Big Data Analytics with Artificial Intelligence Enabled Environmental Air Pollution Monitoring Framework

Environmental sustainability is the rate of renewable resourceharvesting, pollution control, and non-renewable resource exhaustion. Airpollution is a significant issue confronted by the environment particularlyby highly populated countries like India. Due to increased population, thenumber of vehicles also continues to increase. Each vehicle has its individualemission rate;however, the issue arises when the emission rate crosses thestandard value and the quality of the air gets degraded. Owing to the technological advances in machine learning (ML), it is possible to develop predictionapproaches to monitor and control pollution using real time data. With thedevelopment of the Internet of Things (IoT) and Big Data Analytics (BDA),there is a huge paradigm shift in how environmental data are employed forsustainable cities and societies, especially by applying intelligent algorithms.In this view, this study develops an optimal AI based air quality prediction andclassification (OAI-AQPC) model in big data environment. For handling bigdata from environmental monitoring, Hadoop MapReduce tool is employed.In addition, a predictive model is built using the hybridization of ARIMAand neural network (NN) called ARIMA-NN to predict the pollution level.For improving the performance of the ARIMA-NN algorithm, the parametertuning process takes place using oppositional swallow swarm optimization(OSSO) algorithm. Finally, Adaptive neuro-fuzzy inference system (ANFIS)classifier is used to classify the air quality into pollutant and non-pollutant.A detailed experimental analysis is performed for highlighting the betterprediction performance of the proposed ARIMA-NN method. The obtainedoutcomes pointed out the enhanced outcomes of the proposed OAI-AQPCtechnique over the recent state of art techniques.

Identifying factors that affect environmental air quality using geographical detectors in the NKEFAs of China

The establishment of the National Key Ecological Function Areas(NKEFAs)is an important measure for national ecological security,but the current ecological and environmental evaluation of NKEFAs lacks research on the air quality in the NKEFAs.This study presented the current status of the air quality in the NKEFAs and its driving factors using the geographic detector q-statistic method.The air quality in the NKEFAs was overall better than individual cities and urban agglomeration in eastern coast provinces of China,accounting for 9.21%of the days with air quality at Level III or above.The primary air pollutant was PM_(10),followed by PM_(2.5),with lower concentrations of the remaining pollutants.Pollution was more severe in the sand fixation areas,where air pollution was worst in spring and best in autumn,contrasting with other NKEFAs and individual cities and urban agglomerations.The main influencing factors of air quality index(AQI)in the NKEFAs were land use type,wind speed,and relative humidity also weighted more heavily than factors such as industrial pollution and anthropogenic emissions,and most of these influence factors have two types of interactive effects:binary and nonlinear enhancements.These results indicated that air pollution in the NKEFAs was not related with the emission by intensive economic development.Thus,the policies taking the NKEFAs as restricted development zones were effective,but the air pollution caused by PM_(10) also showed the ecological status in the NKEFAs,especially at sand fixation areas was not quite optimistic,and more strict environmental protection measures should be taken to improve the ecological status in these NKEFAs.

The Antifreeze Critical Strength of Low-temperature Concrete Effected by Index

The antifreeze critical strength and the pre-curing time of low-temperature concrete were studied by means of guaranteed rate of compressive strength and antifreeze performance for the structural safety requirement of concrete engineering,suffering once freeze damage under air environment.It is shown that the antifreeze critical strength is 3.7-4.4MPa,pre-curing time is 18-32 h by guaranteed rate of compressive strength,and the antifreeze critical strength is 3.7-4.4MPa,pre-curing time is 18-32 h by guaranteed rate of antifreeze performance.It can be found that the method of guaranteed rate of compressive strength is sensitive to the defect which generated by freeze damage in the concrete interior.The method is fit to evaluate the antifreeze critical strength of low-temperature concrete.

Spatiotemporal variations of PM_(2.5) and PM_(10) concentrations between31 Chinese cities and their relationships with SO_2,NO_2,CO and O_3

The variations of mass concentrations of PM2.5, PMl0, SO2, NO2, CO, and 03 in 31 Chinese provincial capital cities were analyzed based on data from 286 monitoring sites obtained between March 22, 2013 and March 31,2014. By comparing the pollutant concentrations over this length of time, the characteristics of the monthly variations of mass concentrations of air pollutants were determined. We used the Pearson correlation coefficient to establish the relationship between PM2.5, PM10, and the gas pollutants. The results revealed significant differences in the concentration levels of air pollutants and in the variations between the different cities. The Pearson correlation coefficients between PMs and NO2 and SO2 were either high or moderate （PM2.s with NO2： r = 0.256-0.688, mean r = 0,498：PM10 with NO2： r = 0.169-0.713, mean r=0.493; PM2.5 with SO2： r=0.232-0.693, mean r=0.449; PM10 with SO2： r=0.131-0.669, mean r = 0.403）. The correlation between PMs and CO was diverse （PM2.5： r = 0.156-0.721, mean r = 0.437; PMl0： r= 0.06-0.67, mean r= 0.380）. The correlation between PMs and 03 was either weak or uncorrelated （PM2.s： r= -0,35 to 0.089, mean r= -0.164; PM10： r= -0.279 to 0.078, mean r= -0.127）, except in Haikou （PM2.5： r=0.500; PM10： r=0,509）.

ATC simulation for flight training:The missing link

This paper presents the state of piloted flight simulation fidelity with a focus on the missing link needed to complete the flight simulation experience,namely the simulated ATC environment(SATCE).To date,there has been a great deal of effort invested in providing the highest level of flight realism possible.However,little investment has gone into systems which are used to improve communication skills with ATC while in a populated active airspace.It is important to note that the relatively few SATCEs is not due to the lack of technology,since such products have been available for about a decade.The primary reason for its absence is the inability and unwillingness for operators to justify the investment in such a training tool.In the meantime,the aviation industry has recognized that pilots need to have better communication skills while operating in various conditions.Consequently ICAO,with help from ARINC Industry Activities/FSEMC,has already taken steps to recommend the inclusion of SATCE characteristics in flight simulation devices.The aviation and research communities need to assist efforts by producing the necessary studies and metrics which can be used to evaluate and validate SATCEs used in the flight training.