Milan Cisty

• Slovak University of Technology in Bratislava

In the past, river restoration mainly focused on flood protection and somewhat ignored the degradation of river ecosystems, e.g., the habitats of river organisms. In recent decades, however, there has been an increased effort to carefully assess the quality of aquatic habitats as well. The authors have collected data from mountain and sub-mountain...

This study compares the calculation of snow water equivalent (SWE) using machine learning algorithms with the conventional degree-day method. The study uses machine learning techniques such as LASSO, Random Forest, Support Vector Machines, and CatBoost. It proposes an innovative use of feature engineering (FE) to improve the accuracy and robustness...

The authors of this study investigated the use of machine learning (ML) and feature engineering (FE) techniques to accurately determine FAO reference evapotranspiration ( ETo ) with a minimal number of climate variables being measured. The recommended techniques for areas with insufficient measurements are based solely on daily temperature readings...

The paper presents two methods that simplify the estimation of the water retention curves. The case study is evaluated for the soils of Záhorská lowland in the paper. These methods are based on the supposed dependence of the soil water content on the percentage content of the 1st, 2nd, 3rd and 4th Kopecký grain categories, and the dry bulk density....

The present study deals with the similarity of catchments, which is a preliminary investigation before performing various water resource analyses and computations regarding other catchments, e.g., catchments’ similarity may be utilized in the context of analogous calculations of river flows in catchments without measured flows. In this paper, the p...

In this work, a method is proposed that uses machine learning techniques intending to make existing soil moisture time series complete. Authors are assuming and solving the usual situation, in which only data irregularly measured are available. Soil moisture is one of the determining variables of the stress on various ecosystems and agriculture sys...

Measured records of suspended sediment concentrations are vital information to support water management activities. However, these measured time series are often incomplete and, as such, are not suitable for some analyses. This paper sets out the options for modelling suspended sediment concentrations to determine them in periods when measurements...

The paper deals with differences between two types of machine learning river flow modelling, i.e., their simulation and prediction. In this paper, “simulation” means a determination of river flows from only meteorological data. The second type of modelling, i.e., prediction, additionally includes preceding flows in the input data. Preceding flows a...

A soil drought corresponds to such an amount of water content in soil when plants suffer from a chronic water deficiency. In this work a spatial indicator of the threat of droughts, namely the available water capacity of a soil, is proposed and evaluated. Data from a soil survey and data measured in a laboratory were used for the development of the...

In this work, an optimal design of a water distribution network is proposed for large irrigation networks. The proposed approach is built upon an existing optimization method (NSGA-II), but the authors are proposing its effective application in a new two-step optimization process. The aim of the paper is to demonstrate that not only is the choice o...

The problem of drought probability has been investigated by several authors, who have usually analysed droughts using various drought indices such as the Standard Precipitation Index. Various aspects of time series of such indices (intensity, severity and duration) were investigated by several authors using a copula method. Because such analysis is...

This study focuses on the reclassification of a soil texture system following a hybrid approach in which the conventional particle-size distribution (PSD) models are coupled with a random forest (RF) algorithm for achieving more generally applicable and precise outputs. The existing parametric PSD models that could be used for this purpose have var...

This review paper will deal with the possibilities of applying the R programming language in water resources and hydrologic applications in education and research. The objective of this paper is to present some features and packages that make R a powerful environment for analysing data from the hydrology and water resources management fields, hydro...

There are many problems related to pipe network rehabilitation, the main one being how to provide an increase in the hydraulic capacity of a system. Because of its complexity the conventional optimizations techniques are poorly suited for solving this task. In recent years some successful attempts to apply modern heuristic methods to this problem h...

Assessments of irrigation water distribution networks can be approached with two different ways. First approach represents demand-driven analysis, where on the first place lies nodal demand regardless from actual pressure. The other way represents pressure driven analysis which recognizes the relation between nodal heads and nodal flows. This appro...

Various theoretical parametric particle size distribution models exist which could help with soil texture classification transformations. However, there is usually no best parametric model which is superior under all circumstances. Various parametric models frequently show different degrees of precision in different soils and under different enviro...

Ensemble is one of the most widely used methods for improving the performance of data-driven regression models. Two ensemble methods, i.e. bagging and additive regression are applied in this paper for improving the performance of a single regression model for evaluating pedotransfer functions used in soil hydrology. The experimental results with da...

A key physical property used in the description of a soil-water regime is a soil water retention curve, which shows the relationship between the water content and the water potential of the soil. Pedotransfer functions are based on the supposed dependence of the soil water content on the available soil characteristics, e.g., on the relative content...

A key physical property used in the description of a soil-water regime is a soil water retention curve, which shows the relationship between the water content and the water potential of the soil. Pedotransfer functions are based on the supposed dependence of the soil water content on the available soil characteristics. In this paper, artificial neu...

This paper is testing a data-driven technique for forecasting day-ahead streamflow time series based on a self-organizing map (SOM) neural network and multi-layer perceptron (MLP) models. SOM is used to cluster the data according to its similarity in order to obtain similar input regions. The MLP models for regression are constructed for the catego...

The paper proposes a new multiphase methodology based on a combination of differential evolution (DE) and particle swarm optimization (PSO) called DEPSO, for solving the optimal design of a water distribution system. Its effectiveness is determined by applying two basic principles - A multi-step optimization procedure and the DEPSO methodology as a...

Various heuristic and deterministic algorithms have been developed in the past two decades for solving optimization problems and applied to the design of water distribution systems. Nevertheless, there is still some uncertainty about finding a generally trustworthy method that can consistently find solutions which are really close to the global opt...

Information's about soil water content are in the planning of water resources and management very valuable. Modeling and predicting soil water transfer is very important in agriculture or hydrology - e.g. for purposes of the effective irrigation management. Many tried and proven methods of estimating or measuring soil moisture are available. The ch...

This work is focused on evaluation and effectiveness comparison of two different heuristic algorithms in context of hybrid model used for optimization of the pressurized water distribution systems: genetic algorithm (GA) and harmony search methodology (HS). The optimization of the water distribution system is a complex problem which involves determ...

The problems involved in the optimal design of water distribution networks belong to a class of large combinatorial optimization problems. Various heuristic and deterministic algorithms have been developed in the past two decades for solving optimization problems and applied to the design of water distribution systems. Nevertheless, there is still...

In its first part this chapter briefly reviews applications of the Harmony Search (HS) optimization method in the irrigation industry. As will be seen, HS can be applied in similar problem areas as other heuristics. Therefore, other heuristic method applications in the irrigation industry are mentioned in this part of the chapter to encourage the u...

A new optimization model for determining the minimum cost for the design of water distribution systems is described in the paper based on a combination of linear programming methodology (LP) and a genetic algorithms approach (GA). The optimal design of looped hydraulic pipe networks belongs to the class of large combinatorial optimization problems...

A new optimization model for determining the minimum cost for the design of water distribution systems is described in the paper based on a combination of linear programming methodology (LP) and a genetic algorithms approach (GA). A many different heuristic algorithms have been developed in the last two decades and applied to the design of water di...

The problems involved in the optimal design of water distribution networks belong to a class of large combinatorial optimization problems. Various heuristic and deterministic algorithms have been developed in the last two decades for solving optimization problems and applied to the design of water distribution systems. Nevertheless, there is still...

Using of the heuristic search methods is very popular in various water resources management problems and it is being applied on different single and multi-objective tasks. Especially when multi-objective optimization tasks are solving there is in some applications smoky possibility evaluate how close particular method gets to global optimum. For in...

A new optimization model for determining the minimum cost for the design of water distribution systems is described in the paper based on a combination of linear programming methodology (LP) and a genetic algorithms approach (GA). The optimal design of looped hydraulic pipe networks belongs to the class of large combinatorial optimization problems...

Automated calibration of the simulation model of irrigation projects by harmony search optimization The paper deals with calibration of the simulation models of hydraulic part of an irrigation project. Calibrated simulation model can be used in design, reconstruction, enlargement or maintenance of the pressurized irrigation systems. Computer model...

Hydrological processes are generally nonlinear and are governed by general physical laws. It is difficult to observe, describe and model them. Modeling, simulating and predicting water content in soil is essential for development of the agricultural information systems or in hydrology. One of the possibilities of management of soil moisture regime...

Soil moisture content is an important hydrologic component. The paper presents two data driven methods, which makes possibility to estimate water retention curves important for soil moisture forecasting for the soils of Záhorská lowland. These methods are based on supposed dependence of the water content on the percentage content of the Kopecký gra...

Flow forecasting is important part of water management, whether in economical terms and also in terms of security, which is currently very actual, because in last few years was Slovak republic (SR) for nearly every year affected by flooding. Flows are very important part of the water balance of the SR, assessed each year and providing information o...

Water supply and distribution systems are key elements of any urban development or sustainable agricultural development in the case of the irrigation systems. It is not surprising then that various analyses and design techniques for the econmic and efficient design of hydraulic networks have received attention over the years. A possible approach to...

A water distribution network is a system containing pipes, reservoirs, pumps, and valves of different types, which are connected to each other to provide water to consumers. In the case of the design of a pipe network the optimization problem can be stated as follows: minimize the cost of the network components subject to the satisfactory performan...