Artificial neural networks and empirical equations to estimate daily evaporation: application to Lake Vegoritis,Greece

ABSTRACT

Evaporation is one of the most important components in the energy and water budgets of lakes and is a primary process of water loss from their surfaces. An artificial neural network (ANN) technique is used in this study to estimate daily evaporation from Lake Vegoritis in northern Greece and is compared with the classical empirical methods of Penman, Priestley-Taylor and the mass transfer method. Estimation of the evaporation over the lake is based on the energy budget method in combination with a mathematical model of water temperature distribution in the lake. Daily datasets of air temperature, relative humidity, wind velocity, sunshine hours and evaporation are used for training and testing of ANN models. Several input combinations and different ANN architectures are tested to detect the most suitable model for predicting lake evaporation. The best structure obtained for the ANN evaporation model is 4-4-1, with root mean square error (RMSE) from 0.69 to 1.35 mm d^?1 and correlation coefficient from 0.79 to 0.92.

EDITOR M.C. Acreman

ASSOCIATE EDITOR not assigned     

Modelling evaporation using an artificial neural network algorithm

This paper investigates the prediction of Class A pan evaporation using the artificial neural network (ANN) technique. The ANN back propagation algorithm has been evaluated for its applicability for predicting evaporation from minimum climatic data. Four combinations of input data were considered and the resulting values of evaporation were analysed and compared with those of existing models. The results from this study suggest that the neural computing technique could be employed successfully in modelling the evaporation process from the available climatic data set. However, an analysis of the residuals from the ANN models developed revealed that the models showed significant error in predictions during the validation, implying loss of generalization properties of ANN models unless trained carefully. The study indicated that evaporation values could be reasonably estimated using temperature data only through the ANN technique. This would be of much use in instances where data availability is limited. Copyright © 2002 John Wiley & Sons, Ltd.     

Modelling hourly and daily open‐water evaporation rates in areas with an equatorial climate

Evaporation rate estimation is important for water resource studies. Previous studies have shown that the radiation‐based models, mass transfer models, temperature‐based models and artificial neural network (ANN) models generally perform well for areas with a temperate climate. This study evaluates the applicability of these models in estimating hourly and daily evaporation rates for an area with an equatorial climate. Unlike in temperate regions, solar radiation was found to correlate best with pan evaporation on both the hourly and daily time‐scales. Relative humidity becomes a significant factor on a daily time‐scale. Among the simplified models, only the radiation‐based models were found to be applicable for modelling the hourly and daily evaporations. ANN models are generally more accurate than the simplified models if an appropriate network architecture is selected and a sufficient number of data points are used for training the network. ANN modelling becomes more relevant when both the energy‐ and aerodynamics‐driven mechanisms dominate, as the radiation and the mass transfer models are incapable of producing reliable evaporation estimates under this circumstance. Copyright © 2006 John Wiley & Sons, Ltd.     

Dynamic factor analysis and artificial neural network for estimating pan evaporation at multiple stations in northern Taiwan

Abstract

Evaporation is an important reference for managers of water resources. This study proposes a hybrid model (BD) that combines back-propagation neural networks (BPNN) and dynamic factor analysis (DFA) to simultaneously precisely estimate pan evaporation at multiple meteorological stations in northern Taiwan through incorporating a large number of meteorological data sets into the estimation process. The DFA is first used to extract key meteorological factors that are highly related to pan evaporation and to establish the common trend of pan evaporation among meteorological stations. The BPNN is then trained to estimate pan evaporation with the inputs of the key meteorological factors and evaporation estimates given by the DFA. The BD model successfully inherits the advantages from the DFA and BPNN, and effectively enhances its generalization ability and estimation accuracy. The results demonstrate that the proposed BD model has good reliability and applicability in simultaneously estimating pan evaporation for multiple meteorological stations.

Citation Chang, F.J., Sun, W., and Chung, C.H., 2013. Dynamic factor analysis and artificial neural network for estimating pan evaporation at multiple stations in northern Taiwan. Hydrological Sciences Journal, 58 (4), 813–825.     

Modelling evaporation processes in soils from the Huasco salt flat basin,Chile

The need to understand and simulate hydrological phenomena and their interactions, and the impact of anthropogenic and climate changes on natural environments have promoted the study of evaporation from bare soils in arid climates. In closed Altiplano basins, such as those encountered in arid and hyper arid basins in northern Chile, evaporation from shallow groundwater is the main source of aquifer depletion, and thus, its study is crucial for water resources management. The objective of this work is to understand the mechanisms of evaporation in saline soils with shallow water tables, in order to better quantify evaporation fluxes and improve our understanding of the water balance in these regions. To achieve this objective, a model that couples fluid flow with heat transfer was developed and calibrated using column experiments with saline soils from the Huasco salt flat basin, Chile. The model enables determination of both liquid and water vapour fluxes, as well as the location of the evaporation front. Experimental results showed that salt transport inside the soil profile modified the water retention curve, highlighting the importance of including salt transport when modelling the evaporation processes in these soils. Indeed, model simulations only agreed with the experimental data when the effect of salt transport on water retention curves was taken into account. Model results also showed that the evaporation front is closer to the soil surface as the water table depth reduces. Therefore, the model allows determining the groundwater level depth that results in disconnection of liquid fluxes in the vadose zone. A sensitivity analysis allowed understanding the effect of water‐flux enhancements mechanisms on soil evaporation. The results presented in this study are important as they allow quantifying the evaporation that occurs in bare soils from Altiplano basins, which is typically the main water discharge in these closed basins. Copyright © 2016 John Wiley & Sons, Ltd.     

Proposing a formula for evaporation measurement from salt water resources

Evaporation involves the change in state of a liquid to a vapour. The evaporation rate from salt‐water resources depends mostly on saturated vapour pressure above its surface. On the other hand, the saturated vapour pressure is affected by the ion activity coefficient, which stems from the chemical salt concentration of water. Thus, an increase in concentration of water results in a reduction of saturated vapour pressure. In order to acquire the actual rate of evaporation from salt‐water resources, a uniform set of evaporation pans with different but specified salt concentrations were used, in a meteorological station under the same conditions. The difference in evaporation rate of each pan can only stem from the difference in chemical salt concentration and, indeed, the molar fraction of water in each saline solution. Therefore, by applying the water molar fraction in the pressure term of fresh‐water evaporation measurement formulas, these equations were developed further for determination of evaporation rate from salt‐water resources. The proposed formulas using very simple terms seem to be suitable for determination of evaporation rate from any water (typically saline, semi‐saline and fresh water) with a satisfactory precision. Copyright © 2007 John Wiley & Sons, Ltd.     

Identifying surface water evaporation loss of inland river basin based on evaporation enrichment model

Accurately quantifying the evaporation loss of surface water is essential for regional water resources management, especially in arid and semi-arid areas where water resources are already scarce. The long-term monitoring of stable isotopes (δ¹⁸O and δ²H) in water can provide a sensitive indicator of water loss by evaporation. In this study, we obtained surface water samples of Shiyang River Basin from April to October between 2017 and 2019. The spatial and temporal characteristics of stable isotopes in surface water show the trend of enrichment in summer, depletion in spring, enrichment in deserts and depletion in mountains. The Local Evaporation Line (LEL) obtained by the regression of δ²H and δ¹⁸O in surface water has been defined by the lines: δ²H = 7.61δ¹⁸O + 14.58 for mountainous area, δ²H = 4.19δ¹⁸O − 17.85 for oasis area, δ²H = 4.08δ¹⁸O − 18.92 for desert area. The slope of LEL shows a gradual decrease from mountain to desert, indicating that the evaporation of surface water is gradually increasing. The evaporation loss of stable isotopes in surface water is 24.82% for mountainous area, 32.19% for oasis area, and 70.98% for desert area, respectively. Temperature and air humidity are the main meteorological factors affecting the evaporation loss, and the construction of reservoirs and farmland irrigation are the main man-made factors affecting the evaporation loss.     

Predicting daily pan evaporation by soft computing models with limited climatic data

Abstract

Accurate prediction of daily pan evaporation (PE) is important for monitoring, surveying, and management of water resources as well as reservoir management and evaluation of drinking water supply systems. This study develops and applies soft computing models to predict daily PE in a dry climate region of south-western Iran. Three soft computing models, namely the multilayer perceptron-neural networks model (MLP-NNM), Kohonen self-organizing feature maps-neural networks model (KSOFM-NNM), and gene expression programming (GEP), were considered. Daily PE was predicted at two stations using temperature-based, radiation-based, and sunshine duration-based input combinations. The results obtained by the temperature-based 3 (TEM3) model produced the best results for both stations. The Mann-Whitney U test was employed to compute the rank of different input combination for hypothesis testing. Comparison between the soft computing models and multiple linear regression model (MLRM) demonstrated the superiority of MLP-NNM, KSOFM-NNM, and GEP over MLRM. It was concluded that the soft computing models can be successfully employed for predicting daily PE in south western Iran.

Editor D. Koutsoyiannis     

Evaluating best evaporation estimate model for water surface evaporation in semi‐arid region,India

Evaluating performances of four commonly used evaporation estimate methods, namely; Bowen ratio energy balance (BREB), mass transfer (MT), Priestley–Taylor (PT) and pan evaporation (PE), based on 4 years experimental data, the most effective and the reliable evaporation estimates model for the semi‐arid region of India has been derived. The various goodness‐of‐fit measures, such as; coefficient of determination (R²), index of agreement (D), root mean square error (RMSE), and relative bias (RB) have been chosen for the performance evaluation. Of these models, the PT model has been found most promising when the Bowen ratio, β is known a priori, and based on its limited data requirement. The responses of the BREB, the PT, and the PE models were found comparable to each other, while the response of the MT model differed to match with the responses of the other three models. The coefficients, β of the BREB, µ of the MT, α of the PT and K_P of the PE model were estimated as 0·07, 2·35, 1·31 and 0·65, respectively. The PT model can successfully be extended for free water surface evaporation estimates in semi‐arid India. A linear regression model depicting relationship between daily air and water temperature has been developed using the observed water temperatures and the corresponding air temperatures. The model helped to generate unrecorded water temperatures for the corresponding ambient air temperatures. Copyright © 2007 John Wiley & Sons, Ltd.     

River evaporation and corresponding heat fluxes in forested catchments

River water temperature is a very important variable in ecological studies, especially for the management of fisheries and aquatic resources. Temperature can impact on fish distribution, growth, mortality and community dynamics. River evaporation has been identified as an important heat loss and a key process in the thermal regime of rivers. However, its quantification remains a challenge, mainly because of the difficulty of making direct measurements. The objectives of this study were to characterize the evaporative heat flux at different scales (brook vs river) and to improve the estimation of the evaporative heat flux in a stream temperature model at the hourly timescale. Using a mass balance approach with floating minipans, we measured river evaporation at an hourly timescale in a medium‐sized river (Little Southwest Miramichi) and a small brook (Catamaran Brook) in New Brunswick, Canada. With these direct measurements of evaporation, we developed mass transfer equations to estimate hourly evaporation rates from microclimate conditions measured 2 m above the stream. During the summer 2012, river evaporation was more important for the medium‐sized river with a mean daily evaporation rate of 3.0 mm day^?1 in the Little Southwest Miramichi River compared with that of 1.0 mm day^?1 in Catamaran Brook. Evaporation was the main heat loss mechanism in the two studied streams and was responsible for 42% of heat losses in the Little Southwest Miramichi River and 34% of heat losses in Catamaran Brook during the summer. Copyright © 2013 John Wiley & Sons, Ltd.     

Bare soil evaporation under high evaporation demand: a proposed modification to the FAO-56 model

Abstract

This study evaluates the evaporation component of the FAO-56 model under high evaporation demand. To perform this, two data sets were used as field evaluation, and a second model was used for comparison (a model based on the square root of time, SRT). The results show that although FAO-56, the field data and the SRT model present similar cumulative evaporation over the study period (approximately one month), when the data are analysed daily, FAO-56 overestimated evaporation at the beginning of the process and underestimated it at the end. A correction for FAO-56 is proposed to amend the mismatch between FAO-56 and the field-measured data under high evaporation conditions. Consequently, the parameters used by the FAO-56 evaporation component are discussed.

Citation Torres, E. A. & Calera, A. (2010) Bare soil evaporation under high evaporation demand: a proposed modification to the FAO-56 model. Hydrol. Sci. J. 55(3), 303–315.     

鄱阳湖夏季水面蒸发与蒸发皿蒸发的比较

水面蒸发是湖泊水量平衡要素的重要组成部分.基于传统蒸发皿观测蒸发不能代表实际水面蒸发,而实际水面蒸发特征仍不清楚.本研究基于涡度相关系统观测的鄱阳湖水体实际水面蒸发过程,在小时和日尺度分析了水面蒸发的变化规律及其主要影响因子,并与蒸发皿蒸发进行比较.研究表明,实际水面蒸发日变化波动剧烈,变化范围在0~0.4 mm/h之间.水面蒸发的日变化特征主要受风速的影响.鄱阳湖8月份日水面蒸发量与蒸发皿蒸发量在总体趋势上具有很好的一致性.8月份平均日水面蒸发速率(5.90 mm/d)比蒸发皿蒸发速率(5.65 mm/d)高4.6%.水面日蒸发量与蒸发皿蒸发量的比值在8月上、中、下旬平均值分别为1.24、1.00、0.92,呈现下降的趋势.鄱阳湖夏季水面日蒸发量与风速和相对湿度相关性显著,而蒸发皿蒸发与净辐射、气温、饱和水汽压差和相对湿度均呈显著相关.这是由于蒸发皿水体容积小,与湖泊相比其水体热存储能力小,因此更容易受到环境因子的影响.     

Short‐term inflow forecasting using an artificial neural network model

The primary objective of this study is to investigate the possibility of including more temporal and spatial information on short‐term inflow forecasting, which is not easily attained in the traditional time‐series models or conceptual hydrological models. In order to achieve this objective, an artificial neural network (ANN) model for short‐term inflow forecasting is developed and several issues associated with the use of an ANN model are examined in this study. The formulated ANN model is used to forecast 1‐ to 7‐h ahead inflows into a hydropower reservoir. The root‐mean‐squared error (RMSE), the Nash–Sutcliffe coefficient (NSC), the A information criterion (AIC), B information criterion (BIC) of the 1‐ to 7‐h ahead forecasts, and the cross‐correlation coefficient between the forecast and observed inflows are estimated. Model performance is analysed and some quantitative analysis is presented. The results obtained are satisfactory. Perceived strengths of the ANN model are the capability for representing complex and non‐linear relationships as well as being able to include more information in the model easily. Although the results obtained may not be universal, they are expected to reveal some possible problems in ANN models and provide some helpful insights in the development and application of ANN models in the field of hydrology and water resources. Copyright © 2002 John Wiley & Sons, Ltd.     

Daily pan evaporation modelling using multi‐layer perceptrons and radial basis neural networks

This paper reports on investigations of the abilities of three different artificial neural network (ANN) techniques, multi‐layer perceptrons (MLP), radial basis neural networks (RBNN) and generalized regression neural networks (GRNN) to estimate daily pan evaporation. Different MLP models comprising various combinations of daily climatic variables, that is, air temperature, solar radiation, wind speed, pressure and humidity were developed to evaluate the effect of each of these variables on pan evaporation. The MLP estimates are compared with those of the RBNN and GRNN techniques. The Stephens‐Stewart (SS) method is also considered for the comparison. The performances of the models are evaluated using root mean square errors (RMSE), mean absolute error (MAE) and determination coefficient (R²) statistics. Based on the comparisons, it was found that the MLP and RBNN computing techniques could be employed successfully to model the evaporation process using the available climatic data. The GRNN was found to perform better than the SS method. Copyright © 2008 John Wiley & Sons, Ltd.     

Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques

Evaporation, as a major component of the hydrologic cycle, plays a key role in water resources development and management in arid and semi-arid climatic regions. Although there are empirical formulas available, their performances are not all satisfactory due to the complicated nature of the evaporation process and the data availability. This paper explores evaporation estimation methods based on artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) techniques. It has been found that ANN and ANFIS techniques have much better performances than the empirical formulas (for the test data set, ANN R² = 0.97, ANFIS R² = 0.92 and Marciano R² = 0.54). Between ANN and ANFIS, ANN model is slightly better albeit the difference is small. Although ANN and ANFIS techniques seem to be powerful, their data input selection process is quite complicated. In this research, the Gamma test (GT) has been used to tackle the problem of the best input data combination and how many data points should be used in the model calibration. More studies are needed to gain wider experience about this data selection tool and how it could be used in assessing the validation data.     

Quantifying evaporation in a permeable pavement system

Studies quantifying evaporation from permeable pavement systems are limited to a few laboratory studies and one field application. This research quantifies evaporation for a larger field application by measuring the water balance from lined permeable pavement sections. The U.S. Environmental Protection Agency constructed a 0.4 ha parking lot in Edison, NJ, that incorporated three different permeable pavement types in the parking lanes – permeable interlocking concrete pavers (PICP), pervious concrete (PC) and porous asphalt (PA). An impermeable liner installed 0.4 m below the surface in four 11.6 m by 4.74 m sections per each pavement type captures all infiltrating water and routes it to collection tanks that can contain events up to 38 mm. Each section has a design impervious area to permeable pavement area ratio of 0.66:1. Pressure transducers installed in the underdrain collection tanks measured water level for 24 months. Level was converted to volume using depth‐to‐volume ratios for individual collection tanks. Using a water balance approach, the measured infiltrate volume was compared to rainfall volume on an event basis to determine the rainfall retained in the pavement strata and underlying aggregate. Interevent evaporation created additional storage in the pavement and aggregate layers. Events were divided into three groups based on antecedent dry period (ADP) and three 4 month groups of potential evaporation based on historical monthly pan evaporation records. There was a significant difference in rainfall retained among the various combinations of ADP and potential evaporation groups. More rainfall was retained in the pavement and aggregate layers as time between events increased and during warmer months with larger potential evaporation. Average cumulative evaporation from the permeable pavement sections for 134 rainfall events in 24 months was 5.2% of the cumulative rainfall volume, and the range was 2.4–7.6%. Each PC section had more annual evaporation than any individual PICP or PA section. While measureable, evaporation is a small contribution to the total water budget on an annual basis for these systems. Copyright © 2014 John Wiley & Sons, Ltd.     

Estimation of evaporation from the Dead Sea

A project to link the Dead Sea to the Red Sea via a canal is undergoing extensive study. As part of this study, a method to estimate evaporation from the Dead Sea is required as it is a hypersaline lake in which standard methods cannot be applied. Two methods based on Penman and Dalton formulae were examined. The method derived here is a modified Penman model that estimates the evaporation as a function of salinity, humidity, air temperature and wind speed. Other parameters such as water temperature are included implicitly in the model. The results obtained were verified as satisfactory agreement was achieved by comparison with previous measurements. A short‐cut relationship to estimate evaporation as a function of salinity only was also derived. Copyright © 1999 John Wiley & Sons, Ltd.     

南四湖蒸发实验站蒸发器折算系数研究

根据山东省南四湖蒸发实验站历年实测资料,分析了大型蒸发池与各型号蒸发器水面蒸发量的折算系数及其变化规律,并对影响蒸发量折算系数的蒸发器安装方式、结构及制作材料等进行了研究和探讨。在此基础上,综合出了适合本地区的各型号蒸发器的蒸发量折算系数,可在水资源分析评价和工程水文计算设计中应用。     

Influence of below-cloud evaporation on stable isotopes of precipitation in the Yellow River source region

The study of below-cloud evaporation effects under clouds in the Yellow River source region is of great significance for regional water resource generation as well as for water resource security in the arid and semi-arid regions of northern China. In this study, we quantitatively assessed the evapotranspiration effect in the Yellow River source region from March to November based on the improved Stewart model. The study concluded that: (1) below-cloud evaporation was slightly higher in summer than in other seasons (residual fractions of raindrop evaporation were 80.57% in summer, 81.12% in spring, and 84.2% in autumn, respectively); and (2) sub-cloud evaporation diminishes with increasing altitude (residual fractions of raindrop evaporation were 83.09% in the western part of the area, 81.82% in the central part of the area, and 81.36% in the eastern part of the area, respectively). (3) The total linear index between study areas f and ∆d is 2.24, where f > 95%, it is 1.19; that is, the evaporation of raindrops increases by 1% and the reduction in the excess of mercury by about 2‰. (4) Local meteorological factors (temperature, precipitation, and relative humidity) and raindrop diameter have a cross-influence on below-cloud evaporation, with relative humidity having the most significant effect, with the highest correlation coefficient of 3.03 when relative humidity is less than 70%. The results of the study can provide a parameter basis for hydrological and climatic models in the Yellow River Basin.     

鄱阳湖水面蒸发量的计算与变化趋势分析(1955-2004年)

利用器测折算法与气候模式法,分别计算鄱阳湖周围康山、棠荫、都昌、星子、湖口5站的单站水面蒸发量,以5站两种方法计算值的平均值代表鄱阳湖大湖面的水面蒸发量,求得鄱阳湖1955-2004年各月的水面蒸发量和蒸发水量,结果为：多年平均年蒸发量1081．2 mm．年蒸发水量27．06×10~8 m~3．对年、月水面蒸发量在近50年来的变化趋势进行了分析,表明除5月份外,其他各月蒸发量和年蒸发量均呈逐渐减少趋势,年蒸发量平均每年减小2．79 mm,年蒸发水量平均减少0．05×10~8 m~3,对湖区水资源持续利用和湖泊环境将产生明显影响．对水面蒸发量递减原因进行了初步探讨．