International Journal of Water (9 papers in press)

Regular Issues

• Application of support vector machine for river flow estimation
  by Hasan Torabi, Reza Dehghani 
  Abstract: In recent years, the application of intelligent methods has been considered in forecasting hydrological processes. In this research, montlyh river discharge of the Kakareza, a river located in Lorestan province in the west of Iran, was forecast using support vector machine and as genetic programming inference system methods in Dehno stations. In this regard, some different combinations in the period 1979-2015 as input data for estimation of discharge in the monthly index were evaluated. Criteria of correlation coefficient, root mean square error and Nash Sutcliff coefficient to evaluate and compare the performance of methods were used. It showed that a combined structure using surveyed inelegant methods, resulted in an acceptable estimation of discharge to the Kakareza river. In addition, comparison between models shows that support vector machine has a better performance than other models in inflow estimation. In terms of accuracy, support vector machine with correlation coefficients (0.970) has more propriety than root mean square error (0.08m3/s) and Nash Sutcliff (0.94). To sum up, it is mentioned that support vector machine method has a better capability to estimate the minimum, maximum and other flow values.
  Keywords: gene expression programming; Kakareza river; support vector machine.
  
  
• Perceptions and choice of payment behaviour of consumers for rural piped water services in an eastern Indian state  
  by Tapasi Mohanty, Himanshu Sekhar Rout 
  Abstract: Poor invoicing and collection practices of rural water supply have an implication for the institution's financial sustainability. This research aims to explore the perceptions and choice of payment behaviour of consumers for rural pipe water services. The sample unit is rural household consumer. Descriptive statistics and multinomial logistic regression technique are used to find out the result. This study found that colour of the water and the interruption of supply are the main sources of consumer dissatisfaction. The concept of free water service, why should we contribute when others do not, is the main reason for non-payment. The consumers stated that reasons for connecting to piped water were found to be the key variable for all payment choices with respect to non-payment.
  Keywords: rural water services; consumer perception; water quantity and quality; revenue collection.
  DOI: 10.1504/IJW.2022.10052981
   
  
• Marine water quality index classification and prediction using machine learning framework  
  by Komathy Karuppanan 
  Abstract: Quality of marine water has a direct impact on the evolution of the ocean ecosystem, which aggravates the survival of marine organisms and animals. Additionally, the ballast water, carried in ships drawn from the open sea/ocean, may lead to bio-invasion if the quality of the water is unchecked and released into another sea/ocean. The ballast water treatment methods may sometime alter the physicochemical properties, which might be harmful to receiving water region. The objective of this paper is, therefore, to propose a new method for the estimation of marine water quality from the physiochemical and biological properties of the marine water and then a suitable computational architecture supporting machine learning techniques to assist in classifying and predicting the marine water quality. The proposed framework has evaluated various classification models to select the best-fit algorithm for this application through model training and optimizing. The finalized model called stacking classifier was then recommended for ballast water quality prediction with 100% accuracy, which could be deployed prior to the ballast water exchange.
  Keywords: data modelling; machine learning; water quality index; water quality; model optimizing; model training; prediction model.
  DOI: 10.1504/IJW.2022.10053222
   
  
• Ascertaining the impact of balancing the flood dataset on the performance of classification-based flood forecasting models for the northern districts of Bihar  
  by Vikas Mittal, T.V. Vijay Kumar, Aayush Goel 
  Abstract: Bihar is the most flood-affected state in India and the losses incurred amount to one-third of the total losses due to floods in India. These losses can be alleviated by designing models that forecast floods in real time. One such model exists that uses classification-based machine learning techniques to forecast floods in northern districts of Bihar. However, the flood dataset used was imbalanced, as the non-flooding instances far exceeded the flooding instances. This paper attempts to address this problem by balancing this data using oversampling techniques and thereafter use it for designing flood forecasting models. The objective of the paper is to ascertain whether balancing dataset improves the performance of classifiers. Experimental-based comparison showed that the classifiers performed comparatively better on the balanced dataset in terms of accuracy, precision, recall, F-measure and AUC-ROC. Further, the dataset balanced using K-Means SMOTE resulted in the maximum improvement in the performance of all classifiers.
  Keywords: natural hazards; floods; forecasting; artificial intelligence; machine learning; supervised learning; classification; SMOTE.
  
  
• Modelling hydrological processes from Sindh watershed of Kashmir valley using soil and water assessment tool  
  by Dar Sarvat Gull, Shagoofta Rasool Shah 
  Abstract: Although different endeavours have been made to address the flood and soil erosion issues across the world, hardly any efforts have been made for thorough investigation of the Sindh watershed of Kashmir region, which has suffered many disastrous floods and intense soil erosion in the past. Taking into consideration the role of hydrological models in understanding and management of watersheds, a SWAT model was applied due to its computational efficiency in complex watersheds to analyse the spatial distribution of sediment yield, quantification of runoff and soil loss at sub-basin level as well as prioritisation of sub-basins in the Sindh watershed. The model was calibrated and validated using the Sequential Uncertainty Fitting (SUFI-2) algorithm. In general, the model performance statistics showed excellent agreement between observed and simulated values of streamflow and sediment yield for both calibration and validation periods.
  Keywords: calibration; hydrological modelling; runoff; sensitivity analysis; SWAT model; Sindh watershed.
  
  
• The historical trend in temperature of a tropical river basin in Kerala, India  
  by P.P.Nikhil Raj, P.A. Azeez 
  Abstract: While the concern about climate change has been significant in academia for a long time, the first assessment of the IPCC (1990) and then the Kyoto protocol (1997) provided a substantial impetus to study climate change worldwide. Local climatic variations are manifestations of global climate changes jointly with local features. In this study, we examine the daily temperature data of the Bharathapuzha river basin for 1969-2005, collected from the India Meteorological Department, Pune, for its historical trend. Mann-Kendall rank correlation statistics were used to investigate the basin's variations in yearly, monthly and seasonal temperatures. It showed that there is a hike in the annual temperature. Significant hikes in monsoons (southwest and northeast) and winter temperatures were also observed. Although the pre-monsoon temperature showed a hike, it was not statistically significant.
  Keywords: historical climate data; temperature trend; wavelet analysis; Bharathapuzha river basin; Mann-Kendall rank correlation.
  
  
• Determining the floodway and flood fringe of the Gamasiab River, Kermanshah, Iran  
  by Mohammad Mahdi Hosseinzadeh, Somaiyeh Khaleghi, Roya Panahi 
  Abstract: All countries have specific rules for flood management and river protection. This study aimed to provide an appropriate solution for defining applicable hydraulic area and flood hazard to determine the floodway and flood fringe of Gamasiab River in Iran using HEC-RAS. The results showed that the floodway limit was corresponding to the old terraces in the reach 1. In the reaches 3 and 4, the floodway has expanded to more than 1200 meters on average and most of the rural and urban settlements in Bistoon area have been located in the floodway. Therefore, the water level was changed from 38 cm to 1 m in the reach 3 and 4. Finally, it is not possible to use a fixed water height for different rivers even in different reaches. Also the designated height was different based on the status of residential areas and topography of floodplains and riverside lands.
  Keywords: floodway; flood fringe; encroachment; floodplain; return periods; reach; cross-section; management; HEC-RAS; Gamasiab River.
  
  
• Spatial and temporal analysis of rainfall and drought in the Marathwada region of Maharashtra.  
  by Chandrakant Kadam, Udhav Bhosle, Raghunath Holambe 
  Abstract: Among all natural disasters, drought is perhaps the most precarious. The Standardized Precipitation Index (SPI) was selected as the drought index and SPI values were calculated. The entire Marathwada region's spatial and temporal dimensions were investigated. Drought variables such as frequency, duration, and intensity were used to create a thorough characterization of the drought. Drought features were studied, and long-term and short-term droughts were mathematically analysed for several time periods from 1980 to 2020. The intensity of the drought in the region has been reported to range from 39% to 59%. Mild drought was determined to be the most common category during the study period, followed by moderate, intense, and severe drought. Drought was found to be the most severe, affecting the entire region in years such as 1992, 1993, 2004, and 2016. This research study will help to better understand the drought in Marathwada as a regional phenomenon.
  Keywords: drought; standardised precipitation index; meteorological drought; drought intensity.
  
  
• Isoerodent map (R-factor) for the Isser watershed in Algeria  
  by Aziz Maaliou, Mohammed Lamine Tighilt, Liatim Mouzai 
  Abstract: The erosive force of the rains is expressed in the rainfall-runoff erosivity factor (R). Rainfall erosivity takes into account the amount and intensity of rainfall, and is most often expressed by the R factor in the USLE model and its revised version, RUSLE. The low availability of data obliges soil erosion modellers to estimate this factor on the basis of rainfall data with low temporal resolution (daily, monthly, annual averages). The aim of this study is to assess the erosivity of rainfall in the Isser watershed in Algeria in the form of the RUSLE R factor, from the best available datasets. This work represents a cartographic synthesis of the rainfall erosivity index R of the Isser watershed. Thus, this study can prove to be interesting when used with the plot of the values of this index and makes it possible to facilitate the study of the risk erosion.
  Keywords: watershed; rainfall; erosivity index; R-factor; Isoerodent-map; Isser watershed; Algeria.