A Survey on Air quality Forecasting and Agricultural Intelligence using Data mining Techniques

Abstract

Air pollution is gradually becoming a global environmental threat as a result of industrialization, globalization and urbanization. The quality of the air we breathe is becoming essential both for the environment as well to the society. There are numerous tools categorized as numerical and statistical for the prediction and analysis of quality of the air. In this problem area, Artificial Neural Network is considered to be an exceptional predictive and data analysis tool for Air quality forecasting. Agricultural intelligence is a definite field associated with techniques involved to an increased understanding of cultivation, productivity of crop, and reduced risk associated agriculture. Crop prediction is a vital agricultural drawback. To address this drawback, crop prediction technique is used. It is the one of the most typically used intelligence technique supported by data processing (DM) ideas to predict the crop yield for maximising the crop productivity. Hence, this paper focuses on a comprehensive review on existing air quality forecasting techniques through soft computing and studies and records the varied data processing techniques on the market within the literature for higher crop productivity.

Keywords: Air quality, Artificial Neural Network, Fuzzy logic, Air pollutants, Software tools for ANN. Data mining, Crop prediction, k-means, k-nearest neighbor, Fuzzy sets, Regression, Classification, Neural network Association Rule.