Research and Application of an Air Quality Early Warning System Based on a Modified Least Squares Support Vector Machine and a Cloud Model

Low-Cost CO Sensor Calibration Using One Dimensional Convolutional Neural Network

The advent of cost-effective sensors and the rise of the Internet of Things (IoT) presents the opportunity to monitor urban pollution at a high spatio-temporal resolution. However, these sensors suffer from poor accuracy that can be improved through calibration. In this paper, we propose to use One Dimensional Convolutional Neural Network (1DCNN) based calibration for low-cost carbon monoxide sensors and benchmark its performance against several Machine Learning (ML) based calibration techniques. We make use of three large data sets collected by research groups around the world from field-deployed low-cost sensors co-located with accurate reference sensors. Our investigation shows that 1DCNN performs consistently across all datasets. Gradient boosting regression, another ML technique that has not been widely explored for gas sensor calibration, also performs reasonably well. For all datasets, the introduction of temperature and relative humidity data improves the calibration accuracy. Cross-sensitivity to other pollutants can be exploited to improve the accuracy further. This suggests that low-cost sensors should be deployed as a suite or an array to measure covariate factors.

Forecasting Fine Particulate Matter Concentrations by In-Depth Learning Model According to Random Forest and Bilateral Long- and Short-Term Memory Neural Networks

Accurate prediction of fine particulate matter concentration in the future is important for human health due to the necessity of an early warning system. Generally, deep learning methods, when widely used, perform better in forecasting the concentration of PM2.5. However, the source information is limited, and the dynamic process is uncertain. The method of predicting short-term (3 h) and long-term trends has not been achieved. In order to deal with the issue, the research employed a novel mixed forecasting model by coupling the random forest (RF) variable selection and bidirectional long- and short-term memory (BiLSTM) neural net in order to forecast concentrations of PM2.5/0~12 h. Consequently, the average absolute percentage error of 1, 6, and 12 h shows that the PM2.5 concentration prediction is 3.73, 9.33, and 12.68 μg/m3 for Beijing, 1.33, 3.38, and 4.60 μg/m3 for Guangzhou, 1.37, 4.19, and 6.35 μg/m3 for Xi’an, and 2.20, 7.75, and 10.07 μg/m3 for Shenyang, respectively. Moreover, the results show that the suggested mixed model is an advanced method that can offer high accuracy of PM2.5 concentrations from 1 to 12 h post.

24-Hour prediction of PM2.5 concentrations by combining empirical mode decomposition and bidirectional long short-term memory neural network

Accurate prediction of the future PM_2.5 concentration is crucial to human health and ecological environmental protection. Nowadays, deep learning methods show advantages in the prediction of PM_2.5 concentration, but few of the studies can achieve accurate prediction of short term (within 6 h) concentration and also catch longer term (6-24 h) change trends. To address this issue, this study constructs a novel hybrid prediction model by combining the empirical mode decomposition (EMD) method, sample entropy (SE) index and bidirectional long and short-term memory neural network (BiLSTM) to predict 0-24 h PM_2.5 concentrations. The experimental results show that the hybrid model has good performance on PM_2.5 prediction with R² = 0.987, RMSE = 2.77 μg/m³ at T + 1 moment and R² = 0.904, RMSE = 7.51 μg/m³ at T + 6 moment. The novel model improves the accuracy on short-term (within 6 h) prediction of PM_2.5 concentrations by at least 50% compared with other single deep learning models. Moreover, it well catches the variation trend of PM_2.5 concentrations after 6 h till 24 h.

Digital twin-driven intelligence disaster prevention and mitigation for infrastructure: advances, challenges, and opportunities

Natural hazards, which have the potential to cause catastrophic damage and loss to infrastructure, have increased significantly in recent decades. Thus, the construction demand for disaster prevention and mitigation for infrastructure (DPMI) systems is increasing. Many studies have applied intelligence technologies to solve key aspects of infrastructure, such as design, construction, disaster prevention and mitigation, and rescue and recovery; however, systematic construction is still lacking. Digital twin (DT) is one of the most promising technologies for multi-stage management which has great potential to solve the above challenges. This paper initially puts forward a scientific concept, in which DT drives the construction of intelligent disaster prevention and mitigation for infrastructure (IDPMI) systematically. To begin with, a scientific review of DT and IDPMI is performed, where the development of DT is summarized and a DT-based life cycle of infrastructures is defined. In addition, the intelligence technologies used in disaster management are key reviewed and their relative merits are illustrated. Furthermore, the development and technical feasibility of DT-driven IDPMI are illustrated by reviewing the relevant practice of DT in infrastructure. In conclusion, a scientific framework of DT-IDPMI is programmed, which not only provides some guidance for the deep integration between DT and IDPMI but also identifies the challenges that inspire the professional community to advance these techniques to address them in future research.

A systematic literature review of deep learning neural network for time series air quality forecasting

Rapid progress of industrial development, urbanization and traffic has caused air quality reduction that negatively affects human health and environmental sustainability, especially among developed countries. Numerous studies on the development of air quality forecasting model using machine learning have been conducted to control air pollution. As such, there are significant numbers of reviews on the application of machine learning in air quality forecasting. Shallow architectures of machine learning exhibit several limitations and yield lower forecasting accuracy than deep learning architecture. Deep learning is a new technology in computational intelligence; thus, its application in air quality forecasting is still limited. This study aims to investigate the deep learning applications in time series air quality forecasting. Owing to this, literature search is conducted thoroughly from all scientific databases to avoid unnecessary clutter. This study summarizes and discusses different types of deep learning algorithms applied in air quality forecasting, including the theoretical backgrounds, hyperparameters, applications and limitations. Hybrid deep learning with data decomposition, optimization algorithm and spatiotemporal models are also presented to highlight those techniques' effectiveness in tackling the drawbacks of individual deep learning models. It is clearly stated that hybrid deep learning was able to forecast future air quality with higher accuracy than individual models. At the end of the study, some possible research directions are suggested for future model development. The main objective of this review study is to provide a comprehensive literature summary of deep learning applications in time series air quality forecasting that may benefit interested researchers for subsequent research.

Associations between individual perceptions of PM2.5 pollution and pulmonary function in Chinese middle-aged and elderly residents

Background

PM_2.5 pollution has become a major public health concern in urban China. Understanding the residents’ individual perceptions toward haze pollution is critical for policymaking and risk communication. However, the perceptions of middle-aged and elderly residents, who particularly vulnerable to haze pollution, are poorly understood. In this study, we aimed to explore their risk perceptions of haze pollution and investigate its relationship with health status and pulmonary function parameters.

Methods

A cross-sectional study of 400 randomly sampled individuals (aged 40 to 90 years) was conducted in Wuxi, a typical PM_2.5-polluted city in Jiangsu Province, China (during 2015–2017, daily average concentration of PM_2.5 was 52.7 μg/m³). Each participant’s demographic and health information, individual perception and pulmonary function outcomes were collected to explore the relationships between perception factors and personal characteristics and pulmonary function parameters, using linear models.

Results

We found that the mean values for controllability (5 ± 2.8) and dread of risk to oneself (levels of fear for haze-related harm to oneself) (6.9 ± 2.5) were the lowest and the highest values, respectively, in our study. Education and average family income were positively related with all individual perception factors, while age was negatively associated. A history of respiratory disease was positively associated with all individual perception factors except controllability. Significant positive associations were observed between PEF (coefficients ranged from 0.18 to 0.22) and FEF75% (coefficients ranged from 0.18 to 0.29) with a variety of individual perception factors.

Conclusions

There were a lack of concern and knowledge, weak self-protection consciousness and a strong dread of PM_2.5 pollution among the middle-aged and elderly residents in Wuxi. Their individual perceptions were associated with age, education levels, average family income, history of respiratory disease, PEF and FEF75%. Our findings may help policymakers develop effective policies and communication strategies to mitigate the hazards of haze among older residents.

A novel optimal-hybrid model for daily air quality index prediction considering air pollutant factors

Accurate and reliable air quality index (AQI) forecasting is extremely crucial for ecological environment and public health. A novel optimal-hybrid model, which fuses the advantage of secondary decomposition (SD), AI method and optimization algorithm, is developed for AQI forecasting in this paper. In the proposed SD method, wavelet decomposition (WD) is chosen as the primary decomposition technique to generate a high frequency detail sequence WD(D) and a low frequency approximation sequence WD(A). Variational mode decomposition (VMD) improved by sample entropy (SE) is adopted to smooth the WD(D), then long short-term memory (LSTM) neural network with good ability of learning and time series memory is applied to make it easy to be predicted. Least squares support vector machine (LSSVM) with the parameters optimized by the Bat algorithm (BA) considers air pollutant factors including PM_2.5, PM₁₀, SO₂, CO, NO₂ and O₃, which is suitable for forecasting WD(A) that retains original information of AQI series. The ultimate forecast result of AQI can be obtained by accumulating the prediction values of each subseries. Notably, the proposed idea not only gives full play to the advantages of conventional SD, but solve the problem that the traditional time series prediction model based on decomposition technology can not consider the influential factors. Additionally, two daily AQI series from December 1, 2016 to December 31, 2018 respectively collected from Beijing and Guilin located in China are utilized as the case studies to verify the proposed model. Comprehensive comparisons with a set of evaluation indices indicate that the proposed optimal-hybrid model comprehensively captures the characteristics of the original AQI series and has high correct rate of forecasting AQI classes.

A Short-Term Wind Speed Forecasting Model by Using Artificial Neural Networks with Stochastic Optimization for Renewable Energy Systems

To efficiently manage unstable wind power generation, precise short-term wind speed forecasting is critical. To overcome the challenges in wind speed forecasting, this paper proposes a new convolutional neural network algorithm for short-term forecasting. In this paper, the forecasting performance of the proposed algorithm was compared to that of four other artificial intelligence algorithms commonly used in wind speed forecasting. Numerical testing results based on data from a designated wind site in Taiwan were used to demonstrate the efficiency of above-mentioned proposed learning method. Mean absolute error (MAE) and root-mean-square error (RMSE) were adopted as accuracy evaluation indexes in this paper. Experimental results indicate that the MAE and RMSE values of the proposed algorithm are 0.800227 and 0.999978, respectively, demonstrating very high forecasting accuracy.

A Hybrid Forecasting Approach to Air Quality Time Series Based on Endpoint Condition and Combined Forecasting Model

Air pollution forecasting plays a vital role in environment pollution warning and control. Air pollution forecasting studies can also recommend pollutant emission control strategies to mitigate the number of poor air quality days. Although various literature works have focused on the decomposition-ensemble forecasting model, studies concerning the endpoint effect of ensemble empirical mode decomposition (EEMD) and the forecasting model of sub-series selection are still limited. In this study, a hybrid forecasting approach (EEMD-MM-CFM) is proposed based on integrated EEMD with the endpoint condition mirror method and combined forecasting model for sub-series. The main steps of the proposed model are as follows: Firstly, EEMD, which sifts the sub-series intrinsic mode functions (IMFs) and a residue, is proposed based on the endpoint condition method. Then, based on the different individual forecasting methods, an optimal combined forecasting model is developed to forecast the IMFs and residue. Finally, the outputs are obtained by summing the forecasts. For illustration and comparison, air quality index (AQI) data from Hefei in China are used as the sample, and the empirical results indicate that the proposed approach is superior to benchmark models in terms of some forecasting assessment measures. The proposed hybrid approach can be utilized for air quality index forecasting.

A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities

In modern society, air pollution is an important topic as this pollution exerts a critically bad influence on human health and the environment. Among air pollutants, Particulate Matter (PM_2.5) consists of suspended particles with a diameter equal to or less than 2.5 μm. Sources of PM_2.5 can be coal-fired power generation, smoke, or dusts. These suspended particles in the air can damage the respiratory and cardiovascular systems of the human body, which may further lead to other diseases such as asthma, lung cancer, or cardiovascular diseases. To monitor and estimate the PM_2.5 concentration, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are combined and applied to the PM_2.5 forecasting system. To compare the overall performance of each algorithm, four measurement indexes, Mean Absolute Error (MAE), Root Mean Square Error (RMSE) Pearson correlation coefficient and Index of Agreement (IA) are applied to the experiments in this paper. Compared with other machine learning methods, the experimental results showed that the forecasting accuracy of the proposed CNN-LSTM model (APNet) is verified to be the highest in this paper. For the CNN-LSTM model, its feasibility and practicability to forecast the PM_2.5 concentration are also verified in this paper. The main contribution of this paper is to develop a deep neural network model that integrates the CNN and LSTM architectures, and through historical data such as cumulated hours of rain, cumulated wind speed and PM_2.5 concentration. In the future, this study can also be applied to the prevention and control of PM_2.5.

Air Pollution Forecasts: An Overview

Air pollution is defined as a phenomenon harmful to the ecological system and the normal conditions of human existence and development when some substances in the atmosphere exceed a certain concentration. In the face of increasingly serious environmental pollution problems, scholars have conducted a significant quantity of related research, and in those studies, the forecasting of air pollution has been of paramount importance. As a precaution, the air pollution forecast is the basis for taking effective pollution control measures, and accurate forecasting of air pollution has become an important task. Extensive research indicates that the methods of air pollution forecasting can be broadly divided into three classical categories: statistical forecasting methods, artificial intelligence methods, and numerical forecasting methods. More recently, some hybrid models have been proposed, which can improve the forecast accuracy. To provide a clear perspective on air pollution forecasting, this study reviews the theory and application of those forecasting models. In addition, based on a comparison of different forecasting methods, the advantages and disadvantages of some methods of forecasting are also provided. This study aims to provide an overview of air pollution forecasting methods for easy access and reference by researchers, which will be helpful in further studies.

Employing SWOT Analysis and Normal Cloud Model for Water Resource Sustainable Utilization Assessment and Strategy Development

Water Resource Sustainable Utilization (WRSU) is becoming increasingly important, given growing water resource shortages and widening gaps between water supply and demand. Most existing studies have focused on WRSU levels without a dedicated strategy-oriented framework. In addition, uncertainties occur in the process of indicator quantification and grading, leading to a lack of accuracy in the assessment results. Therefore, in this study, stemming from water resource, societal, economic, and environmental dimensions, an indicator system with qualitative description was introduced by Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis to enable development and selection of sustainable water use strategies. A normal cloud model that is capable of addressing uncertainties was used to determine WRSU levels. The comprehensive evaluation results can both reflect the WRSU levels and select the most suitable strategy. The model’s utility was demonstrated by applying it to the case of Shandong province in China. Based on the results, most areas of Shandong province appear to be facing serious unsustainable issues. Appropriate development strategies based on the WRSU levels were provided for improving sustainable use of water resources. The proposed method offers an efficient means for WRSU assessment and strategy development. Moreover, it has the potential to be applied to other water resource issues.