Application Of Data Science Techniques To The Water Quality Analysis

Abstract

From the perspective of the Panchabhuta (Five Elements), the entire cosmic quest of the world and beyond started. They are Water or Jal, Earth or Prithvi, Fire or Agni, Air or Vayu, and Ether or Akasha. From these 5 elements this paper dealing with water. All living beings need water to survive. The source of water is mostly from groundwater. Its quality is a key concern for humankind since it is connected to human wellbeing. Water samples are collected from various 25 locations in Srikakulam Dist. Andhra Pradesh, India. These samples have been tested for different chemical and physical Parameters like, for example, pH, total hardness, chloride, electrical conductivity, calcium, fluorides, and dissolved oxygen by standard methods. Method Weighted Arithmetic Water Quality Index (WQI) and Integrated Fuzzy Logic WQI are used to determine the status of water quality. Correlation analysis provides an excellent method for estimating parameter values within an acceptable degree of precision, and the relationship that exists between multiple independent variables and a dependent variable is quantified by linear regression. Principal Component Analysis (PCA) and Multivariate statistical techniques Cluster Analysis (CA) were applied to evolve the sources of variation in water quality. Identification of physicochemical parameters distribution to check their process capability. The geographical distribution map is plotted according to the water quality rating