Air quality forecasting using artificial neural networks with real time dynamic error correction in highly polluted regions

Assessing the effectiveness of long short-term memory and artificial neural network in predicting daily ozone concentrations in Liaocheng City

Ozone pollution affects food production, human health, and the lives of individuals. Due to rapid industrialization and urbanization, Liaocheng has experienced increasing of ozone concentration over several years. Therefore, ozone has become a major environmental problem in Liaocheng City. Long short-term memory (LSTM) and artificial neural network (ANN) models are established to predict ozone concentrations in Liaocheng City from 2014 to 2023. The results show a general improvement in the accuracy of the LSTM model compared to the ANN model. Compared to the ANN, the LSTM has an increase in determination coefficient (R2), value from 0.6779 to 0.6939, a decrease in root mean square error (RMSE) value from 27.9895 μg/m3 to 27.2140 μg/m3 and a decrease in mean absolute error (MAE) value from 21.6919 μg/m3 to 20.8825 μg/m3. The prediction accuracy of the LSTM is superior to the ANN in terms of R, RMSE, and MAE. In summary, LSTM is a promising technique for predicting ozone concentrations. Moreover, by leveraging historical data and LSTM enables accurate predictions of future ozone concentrations on a global scale. This model will open up new avenues for controlling and mitigating ozone pollution.

Spatial source, simulating improvement, and short-term health effect of high PM2.5 exposure during mutation event in the key urban agglomeration regions in China

Air quality in China has significantly improved owing to the effective implementation of pollution control measures. However, mutation events caused by short-term spikes in PM2.5 in urban agglomeration regions continue to occur frequently. Identifying the spatial sources and influencing factors, as well as improving the prediction accuracy of high PM2.5 during mutation events, are crucial for public health. In this study, we firstly introduced discrete wavelet transform (DWT) to identify the mutation events with high PM2.5 concentration in the four key urban agglomerations, and evaluated the spatial sources for the polluted scenario using Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model. Additionally, DWT was combined with a widely used artificial neural network (ANN) to improve the prediction accuracy of PM2.5 concentration seven days in advance (seven-day forecast). Results indicated that mutation events commonly occurred in the northern regions during winter time, which were under the control of both short-range transportation of dirty airmass as well as negative meteorology conditions. Compared with the ANN model alone, the average band errors decreased by 9% when using DWT-ANN model. The average correlation coefficient (R) and root mean square error (RMSE) obtained using the DWT-ANN improved by 10% and 12% compared to those obtained using the ANN, indicating the efficiency and accuracy of simulating PM2.5, by combining the DWT and ANN. The short-term mortality during mutation events was then calculated, with the total averted all-cause, cardiovascular, and respiratory deaths in the four regions, being 4751, 2554, and 582 persons, respectively. A declining trend in prevented deaths from 2018 to 2020 demonstrated that the pollution intensity during mutation events gradually decreased owing to the implementation of the Three-Year Action Plan to Win the Blue Sky Defense War. The method proposed in this study can be used by policymakers to take preventive measures in response to a sudden increase in PM2.5, thereby ensuring public health.

An enhanced approach for predicting air pollution using quantum support vector machine

The essence of quantum machine learning is to optimize problem-solving by executing machine learning algorithms on quantum computers and exploiting potent laws such as superposition and entanglement. Support vector machine (SVM) is widely recognized as one of the most effective classification machine learning techniques currently available. Since, in conventional systems, the SVM kernel technique tends to sluggish down and even fail as datasets become increasingly complex or jumbled. To compare the execution time and accuracy of conventional SVM classification to that of quantum SVM classification, the appropriate quantum features for mapping need to be selected. As the dataset grows complex, the importance of selecting an appropriate feature map that outperforms or performs as well as the classification grows. This paper utilizes conventional SVM to select an optimal feature map and benchmark dataset for predicting air quality. Experimental evidence demonstrates that the precision of quantum SVM surpasses that of classical SVM for air quality assessment. Using quantum labs from IBM's quantum computer cloud, conventional and quantum computing have been compared. When applied to the same dataset, the conventional SVM achieved an accuracy of 91% and 87% respectively, whereas the quantum SVM demonstrated an accuracy of 97% and 94% respectively for air quality prediction. The study introduces the use of quantum Support Vector Machines (SVM) for predicting air quality. It emphasizes the novel method of choosing the best quantum feature maps. Through the utilization of quantum-enhanced feature mapping, our objective is to exceed the constraints of classical SVM and achieve unparalleled levels of precision and effectiveness. We conduct precise experiments utilizing IBM's state-of-the-art quantum computer cloud to compare the performance of conventional and quantum SVM algorithms on a shared dataset.

Multivariable Air-Quality Prediction and Modelling via Hybrid Machine Learning: A Case Study for Craiova, Romania

Inadequate air quality has adverse impacts on human well-being and contributes to the progression of climate change, leading to fluctuations in temperature. Therefore, gaining a localized comprehension of the interplay between climate variations and air pollution holds great significance in alleviating the health repercussions of air pollution. This study uses a holistic approach to make air quality predictions and multivariate modelling. It investigates the associations between meteorological factors, encompassing temperature, relative humidity, air pressure, and three particulate matter concentrations (PM10, PM2.5, and PM1), and the correlation between PM concentrations and noise levels, volatile organic compounds, and carbon dioxide emissions. Five hybrid machine learning models were employed to predict PM concentrations and then the Air Quality Index (AQI). Twelve PM sensors evenly distributed in Craiova City, Romania, provided the dataset for five months (22 September 2021-17 February 2022). The sensors transmitted data each minute. The prediction accuracy of the models was evaluated and the results revealed that, in general, the coefficient of determination (R2) values exceeded 0.96 (interval of confidence is 0.95) and, in most instances, approached 0.99. Relative humidity emerged as the least influential variable on PM concentrations, while the most accurate predictions were achieved by combining pressure with temperature. PM10 (less than 10 µm in diameter) concentrations exhibited a notable correlation with PM2.5 (less than 2.5 µm in diameter) concentrations and a moderate correlation with PM1 (less than 1 µm in diameter). Nevertheless, other findings indicated that PM concentrations were not strongly related to NOISE, CO2, and VOC, and these last variables should be combined with another meteorological variable to enhance the prediction accuracy. Ultimately, this study established novel relationships for predicting PM concentrations and AQI based on the most effective combinations of predictor variables identified.

Evolution of neural network to deep learning in prediction of air, water pollution and its Indian context

The scenario of developed and developing countries nowadays is disturbed due to modern living style which affects environment, wildlife and natural habitat. Environmental quality has become or is a subject of major concern as it is responsible for health hazard of mankind and animals. Measurements and prediction of hazardous parameters in different fields of environment is a recent research topic for safety and betterment of people as well as nature. Pollution in nature is an after-effect of civilization. To combat the damage already happened, some processes should be evolved for measurement and prediction of pollution in various fields. Researchers of all over the world are active to find out ways of predicting such hazard. In this paper, application of neural network and deep learning algorithms is chosen for air pollution and water pollution cases. The purpose of this review is to reveal how family of neural network algorithms has applied on these two pollution parameters. In this paper, importance is given on algorithm, and datasets used for air and water pollution as well as the predicted parameters have also been noted for ease of future development. One major concern of this paper is Indian context of air and water pollution research, and the research potential presents in this area using Indian dataset. Another aspect for including both air and water pollutions in one review paper is to generate an idea of artificial neural network and deep learning techniques which can be cross applicable for future purpose.

Forecasting PM2.5 concentrations using statistical modeling for Bengaluru and Delhi regions

India is home to some of the most polluted cities on the planet. The worsening air quality in most of the cities has gone to an extent of causing severe impact on human health and life expectancy. An early warning system where people are alerted well before an adverse air quality episode can go a long way in preventing exposure to harmful air conditions. Having such system can also help the government to take better mitigation and preventive measures. Forecasting systems based on machine learning are gaining importance due to their cost-effectiveness and applicability to small towns and villages, where most complex models are not feasible due to resource constraints and limited data availability. This paper presents a study of air quality forecasting by application of statistical models. Three statistical models based on autoregression (AR), moving average (MA), and autoregressive integrated moving average (ARIMA) models were applied to the datasets of PM_2.5 concentrations of Delhi and Bengaluru, and forecasting was done for 1-day-ahead and 7-day-ahead time frames. All three models forecasted the PM_2.5 reasonably well for Bengaluru, but the model performance deteriorated for the Delhi region. The AR, MA, and ARIMA models achieved mean absolute percentage error (MAPE) of 10.82%, 7.94%, and 8.17% respectively for forecast of 7 days and MAPE of 7.35%, 5.62%, and 5.87% for 1-day-ahead forecasts for Bengaluru. For the Delhi region, the model gave an MAPE of 27.82%, 24.62%, and 27.32% for the AR, MA, and ARIMA models respectively in the 7-day-ahead forecast, and 24.48%, 23.53%, and 23.72% respectively for 1-day-ahead forecast. The analysis showed that ARIMA model performs better in comparison to the other models but performance varies with varying concentration regimes. Study indicates that other topographical and meteorological parameters need to be incorporated to develop better models and account for the effects of these parameters in the study.

Machine learning algorithms to forecast air quality: a survey

Air pollution is a risk factor for many diseases that can lead to death. Therefore, it is important to develop forecasting mechanisms that can be used by the authorities, so that they can anticipate measures when high concentrations of certain pollutants are expected in the near future. Machine Learning models, in particular, Deep Learning models, have been widely used to forecast air quality. In this paper we present a comprehensive review of the main contributions in the field during the period 2011-2021. We have searched the main scientific publications databases and, after a careful selection, we have considered a total of 155 papers. The papers are classified in terms of geographical distribution, predicted values, predictor variables, evaluation metrics and Machine Learning model.

Predicting of Daily PM2.5 Concentration Employing Wavelet Artificial Neural Networks Based on Meteorological Elements in Shanghai, China

Anthropogenic sources of fine particulate matter (PM_2.5) threaten ecosystem security, human health and sustainable development. The accuracy prediction of daily PM_2.5 concentration can give important information for people to reduce their exposure. Artificial neural networks (ANNs) and wavelet-ANNs (WANNs) are used to predict daily PM_2.5 concentration in Shanghai. The PM_2.5 concentration in Shanghai from 2014 to 2020 decreased by 39.3%. The serious COVID-19 epidemic had an unprecedented effect on PM_2.5 concentration in Shanghai. The PM_2.5 concentration during the lockdown in 2020 of Shanghai is significantly reduced compared to the period before the lockdown. First, the correlation analysis is utilized to identify the associations between PM_2.5 and meteorological elements in Shanghai. Second, by estimating twelve training algorithms and twenty-one network structures for these models, the results show that the optimal input elements for daily PM_2.5 concentration predicting models were the PM_2.5 from the 3 previous days and fourteen meteorological elements. Finally, the activation function (tansig-purelin) for ANNs and WANNs in Shanghai is better than others in the training, validation and forecasting stages. Considering the correlation coefficients (R) between the PM_2.5 in the next day and the input influence factors, the PM_2.5 showed the closest relation with the PM_2.5 1 day lag and closer relationships with minimum atmospheric temperature, maximum atmospheric pressure, maximum atmospheric temperature, and PM_2.5 2 days lag. When Bayesian regularization (trainbr) was used to train, the ANN and WANN models precisely simulated the daily PM_2.5 concentration in Shanghai during the training, calibration and predicting stages. It is emphasized that the WANN1 model obtained optimal predicting results in terms of R (0.9316). These results prove that WANNs are adept in daily PM_2.5 concentration prediction because they can identify relationships between the input and output factors. Therefore, our research can offer a theoretical basis for air pollution control.

A novel encoder-decoder model based on Autoformer for air quality index prediction

Rapid economic development has led to increasingly serious air quality problems. Accurate air quality prediction can provide technical support for air pollution prevention and treatment. In this paper, we proposed a novel encoder-decoder model named as Enhanced Autoformer (EnAutoformer) to improve the air quality index (AQI) prediction. In this model, (a) The enhanced cross-correlation (ECC) is proposed for extracting the temporal dependencies in AQI time series; (b) Combining the ECC with the cross-stage feature fusion mechanism of CSPDenseNet, the core module CSP_ECC is proposed for improving the computational efficiency of the EnAutoformer. (c) The time series decomposition and dilated causal convolution added in the decoder module are exploited to extract the finer-grained features from the original AQI data and improve the performance of the proposed model for long-term prediction. The real-world air quality datasets collected from Lanzhou are used to validate the performance of our prediction model. The experimental results show that our EnAutoformer model can greatly improve the prediction accuracy compared to the baselines and can be used as a promising alternative for complex air quality prediction.

Quantitative evaluation of impacts of the steadiness and duration of urban surface wind patterns on air quality

The complexity and heterogeneity of urban land surfaces result in inconsistencies in near-surface winds, which in turn influence the diffusion and dispersion of air pollutants. In this study, we classified urban surface wind fields, quantified their steadiness, duration, and influence on air quality using hourly wind observations from 50 meteorological stations, as well as hourly PM_2.5 and NO₂ concentrations from 18 monitoring stations during 2017-2018 in Shenzhen, a mega city in southern China. We found that the K-means clustering technique was reliable for distinguishing surface wind patterns within the city. Urban surface-wind patterns greatly affected pollutant concentrations. When dominated by calm, northerly wind, high PM_2.5/NO₂ concentration episodes occurred more frequently than those during other surface wind patterns. The urban surface transport index (USTI) was used to quantify the steadiness of surface wind classes. High pollutant concentrations were present during both high wind speed periods with a large USTI, indicating external pollutant transport, and during low wind speed periods with a small USTI, indicating pollutant accumulation. The threshold durations for surface wind fields (TDSWF) was proposed to quantify the impacts of surface wind persistence on air quality. We found that poor air quality occurred during the first several hours of a dominant wind pattern, indicating that transitions between wind patterns should be a particular focus when assessing air-quality deterioration. USTI and TDSWF are potentially applicable to other urban areas, owing to their clear definitions and simple calculation. In combination with wind speeds, these indices are likely to improve air quality forecasting and strategic decisions on air pollution emergencies, based on long time series of multiple wind and pollutant concentration observations.

Data-driven predictive modeling of PM2.5 concentrations using machine learning and deep learning techniques: a case study of Delhi, India

The present study intends to use machine learning (ML) and deep learning (DL) models to forecast PM_2.5 concentration at a location in Delhi. For this purpose, multi-layer feed-forward neural network (MLFFNN), support vector machine (SVM), random forest (RF) and long short-term memory networks (LSTM) have been applied. The air pollutants, e.g., CO, Ozone, PM₁₀, NO, NO₂, NO_x, NH₃, SO₂, benzene, toluene, as well as meteorological parameters (temperature, wind speed, wind direction, rainfall, evaporation, humidity, pressure, etc.), have been used as inputs in the present study. Moreover, this is one of the first papers that employ aerodynamic roughness coefficient as an input parameter for the prediction of PM_2.5 concentration. The result of the study shows that the LSTM model with index of agreement (IA) 0.986, root mean square error (RMSE) 21.510, Nash-Sutcliffe efficiency index (NSE) 0.945, (coefficient of determination)R² 0.945, and (correlation coefficient)R 0.972 is the best performing technique for the prediction of PM_2.5 followed by MLFFNN, SVM, and RF models. The sensitivity analysis for the LSTM model reported that PM₁₀, wind speed, NH₃, and benzene are the key influencing parameters for the estimation of PM_2.5. The findings in this work suggest that the LSTM could advance in PM_2.5 forecasting and thus would be useful for developing fine-scale, state-of-the-art air pollution forecasting models.

PM2.5 forecasting for an urban area based on deep learning and decomposition method

Rapid growth in industrialization and urbanization have resulted in high concentration of air pollutants in the environment and thus causing severe air pollution. Excessive emission of particulate matter to ambient air has negatively impacted the health and well-being of human society. Therefore, accurate forecasting of air pollutant concentration is crucial to mitigate the associated health risk. This study aims to predict the hourly PM2.5 concentration for an urban area in Malaysia using a hybrid deep learning model. Ensemble empirical mode decomposition (EEMD) was employed to decompose the original sequence data of particulate matter into several subseries. Long short-term memory (LSTM) was used to individually forecast the decomposed subseries considering the influence of air pollutant parameters for 1-h ahead forecasting. Then, the outputs of each forecast were aggregated to obtain the final forecasting of PM2.5 concentration. This study utilized two air quality datasets from two monitoring stations to validate the performance of proposed hybrid EEMD-LSTM model based on various data distributions. The spatial and temporal correlation for the proposed dataset were analysed to determine the significant input parameters for the forecasting model. The LSTM architecture consists of two LSTM layers and the data decomposition method is added in the data pre-processing stage to improve the forecasting accuracy. Finally, a comparison analysis was conducted to compare the performance of the proposed model with other deep learning models. The results illustrated that EEMD-LSTM yielded the highest accuracy results among other deep learning models, and the hybrid forecasting model was proved to have superior performance as compared to individual models.

Prediction of Monthly PM2.5 Concentration in Liaocheng in China Employing Artificial Neural Network

Fine particulate matter (PM2.5) affects climate change and human health. Therefore, the prediction of PM2.5 level is particularly important for regulatory planning. The main objective of the study is to predict PM2.5 concentration employing an artificial neural network (ANN). The annual change in PM2.5 in Liaocheng from 2014 to 2021 shows a gradual decreasing trend. The air quality in Liaocheng during lockdown and after lockdown periods in 2020 was obviously improved compared with the same periods of 2019. The ANN employed in the study contains a hidden layer with 6 neurons, an input layer with 11 parameters, and an output layer. First, the ANN is used with 80% of data for training, then with 10% of data for verification. The value of correlation coefficient (R) for the training and validation data is 0.9472 and 0.9834, respectively. In the forecast period, it is demonstrated that the ANN model with Bayesian regularization (BR) algorithm (trainbr) obtained the best forecasting performance in terms of R (0.9570), mean absolute error (4.6 μg/m3), and root mean square error (6.6 μg/m3), respectively. The ANN model has produced accurate results. These results prove that the ANN is effective in monthly PM2.5 concentration predicting due to the fact that it can identify nonlinear relationships between the input and output variables.

Assessing the Impact of Local Policies on PM2.5 Concentration Levels: Application to 10 European Cities

In this paper, we propose a methodology to evaluate the effectiveness of local emission reduction policies on PM2.5 concentration levels. In particular, we look at the impact of emission reduction policies at different scales (from urban to EU scale) on different PM2.5 baseline concentration levels. The methodology, based on a post-processing of air quality model simulations, is applied to 10 cities in Europe to understand on which sources local actions are effective to improve air quality, and over which concentration ranges. The results show that local actions are effective on low-level concentrations in some cities (e.g., Rome), whereas in other cases, policies are more effective on high-level concentrations (e.g., Krakow). This means that, in specific geographical areas, a coordinated approach (among cities or even at different administration levels) would be needed to significantly improve air quality. At last, we show that the effectiveness of local actions on urban air pollution is highly city-dependent.

A novel seasonal index-based machine learning approach for air pollution forecasting

Novel machine learning models (MLMs) using the seasonal indexing approach that captures the variation in air quality caused due to meteorological changes have been used to provide short-term, real-time forecasts of PM_2.5 concentration for one of the most polluted air quality control regions (AQCR) in the capital city of Delhi. Two MLMs-multi-linear regression and random forest-have been developed for using time series data for 1-h and 24-h average PM_2.5 concentration. Short-term, real-time forecasts have been made using the developed models. Various model performance evaluation indices indicate satisfactory model performance. R² values for the hourly and daily models varied between 0.95 and 0.72 and between 0.76 and 0.68 for the 1st to 5th h/day, respectively. The lagged values of PM_2.5 concentration (persistence) and the hourly and daily indices are the most influential variables for the forecasts for immediate time steps. In contrast, seasonal indices become more important with the forecasting time horizon. The developed models can be used for making short-term, real-time air quality forecasts and issuing a warning when the pollution levels go beyond acceptable limits.

Time Series Forecasting of Air Quality: A Case Study of Sofia City

Air pollution has a significant impact on human health and the environment, causing cardiovascular disease, respiratory infections, lung cancer and other diseases. Understanding the behavior of air pollutants is essential for adequate decisions that can lead to a better quality of life for citizens. Air quality forecasting is a reliable method for taking preventive and regulatory actions. Time series analysis produces forecasting models, which study the characteristics of the data points over time to extrapolate them in the future. This study explores the trends of air pollution at five air quality stations in Sofia, Bulgaria. The data collected between 2015 and 2019 is analyzed applying time series forecasting. Since the time series analysis works on complete data, imputation techniques are used to deal with missing values of pollutants. The data is aggregated by granularity periods of 3 h, 6 h, 12 h, 24 h (1 day). The AutoRegressive Integrated Moving Average (ARIMA) method is employed to create statistical analysis models for the prediction of pollutants’ levels at each air quality station and for each granularity, including carbon oxide (CO), nitrogen dioxide (NO2), ozone (O3) and fine particles (PM2.5). In addition, the method allows us to find out whether the pollutants’ levels exceed the limits prescribed by the World Health Organization (WHO), as well as to investigate the correlation between levels of a given pollutant measured in different air quality stations.

Applying and Comparing LSTM and ARIMA to Predict CO Levels for a Time-Series Measurements in a Port Area

Air pollution is a major problem in the everyday life of citizens, especially air pollution in the transport domain. Ships play a significant role in coastal air pollution, in conjunction with transport mobility in the broader area of ports. As such, ports should be monitored in order to assess air pollution levels and act accordingly. In this paper, we obtain CO values from environmental sensors that were installed in the broader area of the port of Igoumenitsa in Greece. Initially, we analysed the CO values and we have identified some extreme values in the dataset that showed a potential event. Thereafter, we separated the dataset into 6-h intervals and showed that we have an extremely high rise in certain hours. We transformed the dataset to a moving average dataset, with the objective being the reduction of the extremely high values. We utilised a machine-learning algorithm, namely the univariate long short-term memory (LSTM) algorithm to provide the predicted outcome of the time series from the port that has been collected. We performed experiments by using 100, 1000, and 7000 batches of data. We provided results on the model loss and the root-mean-square error as well as the mean absolute error. We showed that with the case with batch number equals to 7000, the LSTM we achieved a good prediction outcome. The proposed method was compared with the ARIMA model and the comparison results prove the merit of the approach.

Predictions and mitigation strategies of PM2.5 concentration in the Yangtze River Delta of China based on a novel nonlinear seasonal grey model

High delicate particulate matter (PM_2.5) concentration can seriously reduce air quality, destroy the environment, and even jeopardize human health. Accordingly, accurate prediction for PM_2.5 plays a vital role in taking precautions against upcoming air ambient pollution incidents. However, due to the disturbance of seasonal and nonlinear characteristics in the raw series, pronounced forecasts are confronted with tremendous handicaps, even though for seasonal grey prediction models in the preceding researches. A novel seasonal nonlinear grey model is initially designed to address such issues by integrating the seasonal adjustment factor, the conventional Weibull Bernoulli grey model, and the cultural algorithm, simultaneously depicting the seasonality and nonlinearity of the original data. Experimental results from PM_2.5 forecasting of four major cities (Shanghai, Nanjing, Hangzhou, and Hefei) in the YRD validate that the proposed model can obtain more accurate predictive results and stronger robustness, in comparison with grey prediction models (SNGBM(1,1) and SGM(1,1)), conventional econometric technology (SARIMA), and machine learning methods (LSSVM and BPNN) by employing accuracy levels. Finally, the future PM_2.5 concentration is forecasted from 2020 to 2022 using the proposed model, which provides early warning information for policy-makers to develop PM_2.5 alleviation strategies.

Intelligent multivariable air-quality forecasting system based on feature selection and modified evolving interval type-2 quantum fuzzy neural network

Owing to the high nonlinearity and noise in the air quality index (AQI), tackling the uncertainties and fuzziness in the forecasting process is still a prevalent problem. Therefore, this study developed an intelligent hybrid air-quality forecasting system based on feature selection and a modified evolving interval type-2 quantum fuzzy neural network (eIT2QFNN), which provides accurate air-quality forecasting information by considering climate influencing factors. The main contributions of this study are as follows. The optimal input structure of the model is determined by the proposed second-stage feature-selection model, which can better extract the influencing variables and remove redundant information. Moreover, a novel multi-objective chaotic Bonobo optimizer algorithm is proposed to improve the eIT2QFNN. The modified eIT2QFNN implements AQI prediction by considering the importance of influencing variables that can cope with the uncertainties and fuzziness in the forecasting process. Finally, the Diebold-Mariano and modified Diebold-Mariano tests are employed to evaluate the performance of the proposed system. The experimental results demonstrate that our proposed system significantly improves the modeling performance in terms of high accuracy and compact structure, and can thus serve as an effective tool for air-quality management.

Multi-Horizon Air Pollution Forecasting with Deep Neural Networks

Air pollution is a global problem, especially in urban areas where the population density is very high due to the diverse pollutant sources such as vehicles, industrial plants, buildings, and waste. North Macedonia, as a developing country, has a serious problem with air pollution. The problem is highly present in its capital city, Skopje, where air pollution places it consistently within the top 10 cities in the world during the winter months. In this work, we propose using Recurrent Neural Network (RNN) models with long short-term memory units to predict the level of PM10 particles at 6, 12, and 24 h in the future. We employ historical air quality measurement data from sensors placed at multiple locations in Skopje and meteorological conditions such as temperature and humidity. We compare different deep learning models’ performance to an Auto-regressive Integrated Moving Average (ARIMA) model. The obtained results show that the proposed models consistently outperform the baseline model and can be successfully employed for air pollution prediction. Ultimately, we demonstrate that these models can help decision-makers and local authorities better manage the air pollution consequences by taking proactive measures.

A Simple Dendritic Neural Network Model-Based Approach for Daily PM2.5 Concentration Prediction

Air pollution in cities has a massive impact on human health, and an increase in fine particulate matter (PM2.5) concentrations is the main reason for air pollution. Due to the chaotic and intrinsic complexities of PM2.5 concentration time series, it is difficult to utilize traditional approaches to extract useful information from these data. Therefore, a neural model with a dendritic mechanism trained via the states of matter search algorithm (SDNN) is employed to conduct daily PM2.5 concentration forecasting. Primarily, the time delay and embedding dimensions are calculated via the mutual information-based method and false nearest neighbours approach to train the data, respectively. Then, the phase space reconstruction is performed to map the PM2.5 concentration time series into a high-dimensional space based on the obtained time delay and embedding dimensions. Finally, the SDNN is employed to forecast the PM2.5 concentration. The effectiveness of this approach is verified through extensive experimental evaluations, which collect six real-world datasets from recent years. To the best of our knowledge, this study is the first attempt to utilize a dendritic neural model to perform real-world air quality forecasting. The extensive experimental results demonstrate that the SDNN offers very competitive performance relative to the latest prediction techniques.