In this study Active Learning Method (ALM) as a novel fuzzy modeling approach is compared with optimized Support Vector Machine (SVM) using simple Genetic Algorithm (GA), as a well known datadriven model for long term simulation of daily streamflow in Karoon River. The daily discharge data from 1991 to 1996 and from 1996 to 1999 were utilized for training and testing of the models, respectively. Values of the Nash-Sutcliffe, Bias, R2 , MPAE and PTVE of ALM model with 16 fuzzy rules were 0.81, 5.5 m3 s -1, 0.81, 12.9%, and 1.9%, respectively. Following the same order of parameters, these criteria for optimized SVM model were 0.8, -10.7 m3 s-1, 0.81, 7.3%, and -3.6%, respectively. The results show appropriate and acceptable simulation by ALM and optimized SVM. Optimized SVM is a well-known method for runoff simulation and its capabilities have been demonstrated. Therefore, the similarity between ALM and optimized SVM results imply the ability of ALM for runoff modeling. In addition, ALM training is easier and more straightforward than the training of many other data driven models such as optimized SVM and it is able to identify and rank the effective input variables for the runoff modeling. According to the results of ALM simulation and its abilities and properties, it has merit to be introduced as a new modeling method for the runoff modeling. and Cieľom štúdie bolo porovnať možnosti dlhodobej simulácie denných prietokov v rieke Karoon pomocou novovyvinutej fuzzy metódy aktívneho učenia (Active Learning Method - ALM) a známej metódy vektormi podporených strojov (Support Vector Machine - SVM), optimalizovanej genetickým algoritmom (GA). Na tréning a testovanie modelov boli použité časové rady denných prietokov za obdobie rokov 1991 až 1996 a 1996 až 1999. Hodnoty parametrov Nash-Sutcliffe, Bias, R2 , MPAE a PTVE pre model ALM boli 0,81; 5,5 m3 s-1; 0,81; 12,9% a 1,9%. Parametre v tom istom poradí pre model SVM boli 0,8 -10,7 m3 s-1, 0,81; 7,3%; a -3,6%. Z výsledkov simulácií vyplýva, že aplikáciou metód ALM a SVM možno získať porovnateľné a akceptovateľné výsledky. Podobnosť výsledkov medzi ALM a SVM implikuje vhodnosť novovyvinutej metódy ALM pre simuláciu odtoku. Tréning ALM je ľahší a jednoduchší ako je tréning ďalších dátami riadených modelov podobného typu. Navyše algoritmus ALM je schopný identifikovať a zoradiť efektívne vstupné premenné pre modelovanie odtoku. Na základe dosiahnutých výsledkov možno metódu ALM zaradiť medzi nové, alternatívne metódy modelovania odtoku.
Complete descriptions of the particle-size distribution (PSD) curve should provide more information about various soil properties as opposed to only the textural composition (sand, silt and clay (SSC) fractions). We evaluated the performance of 19 models describing PSD data of soils using a range of efficiency criteria. While different criteria produced different rankings of the models, six of the 19 models consistently performed the best. Mean errors of the six models were found to depend on the particle diameter, with larger error percentages occurring in the smaller size range. Neither SSC nor the geometric mean diameter and its standard deviation correlated significantly with the saturated hydraulic conductivity (Kfs); however, the parameters of several PSD models showed significant correlation with Kfs. Porosity, mean weight diameter of the aggregates, and bulk density also showed significant correlations with PSD model parameters. Results of this study are promising for developing more accurate pedotransfer functions.
Estimation of discharge from ungauged catchments based on rainfall-runoff analysis is a very frequent task in engineering hydrology. Very often, design discharges are needed for streams or small rivers where no streamflow data is available (river training works, culverts, small hydropower plants, etc). This study uses a well established lumped hydrologic rainfall-runoff model to compare two different approaches in data preparation. The traditional method of manual obtainment of catchment parameters was compared to a more contemporary methodology using automation with geographic information systems, digital terrain models and available datasets, with an emphasis on open-source tools and freely available datasets. Both techniques were implemented on more than 100 catchments in Serbia to calculate storm runoff response. The results show minor differences that are insignificant compared to the time and resources saved with the automated techniques. The use of such automated methods enables the hydrologist to direct more attention to other factors that influence discharge even more than catchment parameters, such as rainfall, soil and land use data.
Paper presents comparison of the daily reference crop (grass vegetation cover) potential evapotranspiration results calculated by the two modifications of the Penman-Monteith type equation. The first modification was published in FAO recommendation (Allen at al., 1998), PM-FAO, the second is modification according to Budagovskiy (1964) and Novák (1995), PM-BN. Both are used in soil water simulation models HYDRUS-1D and GLOBAL. Calculations were performed for frost-free seasons of the years 2000-2009, using the meteorological station Gabčíkovo (South Slovakia) meteorological data and canopy characteristics. The results indicate significant differences in daily and seasonal potential evapotranspiration. Reasons for those differences are discussed; they should be in different net radiation and aerodynamic resistance estimation methods.
The paper summarises the results of the first year of the project GACR No. 205/99/1426 focused on the comparison of the pollutant concentration in the fog (low cloud ) water of two industrial regions of the Czech Republic with different atmospheric load. During the first project year the samples of the fog (cloud) water were collected and analysed. The number of samples, collected at the mountain observatories Milesovka (Mileschauer) and at Churanov, permitted the first preliminary comparison of the regions. The subject of comparison were the mean values of the pollutant concentration, the concentration of pollutants in dependence on the wind direction and in the dependence on the sector from which the air particles (and consequently also the pollutants) were transported to the considered stand. and Příspěvek shrnuje výsledky 1. roku řešení projektu GA CR 205/99/1426, který je věnován porovnání koncentrací polutantu v mlžné (oblačné) vode průmyslově odlišně zatížených oblastí ČR. V průběhu 1. roku řešení projektu byly odebrány a chemicky analyzovány vzorky mlžné (oblačné) vody. Počet odebraných a analyzovaných vzorků z horské observatoře ÚFA Milešovka a horského pracovište ÚH Churáňov umožnil první porovnání oblastí. Porovnávány byly průměrné hodnoty koncentrací polutantů, koncentrace polutantů v závislosti na směru větru a v závislosti na sektoru, ze kterého jsou vzduchové částice (tedy i polutanty) na dané
stanovište transportovány.
Although the quantification of real evapotranspiration (ETr) is a prerequisite for an appropriate estimation of the water balance, precision and uncertainty of such a quantification are often unknown. In our study, we tested a combined growth and soil water balance model for analysing the temporal dynamics of ETr. Simulated ETr, soil water storage and drainage rates were compared with those measured by 8 grass-covered weighable lysimeters for a 3-year period (January 1, 1996 to December 31, 1998). For the simulations, a soil water balance model based on the Darcy-equation and a physiological-based growth model for grass cover for the calculation of root water uptake were used. Four lysimeters represented undisturbed sandy soil monoliths and the other four were undisturbed silty-clay soil monoliths. The simulated ETr-rates underestimated the higher ETr-rates observed in the summer periods. For some periods in early and late summer, the results were indicative for oasis effects with lysimeter-measured ETr-rates higher than corresponding calculated rates of potential grass reference evapotranspiration. Despite discrepancies between simulated and observed lysimeter drainage, the simulation quality for ETr and soil water storage was sufficient in terms of the Nash-Sutcliffe index, the modelling efficiency index, and the root mean squared error. The use of a physiological-based growth model improved the ETr estimations significantly.
Understanding and modelling the processes of flood runoff generation is still a challenge in catchment hydrology. In particular, there are issues about how best to represent the effects of the antecedent state of saturation of a catchment on runoff formation and flood hydrographs. This paper reports on the experience of mapping saturated areas using measured water table by piezometers and more qualitative assessments of the state of the moisture at soil surface or immediately under it to provide information that can usefully condition model predictions. Vegetation patterns can also provide useful indicators of runoff source areas, but integrated over much longer periods of time. In this way, it might be more likely that models will get the right predictions for the right reasons.
In the study of Tomlain (1997) a soil water balance model was applied to evaluate the climate change impacts on the soil water storage in the Hurbanovo locality (Southwestern Slovakia), using the climate change scenarios of Slovakia for the years 2010, 2030, and 2075 by the global circulation models CCCM, GISS and GFD3. These calculations did not take into consideration neither the various soil properties, nor the groundwater table influence on soil water content. In this study, their calculated data were compared with those monitored at the same sites. There were found significant differences between resulting soil water storage of the upper 100 cm soil layer, most probably due to cappilary rise from groundwater at sites 2 and 3. It was shown, that the soil properties and groundwater table depth are importat features strongly influencing soil water content of the upper soil layer; thus the application of the soil water balance equation (Eq. (1)), neglecting the above mentioned factors, could lead to the results far from reality. and V práci Tomlaina (1997) bol aplikovaný bilančný model vodného režimu pôd na ohodnotenie dopadu klimatickej zmeny na vodné zásoby pôdy v lokalite Hurbanovo (juhozápadné Slovensko), použijúc scenáre klimatickej zmeny pre Slovensko pre roky 2010, 2030 a 2075, založené na globálnych cirkulačných modeloch CCCM, GISS a GFD3. V týchto výpočtoch nebol braný do úvahy vplyv vlastností pôdy a hladiny podzemnej vody na vlhkosť pôdy. V práci boli porovnané vypočítané hodnoty zásob vody s monitorovanými v tej istej lokalite. Bol nájdený význačný rozdiel medzi zásobami vody v 100-cm hornej vrstve pôdy najpravdepodobnejšie spôsobený kapilárnym prítokom od hladiny podzemnej vody v monitorovacích miestach 2 a 3. Bolo ukázané, že pôdne vlastnosti a hĺbka hladiny podzemnej vody sú dôležitými faktormi, ktoré silno ovplyvňujú vlhkosť hornej vrstvy pôdy; z toho vyplýva, že aplikácia bilančnej rovnice (rov. (1)), ktorá zanedbáva vyššie uvedené faktory, nedáva reálne výsledky.
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 of the particle size in the soil and the dry bulk density of the soil. This dependence could be extracted from the available data by various regression methods. In this paper, artificial neural networks (ANNs) and support vector machines (SVMs) were used to estimate a drying branch of a water retention curve. The paper compares the mentioned methods by estimating the water retention curves on regional scale for the Záhorská lowland in the Slovak Republic, where relatively small data set was available. The performance of the models was evaluated and compared. These computations did not fully confirm the superiority of SVMs over ANNs as is often proclaimed in the literature, because the results obtained show that in this study the ANN model performs somewhat better and is easier to handle in determining pedotransfer functions than the SVM models. Nevertheless, the results from both data-driven models are quite close, and the results show that they provide a significantly more precise outcome than a traditional multi-linear regression does., Autori sa v príspevku venujú určovaniu pedotransferových funkcií (PTF), ktoré umožňujú stanoviť body vlhkostných retenčných kriviek pôdy z ľahšie merateľných pôdnych vlastností a sú dôležitým prvkom modelovania vodného režimu pôdy. Ešte v minulej dekáde sa objavili snahy využívať na ich určenie umelé neurónové siete (UNS). Multi-layer perceptron (MLP) čiže viacvrstvový perceptrón je najčastejšie používaný model doprednej umelej neurónovej siete s kontrolovaným typom učenia. Vstupné signály prechádzajú sieťou typu MLP iba dopredným smerom, teda postupne od vrstvy k vrstve. MLP používa tri a viac vrstiev neurónov rozdelených na vstupnú, skrytú a výstupnú vrstvu s nelineárnou aktivačnou funkciou a vie rozpoznať alebo modelovať informácie, ktoré nie sú lineárne oddeliteľné alebo závislé. Novší vývoj v oblasti učiacich algoritmov poskytuje ďalšie možnosti, z ktorých sa v tomto príspevku venujeme tzv. mechanizmom podporných vektorov (Support Vector Machines - SVM). SVM využíva pri svojom kalibrovaní na riešený problém princíp tzv. štrukturálnej minimalizácie namiesto iba minimalizácie chyby - (Vapnik, 1995). Pri trénovaní siete MLP je jediným cieľom minimalizovať celkovú chybu. Pri SVM sa simultánne minimalizuje chyba aj zložitosť modelu. Použitie tohto princípu vedie zvyčajne k vyššej schopnosti generalizácie, t.j. umožneniu presnejších predpovedí pre dáta, ktoré neboli použité pri trénovaní SVM. Vhodnosť štandardnej umelej neurónovej siete, SVM a viacnásobnej lineárnej regresie sa v článku vyhodnocuje na základe údajov získaných z pôdnych vzoriek odobratých v lokalite Záhorskej nížiny. Pôvodné údaje a ich aplikáciu pri vyhodnocovaní vodného režimu pôd uvádza Skalová (2001, 2007), odkiaľ boli prevzaté vstupné dáta a to percentuálny obsah zrnitostných kategórií (I až IV podľa Kopeckého), redukovaná objemová hmotnosť (ρd) a vlhkosti pre vlkostné potenciály hw= -2.5, -56, -209, -558, -976, -3060, -15300 cm, ktoré boli stanovené laboratórne pre potreby určenia a testovania regresných závislostí. Vzhľadom na to, že pri odvodzovaní regionálnych PTF je častým prípadom nedostatok dát pre odvodenie dátovo riadených modelov, autori navrhli riešiť úlohu pomocou ansámblu MLP resp. SVM. Ansámbel dátovo riadených modelov bol vytvorený variabilným rozdelením údajov na trénovacie a validačné (validačnými údajmi sa testuje presnosť modelu vo fáze jeho tvorby, ešte sa používajú konečné testovacie dáta, ktoré neboli pri tvorbe modelu použité). Výsledky ukázali lepšie regresné schopnosti oboch dátovo riadených modelov (SVM aj MLP) voči multilineárnej regresii a o niečo lepšie výsledky boli získané z viacvrstvového perceptrónu než zo SVM., and Keďže v niektorých iných prácach mal zvyčajne vyššiu výpočtovú presnosť model založený na SVM než na UNS, autori odporúčajú pre budúci výskum preveriť vhodnosť kombinácie SVM a MLP modelov v dátovo riadenom skupinovom modeli.
The erosion, transport and deposition of sediments in small valley reservoirs represent a significant impact on their operations, mainly with regard to reducing the volume of their accumulation. The aim of this study is a comparison and uncertainty analysis of two modelling concepts for assessment of soil loss and sediment transport in a small agricultural catchment, with an emphasis on estimating the off-site effects of soil erosion resulted in sedimentation of a small water reservoir. The small water reservoir (polder) of Svacenicky Creek which was built in 2012, is a part of the flood protection measures in Turá Lúka and is located in the western part of Slovakia, close to the town of Myjava. The town of Myjava in recent years has been threatened by frequent floods, which have caused heavy material losses and significantly limited the quality of life of the local residents. To estimate the amount of soil loss and sediments transported from the basin, we applied two modelling concepts based on the USLE/SDR and WaTEM/SEDEM erosion models and validated the results with the actual bathymetry of the polder. The measurements were provided by a modern Autonomous Underwater Vehicle (AUV) hydrographic instrument. From the sediment data measured and the original geodetic survey of the terrain conducted at the time of the construction of the polder, we calculated changes in the storage volume of the polder during its four years of operation. The results show that in the given area, there has been a gradual clogging of the bottom of the polder caused by water erosion. We estimate that within the four years of the acceptance run, 10,494 m3 of bottom sediments on the Svacenicky Creek polder have accumulated. It therefore follows that repeated surveying of the sedimentation is very important for the management of the water reservoir.