linear Loading Strategy for Fuel Cell Initiation Based on Gaussian Process Regression Model

Optimization of Linear Loading Strategy for Fuel Cell Initiation Based on Gaussian Process Regression Model

Machine Learning Model Trained with Finite Element Modeling Can Predict the Risk of Osteoarthritis: Data from the Osteoarthritis Initiative

Objective: Despite long simulation times, recently developed finite element analysis (FEA) models of knee joints have demonstrated their suitability for predicting individual risk of onset and progression of knee osteoarthritis. Therefore, the objective of this study was to assess the feasibility of machine learning (ML) to replicate outcomes obtained from FEA when simulating mechanical responses and predicting cartilage degeneration within the knee joint.Design: Two ML models based on the Gaussian Process Regression (GPR) algorithms were developed. The first model (GPR1) utilized age, weight, and anatomical joint dimensions as predictor variables to predict tissue mechanical responses and cartilage degeneration based on FEA data. The second model (GPR2) utilized age, weight, height, and gender to predict anatomical joint dimensions, which were then used as inputs in the GPR1 model. Finally, the GPR1 and combined GPR1+GPR2 models were used to investigate the importance of clinical imaging when making personalized predictions for knees from healthy subjects with no history of knee injuries.Results: In the GPR1 model, R2 of 0.9 was exceeded for most of the predicted mechanical parameters. The GPR2 model was able to predict knee shape with R2 of 0.67–0.9. Both GPR1 and combined GPR1+GPR2 models offered equally good performances (AUC = 0.73–0.74) in classifying patients at high risk for the onset and development of knee osteoarthritis.Conclusions: In the future, real-time and easy-to-use GPR models may provide a rapid technology to evaluate mechanical responses within the knee for researchers or clinicians who have no former knowledge of FEA.

Research on Stock Price Prediction Model Based on Sentiment Factor and Multi-Core Bagging Algorithm

Stock price prediction model is one of the key research points in the quantitative financial field. With the rapid development of data acquisition and storage technology, the data of emotional factors based on nonlinear structure is increasing. How to combine this part of information with common European technology factors to increase the ability of the model is a problem that needs to be solved. Based on this, this paper proposes a method of uncertainty quantification that combines European-and non-European data. Specifically, on the one hand, the Gaussian process regression model is used to capture the unknown relationship between predictive variables and price; on the other hand, the multi-kernel learning technology based on European and non- European kernel functions is used to combine the effective information of European and non- European predictive variables. Moreover, the proposed method can weigh the bias of the prediction model against the variance by using the Bagging algorithm. The simulated data analysis shows that the proposed method not only improves the prediction performance of the European Gaussian process, but also works in the presence of irrelevant predictive variables. Finally, the actual data analysis shows that the proposed method has achieved good prediction results in the task of predicting the rise and fall of stock prices.

Machine learning based prediction for bulk porosity and static elastic modulus of Yungang Grottoes sandstone

In this work, four mainstream machine learning (ML) techniques are used to evaluate the bulk porosity and static elastic modulus of weathered Yungang Grottoes sandstone. Datasets are gathered from the experiments, which includes 432 groups effective experimental data including 8 inputs features. bulk porosity and static elastic modulus were considered as outputs to determine the weathering degrees of Yungang Grottoes sandstone. The 4 performance criteria were used to evaluate the ML models. Results demonstrate that the Artificial Neural Network (ANN) is the best-fitted models for estimating the bulk porosity and static elastic modulus compared to Multiple Linear Regression (MLR), Support Vector Regression (SVR), Gaussian Process Regression (GPR). The accuracy of the trained model for static elastic modulus is slightly higher than that of bulk porosity. The GPR and ANN model can accurately predict the bulk porosity and static elastic modulus in training stages. The ANN with multi-hidden layers developed is competent with high degree of precision and generalization ability for bulk porosity and static elastic modulus compared to other selected regression-based ML models (MLR, SVR, and GPR). The coefficient of determinations of ANN in the range of (0.9537–0.9641) during the testing stages is more stable and higher than that of (0.8883–0.9453) other built ML models. The prediction efficiency of pretrained ANN model was well adjusted for the actual and forecast datasets at the training and testing stages, and the error range was no more than 0.7% and 0.15 GPa at both stages of prediction for bulk porosity and static elastic modulus respectively. And the ANN based static elastic modulus prediction model’s error proportions significantly decreased and were confined to a modest range between + 10% and − 10%. The proposed surrogate models are valid for the bulk porosity ranging from 7 to 14% and the static elastic modulus ranging from 0.7 to 1.4 Gpa, which can be utilized for the accurate and fast prediction of the weathering degrees of Yungang Grottoes sandstone.

Modeling Many-Body Interactions in Water with Gaussian Process Regression.

We report a first-principles water dimer potential that captures many-body interactions through Gaussian process regression (GPR). Modeling is upgraded from previous work by using a custom kernel function implemented through the KeOps library, allowing for much larger GPR models to be constructed and interfaced with the next-generation machine learning force field FFLUX. A new synthetic water dimer data set, called WD24, is used for model training. The resulting models can predict 90% of dimer geometries within chemical accuracy for a test set and in a simulation. The curvature of the potential energy surface is captured by the models, and a successful geometry optimization is completed with a total energy error of just 2.6 kJ mol-1, from a starting structure where water molecules are separated by nearly 4.3 Å. Dimeric modeling of a flexible, noncrystalline system with FFLUX is shown for the first time.

Remaining useful life prediction of high-capacity lithium-ion batteries based on incremental capacity analysis and Gaussian kernel function optimization

Remaining useful life (RUL) is a key indicator for assessing the health status of lithium (Li)-ion batteries, and realizing accurate and reliable RUL prediction is crucial for the proper operation of battery systems. As high-capacity Li batteries have more complex chemical properties, most of the current RUL prediction methods rely mainly on a priori knowledge to make judgments. As a result, prediction accuracy is not high. In this study, we developed a health indicator-capacity (HI-C) dual Gaussian process regression (GPR) model based on incremental capacity analysis (ICA) and optimized its kernel function to achieve accurate RUL prediction for 280 Ah high-capacity Li batteries. Validation against the United States National Aeronautics and Space Administration’s four battery test datasets showed that the use of the HI-C dual GPR model resulted in a mean absolute percentage error and root mean square error of less than 0.02 and 0.04, respectively, for the four battery-rated capacity predictions. Additionally, this model achieved an absolute error of less than five battery failure turns. Compared with a single model, the HI-C dual GPR model not only had high accuracy but also solved the problem that the HI was not measurable in the actual battery operation, which made it more suitable for RUL prediction of Li batteries.

Comparison of Machine Learning-Based Predictive Models of the Nutrient Loads Delivered from the Mississippi/Atchafalaya River Basin to the Gulf of Mexico

Predicting nutrient loads is essential to understanding and managing one of the environmental issues faced by the northern Gulf of Mexico hypoxic zone, which poses a severe threat to the Gulf’s healthy ecosystem and economy. The development of hypoxia in the Gulf of Mexico is strongly associated with the eutrophication process initiated by excessive nutrient loads. Due to the complexities in the excessive nutrient loads to the Gulf of Mexico, it is challenging to understand and predict the underlying temporal variation of nutrient loads. The study was aimed at identifying an optimal predictive machine learning model to capture and predict nonlinear behavior of the nutrient loads delivered from the Mississippi/Atchafalaya River Basin (MARB) to the Gulf of Mexico. For this purpose, monthly nutrient loads (N and P) in tons were collected from US Geological Survey (USGS) monitoring station 07373420 from 1980 to 2020. Machine learning models—including autoregressive integrated moving average (ARIMA), gaussian process regression (GPR), single-layer multilayer perceptron (MLP), and a long short-term memory (LSTM) with the single hidden layer—were developed to predict the monthly nutrient loads, and model performances were evaluated by standard assessment metrics—Root Mean Square Error (RMSE) and Correlation Coefficient (R). The residuals of predictive models were examined by the Durbin–Watson statistic. The results showed that MLP and LSTM persistently achieved better accuracy in predicting monthly TN and TP loads compared to GPR and ARIMA. In addition, GPR models achieved slightly better test RMSE score than ARIMA models while their correlation coefficients are much lower than ARIMA models. Moreover, MLP performed slightly better than LSTM in predicting monthly TP loads while LSTM slightly outperformed for TN loads. Furthermore, it was found that the optimizer and number of inputs didn’t show effects on the LSTM performance while they exhibited impacts on MLP outcomes. This study explores the capability of machine learning models to accurately predict nonlinearly fluctuating nutrient loads delivered to the Gulf of Mexico. Further efforts focus on improving the accuracy of forecasting using hybrid models which combine several machine learning models with superior predictive performance for nutrient fluxes throughout the MARB.

Time Series Prediction of Gas Emission in Coal Mining Face Based on Optimized Variational Mode Decomposition and SSA-LSTM.

The accurate prediction of gas emissions has important guiding significance for the prevention and control of gas disasters in order to further improve the prediction accuracy of gas emissions in the mining face. According to the absolute gas emission monitoring data of the 1417 working face in a coal mine in Shaanxi Province, a GA-VMD-SSA-LSTM gas emission prediction model (GVSL) based on genetic algorithm (GA)-optimized variational mode decomposition (VMD) and sparrow search algorithm (SSA)-optimized long short-term memory (LSTM) is proposed. Firstly, a VMD evaluation standard for evaluating the amount of decomposition loss is proposed. Under this standard, the GA is used to find the optimal parameters of the VMD. Then, the SSA is used to optimize the key parameters of the LSTM to establish a GVSL prediction model. The model predicts each component and finally superimposes the prediction results for each component to obtain the final gas emission result. The results show that the accuracy of the evaluation indexes of the GVSL model and VMD-LSTM model, as well as the SSA-LSTM model and Gaussian process regression (GPR) model, are compared and analyzed horizontally and vertically under three scenarios with prediction sets of 121,94 and 57 groups. The GVSL model has the best prediction effect, and its fitting degree R2 values are 0.95, 0.96, and 0.99, which confirms the effectiveness of the proposed GVSL model for the time series prediction of gas emission in the mining face.

Predictive modeling of sustainable recycled materials for stone column construction

Climate change due to carbon dioxide emissions is one of the most significant global challenges. Sustainable recycled materials are recognized as a critical factor in mitigating climate change, representing a fundamental strategy for reducing gas emissions and preserving the environment. Promising sustainable recycled materials in construction, such as crushed asphalt, crushed concrete, crushed ceramic, and treated concrete offer numerous advantages, including reduced carbon dioxide (CO2)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ ext{(CO}}_{2} )$$\\end{document} emissions, cost-effectiveness, increased strength, and enhanced mechanical properties. In this study, various machine learning techniques, including the support vector machine (SVM), multiple linear regression (MLR), gaussian process regression (GPR), and artificial neural network (ANN), are used to assess the effectiveness of sustainable recycled materials within stone columns. The MLR model was specifically utilized to predict the ultimate stress equation for these materials within stone columns. Forty-five constructed samples were used in developing the models. The effectiveness of each model was evaluated using various statistical assessment measures, including mean absolute error (MAE), absolute fraction of variation (R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ ext{R}}^{2}$$\\end{document}), and root mean square error (RMSE). The predictive model’s performance was validated using the k-fold cross-validation method. The ANN model with an R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${\ ext{R}}^{2}$$\\end{document} value of 0.962 and an RMSE value of 7.268 kPa, performed better compared to GPR, SVM and MLR models. In summary, the results of the study indicate that the MLR model, utilizing the identified input parameters, can accurately predict the ultimate stress for different sustainable recycled materials. Implementing such technologies within the construction sector can expedite and reduce the cost of assessing material characteristics and the influence of input parameters.

Practical application of machine learning in energy and thermal management: Long-term data analysis of solar-assisted AC systems in portable cabins in Kuwait and Australia

Machine learning techniques are advancing rapidly in theoretical grounds, but their practical application and real evaluation in engineering disciplines are limited. This study investigates one-year of experimental data for indoor air conditions and energy monitoring of two identical portable cabins in Kuwait. Additionally, a 9-month period of solar photovoltaic energy production is experimentally obtained for assessing energy saving aspects of a solar assisted air conditioning system in one of the cabins. A transient system simulation tool model is developed and validated for the portable cabins. Both one-year experimental data and the validated simulation data are used for developing machine learning models for six case studies in Kuwait and Australia. In simulations, there are issues related to lack of access to real-time weather data from a locally installed weather station. In experimental works, there were issues related to disruption of data collection due to power or internet shutdowns. To resolve these issues, nineteen regression models are investigated. It was found that all models performed very well although the Matern 5/2 and Exponential gaussian process regression model performed slightly better, with all models achieving high accuracy, as indicated by R-squared values close to 1.0 in all six case studies. Overall, it was found that the photovoltaic solar-assisted air conditioning system could save annually 26.2 % and 75.7 % energy in Kuwait and Rockhampton, Australia, respectively.

Research on multi-source information fusion tool wear monitoring based on MKW-GPR model

To enhance intelligent manufacturing capabilities and achieve the goal of online real-time high-precision monitoring of tool wear with small sample data, this paper proposes a multi-source information fusion method for turning tool wear monitoring based on the multi-kernel weighted Gaussian process regression (MKW-GPR) model. Firstly, the framework and process of multi-source information fusion for turning tool wear monitoring are established, and the experimental platform is constructed. Secondly, a full-life cutting experiment of the turning tool is conducted. During the experiment, tool wear image data and multi-sensor signal data, including cutting force and vibration signals, are collected. Then, the experimental data were processed to construct a dataset with multi-source information fusion, leading to the establishment of the MKW-GPR model. Subsequently, the experimental dataset was employed to validate the effectiveness of the turning tool wear monitoring model. The results demonstrate that, in recognizing the wear state, the MKW-GPR model exhibited superior recognition performance compared to the single kernel function Gaussian process regression model. Furthermore, in predicting the wear value, the MKW-GPR model is better than the long short-term memory (LSTM), random forest (RF), and scalable end-to-end tree boosting (XGBoost) models. During the small sample size priori point data prediction performance test, the MKW-GPR model achieved the highest accuracy, with a maximum relative error of only 2.8 % in predicting tool life during the severe wear stage. These findings substantiate the feasibility and effectiveness of the proposed turning tool wear monitoring method.

Optimization of ultrasound-assisted extraction of bioactive compounds from Carthamus caeruleus L. rhizome: Integrating central composite design, Gaussian process regression, and multi-objective Grey Wolf optimization approaches

The prediction of ultrasound-assisted extraction (UAE) for total phenolic content (TPC) and total flavonoid content (TFC) from Carthamus caeruleus L. rhizomes was conducted using a Gaussian process regression model (GPR) with a multi-objective Grey Wolf optimization approach (MOGWO). A central composite design (CCD) was employed first, examining ethanol concentration, temperature, time, and solvent-to-solid ratio as independent variables. TPC and TFC responses were analyzed under various conditions, revealing significant quadratic and interaction effects (p < 0.05). The GPR was then utilized to predict TPC and TFC, showing high accuracy with correlation coefficients near 1 and minimal root mean square error (RMSE) values. To simultaneously maximize TPC and TFC, the MOGWO was used in a multi-objective framework. Validation through CCD and GPR highlighted GPR's superior predictive accuracy. Optimal conditions (10% ethanol, 40°C, 20minutes sonication, and 50mLg-1 solvent to solid ratio) showed significant discrepancies in CCD predictions but high accuracy in GPR predictions. An interactive tool predicts TPC and TFC using CCD and GPR models. Users input extraction parameters and receive predictions, with a GWO-based optimization module for optimal conditions. The interface enables model comparison, improves process understanding, and optimizes bioactive compound extraction.

Optimising Sensor Placement for Tool Condition Monitoring: A Comparative Analysis of Acoustic Emission Data

In the monitoring of machining processes and in the context of tool condition monitoring, the position of acoustic emission sensors affects the quality of the resulting information. This drives this comparative study which presents a comparison of acoustic emission data recorded simultaneously by a sensor attached to the side of the milling table and another sensor near the spindle during a tool wear test on a CNC milling machine. The signal information is clearly influenced by the different positions. Whereas the signals near the spindle are dominated by vibrations of the spindle motor during machining, these strong contributions do not occur in the recorded data of the machining process detected by the sensor mounted to the table. However, the position of the sensor near the spindle has the advantage of maintaining a constant distance to the source of the acoustic emissions of the machining process, as the sensor moves with the tool. In contrast, the sensor attached to the milling table is affected from the fact that the distance to the milling tool is constantly changing. This results in different dominant frequencies, that are analysed in this study. To analyse both the entire frequency range and the higher frequencies, two distinct approaches are employed, one without and one with the use of a high-pass filter. Furthermore, the recorded signals were used to calculate the characteristic features, namely the Partial Powers, thereby enabling assessment of the condition of the tool. The results demonstrate that this single feature type is sufficient for training a machine learning model to predict the tool wear, focusing on the flank wear width. This study analyses the efficiency of wear prediction with respect to both sensors and frequency spectra, and compares the results. In this context, the most accurate predictions were achieved with Gaussian process regression models.

Machine learning techniques for predicting the peak response of reinforced concrete beam subjected to impact loading

To meet the growing need for resilient structures in seismic and high-impact zones, accurate prediction of the response of reinforced concrete (RC) beams under impact loads is essential. Traditional methods, such as experimental testing and high fidelity finite element models, are often time consuming and resource intensive. To address these challenges, this study investigates various ensemble and non-ensemble machine learning techniques—including support vector machine, gaussian process regression (GPR), k-nearest neighbor (KNN), gene expression programming, random forest, decision tree, boosted tree, adaptive boosting tree, gradient boosting algorithm, stochastic gradient descent, and artificial neural network—for predicting the peak response of RC beams under impact loads. A set of 145 experimental data points from 12 different sources is used to train and evaluate these machine learning models. Key parameters in the data include beam width and depth, span, reinforcement ratios, concrete strength, steel yield strength, deflection, and impact characteristics. Except for KNN, all models showed satisfactory generalization capabilities with R2 values over 0.8. Statistical errors such as RMSE, a-10 index, MAE, and a-20 index are within acceptable limits. The GPR model is the most effective with R2 value of 0.95. Moreover, Shapely analysis identified beam depth, impact velocity, and beam breadth as critical factors. Overall, this study demonstrates the efficacy of machine learning in accurately predicting the behavior of RC structures under impact loads, providing valuable tools for civil engineers in design and analysis.

Exploring action-law of microplastic abundance variation in river waters at coastal regions of China based on machine learning prediction

Surface waters, particularly the river systems, constitute a vital freshwater resource for human beings and aquatic life on Earth. In economically developed and densely populated coastal regions, river water is facing severe microplastic pollution, posing a threat to public health and ecological safety. Reliable prediction of microplastic abundance (MPA) can significantly reduce the costs associated with microplastic field sampling and analysis. This study employed spatial correlation, geographical detector, principal component analysis and five mainstream machine learning models to analyze 79 datasets of MPAs in seven coastal areas of China and performed correlation, regression and attribution analyses based on 19 terrestrial influencing factors that potentially affect the MPA life cycle processes (generation, aging, and migration). The results showed that the Neural Network (NN) and the Gaussian Process Regression (GPR) models achieved the best prediction performance, with the predicted R2 close to 1. Principal component analysis and Shapley additive explanations concluded that meteorological factors, in particular the annual geotemperature, surface solar radiation, and annual relative humidity, had a key influence on the aging of microplastics. The second key factor in improving the MPA prediction ability was the dynamic description of microplastic migration, which was primarily governed by hydrological factors such as annual precipitation and average terrain slope. Unexpectedly, the effects of land use and level of urbanization were relatively small in describing the generation of microplastics. Only the percentage of built areas was strongly correlated with the MPA levels. Note that the MPA prediction and its contribution factors may vary across different basins. Nevertheless, the findings of this study are applicable to predicting and analyzing the distribution of microplastics in other coastal rivers, and for indicating the main contributing factors, ultimately serving as a basis for guiding microplastic pollution control strategies in different river basins.

MLAPI: A framework for developing machine learning-guided drug particle syntheses in automated continuous flow platforms

Recently, machine learning (ML) models are increasingly being used in process analytical technology (PAT) frameworks for pharmaceutical manufacturing. Yet, the applications of ML-integrated PAT frameworks are limited by big data requirements. This work introduces a computational framework to develop data-efficient ML models to guide drug particle synthesis in an automated continuous flow precipitation platform. The framework incorporates classification algorithms to identify feasible (fouling-free) operating regions of the precipitation platform, a multiple-output Gaussian process (GP) regression model to relate key process parameters to the drug particle size, and active learning to optimally generate new data for training and validation of the GP model. The usefulness of the proposed framework is demonstrated on the synthesis of ibuprofen microparticles in an automated flow precipitation platform. We envision that properly trained GP models developed using the proposed framework can be employed to fine tune the drug particle size, targeting desired particle bioavailability and processability.