ORIGINAL PAPER Development of entropy-river water quality index for predicting water quality classification through machine learning approach Deepak Gupta 1 • Virendra Kumar Mishra 1 Accepted: 20 June 2023 Ó The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023 Abstract Monitoring of river water is necessary to reveal its quality and pollution level so that we can protect human health and the environment. The present study explored the water quality of the Narmada River in India. To evaluate the water quality of the Narmada River, water samples were collected from 13 sites during the pre- and post-monsoon seasons, and were analyzed for different physicochemical parameters. The results from the analysis were used for the development of the entropy-river water quality index (ERWQI). The ERWQI was used to estimate the Narmada river water quality for two different uses: drinking after disinfection (ERWQI d ) and bathing (ERWQI b ). The machine-learning-based classification models, namely the Logistic regression (LR), Support Vector (SV), K-Nearest Neighbor (KNN), Random Forest (RF), and Gradient Boosting (GB) models were examined to predict and classify ERWQI. The precision, recall, F1 score, and confusion matrix were used to evaluate the performance of the model. The findings of this study identified the LR model as the most accurate classification model with the highest accuracy score for both the ERWQI d and ERWQI b . Moreover, this study also revealed that the water quality of the Narmada River was unsuitable for drinking after disinfection and hence, before any further use it requires treatment through conventional or an advanced techniques. However, the ERWQI b of the Narmada River was categorized as excellent to fair. This study has broad implications for the classification of river water quality and can provide some very useful information to monitoring agencies and policymakers. Keywords Entropy  Machine learning  River  Classification  Drinking  Bathing 1 Introduction Rivers are one of the most significant freshwater resources, it offers access to clean water, food and livelihood (Verma et al. 2022). In the last few decades, rapid increase in population and urbanization have triggered a fast increase in the demand for freshwater. In the same timeline, the river water quality is drastically declining due to dynamic environmental variations and human-induced changes resulting in threat to aquatic life and human health (Akhtar et al. 2021). With the increase in human population, the availability of safe water for direct human consumption has become a matter of great concern worldwide. Rivers are being increasingly exploited to supply water for fulfilling human needs. Hence, prior knowledge of river water quality through continuous comprehensive monitoring is needed for safe utilization as well as for maintaining the integrity of aquatic life (Shah and Joshi 2017). Generally, conventional methods are adopted to evalu- ate the water quality parameters i.e., pH, electrical con- ductivity (EC), total dissolved solids (TDS), alkalinity, hardness, dissolve oxygen (DO), biological oxygen demand (BOD), total coliform (TC), etc. Afterward, it is compared with the existing national (ICMR 1975; CPCB 1979; BIS 2012) and international (WHO 2017) standards to check its compliance levels for different uses such as drinking and bathing, etc. The evaluation of individual water quality parameters does not reflect the overall surface water quality due to the variations in measured water quality parameters (Iscen et al. 2008). In order to protect the surface water quality and keeping it safe for different uses, it is the responsibility of concerned regulatory authorities to share the overall water quality status of & Virendra Kumar Mishra virendra78@gmail.com; virendra.mishra@bhu.ac.in 1 Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi 221005, India 123 Stochastic Environmental Research and Risk Assessment https://doi.org/10.1007/s00477-023-02506-0