Development of Machine Learning and Deep Learning Prediction Models for PM_2.5 in Ho Chi Minh City, Vietnam

Abstract

The application of machine learning and deep learning in air pollution management is becoming increasingly crucial, as these technologies enhance the accuracy of pollution prediction models, facilitating timely interventions and policy adjustments. They also facilitate the analysis of large datasets to identify pollution sources and trends, ultimately contributing to more effective and targeted environmental protection strategies. Ho Chi Minh City (HCMC), a major metropolitan area in southern Vietnam, has experienced a significant rise in air pollution levels, particularly PM_2.5, in recent years, creating substantial risks to both public health and the environment. Given the challenges posed by air quality issues, it is essential to develop robust methodologies for predicting PM_2.5 concentrations in HCMC. This study seeks to develop and evaluate multiple machine learning and deep learning models for predicting PM_2.5 concentrations in HCMC, Vietnam, utilizing PM_2.5 and meteorological data over 911 days, from 1 January 2021 to 30 June 2023. Six algorithms were applied: random forest (RF), extreme gradient boosting (XGB), support vector regression (SVR), artificial neural network (ANN), generalized regression neural network (GRNN), and convolutional neural network (CNN). The results indicated that the ANN is the most effective algorithm for predicting PM_2.5 concentrations, with an index of agreement (IOA) value of 0.736 and the lowest prediction errors during the testing phase. These findings imply that the ANN algorithm could serve as an effective tool for predicting PM_2.5 concentrations in urban environments, particularly in HCMC. This study provides valuable insights into the factors that affect PM_2.5 concentrations in HCMC and emphasizes the capacity of AI methodologies in reducing atmospheric pollution. Additionally, it offers valuable insights for policymakers and health officials to implement targeted interventions aimed at reducing air pollution and improving public health.

1. Introduction

Air pollution is a significant global issue, particularly in urban areas, where both short-term and long-term exposure to polluted air can have severe health consequences [1]. Among the various air pollutants, particulate matter with a diameter of 2.5 microns or smaller (PM_2.5) is of particular concern. PM_2.5’s diminutive size enables it to infiltrate the respiratory system, resulting in significant health issues, including respiratory and cardiovascular disorders, and potentially premature mortality [2]. Environmental pollution remains a major global health threat, with recent estimates from 2018 indicating that nine out of ten individuals inhale air that contains elevated levels of pollutants [3]. Both ambient and household air pollution contribute to approximately seven million deaths globally each year, with around 2.2 million of these deaths occurring in the Western Pacific Region alone. In Vietnam, air pollution is accountable for an estimated 60,000 deaths annually [3].

Ho Chi Minh City (HCMC), one of Vietnam’s largest and fastest expanding urban hubs, has experienced a notable rise in air pollution levels in recent years. This increase is primarily driven by metropolitan expansion, industrial growth, and a surge in road traffic [4]. As per a report from GreenID, in the three years 2016, 2017, and 2018, the air quality index (AQI) results reveal a troubling trend, as the percentage of AQI readings categorized as unhealthy escalated from 31.1% in 2016 to 41.9% in 2017, and subsequently to 44.2% in 2018 [5]. The declining air quality in HCMC has emerged as a critical issue for politicians, health officials, and the general populace. This issue has led to increased healthcare costs and economic burdens, necessitating urgent actions such as stricter emissions regulations, public health campaigns, and community engagement to mitigate the adverse effects and improve overall air quality. Therefore, developing effective strategies to predict PM_2.5 in HCMC is crucial.

Air pollutant concentration prediction models play a vital role in both assessing and managing air quality, offering critical insights for policymakers and environmental managers. These models are indispensable in optimizing air quality monitoring systems by providing detailed information on pollution levels, sources of pollutants, and the overall status of air quality in different regions [6]. By predicting future pollution levels, decisionmakers can take proactive measures such as issuing early warnings, implementing public health campaigns, or enforcing stricter emission regulations to mitigate adverse environmental and health impacts. The ability to forecast air quality at specific future points allows for better preparedness and more informed decision making regarding pollution control strategies [7].

There are two primary types of PM_2.5 concentration prediction models: knowledge-driven models and data-driven models. Knowledge-driven models, such as chemical transport models, are based on atmospheric science and require a thorough understanding of pollutant emission sources, transport mechanisms, and chemical transformations in the atmosphere. These models simulate the diffusion, transmission, and cross-regional transport of pollutants, making them highly valuable for detailed atmospheric analysis. However, they are often computationally intensive, requiring precise input data and extensive computational resources. Additionally, the complexity of atmospheric interactions and uncertainties in emission inventories can limit the accuracy of these models, particularly when dealing with real-world data that may not be as well structured as experimental conditions. In contrast, data-driven models are more practical and have become increasingly popular due to their ability to handle large datasets and generate predictions based on data characteristics. These models, which rely on statistical methods or machine learning techniques, are often more flexible and less dependent on detailed atmospheric knowledge. Data-driven approaches can be classified into three groups: statistical models, artificial intelligence (AI) models, and hybrid models that combine elements of both. AI models, in particular, have gained significant attention in recent years, driven by advancements in computational power and the Fourth Industrial Revolution. These models are known for their high accuracy and reliability in air quality prediction, as they excel at modeling complex, nonlinear phenomena and relationships between numerous exogenous variables [8]. One of the key strengths of AI-based models is their ability to process vast amounts of data rapidly, offering significant advantages in terms of processing speed, scalability, and cost-effectiveness. AI models, such as machine learning and deep learning techniques, have the capability to impute missing data, identify hidden patterns in large datasets, and generate accurate predictions of pollution levels at specific future points. Moreover, AI models can provide spatial and temporal predictions, allowing researchers to estimate pollution levels for particular areas and times with a high degree of precision [9]. In addition to their ability to simulate air quality, AI techniques also allow for real-time monitoring and adaptive learning, further enhancing their effectiveness in dynamic environments.

Numerous studies have proven the effectiveness of AI models in predicting air quality, specifically PM_2.5 levels. For example, Bingyue Pan (2018) employed the XGBoost algorithm to predict PM_2.5 levels in Tianjin City [10], whereas Zamani et al. (2019) applied random forest, XGBoost, and deep learning methodologies utilizing multiplatform remote sensing information to forecast PM_2.5 levels in Tehran [11]. Goulier et al. (2020) provided an hourly forecast of ten atmospheric pollutant levels in Münster utilizing an artificial neural network (ANN) methodology [12], whereas Castelli et al. (2020) employed support vector regression (SVR) to anticipate pollutant and particle levels in California [13]. Likewise, Gou et al. (2020) utilized statistical correlation evaluation and ANNs to discern relationships among the air pollution index and weather variables in Xi’an and Lanzhou [14]. Doreswamy et al. (2020) created machine learning models to forecast PM levels of the atmospheric conditions of Taiwan [15]. In the U.S., Zhou et al. (2020) examined several machine learning methodologies employed for air pollution prediction, with applications that span multiple regions, including high-pollution urban areas [16]. Similarly, Chen et al. (2020) investigated how climate change influences PM_2.5 levels, using multimodel projections to assess the effectiveness of predictive models in the U.S [17]. In Europe, Ordóñez et al. (2020) utilized multimodel simulations combined with machine learning techniques to improve air quality predictions, particularly for PM_2.5 levels, while Petetin et al. (2020) developed high-resolution forecasting models to enhance predictive accuracy across the continent [18,19]. In China, Zheng et al. (2021) employed deep learning models to enhance the accuracy of PM_2.5 concentration predictions, showcasing the latest advancements in air quality modeling [20]. These recent studies underscore the global applicability of machine learning in tackling air pollution and provide a strong foundation for the methods employed in this paper for HCMC.

In HCMC, PM_2.5 data are not very available, with limited research focusing on predicting PM_2.5 levels. Few studies are currently available that predict these concentrations. Vo et al. (2021) applied WRF model to predict PM_2.5 level in HCMC [21]. Their study aimed to evaluate the prediction of PM_2.5 concentration by predicting meteorological variables using the WRF model. In addition to utilizing a limited number of meteorological factors (four variables), their study did not thoroughly address the optimization of input scenarios. Another study from Rajnish et al. (2023) built a multivariate model for predicting air quality, taking into account diverse factors like meteorological circumstances, air quality metrics, and urban spatial data, and time factors to forecast NO₂, SO₂, O₃, and CO hourly concentrations [22]. This research attained a significant achievement in forecasting using spatially scattered data; however, the duration of data collection was relatively short, spanning only from February to December 2021. Additionally, data utilized in this investigation were gathered from monitoring stations associated with a specific research project, rather than from official, reliable, and publicly accessible government sources.

The primary objective of this research is to develop and evaluate various machine learning and deep learning algorithms for predicting PM_2.5 concentrations in HCMC, using meteorological and PM_2.5 data. The results from this study are expected to enhance the comprehension of the determinants affecting PM_2.5 levels in this metropolis and underscore the potential of AI methodologies in alleviating air pollution and promoting public health.

2. Methodology

This section delineates the methods utilized for prediction of PM_2.5 levels in HCMC using various machine learning and deep learning algorithms. The establishment of a PM_2.5 prediction model has five key steps (Figure 1): (1) Data processing, (2) analyzing the impact of parameters on PM_2.5, (3) designing scenarios of input datasets, (4) modeling machine learning and deep learning algorithms to predict PM_2.5, and (5) selecting the best prediction model for PM_2.5 among the developed machine learning and deep learning prediction models (Figure 1).

Firstly, daily data over 911 days, from 1 January 2021 to 30 June 2023, including meteorological and PM_2.5 parameters in HCMC, were collected for the development of a prediction model. The meteorological data included ambient temperature, relative humidity, wind speed, rainfall, sunshine hours, and evaporation that were collected from Tan Son Hoa weather station (10.79723° N, 106.6667° E) at 236B Le Van Sy, Tan Binh District, while the PM_2.5 data were obtained from the monitoring station at the U.S Consulate (10.7831° N, 106.7001° E) at 4 Le Duan street in District 1 in HCMC. These two stations are about 4 km apart as the crow flies and about 5 km apart by road. The collected data were then processed by removing unavailable data points and outliers.

Secondly, the processed data were analyzed to determine feature importance and identify the impact of the examined parameters on the objective function.

Thirdly, different sets of input data were generated to develop machine learning-based prediction models.

Fourthly, various machine learning and deep learning algorithms, including RF, XGB, SVR, ANN, GRNN, and CNN, were employed to formulate predictive models for PM_2.5 in HCMC. Each algorithm employed in this work presents a distinct methodology for addressing the intricacies of PM_2.5 prediction, providing varied advantages in feature selection, model training, and predictive accuracy. To evaluate the performance of these models, the dataset was split into training and testing sets. Specifically, 80% of the data were allocated for training, while the remaining 20% were designated for testing to evaluate model performance. For deep learning algorithms such as ANN and CNN, which require a validation set to monitor model training and prevent overfitting, the training data were further divided. In this case, 80% of the training data were used as sub-training data, and 20% of the training data were used for validation. This approach ensured that model training could be halted when validation performance began to decline, reducing the risk of overfitting. The remaining 20% of the dataset was consistently used as the testing set across all models to provide a final evaluation of prediction accuracy.

Random forest, often known as RF, is a type of ensemble learning technique that works by creating a vast ensemble of decision trees through the training process and then displaying the average forecast of each individually constructed tree [23]. Its ensemble structure renders it highly resilient to overfitting. The program initiates the process by generating a randomized dataset derived from the primary data. For every bootstrapped sample, a decision tree is built by selecting the best split from a randomly chosen subset of features at every node. The bootstrap aggregation technique generates multiple bootstrap samples through sampling and replacement, from which decision trees are constructed. The ultimate prediction is the mean of the forecasts from all individual trees [24]. This study selects RF to predict PM_2.5 levels due to its superior performance across several domains, resilience to overfitting, and efficacy in situations characterized by highly nonlinear and complex relationships between features and target variables. The performance of the RF model can be regulated by tuning hyperparameters including the quantity of trees in the forest, the depth of the trees, the minimum samples required for a split, the minimum samples required for a leaf node, and the maximum possible leaf nodes [25].

XGBoost is a powerful and scalable ensemble learning method widely used for regression and classification problems. It improves on traditional gradient boosting by optimizing the handling of regularization and model optimization [26]. This work employs XGB to forecast PM_2.5 values by using its capacity to simulate intricate linkages and interactions in the dataset. The algorithm processes historical air quality and meteorological data, which enables it to discern patterns that affect PM_2.5 concentrations. XGB possesses numerous hyperparameters that could be adjusted to enhance performance, such as the learning rate, the ensemble size, the tree depth, the sample size for each tree, and the feature count for each tree [27].

Support vector regression (SVR) is a type of machine learning algorithm used for regression tasks, which is derived from the support vector machine (SVM) framework [28]. Support vector regression (SVR) is recognized for its capacity to manage high-dimensional data and to represent nonlinear relationships via kernel functions [29]. It develops a model by transforming input data into a higher-dimensional space to facilitate linear regression analysis. SVR seeks to identify a function that diverges from the actual observed objectives by no more than a defined margin ϵ, while simultaneously maintaining maximal flatness. This study utilizes SVR to forecast PM_2.5 concentrations in HCMC by training the model using atmospheric quality and meteorological data. The hyperparameters in SVR comprise the regularization parameter C, the epsilon ϵ that delineates the margin of tolerance, and the parameters linked to the selected kernel function, such as the kernel coefficient γ for the radial basis function kernel.

Artificial neural networks (ANNs) are a category of machine learning techniques designed to emulate the architecture and functionality of the human brain [23,30]. An artificial neural network consists of several interconnected processing nodes, or neurons, that collaboratively execute intricate computations. The method processes a collection of input data via multiple hidden layers to obtain an output. Each neuron within the network takes input from neurons in the preceding layer and use an activation function to generate an output [31]. The output from each neuron is subsequently transmitted to the neurons in the subsequent layer, and this process is reiterated until the output layer is reached. The design of the network, comprising the quantity of layers and the number of neurons per layer, can be tailored to improve efficiency for a certain task. Training ANNs entails modifying weights and biases of neurons to reduce a loss function, which quantifies the disparity between the expected output and observed output [30]. This process is generally executed by backpropagation that entails calculating the gradient of the loss function concerning the weights and biases, subsequently employing it to adjust the network’s parameters. Utilizing the adaptability and efficacy of learning intricate and nonlinear relationships among variables, ANNs are employed to predict PM_2.5 levels by training the network on atmospheric conditions data, atmospheric condition datasets, and other pertinent aspects. The model acquires the ability to discern intricate patterns and relationships in the data that affect PM_2.5 values. An optimum artificial neural network design consists of a configuration of hyperparameters, such as the quantity of hidden layers, the quantity of neurons in each hidden layer, activation function, learning rate, weight constraints, and dropout rate, which produce the most accurate predictions on the validation data.

Generalized regression neural networks (GRNNs) [32] are a category of artificial neural networks grounded in nonparametric predictive modeling. GRNNs are recognized for their rapid training capabilities and proficiency in modeling intricate correlations between input and target variables [33]. GRNNs comprise four layers: the input layer, pattern layer, summation layer, and output layer. Each neuron in the pattern layer denotes a training example and computes a distance metric to the input. These distances are consolidated by the summation layer, which produces weighted outputs. The output layer delivers a predicted value derived from these consolidated data. The fundamental principle of GRNNs is the application of kernel regression to approximate the conditional expectation of the output variable based on the input parameter. It utilizes a radial basis function to evaluate the probability density of data points and generates predictions based on the weighted aggregation of these functions. GRNNs are adept at managing noisy and intricate datasets, making them well suited for predicting air quality, particularly PM_2.5 concentrations, which are influenced by numerous factors. The smoothing parameter (σ) is a hyperparameter in GRNNs. The performance of the model is highly sensitive to the value of σ, with smaller values potentially resulting in overfitting, while larger values may lead to underfitting.

A convolutional neural network (CNN) is a form of deep learning model that integrates several layers including convolutional, pooling, and fully connected layers. Convolutional layers utilize filters on input data to identify characteristics, such as edges or textures, via convolution processes. The dimensionality of data is reduced by pooling layers, which utilize maximum pooling to preserve significant features while reducing computational demands. The fully linked layers at the network’s conclusion integrate these features to generate final predictions. CNNs excel in managing large-scale and high-dimensional data, making them suitable for predicting PM_2.5 levels. The convolutional layers assist in recognizing critical characteristics and trends influencing PM_2.5 values. To improve the efficacy of the CNN model, essential hyperparameters like the quantity and dimensions of convolutional filters, the depth of layers, the learning rate, and the batch size will be systematically maximized. Each best-performing model is tuned to its optimal hyperparameters using a grid search method. The range for each hyperparameter is detailed in the results section for each machine learning algorithm. Optimal hyperparameters are determined using the validation dataset. This optimization process aims to find the hyperparameters that yield the minimal root mean square error (RMSE) on the validation set.

Finally, after evaluating the predictive outcomes of the constructed models, the best-performing model is selected for PM_2.5 prediction in HCMC. In this study, the prediction models are evaluated using various metrics, including root mean square error (RMSE), mean absolute percentage error (MAPE), index of agreement (IOA), and normalized mean bias (NMB). These evaluation metrics are expressed as follows:

$$RMSE=\sqrt{{\displaystyle \frac{1}{n}}\sum _{i=1}^n{\left(y_i-{\hat{\mathrm{y}}}_i\right)}^2}$$

(1)

$$MAPE={\displaystyle \frac{100}{n}}\sum _{i=1}^n\left|{\displaystyle \frac{y_i-{\hat{\mathrm{y}}}_i}{y_i}}\right|$$

(2)

$$IOA=1-{\displaystyle \frac{\sum _{i=1}^n{(y_i-{\hat{\mathrm{y}}}_i)}^2}{\sum _{i=1}^n{(\left|{\hat{\mathrm{y}}}_i-\overline{\mathrm{y}}\right|+\left|y_i-\overline{\mathrm{y}}\right|)}^2}}$$

(3)

$$NMB={\displaystyle \frac{\sum _{i=1}^n\left({{\hat{\mathrm{y}}}_i-y}_i\right)}{\sum _{i=1}^n{y}_i}}$$

(4)

where n is the total number of data points; $\overline{\mathrm{y}}$ is the mean of the actual observed values; $y_i$ and ${\hat{\mathrm{y}}}_i$ are the actual observed value and predicted value for the ith data point, respectively; RMSE measures the square root of the average squared variances between predicted and observed values; and MAPE evaluates the mean absolute percentage error between forecasted and actual values. Furthermore, the IOA quantifies the extent of model prediction inaccuracy on a scale from 0 to 1, with 1 signifying perfect concordance and 0 denoting complete discordance. IOA is formulated to address certain constraints of the coefficient of determination by offering a normalized metric of model prediction error. It considers the disparities between the anticipated and observed values, providing a more balanced measure of model performance, especially in cases with nonlinear relationships or when dealing with outliers. On the other hand, NMB measures the average discrepancy between the anticipated and observed values, normalized by the means of the observed values. It indicates the bias of the model’s predictions. Values approaching 0 signify little bias, whereas positive values denote overestimation and negative values signify underestimating.

3. Experimentation and Results

3.1. General Statistics of Data

The meteorological data and PM_2.5 levels collected in HCMC between 2021 and 2023 are presented in Figure 2, illustrating the seasonal fluctuations of climatic variables and PM_2.5 levels. In total, the dataset contains 911 days of data across seven parameters, which were used for model training, testing, and validation. HCMC has a dry season from December to April, favored for its sunny weather, and a rainy season from May to November, marked by high humidity and frequent heavy rainfalls [34]. The rainy season accounts for about 80–90% of the city’s annual rainfall, with the heaviest downpours typically occurring between June and August [35]. Additionally, temperature, sunshine hours, and evaporation are high during the dry season and low during the rainy season. Conversely, rainfall, humidity, and wind speed are high in the rainy season and reduced during the dry season. Moreover, PM_2.5 concentrations tend to be higher during the dry season compared to the rainy season. The fundamental statistics of the data were shown in

Table 1. Summary of meteorological and PM_2.5 data in HCMC from 1 January 2021 to 30 June 2023.

Parameter	Lower Limit	Average	Upper Limit
Temperature, °C	24.0	28.5	32.2
Wind speed, m/s	0.0	2.3	9.0
Humidity, %	56.0	75.3	93.0
Sunshine hours, h	0.0	5.9	9.9
Rainfall, mm	0.0	5.7	101.5
Evaporation, mm/d	0.8	3.4	6.3
PM2.5, µg/m3	6.5	22.4	90.3

and the distributions were shown in Figure 3.

To provide a comprehensive overview of the data characteristics, Table 1 presents the summary statistics of the meteorological factors and PM_2.5 concentrations. The purpose of this table is to illustrate the variability and distribution of the data, offering key insights into the range and central tendency of each feature. For instance, temperature varied between 24.0 °C and 32.2 °C, and wind speed ranged from 0.0 to 9.0 m/s, highlighting the diverse meteorological conditions during the study period. These variations are critical to understanding how the models interpret and process the input data, as fluctuations in weather patterns are expected to influence PM_2.5 levels. Table 1 provides the foundation for assessing how these features individually and collectively impact air quality. Figure 2 and Figure 3 further complement the information in Table 1 by visualizing the temporal distribution and variability of the meteorological parameters and PM_2.5 concentrations. Figure 2 illustrates different environmental and meteorological data trends from January 2021 to July 2023. Furthermore, Figure 3 shows the distribution of each feature, which helps to identify any skewness, outliers, or anomalies in the data. Together, these figures enhance our understanding of the temporal and distributional characteristics of the dataset.

3.2. Feature Selection

To construct suitable and optimal prediction scenarios, this study analyzed the correlation between meteorological values and PM_2.5 concentrations, identifying the relationships among these parameters to propose scenarios based on the correlation analysis results.

Table 2. Pearson’s correlation between meteorological parameters and PM_2.5 in HCMC.

Parameter	Pearson’s Correlation Coefficient
Humidity	−0.293
Temperature	−0.280
Wind speed	−0.227
Rainfall	−0.111
Evaporation	0.107
Sunshine hours	−0.037

shows the correlation between the meteorological parameters and PM_2.5 concentration in HCMC. The Pearson correlation coefficient (r) was employed to determine the degree of correlation between the input variables and PM_2.5 concentrations. This coefficient ranges from −1 to 1, with values close to 1 indicating a strong positive correlation, values close to −1 indicating a strong negative correlation, and values around 0 indicating little or no linear correlation.

The results showed that humidity, temperature, and wind speed have a strong correlation with PM_2.5, while rainfall, evaporation, and sunshine hours have a moderate correlation with PM_2.5.

Different scenarios of input parameters were generated to develop prediction models. This allows us to evaluate the prediction performance under various sets of input parameters. These scenarios were designed based on the Pearson correlation coefficient obtained from the previous step. In this approach, scenarios were constructed by prioritizing the most correlated parameters down to the less correlated ones [36,37]. Starting with the highest correlation coefficient, each scenario incrementally incorporated additional parameters in descending order of their correlation. This stepwise approach allowed for an exploration of how the predictive power of the models evolved as features of varying correlation were sequentially integrated into the input data, providing insights into the cumulative effect of features on the model’s predicting performance, aiding in the effective optimization and selection of input parameters. The input feature scenarios are detailed in

Table 3. Input scenarios for PM_2.5 prediction.

Scenario	Input Feature
1	Humidity
2	Humidity, temperature
3	Humidity, temperature, wind speed
4	Humidity, temperature, wind speed, rainfall
5	Humidity, temperature, wind speed, rainfall, evaporation
6	Humidity, temperature, wind speed, rainfall, evaporation, sunshine hours

.

3.3. Development of Prediction Models

3.3.1. Random Forest Model

This section details the development of a random forest algorithm designed to predict PM_2.5 concentrations based on many input scenarios detailed in Table 3. The model was trained using various hyperparameters featuring n_estimators, max_depth, min_samples_split, min_samples_leaf, and max_leaf_nodes, as detailed in

Table 4. Range of hyperparameters for training random forest predictive models.

Hyperparameter	Value
n_estimators	1000, 1500, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10,000
max_depth	3, 4, 5, 6, 7, 8, 9, 10, 12, 15, 20, 25, 30, 40, 50
min_samples_split	2, 4, 6, 8, 10, 20, 30, 40, 50, 70, 100
min_samples_leaf	1, 2, 3, 4, 5, 7, 10, 15, 20, 30, 50
max_leaf_nodes	10, 20, 30, 40, 50, 60, 70, 80, 90, 100

.

The random forest model demonstrated strong predictive capabilities, achieving IOA values between 0.361 and 0.789 on the training set and 0.396 to 0.670 on the testing set under all scenarios (

Table 5. Training and testing results of random forest predictive models for PM_2.5.

Input Scenario	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
1	9.101	35.853	0.361	0.000	9.987	42.880	0.396	0.075
2	8.104	31.642	0.627	0.000	9.244	39.944	0.596	0.083
3	7.724	30.089	0.653	−0.001	9.018	38.662	0.597	0.077
4	7.738	30.106	0.662	0.000	8.845	37.840	0.628	0.078
5	7.307	28.282	0.709	0.000	8.631	37.148	0.654	0.076
6	6.464	24.577	0.789	0.001	8.510	36.721	0.670	0.079

). Generally, the inclusion of more input features improved the accuracy in predicting PM_2.5 concentration. In addition, the model achieved relatively low RMSE, MAPE, and NMB values, indicating its effectiveness in accurately predicting PM_2.5 concentrations under each scenario.

The highest prediction accuracy was achieved with input scenario 6, which resulted in high IOA values and relatively low RMSE, MAPE, and NMB values for training and testing evaluation. This indicates that the model is well fitted and capable of reliably predicting PM_2.5 concentrations based on the given input variables. The optimal model was configured with an n_estimators of 1500, a max_depth of 12, a min_samples_split of 4, a min_samples_leaf of 5, and max_leaf_nodes set to 90. Figure 4 illustrates the training and testing results of this optimized random forest model, showing moderate agreement between predicted and actual PM_2.5 values, which suggests a reasonably strong predictive performance.

3.3.2. XGB Model

This section discusses the development and performance analysis of an XGB algorithm aimed at predicting PM_2.5 concentrations using the input scenarios outlined in Table 3. The models were trained and optimized by fine-tuning the hyperparameters listed in

Table 6. Range of hyperparameters for training XGB predictive models.

Hyperparameter	Value
n_estimators	1000, 1500, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10,000
max_depth	1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 20, 30, 40, 50
learning rate	0.0005, 0.0007, 0.0009, 0.001, 0.0011, 0.0013, 0.0015, 0.003, 0.005, 0.01, 0.1, 0.2, 0.3
subsample	0.5, 0.6, 0.7, 0.8, 0.9, 1.0
colsample_bytree	0.5, 0.6, 0.7, 0.8, 0.9, 1.0
min_child_weight	1, 2, 3, 4, 5, 6, 7, 8, 9, 10

.

The training and testing results across different scenarios are summarized in

Table 7. Training and testing results of the XGB predictive models for PM_2.5.

Input Scenario	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
1	9.093	35.897	0.302	0.000	10.168	43.742	0.320	0.073
2	7.600	29.984	0.647	−0.001	9.455	40.090	0.517	0.075
3	7.608	29.757	0.684	−0.001	9.120	38.811	0.600	0.082
4	7.830	30.800	0.625	−0.001	8.962	38.410	0.585	0.076
5	7.134	27.654	0.740	−0.001	8.416	36.195	0.687	0.072
6	7.021	27.082	0.747	0.000	8.397	36.374	0.685	0.076

, demonstrating moderate model performance. IOA values ranged from 0.302 to 0.740 during training and from 0.320 to 0.687 during testing. The model achieved the best predictive accuracy using input scenario 5, which included variables including humidity, temperature, wind speed, rainfall, and evaporation. However, adding more input features did not significantly enhance prediction accuracy.

The optimal XGB model was obtained with hyperparameters including an n_estimators of 10,000, a max_depth of 3, a learning rate of 0.0005, a subsample of 0.5, a colsample_bytree of 0.8, and a min_child_weight of 3. The training and testing results of this optimal model are depicted in Figure 5, which illustrates moderate alignment between predicted and observed PM_2.5 values, confirming the model’s satisfactory predictive ability.

3.3.3. Support Vector Regression Model

This section details the development and evaluation of an SVR algorithm for predicting PM_2.5 concentrations, using the input scenarios provided in Table 3. The models were fine-tuned by adjusting the hyperparameters shown in

Table 8. Range of hyperparameters for training SVR predictive models.

Hyperparameter	Value
Kernel	linear, poly, rbf, sigmoid
gamma	scale, auto
epsilon	0.01, 0.1, 0.2, 0.5, 1.0
degree	2, 3, 4, 5
C	0.1, 1, 10, 100, 1000

.

The performance results across various scenarios are summarized in

Table 9. Training and testing results of SVR predictive models for PM_2.5.

Input Scenario	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
1	9.134	36.028	0.322	−0.004	10.028	43.034	0.361	0.068
2	8.467	33.936	0.540	0.005	9.452	41.675	0.543	0.093
3	8.285	32.762	0.585	0.001	8.930	38.450	0.609	0.080
4	8.306	33.042	0.571	0.005	9.020	39.210	0.593	0.085
5	7.665	26.917	0.720	−0.026	8.391	34.055	0.709	0.041
6	8.214	32.539	0.580	0.003	8.856	38.458	0.607	0.079

, where the model showed moderate effectiveness. IOA values ranged from 0.322 to 0.720 during training and from 0.361 to 0.709 during testing. The highest accuracy was obtained using input scenario 5, which included factors like humidity, temperature, wind speed, rainfall, and evaporation.

The optimal SVR model was configured with the following hyperparameters: a radial basis function (rbf) kernel, C set to 1.0, epsilon at 0.1, and gamma set to scale. Figure 6 presents training and testing results of this optimal model, which showed strong agreement between predicted and actual PM_2.5 values, indicating a solid predictive capability.

3.3.4. Artificial Neural Network Model

This section discusses the application of an ANN algorithm to predict PM_2.5 concentrations based on each input scenario. The hyperparameters of the model, such as the quantity of hidden layers, the number of neurons in each hidden layer, the activation function, learning rate, dropout rate, and weight constraint, were optimized, with their ranges detailed in

Table 10. Range of hyperparameters for training ANN predictive models.

Hyperparameter	Value (Range, Step)
Number of hidden layers	3–10, 1
Number of hidden neurons	20–150, 10
Activation function	relu, elu, tanh, sigmoid
Learning rate	0.0005–0.0015, 0.0001
Dropout rate	0.0–0.9, 0.1
Weight constraint	1–5, 1

.

Table 11. Training and testing results of ANN predictive models for PM_2.5.

Input Scenario	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
1	9.399	32.372	0.357	−0.086	10.089	38.671	0.328	−0.011
2	8.275	31.564	0.614	−0.017	9.349	39.362	0.589	0.070
3	7.948	29.219	0.680	−0.035	8.891	34.948	0.642	0.042
4	8.120	29.116	0.676	−0.047	8.740	33.449	0.672	0.034
5	7.761	28.685	0.695	−0.014	8.390	35.026	0.697	0.060
6	7.675	26.919	0.713	−0.036	7.978	32.452	0.736	0.032

summarizes training results and testing results, which indicate strong performance of ANN model in both phases, with high IOA values and relatively low values of RMSE, MAPE, and NMB. During training, IOA values ranged from 0.357 to 0.713, suggesting the model effectively captures data variability. Testing results showed similar trends, with IOA values between 0.328 and 0.736, further supporting the model’s robustness.

Scenario 6 exhibited the best performance, with the highest IOA and the lowest RMSE, MAPE, and NMB values for both training and testing datasets. Consequently, the model developed using input scenario 6, and hyperparameters specified in

Table 12. Hyperparameters of the optimal ANN predictive model.

Hyperparameter	Value
Number of hidden layers	4
Number of hidden neurons	60, 20, 30, 20
Activation function	relu, tanh, relu, relu
Learning rate	0.0015
Dropout rate	0.4
Weight constraint	3

, was identified as the optimal ANN model. Figure 7 illustrates the training and testing outcomes of this model, showing a strong alignment between predicted and measured PM_2.5 values, confirming its reliable predictive capability.

3.3.5. Generalized Regression Neural Network Model

This section presents the development and assessment of a GRNN algorithm to predict PM_2.5 concentrations, based on the input scenarios described in Table 3. The models were trained and optimized by fine-tuning the hyperparameters listed in

Table 13. Range of hyperparameters for training GRNN predictive models.

Hyperparameter	Value (Range, Step)
Kernel	rbf
sigma	0.1–1, 0.01

.

The performance of the GRNN model, summarized in

Table 14. Training and testing results of GRNN predictive models for PM_2.5.

Input Scenario	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
1	9.089	35.887	0.344	−0.001	10.053	43.200	0.372	0.073
2	8.097	31.887	0.601	−0.006	9.338	39.941	0.545	0.076
3	7.882	30.716	0.631	−0.008	9.013	37.955	0.582	0.066
4	7.854	30.603	0.635	−0.007	9.002	38.016	0.585	0.068
5	7.225	27.579	0.718	−0.008	8.584	37.050	0.652	0.073
6	6.605	24.772	0.785	−0.009	8.306	36.339	0.695	0.068

, ranged from moderate to high, with IOA values between 0.344 and 0.785 for training and between 0.372 and 0.695 for testing. The highest prediction accuracy was observed in scenario 6, which included all input features.

The optimal GRNN model was configured with rbf kernel and a sigma of 0.111. Figure 8 illustrates the training and testing results of this optimized model, showing moderate agreement between predicted and actual PM_2.5 values, confirming its moderate predictive capability.

3.3.6. Convolutional Neural Network Model

This section discusses the development and evaluation of a CNN model designed to predict PM_2.5 concentrations using the input scenarios specified in Table 3. The models were trained and optimized by adjusting the hyperparameters outlined in

Table 15. Range of hyperparameters for training CNN predictive models.

Hyperparameter	Value (Range, Step)
Convolutional filter	32–256, 16
Convolutional kernel size	1–5, 1
Activation function	relu, elu, tanh, sigmoid
Number of neurons in a fully connected layer	32–512, 32
Dropout rate	0–0.5, 0.1
Learning rate	0.0005–0.0015, 0.0001

.

The training and testing results across different scenarios, summarized in

Table 16. Training and testing results of CNN predictive models for PM_2.5.

Input Scenario	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
1	9.199	38.084	0.396	0.039	10.176	46.157	0.437	0.119
2	8.389	33.914	0.573	0.022	9.455	42.403	0.567	0.106
3	8.376	32.519	0.596	−0.013	9.303	39.820	0.589	0.075
4	8.356	33.549	0.561	0.010	9.152	40.394	0.579	0.092
5	8.453	33.670	0.515	0.004	9.199	40.123	0.540	0.080
6	8.345	34.000	0.581	0.022	9.083	40.819	0.607	0.104

, showed that the model’s performance ranges from moderate to high. IOA values were between 0.396 and 0.581 for training, and between 0.437 and 0.607 for testing. The model achieved the highest accuracy using scenario 6, which incorporated all input features. Overall, increasing the number of input parameters generally led to improved accuracy, with scenario 6 yielding the best performance.

The optimal CNN model was configured using 192 convolutional filters, a kernel size of 1, a tanh activation function, 128 neurons in a fully connected layer, a dropout rate of 0.0, and a learning rate of 0.0006. Figure 9 illustrates the training and testing outcomes of this optimized model, showing moderate agreement between predicted and observed PM_2.5 values, which suggests the model’s satisfactory predictive capability.

3.3.7. Selection of Prediction Model for PM_2.5 in HCMC, Vietnam

Within the scope of this investigation, six distinct machine learning methods were utilized to forecast the PM_2.5 concentration: random forest, XGB, SVR, ANN, GRNN, and CNN. The predictive capabilities of each model were evaluated on various input scenarios, with performance compared in terms of IOA, RMSE, MAPE, and NMB for both training and testing datasets.

Among all models, the ANN algorithm emerged as the top performer, achieving the highest IOA value of 0.736 and the lowest RMSE, MAPE, and NMB values of 7.978, 32.452, and 4.8726, respectively (

Table 17. Optimal predictive models for PM_2.5.

Model	Training Result				Testing Result
	RMSE	MAPE	IOA	NMB	RMSE	MAPE	IOA	NMB
RF	6.464	24.577	0.789	0.001	8.510	36.721	0.670	0.079
XGB	7.134	27.654	0.740	−0.001	8.416	36.195	0.687	0.072
SRV	7.665	26.917	0.720	−0.026	8.391	34.055	0.709	0.041
ANN	7.675	26.919	0.713	−0.036	7.978	32.452	0.736	0.032
GRNN	6.605	24.772	0.785	−0.009	8.306	36.339	0.695	0.068
CNN	8.345	34.000	0.581	0.022	9.083	40.819	0.607	0.104

). The SVR algorithm demonstrated solid performance, achieving an IOA of 0.709 and relatively low error metrics. However, the ANN model consistently outperformed the SVR across all evaluation metrics.

Building on these findings, the ANN model was ultimately selected as the optimal predictive model for this particular PM_2.5 dataset. Its higher IOA value and lower error metrics for testing sets suggest that ANN outperforms the other assessed models. Consequently, the trained ANN model was selected for predicting PM_2.5 concentrations in HCMC, Vietnam.

4. Discussion

This study provides a comprehensive comparison of the performance of six different machine learning and deep learning algorithms, random forest, XGB, SVR, ANN, GRNN, and CNN, in predicting PM_2.5 concentrations. Additionally, meteorological variables including temperature, humidity, wind speed, sunshine hours, rainfall, and evaporation were included to enhance the prediction accuracy. Among the models, the ANN model outperformed the others, achieving an IOA of 0.736, an RMSE of 7.978, and an NMB of 0.032 during the testing phase. These findings highlight the effectiveness of machine learning techniques in air quality prediction and highlight the importance of selecting an appropriate algorithm for predicting air pollution. This study provides valuable insights for health officials and policymakers by demonstrating that machine learning models, especially the ANN model, can accurately predict PM_2.5 concentrations. This insight is valuable for policymakers, as it can inform the implementation of effective strategies to mitigate health risks associated with PM_2.5 exposure. For instance, our model could enable authorities to issue air quality alerts when PM_2.5 levels are expected to rise above safe thresholds. This allows citizens to take precautionary measures, such as staying indoors or using masks on high-risk days. In addition, public health campaigns can be timed based on pollution predictions, informing residents of exposure risks and protective actions like wearing air filters or limiting outdoor activities.

Despite the promising results, this study has several limitations that should be addressed in future research. First, this study concentrates exclusively on PM_2.5 levels in HCMC. A more comprehensive comprehension of air quality throughout the nation would be achieved by broadening the scope to include additional communities in Vietnam. Additionally, while machine learning and deep learning methods were applied to simulate and predict PM_2.5 concentrations, the study was limited by the availability of data from a single automatic monitoring station—the U.S. Consulate station in HCMC. Consequently, the results primarily reflect PM_2.5 concentration levels within the vicinity of the consulate. A larger number of standard automatic monitoring stations would enable a more generalized and representative analysis of the entire study area.

Furthermore, this study focused on predicting PM_2.5 concentrations based on meteorological factors, but PM_2.5 concentrations are also influenced by various other factors, such as emission sources and the presence of other air pollutants. Emission sources, including industrial zones, construction sites, and high-traffic areas, are closely related to PM_2.5 concentrations. Factors such as the relative location and proximity of these sources to monitoring stations significantly impact dust concentrations. Additionally, the concentrations of other air pollutants, such as NOx, SOx, CO₂, and H₂S, may interact with PM_2.5 concentrations. Due to data limitations, these parameters were not included in this study. Future research should find the effect of these pollutants on PM_2.5 concentrations and consider integrating them into prediction models.

This study establishes a robust basis for subsequent research on PM_2.5 predictions for HCMC, and its findings can contribute to the development of effective air pollution control and management strategies.

5. Conclusions

This study investigated the prediction of PM_2.5 concentrations in HCMC utilizing six distinct machine learning and deep learning algorithms. The models were trained and validated on a dataset including temperature, humidity, wind speed, sunshine hours, rainfall, and evaporation. Among the algorithms assessed, the ANN showed superior performance in predicting PM_2.5 levels, achieving an IOA of 0.736 and the lowest RMSE, MAPE, and NMB values during testing. These results highlight the potential of machine learning algorithms, particularly ANNs, in accurately predicting PM_2.5 concentrations based on meteorological data. The implications of this research are significant for HCMC, where air pollution poses a critical public health concern. By utilizing these predictive models, policymakers and health officials can implement more targeted and effective interventions to mitigate air pollution, ultimately improving public health outcomes. This study advocates for the integration of advanced machine learning techniques into environmental monitoring systems, offering a framework for proactive urban air quality management.