Abstract
Water is key to life on planet Earth, and hence, maintaining water quality is a critical issue in contemporary times. The water quality index decides the quality of drinking water. The presented work first explores different machine learning algorithms on the already collected water samples to decide the water quality and then applies the coalition game theory-based SHapley Additive exPlanations (SHAP) approach to decide the significance of each parameter in deciding the class of water sample based on quality. The potential of popular algorithms like K-NN, support vector machine, decision tree, etc. are being explored to find out the quality of water samples. All the machine learning algorithms used in the work give over 80% accuracy while the performance of neural network is 96% proving to be the best among all other algorithms. The presented work demonstrates the model agnostic, coalition game theoretic SHAP value-based method for explaining the importance and impact of each of the given parameter pH, HCO3-, Cl-, NO3-, F-, Ca, Mg, Na, Ec, etc. in deciding the quality of the water.
Top1. Introduction
Increase in economic growth results in the production of wastewater that contains a variety of contaminants, posing major risks to natural water ecosystems. As a result, several water-pollution mitigation strategies have been created. Analysis and water quality assessment have greatly increased effectiveness of water pollution control. The water quality depends upon various parameters like pH, Total Dissolved Solids (TDS), Hardness, alkalinity, Bicarbonate (HCO3,) Chloride (Cl), Sodium (Na,), Sulphate (SO4), Fluoride (F), Iron (Fe), Magnesium (Mg) ions (Kothari et al., 2021). The Water Quality Index (WQI) and Trophic State Index (TSI) are commonly applied for the analysis of water quality (Rauen et al., 2018) and both are useful as thumbnail indicators and non-regulatory measurements for water quality assessment. TSI is used for lakes and estuaries, whereas WQI is used for streams, springs, and natural tea- and coffee-colored/black waters (Badal et al., n.d.).
Human health is in danger due to the presence of chemical contaminants in the source of potable water which may have instant health consequences. These pollutants are depending on man-made activities, and industrial, geological, and agricultural conditions. In the modern age, urbanization is one of the biggest problems which affect water quality.
Over-exploitation and improper use of water resources are making things more complex. The Bureau of Indian Standards (BIS, 2012) have been used for estimate the quality of groundwater for drinking purposes and the estimation of WQI. The following attributes are used in this paper to estimate water quality:
- •
pH – pH of water is finding the acidity and basicity of drinking water. As per the Bureau of Indian Standards (BIS, 2012) 6.5 to 8.5 is acceptable range of pH for drinking water. Higher and lower value of pH can cause inflammation in the eyes, skin problem, and mucous membrane in humans (Akter et al., 2016).
- •
Turbidity – Turbidity is the unclearness or cloudiness in water which is caused due to presence of sand, silt, mud, organic and inorganic matter algae, and microorganism and it can be seen with the naked eye. Turbidity reduces the scattering of light. Turbidity reduces the filtering capacity of a treatment plant and can choke the filtering apparatus. As per Bureau of Indian Standards permissible limit of turbidity is 1 NTU.
- •
Total dissolved solids (TDS) – TDS refers to amount of inorganic and organic matter dissolved in water. The main constituents of TDS are calcium, magnesium, sodium, and potassium, and the anions carbonate, bicarbonate, chloride, and sulphate (Priyanka et al., 2017). As per Bureau of Indian Standards (BIS, 1993) acceptable limit of TDS is 500 mg/l.
- •
Total Hardness – The Total Hardness (TH) is due to the presence of divalent ion (salt of Ca and Mg). This is most important parameters of water, it signifies that water can be used for domestic, industrial, or agricultural purposes. (Jameel & Sirajudeen, 2006). Hardness prevents lather formation with soap and increases the consumption of soap, increasing the boiling points of water and corrosion and incrustation of pipes. According to the Bureau of Indian Standards (BIS, 2012) permissible limit of Total Hardness is 200 mg/l.
- •
Fluoride – Higher value of fluoride in water causes fluorosis and molting of teeth. Over-consumption of fluoride for a long period causes crippling of bone. According to the Bureau of Indian Standards (BIS, 1993) acceptable limit of Fluoride is 1 mg/l.
- •
Arsenic – Excess arsenic in water causes very harmful health effects on human beings such as cancer, diabetes, and liver damage. It also increases the risk of hypertension and causes acute arsenic toxicity. Arsenic in water is due to both natural and anthropogenic activities of humans. According to the Bureau of Indian Standards (BIS, 1993) acceptable limit of arsenic in water is 0.01mg/l.