IoT Based Smart Water Quality Monitoring: Recent Techniques, Trends and Challenges for Domestic Applications

Abstract

Safe water is becoming a scarce resource, due to the combined effects of increased population, pollution, and climate changes. Water quality monitoring is thus paramount, especially for domestic water. Traditionally used laboratory-based testing approaches are manual, costly, time consuming, and lack real-time feedback. Recently developed systems utilizing wireless sensor network (WSN) technology have reported weaknesses in energy management, data security, and communication coverage. Due to the recent advances in Internet-of-Things (IoT) that can be applied in the development of more efficient, secure, and cheaper systems with real-time capabilities, we present here a survey aimed at summarizing the current state of the art regarding IoT based smart water quality monitoring systems (IoT-WQMS) especially dedicated for domestic applications. In brief, this study probes into common water-quality monitoring (WQM) parameters, their safe-limits for drinking water, related smart sensors, critical review, and ratification of contemporary IoT-WQMS via a proposed empirical metric, analysis, and discussion and, finally, design recommendations for an efficient system. No doubt, this study will benefit the developing field of smart homes, offices, and cities.

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

“…The application of virtual (or soft) sensing for surface and groundwater quality assessment is emerging. This is evidenced by the low number of publications (16) and the fact that 63% of the articles [22,29,55,85,[94][95][96][97][98][99] were published in the last three years (2019-2021). Therefore, as seen in Figure 4, it is not surprising that artificial neural network (ANN) related algorithms are the most applied ML techniques.…”

“…The coordinator module links the sensing and data processing modules. The module usually uses the Arduino microcontroller to receive all the parameter measurements from the various in situ sensors connected to it [16,130]. The system includes a cellular modem and a data logger that allows the transmission of this data to a dedicated website or control room equipped with an alert facility to inform the user of any alarming deviation of water quality parameters.…”

“…With more advances in portable sensors, computing technologies, and communication, the research moved towards using wireless sensor network (WSN) technology. Generally, WSN-based WQM systems work as follows [15,16]: first, a WSN comprises sensors that take specific parameter readings (e.g., pH) that are then sent to a controller through a wireless (optional) communication device. Next, the information is transmitted to the central station through wireless communication media, where all the necessary analysis and processing takes place.…”

“…For example, high power requirements, the vulnerability of sensor data to cyber-attacks, high installation or maintenance costs, storage issues, etc. [3,16]. At the same time, researchers also involved machine learning (ML) techniques in assessing WQ using a relatively small number of WQ parameters [15].…”

“…Consequently, the ability of ML (a subfield of artificial intelligence) to extract useful information from an accessible historical database makes it ideal for virtual sensor applications [22,24,29]. In this context, the other significant contribution of the IoT-based WQM system is that it enables the integration of ML tools in the cloud server in order to predict these hard-to-measure parameters based on surrogates measured using sensors [16]. This essentially implies that monitoring costs can be significantly reduced since only parameters commonly measured in situ can be used as surrogates.…”