A Multi-sensor Process for In-Situ Monitoring of Water Pollution in Rivers or Lakes for High-Resolution Quantitative and Qualitative Water Quality Data

Abstract

Sensor based environmental monitoring is beginning to gain traction given the recent advancements in sensor development technology. Sensor platforms offer several advantages in comparison to the traditional monitoring approaches based on discrete sampling methods as they offer the capability of providing high resolution data. Access to high-frequency spatial and temporal information facilitates real-time event detection or then understanding the impact of pollution to the water quality in natural water resources. In this paper, we report a multi-sensor process that we developed for in-situ monitoring of water pollution in rivers/lakes in which we acquire real-time water quality data using (a) a multiparametric sensor probe for quantitative data, (b) a crowd sensor via a mobile app for qualitative data and integrate these data onto a cloud platform i.e Bluemix which enables interactive visualization of data as Heatmap combined with geographical mapping. This type of visualization technique not only facilitates effective handling of high-resolution data but also allows large-scale data-driven inspection to identify affected/polluted zones and detection of pollution violations, thereby making it an important tool for enabling decision-making. Data analysis based on clustering techniques is also presented. We compare our techniques to traditional data collection methods. Furthermore, to support our efforts in water quality monitoring, we have also developed several web-based applications that are aimed at incorporating sensing data as well as data from various other sources onto a common online platform. We demonstrate the capabilities of our tools through a case study done on Yamuna river in New Delhi where we monitor the river pollution in real-time.