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.