Ensemble Machine Learning Methods Research Articles

Deep learning-based fault diagnosis of high-power PEMFCs with ammonia-based hydrogen sources

The fault diagnosis of high-power proton exchange membrane fuel cells (PEMFCs) with ammonia-based hydrogen sources (AHSs) is studied by an ensemble machine learning methods as considering various operating conditions. Under various operating conditions, the results show that when the single-fault state and the multiple-faults state, appear in a single high-power PEMFC system, the overall diagnostic accuracy of 98.89% is realized by the optimized hidden Markov model (HMM) coupling with the convolutional neural network (CNN) and the t-distributed stochastic neighbor embedding (t-SNE). When using the t-SNE-CNN-HMM fault diagnosis model, the overall diagnostic accuracy is 100% in a single AHS system. Similarly, the overall diagnostic accuracy is 98.58% for the single-fault and the multiple-faults states in the AHSs-PEMFCs coupled system. Based on these single-fault and multiple-faults states, the overall diagnostic accuracy of t-SNE-CNN-HMM model is larger in comparison with these of other diagnosis models, of which these diagnosis models are composed of the support vector machine (SVM), backpropagation neural network (BPNN) and only-CNN models. The t-SNE-CNN-HMM method integrates the generalization and identification ability of CNN and HMM, leading to provide an efficient and accurate fault diagnosis for the AHSs-PEMFCs coupled system.

RAGN-R: A multi-subject ensemble machine-learning method for estimating mechanical properties of advanced structural materials

RAGN-R: A multi-subject ensemble machine-learning method for estimating mechanical properties of advanced structural materials

Robust classification model for identifying stroke patients utilising a machine learning-based ensemblestacking method

Abstract Purpose of the study: Cerebrovascular accident (CVA) occurs swiftly
and disrupts brain blood flow, causing neurological issues. Risk factors include
smoking, diabetes, hyperlipidemia, hypertension, and atrial fibrillation. Many brain
stroke prediction systems are computationally demanding, sluggish, and unreliable.
This study uses interpolation spline curves impute data and Principal Component
Analysis to identify the most important factors for stroke prediction. By using stack
ensemble machine learning methods, the goal is to improve the precision of stroke
disease identification.
Used method: Using interpolation spline curve data imputation and Principal
Component Analysis to preprocess and extract EHR data is unique. In addition, this
article also proposes a novel stacking ensemble technique using bagging and boosting
as foundation learners. Bagging and boosting enhance prediction by reducing variation
and bias. Stack-based ensemble learning classifies brain strokes. Build base and meta-
learners with Random Forest, XGBoost, Decision tree classifier, KNN, and Logistic
Regression. Evaluation of machine learning model efficiency determines the optimal
stacking ensemble meta-learner model.
Brief Description of Results: The results emphasize the stacking ensemble’s best
meta-learner model and imputation technique’s impact on electronic health record
representation. By using PCA, most important factors has identified for detecting
stroke. The analysis results showed that the Logistic Regression as a meta learner had
the best predictive performance which achieves 0.96 precision and 0.98 recall value
respectively with 97% accuracy and AUC curve value of 0.99.
Findings: The Decision Tree Classifier and K-Nearest Neighbour as meta learner got
95%, 96%accuracy, and both 0.95 AOC curve values on this dataset, showing that the
method works. Precision values of 0.93, and 0.95 for the Decision Tree Classifier and
KNN Classifiers as meta-learner confirm their robustness. These findings suggest that
interpolation spline curve and stacking based ensemble machine learning can improve
the identification of brain stroke from incomplete electronic health records.

АНСАМБЛЕВІ МЕТОДИ НА ОСНОВІ ЦЕНТРУВАННЯ ДЛЯ СЕГМЕНТАЦІЇ ЗОБРАЖЕННЯ

Ensemble methods can be used for many tasks, some of the most popular being: classification, regression, and image segmentation. Image segmentation is a challenging task, where the use of ensemble machine learning methods provides an opportunity to improve the accuracy of neural network predictions. In this study, three new methods for combining neural network predictions were proposed, which were compared with the ensemble averaging method and the conventional use of neural networks. These methods are based on the idea of ​​mask centering and different methods of combining predictions. The main goal of the research is to create more reliable and high-quality ensemble methods that can perform their tasks regardless of image quality. These methods are based on different approaches, which makes it possible to choose a more suitable method for solving a specific problem. Thanks to the use of the proposed methods, a good efficiency of segmentation of medical images on different data was obtained. The obtained results indicate that the proposed methods of combining predictions make it possible to minimize the overall error, better generalize the data and increase the reliability of using predictions. Key words: ensemble methods, deep learning, machine learning, image segmentation.

HARD-VOTING DAN SOFT-VOTING CLASSIFIER: MODEL KLASIFIKASI RISIKO KEMATIAN PADA PASIEN GAGAL GINJAL KRONIK

Chronic kidney failure is a serious disease that can lead to death if not detected and treated early. This study aims to predict the risk of death in hospitalized chronic kidney failure patients using ensemble machine learning methods, specifically hard-voting and soft-voting. The voting classifier is used to combine predictions from several classification models, where hard-voting makes decisions based on the majority vote, and soft-voting considers the average prediction probability. However, with imbalanced data, classification models tend to be biased toward the majority class. To address this, the synthetic minority oversampling technique (SMOTE) is applied to balance the class distribution. The model's performance is evaluated using accuracy, precision, and specificity metrics. The results of the study show that the hard-voting classifier provided the best performance with an accuracy of 85,156%, precision of 86,726%, and specificity of 89,908%, outperforming the soft-voting classifier. The use of SMOTE proved to improve prediction for the minority class, which is crucial in detecting high-risk patients who may die during hospitalization. This approach is expected to aid in the early detection and better management of hospitalized chronic kidney failure patients, potentially reducing mortality rates from this disease.

Optimizing Cardiomegaly Detection: A Random Forest Approach to Processed Chest X-ray Imagery

This study explores the application of a Random Forest Classifier for the automated detection of Cardiomegaly from chest X-ray images, utilizing a dataset processed and derived from the NIH Chest X-ray Dataset. Given the crucial need for accurate and timely diagnosis of Cardiomegaly to inform appropriate treatment decisions, this research aims to determine the efficacy of machine learning models in augmenting diagnostic processes. Employing image pre-processing techniques such as Sobel filtering for edge detection and Hu Moments for feature extraction, the study enhances the input features for the model. The performance of the classifier was evaluated using a 5-fold cross-validation approach, yielding results with average accuracy, precision, recall, and F1-scores ranging approximately between 52% and 54%. These findings suggest a moderate level of reliability and consistency, indicating the potential utility of ensemble machine learning methods in medical imaging analysis. However, the variability in performance across different data subsets highlights the challenges and necessitates further optimization. This research contributes to the ongoing discourse on integrating machine learning into clinical settings, demonstrating the potential benefits and current limitations. Future research is recommended to expand the dataset variety, integrate advanced deep learning methodologies, and rigorously test these models in clinical environments. The findings hold significant implications for the development of automated diagnostic tools in healthcare, potentially leading to enhanced diagnostic accuracy and efficiency.

Heart disease detection using ensemble and non-ensemble machine learning methods

Heart disease detection using ensemble and non-ensemble machine learning methods

Analysis of ensemble machine learning classification comparison on the skin cancer MNIST dataset

This study aims to analyze the performance of various ensemble machine learning methods, such as Adaboost, Bagging, and Stacking, in the context of skin cancer classification using the skin cancer MNIST dataset. We also evaluate the impact of handling dataset imbalance on the classification model’s performance by applying imbalanced data methods such as random under sampling (RUS), random over sampling (ROS), synthetic minority over-sampling technique (SMOTE), and synthetic minority over-sampling technique with edited nearest neighbor (SMOTEENN). The research findings indicate that Adaboost is effective in addressing data imbalance, while imbalanced data methods can significantly improve accuracy. However, the selection of imbalanced data methods should be carefully tailored to the dataset characteristics and clinical objectives. In conclusion, addressing data imbalance can enhance skin cancer classification accuracy, with Adaboost being an exception that shows a decrease in accuracy after applying imbalanced data methods.

Correction: Uncertainty Assessment of Surface Water Salinity Using Standalone, Ensemble, and Deep Machine Learning Methods: A Case Study of Lake Urmia

Correction: Uncertainty Assessment of Surface Water Salinity Using Standalone, Ensemble, and Deep Machine Learning Methods: A Case Study of Lake Urmia

Modeling the seasonal wildfire cycle and its possible effects on the distribution of focal species in Kermanshah Province, western Iran.

Predicting environmental disturbances and evaluating their potential impacts on the habitats of various plant and animal species is a suitable strategy for guiding conservation efforts. Wildfires are a type of disturbance that can affect many aspects of an ecosystem and its species. Therefore, through the integration of spatial models and species distribution models (SDMs), we can make informed predictions of the occurrence of such phenomena and their potential impacts. This study focused on five focal species, namely, the brown bear (Ursus arctos), wild goat (Capra aegagrus), wild sheep (Ovis orientalis), wildcat (Felis silvestris), and striped hyena (Hyaena hyaena). This study used MODIS active fire data and ensemble machine learning methods to model the risk of wildfire occurrence in 2023 for spring, summer, and autumn separately. This study also investigated the suitability of habitats for focal species via SDMs. The predicted probability maps for wildfire risk and habitat suitability were converted to binary values via the true skill statistic (TSS) threshold. The overlap of the habitat suitability map and wildfire occurrence areas was analyzed via GAP analysis. The area prone to fire in spring, summer and winter is equal to 9077.32; 10,199.83 and 13,723.49 KM2 were calculated, which indicates an increase in wildfire risk. Proximity to roads is one of the most important factors affecting the possible effects of wildfires in all seasons. Most fire occurrences are concentrated on agricultural lands, which, when integrated with other land use types, have wildfire potential in all seasons. The use of fire to destroy agricultural residues is a critical factor in the occurrence of wildfires. The distribution range of each focal species is considered the most important component of fire susceptibility. Hence, the suitable habitat for Hyaena hyaena in spring, summer, and autumn, with areas of 5.257, 5.856, and 6.889 km2 respectively, is the most affected by the possibility of fire. In contrast, these areas have the lowest values for Ovis orientalis, with 162, 127, and 396 km2 respectively. Therefore, species that are dependent on human-based ecosystems have the highest vulnerability to wildfire. Conservation efforts should focus on familiarizing farmers with methods of destroying agricultural residues as well as the consequences of intentional fires. The findings of this study can be used to mitigate the negative impacts of wildfire and protect the habitat of focal species.

An Ensemble Machine Learning Model to Enhance Extrapolation Ability of Predicting Coarse Particulate Matter with High Resolutions in China.

Accurate exposure assessment is important for conducting PM10-2.5-related epidemiological studies, which have been limited thus far. In this study, we aimed to develop an ensemble machine learning method to estimate PM10-2.5 concentrations in mainland China during 2013-2020. The study was conducted in two stages. In the first stage, we developed two methods: the indirect method refers to developing models for PM2.5 and PM10 separately and subsequently calculating PM10-2.5 as the difference between them; and the direct method refers to establishing a model between PM10-2.5 measurements and relevant predictors directly. In the second stage, we employed an ensemble method by integrating predictions from both indirect and direct methods. Internal and external cross-validation (CV) were performed to validate the extrapolation capacity of models. The ensemble method demonstrated enhanced extrapolation accuracy in both internal and external CV compared to indirect and direct methods. The predictions produced by the ensemble method captured the spatiotemporal pattern of PM10-2.5, even in the sand and dust storm seasons. Our study introduces an ensemble strategy leveraging the strengths of both indirect and direct methods to estimate PM10-2.5 concentrations, which holds significant potential to support future epidemiological studies to address knowledge gaps in understanding the health effects of PM10-2.5.

Traffic noise prediction model using GIS and ensemble machine learning: a case study at Universiti Teknologi Malaysia (UTM) Campus.

This study represents a pioneering effort to integrate geographic information systems (GIS) and ensemble machine learning methods to predict noise levels on a university campus. Three ensemble models including random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGB) were developed to predict traffic noise based on data collected over a 4-week period at the Universiti Teknologi Malaysia (UTM) campus. Noise measurements were obtained during peak morning hours (7:30 to 9:30 a.m.) on weekdays within the UTM campus in Johor. Additional predictor variables, including data from the digital elevation model (DEM) and land use, were incorporated to capture the complex nonlinear relationships influencing noise levels. The models were optimized through hyperparameter tuning, resulting in high precision, as evidenced by performance metrics such as the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE). The XGB model emerged as the most accurate, with R2 = 0.96, MAE = 0.9, and MSE = 0.3. Noise maps generated using the inverse distance weighting (IDW) interpolation technique highlighted the spatial distribution of noise levels, classified into five classes considering WHO standards. The findings identified distance from roads, the number of light vehicles, and proximity to green areas as the most significant predictors. However, challenges remain in accurately predicting noise levels associated with other predictors. The outcomes of the study indicate the superior performance of the XGB model compared to the GB and RF models. The study recommends several measures to manage and control noise pollution on the UTM campus, including raising awareness, regulating and enforcing vehicle speed limits, reevaluating land use, installing sound insulation systems, and planting trees and vegetation buffer zones around and within educational buildings.

Forecasting Heart Disease Risk with a Stacking-Based Ensemble Machine Learning Method

As one of the main causes of sickness and mortality, heart disease, also known as cardiovascular disease, must be detected early in order to be prevented and treated. The rapid development of computer technology presents an opportunity for the cross-combination of medicine and informatics. A novel stacking model called SDKABL is presented in this work. It uses three classifiers, namely K-Nearest Neighbor (KNN), Decision Tree (DT), and Support Vector Machine (SVM) at the base layer and the Bidirectional Long Short-Term Memory based on Attention Mechanisms (ABiLSTM) model at the meta layer for the ultimate prediction. For lowering the temporal complexity and enhancing the model’s accuracy, the dimensionality reduction approach is seen to be crucial. Principal Component Analysis (PCA) was utilized in SDKABL to minimize dimensionality and facilitate feature fusion. Using several performance measures, including precision, F1-score, accuracy, recall, and Receiver Operating Characteristic (ROC) score, the performance of SDKABL was compared to that of other independent classifiers. The experimental findings demonstrate that our proposed model combining individual classifiers with the stacking method helps improve the prediction model’s accuracy.

Enhanced intrusion detection model based on principal component analysis and variable ensemble machine learning algorithm

The intrusion detection system (IDS) model, which can identify the presence of intruders in the network and take some predefined action for safe data transit across the network, is advantageous in achieving security in both simple and advanced network systems. Several IDS models have various security problems, such as low detection accuracy and high false alarms, which can be caused by the network traffic dataset's excessive dimensionality and class imbalance in the creation of IDS models. Principal Component Analysis (PCA) has proven to be a helpful feature selection technique for dimensionality reduction. As a result, because it is a linear transformation, it has challenges capturing non-linear relationships between feature properties in the network traffic datasets. This paper proposes a variable ensemble machine learning method to solve the problem and achieve a low variance model with high accuracy and low false alarm. First, PCA is combined with the AdaBoost ensemble machine learning algorithm, which acts as stagewise additive modelling to compensate for PCA's deficiency in feature selection in network traffic by minimizing the exponential loss function. Secondly, PCA is used for feature selection, and a LogitBoost classifier algorithm can be used for multiclass classification and acts as an additive tree regression to compensate for the PCA's weakness by minimizing the Logistic Loss to provide an optimal classifier output. Finally, the low variance ability of RandomForest, which employs the bagging approach, is applied to eliminate overfittings. The experiments of the IDS model developed from the proposed methods were evaluated on the WSN-DS, NSL-KDD, and UNSW-N15 datasets. The performance of the methods, PCA with AdaBoost, on the WSN-DS dataset has an accuracy score of 92.3 %, an 89.0 % accuracy score on the NSL-KDD dataset, and a 67.9 % accuracy score on UNSW-N15, which is the least accurate score. PCA and RandomForest surpassed them by scoring 100 % accuracy on all three datasets. PCA and Bagging have an accuracy score of 99.8 % on the WSN-DS dataset, 100 % on the NSL-KDD dataset, and 93.4 % on the UNSW-N15 dataset. In comparison, PCA and LogitBoost have an accuracy score of 98.9 % on the WSN-DS dataset, 100 % on the NSL-KDD dataset, and 88.7 % on the UNSW-N15 dataset.

Application of Ensemble Machine Learning Methods for QSAR Classification of Leukotriene A4 Hydrolase Inhibitors in Drug Discovery

Inflammatory diseases such as asthma, rheumatoid arthritis, and cardiovascular conditions are driven by overproduction of leukotriene B4 (LTB4), a potent inflammatory mediator. Leukotriene A4 hydrolase (LTA4H) plays a critical role in converting leukotriene A4 into LTB4, making it a prime target for drug discovery. Despite ongoing efforts, developing effective LTA4H inhibitors has been challenging due to the complex binding properties of the enzyme and the structural diversity of potential inhibitors. Traditional drug discovery methods, like high-throughput screening (HTS), are often time-consuming and inefficient, prompting the need for more advanced approaches. Quantitative Structure-Activity Relationship (QSAR) modeling, enhanced by ensemble machine learning techniques, provides a promising solution by enabling accurate prediction of compound bioactivity based on molecular descriptors. In this study, six ensemble machine learning methods—AdaBoost, Extra Trees, Gradient Boosting, LightGBM, Random Forest, and XGBoost—were employed to classify LTA4H inhibitors. The dataset, comprising 636 compounds labeled as active or inactive based on pIC50 values, was processed to extract 450 molecular descriptors after feature engineering. The results show that the LightGBM model achieved the highest classification accuracy (83.59%) and Area Under the Curve (AUC) value (0.901), outperforming other models. XGBoost and Random Forest also demonstrated strong performance, with AUC values of 0.890 and 0.895, respectively. The high sensitivity (95.24%) of the XGBoost model highlights its ability to accurately identify active compounds, though it exhibited slightly lower specificity (61.36%), indicating a higher false-positive rate. These findings suggest that ensemble machine learning models, particularly LightGBM, are highly effective in predicting bioactivity, offering valuable tools for early-stage drug discovery. The results indicate that ensemble methods significantly enhance QSAR model accuracy, making them viable for identifying promising LTA4H inhibitors, potentially accelerating the development of anti-inflammatory therapies.

Exploring explainable ensemble machine learning methods for long-term performance prediction of industrial gas turbines: A comparative analysis

In today's modern life, where electricity demand is one of the fundamental necessities, gas turbines play a pivotal role in meeting this demand. As such, it is imperative to address the challenges faced in the field. Current models often rely on simplifying assumptions, neglecting the intricate relationships between variables. This limitation leads to reduced accuracy and reliability, ultimately affecting the overall efficiency of gas turbine systems. Furthermore, the complexity of gas turbine behavior, coupled with the scarcity of comprehensive datasets, exacerbates the problem.To address these challenges, this research aimed to develop an advanced model capable of accurately forecasting real gas turbine behavior. The proposed approach leveraged ensemble decision trees, robust preprocessing techniques, and rigorous evaluation using an extensive dataset spanning from 2011 to 2015. The training and validation phases were conducted on data from 2011 to 2014, with the 2015 dataset reserved for evaluation.The results demonstrated that the bagging structure outperformed the boosted structure, exhibiting lower complexity and higher reliability. Remarkably, the bagging approach with only 30 estimators achieved a superior root mean square error of 1.4176, outperforming the boosted trees with 200 learners. The model effectively captured the overall gas turbine performance, though it encountered limitations in certain specific operating ranges.To further investigate the model's behavior, an evaluation was conducted to assess the effects of the input variables on the output power. While the interpretability of the results posed some challenges, the overall findings were deemed acceptable and provide valuable insights for optimizing gas turbine performance. The significance of this research lies in its potential to inform decision-making and enhance the efficiency of gas turbine systems, ultimately contributing to the reliable and sustainable supply of electricity.

Field scale wheat yield prediction using ensemble machine learning techniques

Wheat is crucial for global food security and plays significant role in achieving United Nations Sustainable Development Goal 2 (Zero Hunger). In India, wheat accounts for 33.5 % of total cereal production. Accurate and cost effective yield predictions are essential for maintaining food security. Wheat yield forecasting is influenced by various factors, such as genotype and environmental conditions. Among these, the effect of morpho-physiological traits in the field is important for predicting yield but hasn't been studied much using ensemble machine learning methods. This study aims to bridge this gap by evaluating 29 morpho-physiological traits to predict site specific wheat yield. Big data framework was used to develop and refine several ensemble machine learning models based on field trial datasets. The developed models are optimized to reduce errors and prevent overfitting and underfitting, boosting their predictive precision. Each model's efficiency was evaluated using performance metrics such as mean absolute error, mean absolute deviation, root mean square error, R2, and overall accuracy. The ensemble model, which combines random forest (RF) and artificial neural networks (ANN), demonstrated better performance by achieving a mean absolute percentage error of 4.65 %, and R2 value of 98.48 % and 98.18 % accuracy on test data.Our results demonstrate that ensemble models combining RF with support vector regression (SVR) outperformed individual models such as RF, SVR, ANN, multivariate adaptive regression splines (MARS). These findings are a promising step towards future research focused on creating more advanced ensemble methods with finely tuned hyperparameters for improving the accuracy of large-scale wheat yield prediction.

Determination of Possible Biomarkers for Predicting Well-Differentiated Thyroid Cancer Recurrence by Different Ensemble Machine Learning Methods

Objective: Well-differentiated thyroid cancer (WDTC) is the most common thyroid malignancy and although it is curable, the risk of recurrence is high. In this study, classification algorithms based on clinicopathologic features of WDTC patients were used to determine the possible of recurrence in WDTC and to evaluate potential predictive factors, and possible biomarkers based on the optimal model were identified. Method: In this study, open access data on 383 patients with WDTC, 108 with recurrence and 275 without recurrence, were used. In order to predict recurrence in WDTC patients, features were selected using recursive feature elimination variable selection method among features and classification was performed with two ensemble learning methods (Random Forest, Adaboost). Results: Two different ensemble learning models used to classify recurrence in WDTC were Random Forest with an accuracy of 0.957, sensitivity of 0.889, specificity of 0.978, positive predictive value of 0.923, negative predictive value of 0.967, Matthews correlation coefficient of 0.878, G-mean of 0.945, F1-score of 0.906, and accuracy of 0.940, sensitivity of 0.889, specificity of 0.955, positive predictive value of 0.857, negative predictive value of 0.966, Matthews correlation coefficient of 0.833, G-mean of 0.910, F1-score of 0.873. Conclusion: According to variable importance based on the Random Forest, the 5 possible clinical biomarkers for predicting WDTC recurrence are Response, Risk, Node, Tumor, and age. In the light of these findings, patient management and treatment planning can be organized.

Predicting gross domestic product using the ensemble machine learning method

The need for more accurate GDP predictions in Nigeria has necessitated the exploration of additional indicators that reflect economic activities and socio-economic factors. This research pioneers a comprehensive approach to predicting Nigeria's Gross Domestic Product (GDP) by integrating a wide array of indicators beyond traditional economic metrics. The primary objective is to enhance the prediction accuracy of Nigeria's GDP using a diverse range of socio-economic indicators. Drawing from data spanning 2000 to 2021, the study incorporates variables like healthcare expenditure, net migration rates, population demographics, life expectancy, access to electricity, and internet usage. Utilising machine learning techniques such as Random Forest Regressor, XGBoost Regressor, and Linear Regression, the study rigorously evaluates the efficacy of these algorithms in forecasting GDP. The analysis reveals that all selected indicators have a strong correlation with GDP. Significantly, the Random Forest Regressor emerges as the most robust model, boasting an R2 score of 0.96 and a Mean Absolute Error (MAE) of 24.29. The study underscores that optimising factors like healthcare, internet access, and electricity availability could serve as pivotal levers for accelerating Nigeria's economic growth.

High resolution mapping of nitrogen dioxide and particulate matter in Great Britain (2003–2021) with multi-stage data reconstruction and ensemble machine learning methods

In this contribution, we applied a multi-stage machine learning (ML) framework to map daily values of nitrogen dioxide (NO2) and particulate matter (PM10 and PM2.5) at a 1 km2 resolution over Great Britain for the period 2003–2021. The process combined ground monitoring observations, satellite-derived products, climate reanalyses and chemical transport model datasets, and traffic and land-use data. Each feature was harmonized to 1 km resolution and extracted at monitoring sites. Models used single and ensemble-based algorithms featuring random forests (RF), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), as well as lasso and ridge regression. The various stages focused on augmenting PM2.5 using co-occurring PM10 values, gap-filling aerosol optical depth and columnar NO2 data obtained from satellite instruments, and finally the training of an ensemble model and the prediction of daily values across the whole geographical domain (2003–2021). Results show a good ensemble model performance, calculated through a ten-fold monitor-based cross-validation procedure, with an average R2 of 0.690 (range 0.611–0.792) for NO2, 0.704 (0.609–0.786) for PM10, and 0.802 (0.746–0.888) for PM2.5. Reconstructed pollution levels decreased markedly within the study period, with a stronger reduction in the latter eight years. The pollutants exhibited different spatial patterns, while NO2 rose in close proximity to high-traffic areas, PM demonstrated variation at a larger scale. The resulting 1 km2 spatially resolved daily datasets allow for linkage with health data across Great Britain over nearly two decades, thus contributing to extensive, extended, and detailed research on the long-and short-term health effects of air pollution.