clustering

The purpose of this research is to create a spatio-temporal map illustrating the expansion of modern irrigation systems across Iran's provinces using the t-map package in R-Studio. The raw data used in this research was obtained from the statistical tables provided by the statistics center of the Ministry of Agricultural Jihad regarding the development of advanced irrigation systems in Iran from 2009 to 2022. First, an Excel file was prepared using the raw data, ensuring its compatibility with the geographical information of Iran's provinces. This data was then integrated with geographic information in R-Studio software, and spatio-temporal maps were generated using the functions of the t-map package. For clustering analysis, functions from the factoextra package were used. This package allows for data standardization before clustering using various methods. Moreover, in this research, Iran's provinces were clustered according to three criteria: the percentage of completion of modern irrigation systems, the percentage of development of irrigation and drainage networks, and the percentage of coverage of traditional irrigation canals in 2022. The findings indicate that out of 6,014,211 hectares of irrigated agricultural land, 2,469,835 hectares have been equipped with modern irrigation systems, reflecting an average implementation rate of 41% nationwide. Furthermore, the development percentages of irrigation and drainage networks and the coverage of traditional canals were found to be 15% and 0.5%, respectively. The spatio-temporal map of modern irrigation system implementation revealed that provinces with the most extensive irrigated agriculture exhibited lower adoption rates of these systems compared to others. For example, Khuzestan and Fars, which cumulatively account for 31% of the country's irrigated lands, have only progressed by 9% and 18%, respectively, in establishing new irrigation systems. It is important to note that while advanced irrigation systems enhance irrigation efficiency at the farm level, their significant effect on levels of groundwater table requires the presence of smart meters for agricultural wells that supply these systems.

Estimation of leakage, pressure management, and emergency management are among the advantages of establishing DMA in the WDN. However, the unprincipled development of WDN in a traditional way has turned this issue into a complex problem in terms of essential indexes in creating DMA. In this study, a method is presented to design DMAs with optimal selection indicators. For this purpose, three water distribution networks of Balerma, Madena, and D-Town were used for clustering using the Girvan-Newman and Fast Newman methods, which are based on the modularity criterion. Then, with use of a genetic algorithm and EPANET software, to reduce the cost in physical zoning, it was determined by observing the condition of minimum nodal pressure, and with the help of cost, hydraulic, and quality indicators, the zoning results of the research were analyzed and their effectiveness was discussed. The results showed that the mentioned indicators could lead to the optimal selection of the best-proposed plan to modify existing traditional networks and stablish DMA in WDN. The cost and modularity criteria had more effect than other indicators in determining the optimal number of areas. The Girvan-Newman's method provided more relevant results in comparison with the Fast Newman's method.

Reuse of treated wastewater is becoming a common source of extra renewable water source in regions and countries with water-scarcity. The expansion of the urban population and the increase in the sewage networks will increase the amount of municipal wastewater. The produced wastewater can become a source of renewable water that can be used for various non-potable reuse, specifically. In the current research study, the newly established Pardis city has been selected as a case study for using recycled water (reuse of treated wastewater) for sustainable water resources management. To accomplish the overall objective of the study, Geo-land method for water reuse is employed. For this study the use of regional wastewater facility instead of centralized wastewater treatment facility as well as the related capital cost savings, job opportunities, and environmental benefits were evaluated. Statistical analyses were performed based on multiple factors and classification indicators. The results showed that the highest amount of savings and financial surplus income, 36.17% and 31.25%, respectively, of the overall savings and income as the main priority and recommendation in place of water source will occur in the study area. On the other hand, savings and financial surplus for the group that does not need to use treated wastewater is only for 1.15% of the total study area which stands as the last priority.Results obtained from this study revealed that prioritization of decentralized use of wastewater for urban areas was a highly efficient plan for a significant part of residential areas, while reducing water consumption along with economic savings and increasing regional income happened. The proposed study can also be used as a sustainable water resources management decision-making tool for Pardis city officials.

Given the environmental conditions governing it, its stakeholders' expectations and its organizational mission and in the context of supplying and distribution of water and safe disposal of wastewater, the water and wastewater sector needs to grow and develop in parallel to the changes in environmental conditions. For this reason identifying the development condition of the water and wastewater sector is a necessity in the context of targeting plans and strategies from the aspect of sectorial management and senior management. This research was undertaken to identify the level of development of the water and wastewater companies (35 companies) from the aspect of the different indicators specific to the water and wastewater industry in the context of clarifying the economic plans and to enhance and improve operational activities. In the course of the study, after identifying 18 indicators, the exploratory factor analysis was undertaken and the number of indicators was reduced to 5 significant factors. Then the combined indicator was calculated according to the weight of factors and the entire sector was classified. In continuation and by applying the hierarchal clustering method the development levels of water and wastewater companies were categorized on the basis of 5 factors in three homogenized groups of development. The study's results indicate an unbalanced and non-homogenous level of development in the sector, with some companies failing to achieve the desirable level of development and needing greater attention and planning to improve the developmental conditions.

Detection of tampering in water meters as part of unauthorized usage is a key step in development of service delivery and increasing water resource productivity, and requires special attention. Data used to identify unauthorized water usage, due to tampering in water meters, include 671 subscribers with a history of meter tampering during the years 2017-2019 and a random sample of 3120 subscribers with no tampering record (clean) among Qom’s residential water users. Data analysis was conducted using subscriber’s water consumption and invoice payment history as well as supervised data mining techniques such as decision tree,  support vector machine, neural network, logistic regression, K-nearest neighbor and unsupervised clustering method. The comparison of different data mining techniques between two groups of tampered and non-tampered water meters showed that among the supervised methods, the accuracy of the models is close to each other and there is a 1–3% difference between them. On the other hand, given the percentage of correct responses among the methods, logistic regression, as the best data mining model, with correct detection of 85% of tampered and 91% of non-tampered cases as well as 89% overall accuracy on the testing data, can be used for identification of tampered meters. The study used clustering as an unsupervised technique. The subscribers were grouped into six clusters. Cluster 3 (n=160 subscribers) showed distinct behavior from the other clusters. About 86% of subscriptions in cluster 3 are tampered cases. Moreover, 18% of the tampered cases detected by logistic regression are in this cluster. Data mining techniques for identification of water meter tampering were presented in this study. Findings of the study indicated that both supervised (including response variable) and unsupervised methods (no response variable) such as clustering can be used for the identification of unauthorized water consumption In this study, logistic regression, due to its high accuracy, was selected as the most appropriate model for detection of tampered meters.

Extensive available hydrological characteristics (precipitation, temperature, streamflow data and physiographic attributes of catchments) can be used to extract hydrological similar catchments. In this research cluster analysis as a new and effective method, was used for grouping catchments into several groups or clusters. In order to understanding the hydrologic similarity, 28 characteristics (descriptors) of location, physiographic, climatic and land use of 15 catchments with heterogeneous characteristics located in the western part of the Hamoun-Jazmourian river basin were used. Selecting of characteristics were done based on the hydrological response specification which provided insight into the hydrologic performance of the catchments. In RStudio software, using PCA algorithm, the components and main characteristics were extracted, then the number of optimum clusters with the Davies-Bouldin criterion was determined and the clustering of the catchments into homogenous classes was performed using k-means algorithm. The results showed that the latitude of gravity center, area, length of main river, height of hydrometric gauge, slope and percentage of poor rangelands are as the main attributes from 28 attributes, also, the Davies-Bouldin criterion was 2.46 for the number of clusters equal to 3, which indicates the number of clusters in the k-means algorithm. After clustering the catchments, it was determined that most of the catchments in the same clusters are located in the vicinity of each other. The results of this study enable us to interpret the hydrologic behavior in the study area for purposes such as streamflow regionalization in ungauged catchments of this region and regional flood frequency analysis.

Prediction of water consumption and its effective factors is an important step in water crisis management. Studies showed that meteorological parameters are considered as the most important factor for short-term prediction of water consumption. In this research, cluster-based sliced inverse regression method was used to identify the meteorological variables affecting the household water consumption in Qom. In addition to dimension reduction, this method can be used to remove collinearity. The data consisted of seven meteorological parameters and monthly household water consumption from 2001 to 2013. Data analysis indicated that instead of seven primary variables, only two new components which are linear combinations of independent variables can be used. The negatively charged maximum wind speed and relative humidity (0.757 and 0.4) of the first component, and the negatively charged average minimum temperature (0.753) and positively charged average air temperature (0.634) of the second component had the greatest impact on the components. The regression analysis indicated that the average minimum temperature coefficient 0.018, the maximum wind speed coefficient -0.004, and determination coefficient 0.92% are significant. Comparing the method proposed in this paper with the usual method of principal component analysis (PCA) for multivariate data analysis indicated that cluster-based sliced inverse regression has fewer errors. Moreover, noticing the impact of collinearity on the outputs of neural networks, the method proposed in this paper had better performance than the usual methods and consequently predicts water consumption.