• Water for future
• /
• v.5 no.2
• /
• pp.44-48
• /
• 1972

This article includes hydrometeorological analysis of evapotranspiration and precipitation, which are used available basic data for a certain basin water budget. Evapotranspiration on water surface, bare soil and rice fields is directly measured by Thornthwaite's type Lysimeter and on water surface and vegetables computed using the Penman's equation. Areal precipitation is analized through the Thiessen method and arithmatic mean method. It is interested fact that the correlation coefficient for Class A Pan's evaporation vs. the actual evapotranspiration is the highest value among the coefficients for different type evaporimeter and Penman equation, and evaporation ratio on rice field's evapotranspiration vs. Class A Pan's evaporation is 1. 5-2. 3.

• Smart Structures and Systems
• /
• v.30 no.4
• /
• pp.421-432
• /
• 2022

Regarding the high significance of correct pan evaporation modeling, this study introduces two novel neuro-metaheuristic approaches to improve the accuracy of prediction for this parameter. Vortex search algorithms (VSA), sunflower optimization (SFO), and stochastic fractal search (SFS) are integrated with a multilayer perceptron neural network to create the VSA-MLPNN, SFO-MLPNN, and SFS-MLPNN hybrids. The climate data of Arcata-Eureka station (operated by the US environmental protection agency) belonging to the years 1986-1989 and the year 1990 are used for training and testing the models, respectively. Trying different configurations revealed that the best performance of the VSA, SFO, and SFS is obtained for the population size of 400, 300, and 100, respectively. The results were compared with a conventionally trained MLPNN to examine the effect of the metaheuristic algorithms. Overall, all four models presented a very reliable simulation. However, the SFS-MLPNN (mean absolute error, MAE = 0.0997 and Pearson correlation coefficient, R_P = 0.9957) was the most accurate model, followed by the VSA-MLPNN (MAE = 0.1058 and R_P = 0.9945), conventional MLPNN (MAE = 0.1062 and R_P = 0.9944), and SFO-MLPNN (MAE = 0.1305 and R_P = 0.9914). The findings indicated that employing the VSA and SFS results in improving the accuracy of the neural network in the prediction of pan evaporation. Hence, the suggested models are recommended for future practical applications.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.7 no.1
• /
• pp.91-97
• /
• 2005

Class A evaporation pan has been used throughout the world to measure free water evaporation mainly by manual observation once a day. In this study, a new automatic water level measurement method is used for understanding of free water evaporation and numerical analysis. This new technique measures the weight of buoyancy bar in water, and does not need calibration because it is not affected by water density change with water temperature. Field observations of evaporation were made near Haenam Meteorological Station over paddy field located in southwestern Korea from 20 April to 30 May 2004 and the data from ten clear days (16 - 25 May) were used for this analysis. The observed total evaporation was about 50.7mm during this period whereas the estimated from an empirical equation was 50.4mm. As expected, the pan evaporation is well correlated with wind speed and the vapor pressure deficit between the water surface and the air.

• Water for future
• /
• v.6 no.1
• /
• pp.5-12
• /
• 1973

A simple regression formula for estimating the lake evaporation rate from the copper-plated pan (diameter 20cm, height 10cm) is derived. A comparison with other formulae indicates that the formula is more accurate than others. An annual map of man evaporation in Korean peninsula has been prepared using the relation. It demonstrates the areal average distribution of mean annual evaporation from a free water surface with no heat storage effect and avected energy owing to differences in the temperature of in-and outflow. The mean annual ratio of the lake to the copper-plated pan evaporation is found to be 0.64. The ratio varies with local conditions from 0.62 to 0.66, and hence it can be considered fairly uniform. However the seasonal variation of the ratio appears to be rather significant. It changes from the lowest of 0.61 to the highest of 0.75.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.115-119
• /
• 2006

The goal of this research is to develop and apply the generalized regression neural networks model (GRNNM) embedding genetic algorithm (GA) for pan evaporation, which is missed or ungaged and for the alfalfa reference evapotranspiration, which is not measured in South Korea. The GRNNM-GA is evaluated using the training, the testing, and reproduction performance respectively for the estimation of the PE and the alfalfa reference evapotranspiration. Since the observed data of the alfalfa reference evapotranspiration using lysimeter have not been measured for a long time in South Korea, the PM method is used to assume and estimate the observed alfalfa reference evapotranspiration. From this research, we evaluate the impact of the limited climatical variables on the accuracy of the GRNNM-GA. We should, furthermore, construct the credible data of the PE and the alfalfa reference evapotranspiration and suggest the reference data for irrigation and drainage networks system in South Korea.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1147-1150
• /
• 2008

The goal of this research is to apply the neural networks models for the disaggregation of the pan evaporation (PE) data, Republic of Korea. The neural networks models consist of the support vector machines neural networks model (SVM-NNM) and multilayer perceptron neural networks model (MLP-NNM), respectively. The SVM-NNM in time series modeling is relatively new and it is more problematic in comparison with classifications. In this study, The disaggregation means that the yearly PE data divides into the monthly PE data. And, for the performances of the neural networks models, they are composed of training, cross validation, and testing data, respectively. From this research, we evaluate the impact of the SVM-NNM and the MLP-NNM for the disaggregation of the nonlinear time series data. We should, furthermore, construct the credible data of the monthly PE data from the disaggregation of the yearly PE data, and can suggest the methodology for the irrigation and drainage networks system.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1439-1442
• /
• 2010

Time-lag recurrent neural networks model (Time-Lag RNNM) is used to estimate daily pan evaporation (PE) using limited climatic variables such as max temperature ($T_{max}$), min temperature ($T_{min}$), mean wind speed ($W_{mean}$) and mean relative humidity ($RH_{mean}$). And, for the performances of Time-Lag RNNM, it is composed of training and test performances, respectively. The training and test performances are carried out using daily time series data, respectively. From this research, we evaluate the impact of Time-Lag RNNM for the modeling of the nonlinear time series data. We should, thus, construct the credible data of the daily PE using Time-Lag RNNM, and can suggest the methodology for the irrigation and drainage networks system. Furthermore, this research represents that the strong nonlinear relationship such as pan evaporation modeling can be generalized using Time-Lag RNNM.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1560-1563
• /
• 2010

The goal of this research is to apply the neural networks model for the disaggregation of the pan evaporation (PE) data, Republic of Korea. The neural networks model consists of support vector machine neural networks model (SVM-NNM). The disaggregation means that the yearly PE data divides into the monthly PE data. And, for the performances of the neural networks model, it is composed of training and test performances, respectively. The training and test performances consist of the historic, the generated, and the mixed data, respectively. From this research, we evaluate the impact of SVM-NNM for the disaggregation of the nonlinear time series data. We should, furthermore, construct the credible data of the monthly PE from the disaggregation of the yearly PE data, and can suggest the methodology for the irrigation and drainage networks system.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.25 no.2
• /
• pp.86-95
• /
• 1983

Evapotranspiration is a major factor determining the water consumption in the rice fields. Therefore, realistic evapotranspiration estimates are important to the agricultural water resources planning. In Korea, however, the Blaney-Criddle formula, which was developed under the meteorological condition of western arid United States and the upland cultivation, has been widely used to estimate evapotranspiration from paddy fields. Hence, it has considered that the Blaney-Criddle formula would not be the proper method for the Korean paddy condition. The purpose of this study is to select the most appropriate and realistic method for estimating evapotranspiraion from paddy field in Korea and to derive crop coefficients using the chosen method. The results are summerized as follows. 1. Total seasonal-average evapotranspiration by the field observation was 660mm for Tongil and 621. Ornm for the Japonica variety of rice. The amount of evapotranspiration for Tongil variety was 6% larger than that of the Japonica variety. 2. There was no significant differences in the amount of evapotranspiration among early, middle and late mature varieties, that is, early 638mm, middle 627mm and late 630mm for the whole growing season. 3. The rate of peak evapotranspiration appeared at the beginning of August and was in the range of 7.7-8. Omm/day according to the different mature varieties. 4. The correlation between pan evaporation data and the calculated evapotranspiration using related meteorological data from various methods suggested such as Radiation (FAO), Hargreaves, Christiansen, Hargreaves-Christiansen, Jensen-Haise, showed high statistic significance. Therefore, it seemed to use those formulars in estimating evapotranspiration inste4 of using pan evaporation data. 5. It was concluded from the analysis of field data that the evapotranspiration estimate for Blaney-Criddle method might not be appropriate in Korea. On the other hand, Penman equation showed more accurate estimation at the flourishing stage of rice than the pan evaporation method. 6. The crop coefficients for the Penman and pan-evaporation method were obtained by graphical representation.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.37-47
• /
• 2023

Indirect determination of pan evaporation (PE) has been highly regarded, due to the advantages of intelligent models employed for this objective. This work pursues improving the reliability of a popular intelligent model, namely multi-layer perceptron (MLP) through surmounting its computational knots. Available climatic data of Fresno weather station (California, USA) is used for this study. In the first step, testing several most common trainers of the MLP revealed the superiority of the Levenberg-Marquardt (LM) algorithm. It, therefore, is considered as the classical training approach. Next, the optimum configurations of two metaheuristic algorithms, namely cuttlefish optimization algorithm (CFOA) and teaching-learning-based optimization (TLBO) are incorporated to optimally train the MLP. In these two models, the LM is replaced with metaheuristic strategies. Overall, the results demonstrated the high competency of the MLP (correlations above 0.997) in the presence of all three strategies. It was also observed that the TLBO enhances the learning and prediction accuracy of the classical MLP (by nearly 7.7% and 9.2%, respectively), while the CFOA performed weaker than LM. Moreover, a comparison between the efficiency of the used metaheuristic optimizers showed that the TLBO is a more time-effective technique for predicting the PE. Hence, it can serve as a promising approach for indirect PE analysis.