Enhanced radial basis function neural networks for ozone level estimation

Identification and quantification of anomalies in environmental gamma dose rate time series using artificial intelligence

Gamma dose rate (GDR) monitors are the most widely used tool for continuous monitoring of environmental radioactivity. They are inexpensive to procure and operate, and generally require little maintenance. However, since no spectral information is available, the detection limit for irregularities is correspondingly high; A value around 20 nSv/h is often called out. By adding weather data to the GDR measurement and a sequence of machine learning algorithms, the anomaly detection sensitivity can be significantly increased while simultaneously decreasing the number of false positives. The algorithms were designed such that an integrated safety net prevents false negatives. First, the precipitation-induced GDR peaks from washed-out Radon progeny are removed by means of regression, provided that a check of the regression parameters shows sufficient agreement with past data at the measurement site. A neural network then calculates the expected value of the remaining GDR baseline for the prevailing conditions. Finally, an anomaly detection is carried out on the remainder between the expected and actual GDR baseline value. Extreme value theory is used to detect point anomalies, and hierarchical clustering of subsequences for slower processes. By combining the two detection methods, the full spectrum of irregularities is covered. The algorithms were implemented in Python and trained with real measurement data from the German GDR monitoring network. For verification, the data were enriched with results from JRODOS simulations of a nuclear power plant accident. Altogether, the presented methodology can lower the detection limit of irregularities to about 4 nSv/h, i. e. about a factor of 5 below the previous consensus value. The algorithm detects as well as quantifies the anomaly in the GDR, allowing for additional conclusions like potentially involved isotopes. Most important, it allows to refrain from the current practice of defining fixed alarming thresholds between the two contradicting goals of high sensitivity and low false alarm rate. Instead, it allows to transition to the more natural alarming on deviations from the expectation.

Poor Air Quality and Its Association with Mortality in Ho Chi Minh City: Case Study

Along with its rapid urban development, Ho Chi Minh City (HCMC) in recent years has suffered a high concentration of air pollutants, especially fine particulate matters or PM2.5. A comprehensive study is required to evaluate the air quality conditions and their health impact in this city. Given the lack of adequate air quality monitoring data over a large area of the size of HCMC, an air quality modeling methodology is adopted to address the requirement. Here, by utilizing a corresponding emission inventory in combination with The Air Pollution Model-Chemical Transport Model (TAPM-CTM), the predicted concentration of air pollutants is first obtained for PM2.5, NOx, and SO2. Then by associating the pollutants exposed with the mortality rate from three causes, namely Ischemic Heart Disease (IHD), cardiopulmonary, and lung cancer, the impact of air pollution on human health is obtained for this purpose. Spatial distribution has shown a high amount of pollutants concentrated in the central city with a high density of combustion vehicles (motorcycles and automobiles). In addition, a significant amount of emissions can be observed from stevedoring and harbor activities, including ferries and cargo handling equipment located along the river. Other sources such as household activities also contribute to an even distribution of emission across the city. The results of air quality modeling showed that the annual average concentrations of NO2 were higher than the standard of Vietnam National Technical Regulation on Ambient Air Quality (QCVN 05: 2013 40 µg/m3) and World Health Organization (WHO) (40 µg/m3). The annual average concentrations of PM2.5 were 23 µg/m3 and were also much higher than the WHO (10 µg/m3) standard by about 2.3 times. In terms of public health impacts, PM2.5 was found to be responsible for about 1136 deaths, while the number of mortalities from exposure to NO2 and SO2 was 172 and 89 deaths, respectively. These figures demand some stringent measures from the authorities to potentially remedy the alarming situation of air pollution in HCM City.

Soft Computing Applications in Air Quality Modeling: Past, Present, and Future

Air quality models simulate the atmospheric environment systems and provide increased domain knowledge and reliable forecasting. They provide early warnings to the population and reduce the number of measuring stations. Due to the complexity and non-linear behavior associated with air quality data, soft computing models became popular in air quality modeling (AQM). This study critically investigates, analyses, and summarizes the existing soft computing modeling approaches. Among the many soft computing techniques in AQM, this article reviews and discusses artificial neural network (ANN), support vector machine (SVM), evolutionary ANN and SVM, the fuzzy logic model, neuro-fuzzy systems, the deep learning model, ensemble, and other hybrid models. Besides, it sheds light on employed input variables, data processing approaches, and targeted objective functions during modeling. It was observed that many advanced, reliable, and self-organized soft computing models like functional network, genetic programming, type-2 fuzzy logic, genetic fuzzy, genetic neuro-fuzzy, and case-based reasoning are rarely explored in AQM. Therefore, the partially explored and unexplored soft computing techniques can be appropriate choices for research in the field of air quality modeling. The discussion in this paper will help to determine the suitability and appropriateness of a particular model for a specific modeling context.

Forecasting Particulate Matter Concentration Using Linear and Non-Linear Approaches for Air Quality Decision Support

Air quality status on the East Coast of Peninsular Malaysia is dominated by Particulate Matter (PM10) throughout the years. Studies have affirmed that PM10 influence human health and the environment. Therefore, precise forecasting algorithms are urgently needed to determine the PM10 status for mitigation plan and early warning purposes. This study investigates the forecasting performance of a linear (Multiple Linear Regression) and two non-linear models (Multi-Layer Perceptron and Radial Basis Function) utilizing meteorological and gaseous pollutants variables as input parameters from the year 2000–2014 at four sites with different surrounding activities of urban, sub-urban and rural areas. Non-linear model (Radial Basis Function) outperforms the linear model with the error reduced by 78.9% (urban), 32.1% (sub-urban) and 39.8% (rural). Association between PM10 and its contributing factors are complex and non-linear in nature, best captured by an Artificial Neural Network, which generates more accurate PM10 compared to the linear model. The results are robust enough for precise next day forecasting of PM10 concentration on the East Coast of Peninsular Malaysia.

Spatial interpolation and radiological mapping of ambient gamma dose rate by using artificial neural networks and fuzzy logic methods

The aim of this study was to determine spatial risk dispersion of ambient gamma dose rate (AGDR) by using both artificial neural network (ANN) and fuzzy logic (FL) methods, compare the performances of methods, make dose estimations for intermediate stations with no previous measurements and create dose rate risk maps of the study area. In order to determine the dose distribution by using artificial neural networks, two main networks and five different network structures were used; feed forward ANN; Multi-layer perceptron (MLP), Radial basis functional neural network (RBFNN), Quantile regression neural network (QRNN) and recurrent ANN; Jordan networks (JN), Elman networks (EN). In the evaluation of estimation performance obtained for the test data, all models appear to give similar results. According to the cross-validation results obtained for explaining AGDR distribution, Pearson's r coefficients were calculated as 0.94, 0.91, 0.89, 0.91, 0.91 and 0.92 and RMSE values were calculated as 34.78, 43.28, 63.92, 44.86, 46.77 and 37.92 for MLP, RBFNN, QRNN, JN, EN and FL, respectively. In addition, spatial risk maps showing distributions of AGDR of the study area were created by all models and results were compared with geological, topological and soil structure.