Air Quality Prediction and Ranking Assessment Based on Bootstrap-XGBoost Algorithm and Ordinal Classification Models

With the quick development of society and industry, air quality has become a grim and global environmental concern. Predicting and rating air quality for many cities remains a significant challenge. Consequently, machine learning algorithms have garnered considerable attention for their potential to address these issues effectively. In this paper, firstly, based on daily air quality data from July 1, 2022 to June 30, 2023 in Lanzhou city of China, five machine learning models, including Bayes Model Averaging (BMA), Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are developed to predict the Air Quality Index (AQI) via six major air pollutants (PM2.5, PM10, SO2, NO2, O3 and CO). Secondly, we integrate Bootstrap algorithm into the optimal model, leading to the proposal of the LSTM-Bootstrap algorithm for deriving the standard errors and confidence intervals of the predicted AQI. Thirdly, a cumulative logit model is employed to evaluate and forecast AQI rating. The analysis results indicate that AQI rating is significantly affected by PM10, CO and O3. Additionally, to validate the efficacy of the suggested methods, a similar analysis is conducted on air quality data from Chengdu city for the same period. The findings provide valuable insights for future environmental policies and air quality management strategies.

Abstract. As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up to date and accurate and provides means to avoid exposure to high air pollution levels. Long- and short-term exposure to outdoor air pollution is associated with increased risks of mortality and morbidity. Up-to-date information on present and coming days' air quality helps people avoid exposure during episodes with high levels of air pollution. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process-oriented dispersion modelling. In this paper, we apply different machine learning (ML) algorithms – random forest (RF), extreme gradient boosting (XGB), and long short-term memory (LSTM) – to improve 1, 2, and 3 d deterministic forecasts of PM10, NOx, and O3 at different sites in Greater Stockholm, Sweden. It is shown that the deterministic forecasts can be significantly improved using the ML models but that the degree of improvement of the deterministic forecasts depends more on pollutant and site than on what ML algorithm is applied. Also, four feature importance methods, namely the mean decrease in impurity (MDI) method, permutation method, gradient-based method, and Shapley additive explanations (SHAP) method, are utilized to identify significant features that are common and robust across all models and methods for a pollutant. Deterministic forecasts of PM10 are improved by the ML models through the input of lagged measurements and Julian day partly reflecting seasonal variations not properly parameterized in the deterministic forecasts. A systematic discrepancy by the deterministic forecasts in the diurnal cycle of NOx is removed by the ML models considering lagged measurements and calendar data like hour and weekday, reflecting the influence of local traffic emissions. For O3 at the urban background site, the local photochemistry is not properly accounted for by the relatively coarse Copernicus Atmosphere Monitoring Service ensemble model (CAMS) used here for forecasting O3 but is compensated for using the ML models by taking lagged measurements into account. Through multiple repetitions of the training process, the resulting ML models achieved improvements for all sites and pollutants. For NOx at street canyon sites, mean squared error (MSE) decreased by up to 60 %, and seven metrics, such as R2 and mean absolute percentage error (MAPE), exhibited consistent results. The prediction of PM10 is improved significantly at the urban background site, whereas the ML models at street sites have difficulty capturing more information. The prediction accuracy of O3 also modestly increased, with differences between metrics. Further work is needed to reduce deviations between model results and measurements for short periods with relatively high concentrations (peaks) at the street canyon sites. Such peaks can be due to a combination of non-typical emissions and unfavourable meteorological conditions, which are rather difficult to forecast. Furthermore, we show that general models trained using data from selected street sites can improve the deterministic forecasts of NOx at the station not involved in model training. For PM10 this was only possible using more complex LSTM models. An important aspect to consider when choosing ML algorithms is the computational requirements for training the models in the deployment of the system. Tree-based models (RF and XGB) require fewer computational resources and yield comparable performance in comparison to LSTM. Therefore, tree-based models are now implemented operationally in the forecasts of air pollution and health risks in Stockholm. Nevertheless, there is big potential to develop generic models using advanced ML to take into account not only local temporal variation but also spatial variation at different stations.

Air quality is an important environmental component that has a significant influence on public health and well-being. Poor air quality can cause a variety of health problems, including respiratory and cardiovascular disorders. Therefore, there is a growing demand for air quality prediction tools to enable consumers and authorities to take the best decisions and to implement the necessary actions to reduce air pollution. The present paper describes an innovative application that uses machine learning techniques to supply to the users real-time air quality predictions made on past data from their unique location. The Scikit-learn Python package was used to implement five machine learning algorithms, including K-Nearest Neighbors, Random Forest, Gradient Boosting, Support Vector Regression (SVR) and AdaBoost. To achieve robust model performance, compatibility with cross-validation approaches was evaluated. The obtained results indicate that these machine learning techniques are successful at forecasting air quality. The AdaBoost method emerged as the best accurate predictor after extensive investigation, closely followed by Gradient Boosting, SVR, Random Forest, and K-Nearest Neighbors. Furthermore, the investigation also focused on the adapted handling of inaccurate data and providing graphical visualizations to highlight the algorithm's efficacy.

How urban air quality affects land values: Exploring non-linear and threshold mechanism using explainable artificial intelligence

The frequent occurrence and spread of wildfires pose a serious threat to the ecological environment and urban development. Therefore, assessing regional wildfire susceptibility is crucial for the early prevention of wildfires and formulation of disaster management decisions. However, current research on wildfire susceptibility primarily focuses on improving the accuracy of models, while lacking in-depth study of the causes and mechanisms of wildfires, as well as the impact and losses they cause to the ecological environment and urban development. This situation not only increases the uncertainty of model predictions but also greatly reduces the specificity and practical significance of the models. We propose a comprehensive evaluation framework to analyze the spatial distribution of wildfire susceptibility and the effects of influencing factors, while assessing the risks of wildfire damage to the local ecological environment and urban development. In this study, we used wildfire information from the period 2013–2022 and data from 17 susceptibility factors in the city of Guilin as the basis, and utilized eight machine learning algorithms, namely logistic regression (LR), artificial neural network (ANN), K-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM), and eXtreme gradient boosting (XGBoost), to assess wildfire susceptibility. By evaluating multiple indicators, we obtained the optimal model and used the Shapley Additive Explanations (SHAP) method to explain the effects of the factors and the decision-making mechanism of the model. In addition, we collected and calculated corresponding indicators, with the Remote Sensing Ecological Index (RSEI) representing ecological vulnerability and the Night-Time Lights Index (NTLI) representing urban development vulnerability. The coupling results of the two represent the comprehensive vulnerability of the ecology and city. Finally, by integrating wildfire susceptibility and vulnerability information, we assessed the risk of wildfire disasters in Guilin to reveal the overall distribution characteristics of wildfire disaster risk in Guilin. The results show that the AUC values of the eight models range from 0.809 to 0.927, with accuracy values ranging from 0.735 to 0.863 and RMSE values ranging from 0.327 to 0.423. Taking into account all the performance indicators, the XGBoost model provides the best results, with AUC, accuracy, and RMSE values of 0.927, 0.863, and 0.327, respectively. This indicates that the XGBoost model has the best predictive performance. The high-susceptibility areas are located in the central, northeast, south, and southwest regions of the study area. The factors of temperature, soil type, land use, distance to roads, and slope have the most significant impact on wildfire susceptibility. Based on the results of the ecological vulnerability and urban development vulnerability assessments, potential wildfire risk areas can be identified and assessed comprehensively and reasonably. The research results of this article not only can improve the specificity and practical significance of wildfire prediction models but also provide important reference for the prevention and response of wildfires.

Clean air is essential for maintaining a healthy lifestyle, yet poor air quality remains a major contributor to numerous respiratory ailments.Air pollutants such as PM2.5, NOx, COx, and SOx significantly impact human health, emphasizing the need for accurate forecasting models.However, predicting air quality is challenging due to the dynamic interplay of various factors, including meteorological conditions, vehicular emissions, and industrial discharges.This study proposes a novel hybrid forecasting model, Hyb_LSTM+KCNN, which combines Long Short-Term Memory (LSTM) networks and Kernel Convolutional Neural Networks (KCNN) for time-series prediction of the Air Quality Index (AQI).The LSTM component captures temporal dependencies in air quality data, enabling effective modeling of sequential patterns over time.Meanwhile, the KCNN module enhances feature extraction by leveraging convolutional kernels to identify local data patterns.By integrating these complementary strengths, the hybrid architecture provides a more robust and accurate AQI forecasting model.The proposed model was evaluated on comprehensive datasets, incorporating various pollutant levels and meteorological parameters.Experimental results demonstrated that the Hyb_LSTM+KCNN model consistently outperforms traditional forecasting techniques, achieving higher prediction accuracy and generalization capabilities.The model effectively captures correlations between pollutants and environmental factors, leading to precise AQI forecasts even under dynamic and complex conditions.This study presents a promising solution for air quality prediction, with practical implications for environmental monitoring and public health management.Future research will explore further optimization of the model for real-time applications and investigate its performance when integrating additional data sources, such as satellite and hyperspectral imagery.

In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN). AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air. Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution. Also, the current air quality is dependent on the climate conditions and industrialization in that area. Thus, the AQI is history-dependent. To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo's derivative has been used in the backpropagation algorithm for training of the RNN. Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction. But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives. The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy. It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).

Since most of the existing air quality index (AQI) predicting models focused on prediction of the time series data of a single target monitoring station, they failed to consider the correlation and mutual influence among the air quality monitoring station sites and the spatio-temporal characteristics of air quality. And this will lead to a certain one-sidedness during air quality prediction of a particular site. Aimed at this problem, a short-term air quality prediction model based on K-nearest neighbor (KNN) and Long Short-Term Memory (LSTM) was proposed. The model firstly used KNN algorithm to select the time and space-related monitoring stations, then the air quality index sequences of these stations were constructed into data sets, followed by training and testing processes in the LSTM model, and finally the model was verified with real data. It is suggested that the prediction accuracy of the hybrid prediction model constructed in this paper is acceptable in terms of the space-time correlation, and it could be an alternative for further application of air quality prediction.

Radiomics and machine learning have been extensively utilized in the realm of urinary stones, particularly in forecasting stone treatment outcomes. The objective of this study was to integrate clinical variables and radiomic features to develop a machine learning model for predicting the stone-free rate (SFR) following percutaneous nephrolithotomy (PCNL).A total of 212 eligible patients who underwent PCNL surgery at the Second Affiliated Hospital of Nanchang University were included in a retrospective analysis. Preoperative clinical variables and non-contrast-enhanced CT images of all patients were collected, and radiomic features were extracted after delineating the stone ROI. Univariate analysis was conducted to identify clinical variables strongly correlated with the stone-free rate after PCNL, and the least absolute shrinkage and selection operator algorithm (lasso regression) was utilized to screen radiomic features. Four supervised machine learning algorithms, including Logistic Regression, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Decision Tree (GBDT), were employed. The clinical variables with strong correlation and screened radiomic features were integrated into the four machine learning algorithms to construct a prediction model, and the receiver operating curve was plotted. The area under the receiver operating curve (AUC), the accuracy rate, the specificity, etc., were used to evaluate the predictive performance of the four models.After analyzing postoperative statistics, the stone-free rate following the procedure was found to be 70.3% (n = 149). Among the various clinical variables examined, factors, such as stone number, stone diameter, stone CT value, stone location, and history of stone surgery, were identified as statistically significant in relation to the stone-free rate after PCNL. A total of 121 radiomic features were extracted, and through lasso regression, 7 features most closely associated with the stone-free rate post-PCNL were identified. The predictive accuracy of different models (Logistic Regression, RF, XGBoost, and GBDT) for determining the stone-free rate after PCNL was evaluated, yielding accuracies of 78.1%, 76.6%, 75.0%, and 73.4%, respectively. The corresponding area under the curve AUC (95%CI) were 0.85 (0.83-0.89), 0.81 (0.76-0.85), 0.82 (0.78-0.85), and 0.77 (0.73-0.81), positioning these models among the top performers in logistic regression prediction. In terms of predictive importance scores, the key factors identified by the logistic regression model were number of stone, zone percentage, stone diameter, and surface area. Similarly, the RF model highlighted number of stone, stone CT value, stone diameter, and surface area as the top predictors.Among the four machine learning models, the logistic regression model demonstrated the highest accuracy and discrimination ability in predicting the stone-free rate following PCNL. In comparison to XGBoost and GBDT, RF also exhibited superior accuracy and a certain level of discrimination ability. However, based on the performance of all four models, logistic regression is more likely to aid in clinical decision-making by assisting clinicians in diagnosing PCNL in patients. This enables us to effectively predict the presence of residual stones post-surgery and ultimately select patients who are suitable candidates for PCNL.

Glass forming ability prediction of bulk metallic glasses based on fused strategy

Modeling time series of vegetation indices in tallgrass prairie using machine and deep learning algorithms

The adverse effect of air pollution has always been a problem for human health. The presence of a high level of air pollutants can cause severe illnesses such as emphysema, chronic obstructive pulmonary disease (COPD), or asthma. Air quality prediction helps us to undertake practical action plans for controlling air pollution. The Air Quality Index (AQI) reflects the degree of concentration of pollutants in a locality. The average AQI was calculated for the various cities in China to understand the annual trends. Furthermore, the air quality index has been predicted for ten major cities across China using five different deep learning techniques, namely, Recurrent Neural Network (RNN), Bidirectional Gated Recurrent unit (Bi-GRU), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network BiLSTM (CNN-BiLSTM), and Convolutional BiLSTM (Conv1D-BiLSTM). The performance of these models has been compared with a machine learning model, eXtreme Gradient Boosting (XGBoost) to discover the most efficient deep learning model. The results suggest that the machine learning model, XGBoost, outperforms the deep learning models. While Conv1D-BiLSTM and CNN-BiLSTM perform well among the deep learning models in the estimation of the air quality index (AQI), RNN and Bi-GRU are the least performing ones. Thus, both XGBoost and neural network models are capable of capturing the non-linearity present in the dataset with reliable accuracy.

Addressing the constraints inherent in traditional primary Air Quality Index (AQI) forecasting models and the shortcomings in the exploitation of meteorological data, this research introduces a novel air quality prediction methodology leveraging machine learning and the enhanced modeling of secondary data. The dataset employed encompasses forecast data on primary pollutant concentrations and primary meteorological conditions, alongside actual meteorological observations and pollutant concentration measurements, spanning from 23 July 2020 to 13 July 2021, sourced from long-term air quality projections at various monitoring stations within Jinan, China. Initially, through a rigorous correlation analysis, ten meteorological factors were selected, comprising both measured and forecasted data across five categories each. Subsequently, the significance of these ten factors was assessed and ranked based on their impact on different pollutant concentrations, utilizing a combination of univariate and multivariate significance analyses alongside a random forest approach. Seasonal characteristic analysis highlighted the distinct seasonal impacts of temperature, humidity, air pressure, and general atmospheric conditions on the concentrations of six key air pollutants. The performance evaluation of various machine learning-based classification prediction models revealed the Light Gradient Boosting Machine (LightGBM) classifier as the most effective, achieving an accuracy rate of 97.5% and an F1 score of 93.3%. Furthermore, experimental results for AQI prediction indicated the Long Short-Term Memory (LSTM) model as superior, demonstrating a goodness-of-fit of 91.37% for AQI predictions, 90.46% for O3 predictions, and a perfect fit for the primary pollutant test set. Collectively, these findings affirm the reliability and efficacy of the employed machine learning models in air quality forecasting.

Travel planning is a process that allows users to obtain maximum benefit from their time, cost and energy. When planning a route from one place to another, it is an important option to present alternative travel areas on the route. This study proposes a travel route planning (TRP) architecture using a Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) model to improve both travel efficiency and environmental sustainability in route selection. This model incorporates carbon emissions directly into the route planning process by unifying user preferences, location recommendations, route optimization, and multimodal vehicle selection within a comprehensive framework. By merging environmental sustainability with user-focused travel planning, it generates personalized, practical, and low-carbon travel routes. The carbon emissions observed with TRP’s artificial intelligence (AI) recommendation route are presented comparatively with those of the user-determined route. XGBoost, Random Forest (RF), Categorical Boosting (CatBoost), Light Gradient Boosting Machine (LightGBM), (Extra Trees Regressor) ETR, and Multi-Layer Perception (MLP) models are applied to the TRP model. LSTM is compared with Recurrent Neural Networks (RNNs) and Gated Recurrent Unit (GRU) models. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), and Normalized Root Mean Square Error (NRMSE) error measurements of these models are carried out, and the best result is obtained using XGBoost and LSTM. TRP enhances environmental responsibility awareness within travel planning by integrating sustainability-oriented parameters into the decision-making process. Unlike conventional reservation systems, this model encourages individuals and organizations to prioritize eco-friendly options by considering not only financial factors but also environmental and socio-cultural impacts. By promoting responsible travel behaviors and supporting the adoption of sustainable tourism practices, the proposed approach contributes significantly to the broader dissemination of environmentally conscious travel choices.

Optimized ensemble learning with multi-feature fusion for enhanced anti-inflammatory peptide prediction.