Abstract

     With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.

Introduction

     With rapid economic development, wastewater containing various pollutants is generated, posing serious threats to natural water environments. Thus, various water pollution control measures have been developed. To a large extent, water quality analysis and evaluation have substantially improved the efficiency of water pollution control [1]. To date, many methods have been developed to monitor and assess water quality worldwide, such as the multivariate statistical method [2], fuzzy inference [3], and the water quality index (WQI) [4]. For evaluating water quality, although most water quality parameters can be monitored according to the procedures defined in the relevant standards, the final water quality evaluation results may widely vary owing to the choice of parameters [5]. Considering all water quality parameters is unrealistic because it is not only expensive and technically difficult but also fails to deal with the variability in water quality [6]. However, in recent years, with the advances in machine learning methods, an increasing number of researchers believe that vast amounts of data can be successfully captured and analyzed to meet the complex and large-scale water quality evaluation requirements.

Concluding remarks

     Machine learning has been widely used as a powerful tool to solve problems in the water environment because it can be applied to predict water quality, optimize water resource allocation, manage water resource shortages, etc. Despite this, several challenges remain in fully applying machine learning approaches in this field to evaluate water quality: (1) Machine learning is usually dependent on large amounts of high-quality data. Obtaining sufficient data with high accuracy in water treatment and management systems is often difficult owing to the cost or technology limitations. (2) As the conditions in real water treatment and management systems can be extremely complex, the current algorithms may only be applied to specific systems, which hinders the wide application of machine learning approaches. (3) The implementation of machine learning algorithms in practical applications requires researchers to have certain professional background knowledge.

The aim of this study is to assess the water quality of Lower Jhelum Canal (LJC) and its suitability for irrigation purposes. An effort has been made to develop a method by integrating water quality index with geographic information system (GIS) for an effective interpretation of LJC water quality. The pollution status of LJC was estimated by different physicochemical and biological parameters. Based on results of analysis, a spatial distribution map of selected water quality parameters was prepared using GIS. An inverse distance weighting (IDW), which is an interpolation technique, was applied to prepare a thematic layer of parameters at each station of Lower Jhelum canal. The results of individual parameters showed that the concentrations of contamination were within permissible limits of WHO and NEQS guidelines except for E. coli. Overall, most of the water falls in excellent quality category indicating the suitability of water for irrigation purpose. The results suggest that most of the water can be used for irrigation and various intended purposes except direct use of water for potable or drinking purposes without treatment.

Introduction

Water is the most significant ingredient for supporting and evolution of life (Kuutondokwa, 2008). Humans get different sorts of benefits from freshwater, which includes water for drinking, industrialization, domestic uses, irrigation, for the production of waterfowl and fisheries, use for leisure, shipping, and waste discarding (Jackson et al., 2001). Water is a source of economic gain. Almost 70% of water is used in agricultural production, which is indirectly the cause of economic growth (Brown and Matlock, 2011). Water resources (Freshwater) are becoming limited for individuals due to overpopulation, so the accessibility of freshwater for human beings decreases (Iqbal et al., 2018). Quality of freshwater deteriorates by developmental activities that contaminate the water bodies, their effects on human health, ecosystem disturbance and issues related to its management and monitoring (Iqbal et al., 2019). Water quality deterioration is the primary threat to public health at the global level (Rahman et al., 2020). Anthropogenic actions, like improper disposal of municipal, industrialized effluents, and unsystematic use of chemicals in agriculture, are vital aspects causative in the worsening of water quality (Azizullah et al., 2011; Iqbal et al., 2020; Subedi et al., 2019; Shirani et al., 2018; Li et al., 2020). The result of these activities is eutrophication, loss of water quality, loss of biodiversity, effects on human health and social security, deposition of nutrients and other inorganic pollutants, acidification and significant economic losses (Kraemer et al., 2001). Contamination of water leads to water scarcity or it may be polluted at that level where it is expensive to treat (Gupta et al., 2012; Maged et al., 2020; Imran et al., 2020). Consequences of both water treatment and water scarcity with high cost would be the reason for the increase in water prices (Kuutondokwa, 2008). According to (Rogers et al., 2002), water is an efficient good. However, the nations which have water resources could grow their economies, while on the other hand, it will be difficult for poor or developing countries, even to avail of their essential needs.

Groundwater is among the vital water resources on the earth planet, being exploited for fundamental uses such as drinking, agriculture and industry (Wu and Sun, 2016; Li et al., 2016; Chitsaz and Azarnivand, 2016; Jamshidzadeh and Mirbagheri, 2011). Rainfall penetration through the soil and stones on the ground surface is the most important source of groundwater provision. This water resource accompanied by water penetration of rivers/lakes as well as artificial recharge of groundwater and reused waste waters are the major sources for augmentation of groundwater resources (Adetunde et al., 2011). In general, population growth and the expansion of urbanization as the chief cause of agriculture and industry evolution gave rise to instability of aquifers (Krishan et al., 2016). Moreover, the exponential rise of population and over exploitation of groundwater resources has ended in quality degradation of groundwater (Pophare et al., 2014). In particular, just like the quantity, quality of groundwater should be taken into a serious consideration (Aghazadeh and Asghari-Moghadam, 2010). Considering this fact that, artificial recharge, environmental rainfall, ground water penetration and groundwater geo-chemical reactions might influence the quality of groundwater (Vasanthavigar et al., 2010), its pollution would threaten human’s health, economic development and social welfare (Milovanovic, 2007). Several factors and methods have so far, been innovated to present water quality parameters. Among all, Water Quality Index (WQI) is appreciated as a prominent factor for classification and quality management of groundwater (Hosseini-Moghari et al., 2015). In order to evaluate the quality of drinking water in Sabalan aquifer eas a volcanic region- Mosaferi and his colleagues (Mosaferi et al., 2015) put WQI into practice using 7 qualitative parameters. In addition, Sadat-Noori et al. (2013) performed zoning of adequate regions for drinking exploitations in Saveh-Arak plane. While having a positive effect on the qualitative assessment of groundwater resources, WQI is expected to entail drawbacks. Lermontov et al. (2009) stated that classifications which are adopted from this index would generate inflexible and definite results. Moreover, Dahiya et al. (2007) explained that this analysis, in some cases, presents unreliable consequences. For instance, based on the analysis made by WQI, the quality of water has been reported to be adequate for drinking purposes, while assessed to be inadequate for agriculture using Wilcox diagram. Such an assumption should be considered a genuine contradiction as sensitivities to drinking water is remarkably higher compared to the water used in agriculture. In line with the above elucidation, Multicriteria decision making methods were recommended in order to avoid conflicts in the qualitative classification of samples.

پیش بینی کمیتی تاثیرات زیست محیطی بر سناریو های تغییر جوی و کاربری زمین در آبخیز می تواند به عنوان مبنایی عالی برای توسعه الگوهای مدیریت آبخیز خدمت می کنند . کمیت و کیفیت آب از جمله شاخص های کلیدی زیست محیطی می باشند که نسبت به انواع اختلال های بیرونی حساس می باشند . هدف این بررسی این است تا تاثیرات تغییر کاربری و تغییرات جوی بر مقدار و کیفیت آب در مقیاس آبخیز و درک روابط بین اجزای آب شناسی و کیفیت آب در آن مقیاس تحت سناریو های مختلف جوی و استفاده از زمین را ارزیابی نمایند . ما یک رویکرد را برای مدل سازی و بررسی تاثیرات استفاده از زمین و سناریو های تغییر جوی در چرخه های آب و ماده مغذی و آب شناسی آبخیز و مدل ماده مغذی را برای آبخیز رودخانه نشیو در هوکایدو در شمال ژاپن توسعه داده ایم . تغییر کاربری زمین پیش بینی شده تحت شرایط جوی و خط مبناء باعث کاهش بارهای رسوب ، نیتروژن و فسفر کلی از آبخیز به رودخانه گردید . این وضعیت را به دریافت ماده مغذی بالاتر توسط غلات و ماده مغذی کمتر معدنی سازی توسط میکروب ها ، نشت ماده مغذی کاهش یافته از خاک و راندمان های آب کمتر در مزرعه نسبت می دهند . تغییرات جوی ( رسوب و دما ) برنامه ریزی شده بودند تا تاثیر بیشتر بر افزایش یافتن جریان آب سطحب ، جریان جانبی ، تخلیه آب زیرزمینی و بازده آب نسبت به تغییر کاربری زمین داشته باشند . رواناب سطحی بویژه در ماه های اوریل و می کاهش یافته بود و در ماه های مارس و دسامبر با زیاد شدن دما کاهش یافته بود .