Evaporation Estimates Research Articles

Crop yield prediction with environmental and chemical variables using optimized ensemble predictive model in machine learning

Abstract Enhanced crop yield prediction is necessary for agronomists to make dynamic premonsoon decisions. The input variables precipitation, temperature, evaporation, wind speed, and chemical use influence crop yield estimations. In this study, we analyzed the correlation between crop yield and input features, and scaled up the prediction power of the crop yield model using optimized ensemble learning for machine learning. The proposed model is expected to deal with the limitations of existing models by minimizing effort and data requirements. It achieved better performance than the other approaches with a MSE (Mean Squared Error) of 42963, MAE (Mean Absolute Error) of 87, and R 2 (Coefficient of Determination) of 0.96. The findings of this study have important suggestions for agricultural management and policy-making. The proposed model offers possible applications for enhancing crop yield prediction across various perspectives, thereby assisting more informed decision-making in agriculture.

Unraveling the discrepancies between Eulerian and Lagrangian moisture tracking models in monsoon- and westerly-dominated basins of the Tibetan Plateau

Abstract. Eulerian and Lagrangian numerical moisture tracking models, which are primarily used to quantify moisture contributions from global sources to specific regions, play a crucial role in hydrology and (paleo)climatology studies on the Tibetan Plateau (TP). Despite their widespread applications in the TP region, potential discrepancies in their moisture tracking results and their underlying causes remain unexplored. In this study, we compare the most widely used Eulerian and Lagrangian moisture tracking models over the TP, i.e., WAM2layers (the Water Accounting Model – 2 layers) and FLEXPART-WaterSip (the FLEXible PARTicle dispersion model coupled with the “WaterSip” moisture source diagnostic method), specifically focusing on a basin governed by the Indian summer monsoon (Yarlung Zangbo River basin, YB) and a westerly-dominated basin (upper Tarim River basin, UTB). Compared to the bias-corrected FLEXPART-WaterSip, WAM2layers generally estimates higher moisture contributions from westerly-dominated and distant sources but lower contributions from local recycling and nearby sources downwind of the westerlies. These differences become smaller with higher spatial and temporal resolutions of forcing data in WAM2layers. A notable advantage of WAM2layers over FLEXPART-WaterSip is its closer alignment of estimated moisture sources with actual evaporation, particularly in source regions with complex land–sea distributions. However, the evaporation biases in FLEXPART-WaterSip can be partly corrected through calibration with actual surface fluxes. For moisture tracking over the TP, we recommend using high-resolution forcing datasets, prioritizing temporal resolution over spatial resolution for WAM2layers, while for FLEXPART-WaterSip, we suggest applying bias corrections to optimize the filtering of precipitation particles and adjust evaporation estimates.

Estimating the sensitivity of the Priestley–Taylor coefficient to air temperature and humidity

Abstract. The Priestley–Taylor (PT) coefficient (α) is generally set as a constant value or is fitted as an empirical function of environmental variables, and it can bias the evaporation estimation or hydrological projections under global warming. By using an atmospheric boundary layer model, this study derives a theoretical and parameter-free equation for estimating α as a function of air temperature (T) and specific humidity (Q). With observations from several waterbodies and non-water-limited land sites, we demonstrate that, in addition to estimating the value of α well, the derived expressions can also capture the sensitivity of α to T and Q, that is, dα/dT and dα/dQ. α is generally negatively associated with T and Q, in which regard T plays a more fundamental role in controlling α behaviors. Based on climate model data, we further show that this negative relationship between α and T is of great importance for long-term hydrological predictions. We also provide a lookup graph for practical and broad uses to directly find the values of dα/dT and dα/dQ under specific conditions. Overall, the derived expression gives a physically clear and straightforward approach to quantify changes in α, which is essential for PT-based hydrological simulation and projections.

On the importance of plant phenology in the evaporative process of a semi-arid woodland: could it be why satellite-based evaporation estimates in the miombo differ?

Abstract. The miombo woodland is the largest dry woodland formation in sub-Saharan Africa, covering an estimated area of 2.7–3.6 million km2. Compared to other global ecosystems, the miombo woodland demonstrates unique interactions between plant phenology and climate. For instance, it experiences an increase in the leaf area index (LAI) during the dry season. However, due to limited surface exchange observations in the miombo region, there is a lack of information regarding the effect of these properties on miombo woodland evaporation. It is crucial to have a better understanding of miombo evaporation for accurate hydrological and climate modelling in this region. Currently, the only available regional evaporation estimates are based on satellite data. However, the accuracy of these estimates is questionable due to the scarcity of field estimates with which to compare. Therefore, this study aims to compare the temporal dynamics and magnitudes of six satellite-based evaporation estimates – the Topography-driven Flux Exchange (FLEX-Topo) model, Global Land Evaporation Amsterdam Model (GLEAM), Moderate-Resolution Imaging Spectrometer (MODIS) MOD16 product, operational Simplified Surface Energy Balance (SSEBop) model, Thornthwaite–Mather climatic Water Balance (TerraClimate) dataset, and Water Productivity through Open access of Remotely sensed derived data (WaPOR) – during different phenophases in the miombo woodland of the Luangwa Basin, a representative river basin in southern Africa. The goal of this comparison is to determine if the temporal dynamics and magnitudes of the satellite-based evaporation estimates align with the documented feedback between miombo woodland and climate. In the absence of basin-scale field observations, actual evaporation estimates based on the multi-annual water balance (Ewb) are used for comparison. The results show significant discrepancies among the satellite-based evaporation estimates during the dormant and green-up and mid-green-up phenophases. These phenophases involve substantial changes in miombo species' canopy phenology, including the co-occurrence of leaf fall and leaf flush, as well as access to deeper moisture stocks to support leaf flush in preparation for the rainy season. The satellite-based evaporation estimates show the highest agreement during the senescence phenophase, which corresponds to the period of high temperature, high soil moisture, high leaf chlorophyll content, and highest LAI (i.e. late rainy season into the cool-dry season). In comparison to basin-scale actual evaporation, all six satellite-based evaporation estimates appear to underestimate evaporation. Satellite-based evaporation estimates do not accurately represent evaporation in this data-sparse region, which has a phenology and seasonality that significantly differ from the typical case in data-rich ground-truth locations. This may also be true for other locations with limited data coverage. Based on this study, it is crucial to conduct field-based observations of evaporation during different miombo species phenophases to improve satellite-based evaporation estimates in miombo woodlands.

Hybridization of deep learning, nonlinear system identification and ensemble tree intelligence algorithms for pan evaporation estimation

A reliable pan evaporation (Epan) estimation over a daily scale is vital for sustainable water and agriculture management, especially for designing water use allocations, irrigation system management, and demand and utilization assessments. However, designing a reliable computational methodology is a challenging task for Epan estimation due to its stochastic and random characteristics. In this study, the potential of five machine learning (ML) models namely Hammerstein-Weiner (HW), Random Forest (RF), Boosted Regression Tree (BRT), Long Short-Term Memory (LSTM), and Stepwise Linear Regression (SWLR) models were evaluated for Epan modeling in Lake Hawassa catchment, Ethiopia. Afterward, hybrid SWLR-LSTM, SWLR-RF, SWLR-BRT, and SWLR-HW models were developed to benefit from the strength of the non-linear and linear characteristics of the models. The estimation results were evaluated using determination coefficient (R2), Nash-Sutcliffe efficiency (NSE), mean absolute error (MAE) and Root Mean Square Error (RMSE), Index of Agreement (IA) and Kling-Gupta efficiency (KGE). The performance analysis result of individual models showed that the RF model led to more accurate estimation with NSE = 0.938, IA = 0.956, R2 = 0.94, KGE = 0.852, RMSE = 0.483 mm/day and Pbias = -1.193 mm/day during the validation phase. Among the hybrid models, SWLR-RF provides the best predictive performance improving SWLR, HW, LSTM, BRT and RF by 26.563 %, 21.348 %, 15.577 %, 9.091 % and 3.514 %, respectively based on the validation phase NSE value. Generally, the results of the current study demonstrated the capability of deep learning, ensemble tree and hybrid linear-nonlinear models for Epan estimation in the data-scarce catchment.

Development of machine learning models for estimation of daily evaporation and mean temperature: a case study in New Delhi, India

ABSTRACT Accurate prediction of pan evaporation and mean temperature is crucial for effective water resources management, influencing the hydrological cycle and impacting water availability. This study focused on New Delhi's semi-arid climate, data spanning 31 years (1990–2020) were used to predict these variables using advanced algorithms such as Bagging, Random Subspace (RSS), M5P, and REPTree. The models were rigorously evaluated using 10 performance metrics, including correlation coefficient, mean absolute error (MAE), and Nash–Sutcliffe Efficiency (NSE) model coefficient. The Bagging model emerged as the best model with performance indices values as r, MAE, RMSE, RAE, RRSE, MBE NSE, d, KGE, and MAPE as 0.86, 0.76, 1.43, 32.70, 49.44, 0.03, 0.85, 0.96, 0.90, and 22.0, respectively, during model testing phase for pan evaporation prediction. In predicting mean temperature, the Bagging model reported the best results with performance indices values as r, MAE, RMSE, RAE, RRSE, MBE NSE, d, KGE, and MAPE as 0.86, 0.76, 1.43, 32.70, 49.44, 0.03, 0.85, 0.96, 0.90 and 22.0, respectively, during the model testing phase. These findings offer valuable insights for enhancing relative humidity prediction models in diverse climatic conditions. The Bagging model's robust performance underscores its potential application in water resource management.

Priestly-Taylor Coefficient Evaluation for Konya Closed Basin

Measurement of evaporation in the field is difficult and expensive; thus, the empirical evaporation estimation methods have been developed. However, these estimation methods have both advantages and disadvantages. The main disadvantage is that their coefficients were determined by the climatic conditions of the study areas. One of these methods is Penman. The Penman method, accepted as a reference, has reached the closest estimations to the measurement of evaporation in the field of the different parts of the world. However, it needs lots of measured climatic data. The Priestley-Taylor method was derived to reduce the measured data needs of the Penman method. Priestly and Taylor represented the variables such as saturated and actual vapor pressures and wind speed with coefficient of 1.26. The researchers have continued to study on the calibration of the  coefficient for their studies’ area since this method has been known to underestimate evaporation value in areas where advection is effective. The present study consists of two stages. First, evaporation was tried to be estimated with these two methods by using the measured climatic data of five meteorological stations in the Konya Closed Basin. Estimated values were evaluated making comparison with the pan measurements. Although slightly higher values were estimated from the pan measurements with each method, the Penman method was found to be relatively more consistent on the basis of statistical indicators. Second,  coefficient was obtained as 1.28 for the study area by using three artificial intelligence-based optimization algorithms. The Penman method was used for comparison in this stage. It was concluded that there was no need for any calibration of the  coefficient and the original one was found to be valid for the study area as well.

Improving estimates of water resources availability over North Tropical South America: comparison of two satellite precipitation merging schemes

Low-density precipitation measurements impair the ability of hydrological models to estimate surface water resources accurately. Remote sensing techniques and climate models can help to improve the estimation of the space-time rainfall variability. However, they alone are not good enough to be used in surface models built to support water management. In this research, we test the improvement of rainfall field estimation by using hydrological modelling based on the premise that a higher hydrological performance generally implies that precipitation is more consistent with streamflow observations and evaporation estimates in the basin. The SWAT model was forced with two satellite and rain gauge blending techniques and with the traditional IDW deterministic interpolation method from stations. The three simulated streamflows were compared separately against observed records. We do not only focus the comparison on one hydrological performance metric but also conduct a deeper evaluation using several hydrological signatures and statistics. We included the bias, the temporal correlation, the relation of general variability, and an analysis of the Flow Duration Curves (we found that low and medium segments were estimated correctly, whereas the high segments were underestimated). We conclude that either combination technique has its advantages over the other and that both outperform the performance achieved by the IDW in most of the defined criteria, with an overall 10% improvement and with individual streamflow gauge performance enhancement up to 50%.

Estimate of the Surface Evaporation from the Tharthar Lake (Buhayrat Tharthar) in Iraq, Based on Remote Sensing Data and Techniques of Geographic Information Systems GIS

Tharthar is the largest water reservoir in Iraq. It is Giving the circumstances of drought and water crisis in Iraq, which is considered a semi-arid region, along with significantly feverish temperatures, especially in the summer. It is expected that evaporation rates will increase. Therefore, it was necessary to determine the water loss due to evaporation from Lake Tharthar. Due to the lack of ground measurement stations providing such data, the study relied on remote sensing data, specifically satellite imagery from Landsat 8 and Landsat 9. These images were used to extract temperature values for Lake Tharthar for the hydrological year extending from October 2022 to September 2023. This was done in conjunction with geographic information system (GIS) software and using ArcMap to calculate the annual evaporation rate and volume of the lake. Spatial modeling of evaporation was conducted for each month using the modified Lambert equation, adapted from the Penman-Cridle equation, which is most suitable for the climatic conditions of Iraq. Using this methodology saved time, effort, and cost, and yielded satisfactory results compared to field measurements of nearby water bodies. Temperature and evaporation rates were calculated at the level of each image pixel (30×30 meters). The research concluded many important findings, including that the total annual evaporation from the lake is estimated at 1881.16 millimeters (2.930 billion cubic meters per year). Accordingly, the annual loss per square kilometer from Lake Tharthar is estimated at 188 million cubic meters. This means that when Lake Tharthar reaches its maximum capacity, expanding the area to 2710 square kilometers, the evaporation loss will increase to 5.089 billion cubic meters per year. This necessitates relevant authorities to take necessary measures to reduce the annual evaporation loss from the lake surface. The study recommends adopting this method in cases where data is not available for locations lacking weather stations or when there is a data shortage.

How much evaporation occurs in Brazilian reservoirs? A multi-model perspective

Estimating evaporative losses from reservoirs is essential for water resource management. While remote sensing provides great opportunities for better constrain this process, there are still large uncertainties related to the behavior of evaporative losses across large domains. Here, we present a multi-model approach combined with remote sensing data to estimate evaporation losses at a national scale for dozens of reservoirs in Brazil. Open water evaporation (Ew) rates were obtained using two surface energy balance (SEB) models (the Google Earth Engine implementation of the Surface Energy Balance Algorithm for Land (geeSEBAL) and the Simplified Surface Energy Balance (SSEBop)). Due to the lack of in situ evaporation data, the estimations were cross-validated with results from the validated product Moderate-Resolution Imaging Spectroradiometer (MODIS) Water Reservoir Monthly Level 3 Global (MOD28C3) and the widely used open water evaporation equation described by Penman. Ew estimates were obtained for 74 large reservoirs, representing almost 70% of the area occupied by artificial water bodies in Brazil. Monthly estimates of Ew showed satisfactory agreement among the models, especially for geeSEBAL, SSEBop, and MOD28C3. Reservoirs with higher Ew were located in the semi-arid Caatinga Biome. The total annual evaporation and net evaporation (difference between lake Ew and surrounding evapotranspiration) for the assessed reservoirs were 46.6 ± 1.0 km³ and 16.4 ± 0.5 km³, respectively, for the period 2003–2021, based on an average of geeSEBAL and SSEBop. We also found that net evaporation is very high in dry climate zones and lower in tropical and humid subtropical climate zones. Our results show the advantage of integrating remote sensing datasets and evaporation models with cloud computing to obtain evaporation estimates in a tropical region and over a large domain. These multi-model evaporation estimates can improve our understanding of water resources in ungauged regions at a large spatial scale.

High Spatiotemporal Estimation of Reservoir Evaporation Water Loss by Integrating Remote-Sensing Data and the Generalized Complementary Relationship

Accurately estimating the reservoir evaporation loss is crucial for water resources management. The existing research on reservoir evaporation loss estimates primarily focuses on large spatiotemporal scales and neglects the rapid dynamic changes to reservoirs’ surface area. For reservoirs essential for frequent flood control and regular water supply, high spatiotemporal evaporation data are crucial. By integrating remote sensing and the evaporation model, this study proposes a new method for the high spatiotemporal estimation of the evaporation losses from reservoirs. The proposed method is applied to the largest artificial freshwater lake in Asia, i.e., Danjiangkou (DJK) Reservoir. The daily reservoir water surface area is extracted at a spatial resolution of 30 m during the period 2014–2018 based on the Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model (ESTARFM). The daily evaporation rate is estimated at a spatial resolution of 100 m using the generalized complementary relationship (GCR). The results show that the water surface area of the DJK Reservoir exhibits rapid and frequent fluctuations from 2015 to 2018, with a multi-year average area of 731.9 km2 and a maximum and minimum difference of 304 km2. Significant seasonal variations are observed in both the evaporation rate and volume, with a multi-year average evaporation rate of 806 mm and evaporation volume of 595 million m3. The estimated results align well with three other independent estimates, indicating that the GCR is capable of water surface evaporation estimation. Further analysis suggests that the data resolution has a great influence on the evaporative water loss from the reservoir. The estimated mean annual evaporation volume based on the 1000 m resolution water surface area data is 14% lower than that estimated using the 30 m resolution water surface area data. This study not only provides a new method for the high spatiotemporal estimation of reservoir evaporation by integrating remote-sensing data and the GCR method but also highlights that reservoir evaporation water loss should be quantified using the volume rather than the rate and that the estimated loss is noticeably affected by the estimation spatial resolution.

Predicted evaporation in Basrah using artificial neural networks

Abstract Accurate evaporation estimation is crucial for managing hydrologic, hydraulic, and agricultural systems, among many other applications of water resources. Empirical formulae for estimating evaporation exist, but their performance is not always sufficient due to the intricacy of the process and its nonlinear connection with other elements of the hydrological cycle. For this reason, a model of artificial neural networks was developed to estimate the daily potential evaporation in the southern Iraqi city of Basrah. A feedforward backpropagation (BP) network with a single hidden layer has been used to construct the mode. Different networks with various neuron counts were assessed. The developed models have been trained, tested, and validated using daily observations of the average rainfall, wind speed, average temperature, average relative humidity, and evaporation. The final evaporation was predicted using an artificial neural network (ANN) model. The proposed model was found to be more suitable to describe evaporation in any region of the world based on the values of the error analysis and the coefficient of determination, according to the ANN model. The Levenberg–Marquardt algorithm (LMA) was determined to have the lowest mean-squared error (MSE) and highest value of the coefficient of correlation (R) of the six proposed BP algorithms. The LMA’s hidden layer’s ideal neuron count was 30 neurons, with an MSE of 0.00288 and R 2 = 99. As a result, ANN displayed excellent performance in terms of evaporation prediction value. The study’s findings highlight the significance of predicting evaporation as the main metric for evaluating the effects of climate change on water resources.

Improving the daily pan evaporation estimation of long short-term memory and support vector regression models by using the Wild Horse Optimizer algorithm

ABSTRACT Evaporation is a basic element in the hydrological cycle that plays a vital role in a region's water balance. In this paper, the Wild Horse Optimizer (WHO) algorithm was used to optimize long short-term memory (LSTM) and support vector regression (SVR) to estimate daily pan evaporation (Ep). Primary meteorological variables including minimum temperature (Tmin), maximum temperature (Tmax), sunshine hours (SSH), relative humidity (RH), and wind speed (WS) were collected from two synoptic meteorological stations with different climates which are situated in Fars province, Iran. One of the stations is located in Larestan city with a hot desert climate and the other is in Abadeh city with a cold dry climate. The partial mutual information (PMI) algorithm was utilized to identify the efficient input variables (EIVs) on Ep. The results of the PMI algorithm proved that the Tmax, Tmin, and RH for Larestan station and also the Tmax, Tmin, and SSH for Abadeh station are the EIVs on Ep. The results showed the LSTM–WHO hybrid model for both stations can ameliorate the daily Ep estimation and it can also reduce the estimation error. Therefore, the LSTM–WHO hybrid model was proposed as a powerful model compared to standalone models in estimating daily Ep.

Investigating the influences of wind function parameterization on evaporation estimation using the generalized complementary principle

The complementary principle (CR) is the most practical method for estimating regional evaporation (E) based only on routine meteorological observations. However, CR-based models have certain problems that must be solved for widespread application, such as the influence of wind function types and parameterization. In this study, the generalized CR with polynomial forms (GCR) as a case study is applied to investigate the influences of two different parameterization schemes of wind function—the Penman wind function (fPM) and theoretical wind function (fSM)—on evaporation estimation. The observed daily E values from nine eddy flux stations in Australia with contrasting climates and land cover types were collected to quantify the influences. The results showed that the GCR successfully estimated the E value of flux stations with both the fPM and fSM, and the E value estimated with fSM was more sensitive to wind speed than that with fPM. The estimated aerodynamic term (EA), estimated evaporation error (Eerror), and parameter αc showed marked differences between the two wind functions. The EA-SM (hereafter, subscripts PM and SM represent the wind function type) is approximately 1.05- to 5.06-fold greater than the EA-PM across stations, with a mean of 2.60 ± 1.33 (mean ± standard deviation). The correlation between Eerror-SM with wind speed (u) was positive with an average slope of 0.19, while that of fSM was negative with an average slope of −0.13. The difference in the calibrated parameter of the GCR (i.e., αc) between the two wind functions varied site-to-site, ranging from 0.02 to 0.31. This study highlights that both wind function parameterization schemes successfully estimate regional evaporation, but highly differed in evaporation components, errors, and parameter. These results can help to understand and adopt proper wind parameterization schemes for wider applications of GCR method. Additional studies are required to generalize the spatial variability of different wind function parameters and their influence on the applicability of the GCR.

Experimental research and estimation model of gasoline evaporative emissions from vehicles in China

Evaporative emission is an important source of vehicle pollutant emission and volatile organic compounds (VOCs), causing serious environmental pollution. Carbon canisters are used to store fuel vapor in evaporative emission control (EVAP) system, but canisters are prone to saturation, leading to the direct release of fuel vapor into the atmosphere. Therefore, accurate estimation of fuel vapor generation is crucial for EVAP system. Gasoline evaporation rate is mainly influenced by vapor-liquid interface area, gasoline saturated vapor pressure, filling level and temperature. The quantitative relation between different parameters and gasoline evaporation rate has rarely been reported, and a gasoline evaporative emission estimation model suitable for China needs to be proposed urgently. In this study, gasoline evaporative emission tests have been carried out in VT-SHED, and the effects of vapor-liquid interface area, filling level and temperature on gasoline evaporative emissions have been analyzed under the premise of consistent gasoline temperature and ambient temperature. Some valuable conclusions are obtained. The results show that different from expectation, gasoline evaporative emissions are not positively correlated with the vapor-liquid interface area. There is an approximately exponential relationship between the headspace volume and gasoline evaporative emissions. The widely used Reddy equation and Hata equation underestimate the gasoline vapor generation in China. Based on China VI test program and gasoline, accurate estimation of mass transfer coefficient has been conducted, and a new semi-empirical estimation model for vapor generation has been proposed. The model can accurately estimate the fuel evaporation of vehicles in China, providing guidance for the matching and optimization of EVAP system.

Comment on “Comparison of the Efficiencies of the Prognostic Generalized Complementary Functions on Evaporation Estimation” by Wang, L., et al., Published in Journal of Geophysical Research: Atmospheres

AbstractSurprising significant underperformance of the polynomial complementary relationship (PCR) of evaporation (Szilagyi et al., 2017, https://doi.org/10.1002/2016jd025611) by Wang et al. (2023, https://doi.org/10.1029/2023jd038683) is caused by the (a) station‐by‐station application of a grid‐based estimation procedure of the Priestley‐Taylor parameter (α) value, and (b) choice of the wind function. Application of the Rome wind function in the Penman equation together with either a well‐chosen single (constant) α or α as a function of the wet‐environment air temperature, should result in much improved evaporation estimates by the PCR in line with previous studies.

Evaluation of soft-computing techniques for pan evaporation estimation

Estimation of pan evaporation (Epan) can be useful in judicious irrigation scheduling for enhancing agricultural water productivity. The aim of present study was to assess the efficacy of state-of-the-art LSTM and ANN for daily Epan estimation using meteorological data. Besides this, the effect of static time-series (Julian date) as additional input variable was investigated on performance of soft-computing techniques. For this purpose,the models were trained, tested and validated with eight meteorological variables of 37 years by using preceding 1-, 3- and 5- days’ information. Data were partitioned into three groups as training (60%), testing (20%), and validation (20%) components. It was observed that the models performed well (best) with preceding 5-days meteorological information followed by 3-days and 1-day. However, all LSTMs simulated peak value of Epan was more accurate as compared to lower values. Meteorological data with julian date improved the performance of LSTMs (0.75<NSE 1; PBias< 10; KGE 0.75). The ANN trained using only meteorological data (preceding 5-days information) had better performance error statistics among all other ANNs and LSTMs with minimum MAE (0.68 to 0.86), RMSE (0.93 to 1.22), PBias (-0.73 to 2.44) and maximum NSE (0.83 to 0.84) and KGE (0.89 to 0.92). Overall, it was inferred that the forecasting of meteorological parameters using a few days preceding information along with Julian date as the time series variables resulted in better estimation of Epan for the study region.

Developing a General Daily Lake Evaporation Model and Demonstrating Its Application in the State of Texas

AbstractOpen water evaporation, which often consumes a large fraction of annual storage (especially in arid and semi‐arid regions), is a controlling variable for modern water resource management. Developing a daily reservoir evaporation data set is necessary for reservoir operations to consider the influence of evaporation in a timely manner. However, over the past few decades, the quantification of reservoir evaporation has primarily relied on monthly Class A pan evaporation observations, which might lead to largely biased estimations because they do not incorporate the effects of heat storage and fetch. In this study, we developed a general Daily Lake Evaporation Model (DLEM) based on Penman's equation combined with daily atmospheric reanalysis data sets, to improve the validity and frequency of reservoir evaporation monitoring. Compared with daily evaporation estimates from eddy covariance systems, the DLEM showed good quality and reliability, with R2 values ranging from 0.50 to 0.73 and RMSE values ranging from 1.13 to 1.97 mm day−1 in four different sites. By applying DLEM to all 188 major reservoirs in Texas, we generated a long‐term data set of (1 January 1981–31 December 2021) daily evaporation rates. The results reveal a clear geographic distribution and strong seasonality of evaporation throughout Texas, where the mean evaporation rate is highest during July, with 6.85 mm day−1. Trend analysis indicates that the annual average evaporation rate has significantly increased since 1981 at a rate of 0.076 mm day−1 decade−1. This study provides sufficient data support for water resource operations and management, and regional water planning.

The Impact of Preprocessing Approaches on Neural Network Performance: A Case Study on Evaporation in Adana, a Mediterranean Climate

The application of artificial intelligence (AI) technologies is quickly expanding in water management. Additionally, the artificial neural network methodology has an advantage over traditional statistical approaches in that it does not need assumptions about the distribution of data and variables. These methods can be used if there is a large enough data collection and criteria relevant to the nature of the problem. Preprocessing data before utilizing it improves the performance of the AI model. Evaporation matters in water management, agriculture processes and soil science. It is critical to ensure proper estimation of evaporation losses for effective water resource planning and management particularly in drought-prone areas such as Adana. Artificial intelligence approaches can be applied successfully in evaporation calculation. In this research, we used the Standard scaler, power transformer, robust scaler quantile transformer (Uniform) and quantile transformer (Normal), and min-max scaler preprocessing techniques to preprocess the multilayer perceptron neural network (MLPNN). We also trained the MLPNN using unprocessed data and compared it to the results of the preprocessed model. In the setup of the model, daily temperature, pressure, wind, sunny hours, and humidity parameters covering the years 2018-2021 were presented as input to the MLPNN model. Consequently, we pinpoint that all preprocessing approaches produce better outcomes than unscaled. Although all models produced statistically high accuracy predictions according to statistical criteria, the MLPNN model established without transformation (test phase: r2: 0.93, NSE : 0.927, SMAPE: 10.77, RMSE: 1.2, MAE: 0.9) exhibited the lowest accuracy. The evaporation prediction model that was developed using the MLPNN-based standard scalar optimization algorithm exhibited the highest level of accuracy (test phase: r2: 0.978, NSE: 0.977, SMAPE: 5.93, RMSE: 0.68, MAE: 0.48). Power Transformer (test phase: r2: 0.978, NSE: 0.977, SMAPE: 5.81, RMSE: 0.67, MAE: 0.49) showed second-degree promising results. It can be concluded from these results that the estimation of meteorological variables requires the scaling and presentation of data in a uniform structure. Therefore, improving efficiency and productivity in water management or agricultural processes can be enhanced by making more accurate evaporation estimates.

Estimation and Spatiotemporal Analysis of Surface Evaporation in the Yangtze River Basin from 2010 to 2019

Evaporation is a critical process involved in energy and water balance at the Earth’s surface and bears significant implications for water resource management, agricultural irrigation, and drought monitoring, among others. In this study, we focused on establishing a 1 km daily surface evaporation estimation for the Yangtze River Basin from 2010 to 2019 by using a machine learning method, and then analyzed its spatiotemporal patterns. The findings showed spatial heterogeneity in the Yangtze River Basin, indicating higher evaporation rates in the southwestern and southeastern regions in contrast to the western and northern areas. Additionally, the basin exhibited a strong spatial autocorrelation, indicating the influence of one spatial unit on the others. Furthermore, most regions in the basin displayed non-significant changes in surface evaporation, with some areas in the upper reaches exhibiting significant increases and a few regions near the source of the Yangtze River experiencing significant decreases. This study contributes to a better understanding of the spatial and temporal distribution of evaporation in the Yangtze River Basin, providing valuable insights for water resource management, environmental studies, and hydrological modeling in the region.