FAO Penman-Monteith Research Articles

Advanced geospatial analytics for evapotranspiration dynamics: Integration of Sentinel-1A and FAO Penman-Monteith method

Evapotranspiration (ET0) is vital for agriculture and environmental management, facing challenges from climate change. Optical remote sensing overcomes reliance on weather station data. The modeled ET0 using the FAO Penman-Monteith method and Partial Least Squares Regression on Sentinel-1A data with 2016-2017 meteorological archives. Comparative analyses revealed stability in transportation areas within deciduous forests and wetlands, contrasting temporal variations. ET0 was significantly influenced by relative humidity (RH) (70.80% to 89.89%), with temperature (T) playing a crucial role. Urban vegetated areas maintained stable T values (29.37°C), while forests exhibited dynamic T variations (24.24°C to 28.94°C). VH polarization captured diverse climatic influences, resulting in a broader range of dynamic ET0 values (7.38 to 10.76 mm/day) compared to VV polarization (6.74 to 9.34 mm/day). VH sensor performance varied; in October 2016 showed moderate accuracy R2 was 0.50 with slight underestimation Bias -0.08, while exceptional accuracy was seen in December 2017 R2 was 1.00 with positive bias (0.57) and excellent agreement KGE was 0.92. VV sensors in October 2016 had a firm fit R2 was 0.55, with moderate underestimation Bias -0.87, and in December 2017 displayed a good fit the R2 was 0.57, with slight overestimation Bias 0.44, and good agreement KGE 0.44. Integrating machine learning and satellite imagery enhances ET0 accuracy for real-time monitoring in adaptive management, addressing climate change, and showcasing sensor-specific variations. Future research should integrate multi-source synthetic aperture radar satellite data and machine learning for precise ET0 estimation in adaptive environmental management.

Alternative Solution to Estimate Cucumber Crop Evapotranspiration in Shade Nets for the Valle de Culiacán, Mexico

Objective: This work aimed to estimate the evapotranspiration of cucumber crop grown in a shade house in Valle de Culiacán, México. Design/methodology/approach: The FAO56 method was used with a variation of the FAO Penman-Monteith equation, and a non-conventional evaporimeter to measure evaporation inside the shade house. Using the estimated reference evapotranspiration and the measured evaporation, pan coefficients were calculated, and a mathematical model was proposed to calculate this coefficient based on the meteorological parameters: air temperature, relative humidity, and net solar radiation. Results: The estimated crop evapotranspiration was 417.6 mm. The linear regression between the reference evapotranspiration estimated with FAO56 and calculated with evaporation and adjusted evaporimeter pan coefficient yielded excellent statistical estimators (R2>0.9). Findings/conclusions: The analysis of the evaporimeter pan coefficient's dependence on meteorological parameters indicates a strong dependence on air temperature, net solar radiation, and vapor pressure deficit, but not on relative humidity.

Development and evaluation of site-specific evapotranspiration models in Malawi through a comparative analysis of existing models

Locally based information on reference evapotranspiration pertinent to efficient irrigation water management is scarce in developing countries. This compromises the accuracy in determining irrigation crop water requirements since most existing reference evapotranspiration models are empirically based and less accurate unless calibrated to local conditions. The FAO Penman-Monteith equation has been proven to estimate reference evapotranspiration for different environments worldwide. However, its intensive data input requirements impede utilization of the model in developing countries due to inadequate climate data collection and management capacities. Therefore, a need existed to develop site-specific models that are less data intensive. A study was conducted aimed at developing site-specific evapotranspiration models using comparative analysis of the Kharrufa, Linacre, Hargreaves Original and Hargreaves Modified empirical models during the wet and dry season. Performance of each model was compared with the FAO Penman-Monteith model, regarded as the standard model. The models whose Root Mean Square Error (RMSE), Mean Bias Error (MBE) and coefficient of determination (R2) were satisfactory were selected. The selected models were developed statistically through regression analysis. Performance of the Kharrufa model was satisfactory comparatively as observed from its RMSEs of 1.02 mm/day and MBE -0.34 to 0.8 for the dry season. However, the model less accurately estimated reference evapotranspiration during the wet season (RMSE 2.18 mm/day and MBE 1.03 to 2.13). The study recommends the use of the Kharrufa model in the study locations in dry seasons while utilization in wet season may require further studies to ascertain the model's useability and reliability.

Seasonal and annual trends in reference evapotranspiration and prediction using machine learning models across seven climatic zones of Bangladesh

ABSTRACT The primary aim of this investigation is to examine the historical (1989–2020) and future trends and magnitude of Reference Evapotranspiration (ET0) in terms of spatiotemporal measures, considering its significance as a hydro-meteorological parameter influenced by changing climate. The FAO-56 Penman-Monteith method is employed to analyze ET0, while the Modified Mann Kendall test is utilized to assess trends and Sen’s Slope Estimator is used for magnitude analysis. The future prediction is conducted using Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest (RF) models. Results show an increasing ET0 trend annually in the southeastern and northeastern zones, while decreased values are observed in other regions, particularly in the northwest (0.83 mm). Sen’s slope estimator reveals distinct fluctuations in ET0, with notable disparities in the Southeastern, Northeastern, Southwestern, and South-Central zones. Notably, Chattogram and Sitakunda experience an ET0 magnitude of 0.02 mm/Year, while other zones show a magnitude of 0.01 mm/Year. SVM outperformed other models, predicting rising ET0 in various seasons. These findings offer insights for optimizing irrigation systems and sustainable water management under changing climatic conditions.

Future drought overestimations due to no constraints of CO2 physiological effect and land-atmosphere coupling on potential evapotranspiration

Abstract Various offline drought indices have been widely used to project dryness/wetness and drought changes. However, the results derived from these indices often differ from or even contradict observations and direct projections made by coupled climate models. Therefore, it is crucial to investigate this scientific debate thoroughly and identify the potential causes. This study adopts a water demand-side perspective, focusing on potential evapotranspiration (PET), to address such controversy. Employing the Standardized Precipitation-Evapotranspiration Index (SPEI), three PET models including the Food and Agriculture Organization of the United Nations’ report 56 (FAO-56) Penman-Monteith (PM) model, a corrected FAO-56 PM model incorporating CO2 physiological effect (PMCO2), and a land-atmosphere coupled PET model (PET-LAC) are further compared. Despite projected increases in PET across most land areas, the PM shows the most pronounced increases among these PET models. Compared to PMCO2 and PET-LAC, the PM model predicts the most significant drying, with the 3-month SPEI decreasing by 0.50±0.23 /yr. Additionally, it projects the most substantial drought intensification, with increases in areas, intensity, and duration of 28±6.9%, 0.70±0.20/yr, and 2.90±0.83 month/yr, respectively. Meanwhile, these projections correspond to the most extensive area percentages, with 78.5±10% for drying, 94.8±7.2% for drought intensity, and 93.6±7.9% for drought duration. These findings imply that the commonly used PM model overestimates future drought conditions. Differences and contradictions between the drought projections from PM-based offline indices and direct climate model outputs can be partly attributed to the omission of CO2 physiological effect and land-atmosphere coupling constraints in the PM model. This study highlights the importance of improving PET models by incorporating these constraints, thereby providing valuable insights for enhancing the accuracy of future drought assessments.

A comparative study of crop evapotranspiration estimation in maize using empirical methods, pan evaporation and satellite-based remote sensing technique

A research study was conducted at the Agricultural College and Research Institute, Coimbatore to estimate the evapotranspiration (ET) of maize crop (Zea mays) over 2 consecutive seasons in 2022-2023. Among the different methods used to estimate crop evapotranspiration, the Food and Agricultural Organization Penman-Monteith model (FAO P-M) is widely recognized as the standard approach for ET estimation. This study aimed to compare the effectiveness of three alternative methods - Thornthwaite (TW), NDVI-based and pan methods against the FAO Penman-Monteith (P-M) model in estimating maize evapotranspiration. Meteorological data were collected from the TNAU weather station spanning the period from 2022 to 2023.The performance of the estimation methods was assessed using statistical metrics such as coefficient of determination (R2), root mean squared error (RMSE), percentage error and mean bias error. The findings revealed that the NDVI-based method, relying on satellite data, provided higher accuracy in estimating maize evapotranspiration compared to the FAO PM method. Specifically, the NDVI-based method achieved the highest coefficient of determination (R2) of 0.87 and 0.89, the lowest RMSE of 12.44 mm/month and 15.5 mm/month, the lowest percentage error of 4.8 % and 9.00 % and the lowest mean bias error of 5.5 and 7.85 for the first and second seasons respectively. This study highlights the effectiveness of the NDVI-based ET estimation method for accurately assessing maize evapotranspiration. While the FAO-56 Penman-Monteith method is highly regarded for its accuracy in both theoretical and practical contexts, the comparative evaluation presented in this paper offers valuable insights for selecting alternative methods that require less data, particularly in regions with limited data availability.

Growth, Evapotranspiration, Gas Exchange and Chl a Fluorescence of Ipê-Rosa Seedlings at Different Levels of Water Replacement.

In general, young plants in the establishment phase demonstrate sensitivity to changes in environmental conditions, especially regarding water availability. The effects of the seasonality of biophysical processes on plant physiology can trigger differential responses, even within the same region, making it necessary to conduct studies that characterize the physiological performance of the species at different spatial and temporal scales, making it possible to understand their needs and growth limits under water stress conditions. This paper aimed to evaluate the growth, gas exchange and Chl a fluorescence in ipê-rosa seedlings subjected to levels of water replacement (LWRs) of 100, 75, 50 and 25% in a greenhouse. The morphometric variables of plant height, diameter at stem height, numbers of leaves and leaflets, root length and volume, plant dry mass and leaf area were evaluated. The potential evapotranspiration of seedlings (ETc) was obtained using direct weighing, considering the water replacement of 100% of the mass variation between subsequent days as a reference; the cultivation coefficients (kc) were obtained using the ratio between ETc and the reference evapotranspiration (ETo) obtained by the Penman-Monteith FAO-56 method. Biomass and evapotranspiration data were combined to determine water sensitivity. Diurnal fluxes of gas exchange (net photosynthesis rate, transpiration rate, stomatal conductance, internal and atmospheric carbon ratio, water use efficiency and leaf temperature) and Chl a fluorescence (Fv/Fm, ΦPSII, ETR, Fv'/Fm', NPQ and qL) were evaluated. Water restriction caused reductions of 90.9 and 84.7% in the increase in height and diameter of seedlings subjected to 25% water replacement when compared to seedlings with 100% water replacement. In comparison, biomass accumulation was reduced by 96.9%. The kc values increased throughout the seedling production cycle, ranging from 0.59 to 2.86. Maximum water sensitivity occurred at 50% water replacement, with Ky = 1.62. Maximum carbon assimilation rates occurred in the morning, ranging from 6.11 to 12.50 µmol m-2 s-1. Ipê-rosa seedlings regulate the physiology of growth, gas exchange and Chl a fluorescence depending on the amount of water available, and only 25% of the water replacement in the substrate allows the seedlings to survive.

Stormwater retention capacity of blue-green roofs with various configurations: Observational data and modelling

Although dynamic changes in stormwater retention capacity (SRC) determine overall stormwater retention performance of blue-green roofs, few previous studies have investigated the dynamic changes of SRC of blue-green roofs with various configurations. In this research, an experiment was designed to observe hydrological processes of blue-green roofs in Beijing. Based on the water balance theory, a conceptual hydrological model was developed by integrating a modified FAO-56 Penman-Monteith model, an AET formula with a water stress coefficient and Dalton’s equation. Then the proposed model was validated using experimental data. Results show that the model can simulate the SRC dynamics well, with the Nash-Sutcliffe and determination coefficients both exceeding 0.6. The consumption and recovery of the SRC in blue-green roofs are mainly driven by rainfall and actual evapotranspiration, respectively. As actual evapotranspiration decreases with seasonal changes, the fluctuation amplitude of SRC in blue-green roofs diminishes, ranging from 32.53 mm to 11.34 mm. Although increasing the depth of substrate and storage layers is able to enhance the SRC of blue-green roofs, there are optimal upper limits for these depth because of regional climate conditions. In Beijing, the optimal upper limits for substrate and storage layer depths are 300 and 30 mm, respectively. This information can assist designers in evaluating the cost-effectiveness of design choices for blue-green roofs. The developed model serves as an effective tool for simulating SRC and is expected to aid in the design of blue-green roofs.

Comparison of Empirical Methods to Estimated Reference Evapotranspiration

Evapotranspiration plays an important role in agricultural water management and crop modelling. Estimating reference Evapotranspiration (ETo) using meteorological variables, both theoretical and empirical methods, is highly recommended considering the availability of weather data in several locations. The estimation method recommended as the standard method is FAO Penman Monteith (FAOPM), but due to the limited meteorological data in a region and the difficulty and complexity of FAOPM, it is recommended to use the empirical method which is easier and only requires a few simple meteorological variables. The aim of this research is to compare and evaluated empirical methods for estimating ETo against the FAOPM. The statistical analysis using in this research are RSME, MAE, coefficient Correlation, NSE, Average bias, index of agreement, and confidence index (c). Evaluation for the best models based on statistic analyzed shows that several empirical methods show terrible performance in estimating the monthly average ETo (mm/day), which are Thornthwaite-Mather, Hargraves-Samani, Makkink, Hamon, Romaneko, and Kharauffa. Modified Blaney-Criddle method showed a good performance method, while PMAWS showed very good performance The Turc and Hansen method showed excellent performance with RMSE, MAE, NSE, and C values ​​for the Turc method, are 0.12, 0.11, 0.78, 0.92 respectively, and for the Hansen method are 0.12, 0.1, 0.8, and 0.89 respectively.

Impact of native vegetation and soil moisture dynamics on evapotranspiration in green roof systems

Evapotranspiration (ET) is an important water budget term for understanding the recovery of stormwater retention in green roof systems (GRs). However, ET evaluations, particularly in full-scale GRs, remain challenging. This study investigated ET dynamics within a GR in the City of Pittsburgh, USA, using a water balance based on continuously monitored soil moisture from moisture sensors over 15 months. Results suggest under well-watered soil conditions, daily moisture loss correlated with solar radiation, temperature, and humidity, in decreasing order of correlation strength, while wind speed had limited effects. Compared to sensor-informed moisture loss (using moisture-based water balance), the Hargreaves and FAO-56 Penman-Monteith equations predicted cumulative ET that was 1.8 and 2.1 times higher, respectively. When soil moisture declined and approached the temporary wilting points, a noticeable reduction in daily moisture loss was observed. This suggests the necessity of using a water stress coefficient alongside a crop coefficient to represent actual ET based on FAO-56 Penman–Monteith estimates. Seasonal crop coefficients from dominant native plant species present at our monitored location, eastern bluestar (Amsonia tabernaemontana) and creeping woodsorrel (Oxalis corniculata), had mean values of 0.48, 0.62, and 0.65 for fall, spring, and summer, respectively. The impact of water stress on ET could be characterized by a linear relationship with moisture content. Our results highlight the importance of soil moisture in regulating ET processes and demonstrate the utility of soil moisture data for evaluating ET in GRs and informing irrigation practices.

Impact of drip irrigation and plastic mulching on yield and economics of cucumber (Cucumis sativus L.)

Drip irrigation is crucial in the current agricultural scenario for vegetable crops, as it optimizes water use efficiency by delivering precise amounts of water directly to the plant roots, thereby conserving water resources and enhancing crop yields. Yield enhancement in cucumber, a significant horticultural crop, can be achieved by integrating drip irrigation and plastic mulching to maximize water productivity while minimizing losses. In the current consequences, a field study was conducted from November to December in two consecutive years (2021-2022 and 2022-23) at the experimental field of Precision Farming Development Centre, Indian Institute of Technology, Kharagpur, India. The study aimed to quantify the irrigation water requirements for cucumber using drip irrigation and plastic mulch. Eight treatments with varying irrigation levels and the use of plastic mulch were assessed in a randomized block design with three replications. The crop's irrigation water requirement was determined using the FAO-56 Penman-Monteith model. The results showed that the highest plant height (193.5 cm), number of leaves (43.3), fruit length (18.5), fruit weight (279.0 g), and cucumber yield (15.9 t/ha) were achieved with 100% irrigation water requirement along with plastic mulch during the first and second season. These results were closely followed by treatments with 80% of the crop water requirement using drip irrigation and plastic mulch. The study concluded that applying 80% of the estimated irrigation water (142.1 mm) using drip irrigation and plastic mulch could be recommended to obtain higher productivity in cucumber.

Comparison between evapotranspiration estimate methods in the state of Rio Grande do Sul

The characterization of evapotranspiration requires time and financial investment, but from meteorological data, it is possible to estimate the values of this phenomenon by means of indirect methods. The Penman-Monteith FAO (PM) method is considered the most accurate by the Food and Agriculture Organization of the United Nations (FAO), which recommends its use because it takes into account solar radiation, temperature, relative humidity, and wind speed, data that are not always available in some locations in Brazil, making it necessary to use more simplified methods. Therefore, the objective of this work is to compare the evapotranspiration estimated by the Penman-Monteith FAO method with the evapotranspiration estimated by the methods of Penman-Monteith Simplified (PMS), Priestley-Taylor (PT), and Hargraves-Samani (HS) for the 10 weather stations of the National Institute of Meteorology (INMET) distributed in the Pampa biome in the state of Rio Grande do Sul. The results obtained indicated some divergences between the compared methods. However, the PT method showed more accurate results, with the best performance among the proposed methods. This indicates that this method can be used in future studies in the region, especially in cases of a lack of meteorological data.

Performance Evaluation of Artificial Neural Networks for Estimating Refer-ence Evapotranspiration in Shahat, Libya using limited climatic data

This study was conducted with the aim of evaluating the performance of artificial neural networks (ANNs) to estimate the reference evapotranspiration using limited climate data in Shahat region in Libya, compared to using the FAO Penman-Monteith equation (FPM), which requires temperature, wind speed, relative humidity and number of sunshine hours, which are rarely available in most meteorological stations in developing countries. In this study, we used the average temperature (Tmean) and the average relative humidity (RHmean) obtained from Shahat meteorological station for the period from 1963 to 1999, and the extraterrestrial radiation (Ra), which can be calculated given the location and time of the day. These data are divided into two groups, from 1963 to 1988 and from 1989 to 1999 for the training and validation phases of the neural networks, respectively. This study concluded that using (Tmean), (RHmean) and (Ra) gave the best agreement with the results calculated with the FAO Penman-Monteith equation, where the values of R2 and RMSE are equal to 0.98 and 0.26, respectively.

Analysis of factors affecting evapotranspiration zoning.

Reference evapotranspiration (ETo) has a significant role in water resource planning and management as well as analysis of crop production and other agricultural tasks. Methods for estimating ETo may require diurnal/monthly assessments to perceive the consequences of climatic changes on local regions. The spatial and temporal patterns of ETo were analyzed in the current work using data from 340 weather stations in Iran. The entropy theory was used to assess the uncertainty of the utilized variables and the modified Kendall test was applied for temporal trend analysis. The interpolation (e.g., kriging) and ordinary least squares (OLS) methods were used for spatio-temporal ETo classification/modeling. The spatial analysis demonstrated that the OLS method with a good fit measure (R2 = 0.985) successfully simulated the spatial relationships of ETo with climatic parameters. After examining error indices, the cokriging method with an exponential variogram was introduced as the best method of seasonal and annual ETo classification in Iran. Spatially and temporally calculated ETo patterns using modified Hargreaves (MHGR) and MODIS methods closely resembled the standard FAO Penman-Monteith (FPM-56) method, all indicating a gradual increase in ETo. MHGR and MODIS methods serve as suitable alternatives for estimating ETo in various climatic regions of Iran, provided data availability.

Vegetation Indices Based Spatial Water Demand of Rabi Onion Crop

There are numerous methods for estimating the water requirements of crops. However, the FAO Penman-Monteith Method has been adopted worldwide but it lacks spatial variability. The accuracy can be improved by adopting VI based method. Therefore, the present study was planned to investigate the use of vegetation indices (VIs) as a surrogate of crop coefficients in place of tabulated crop coefficients and find the best VI in the case of onion crops which require the amount of water. The study was conducted in 3 districts of Maharashtra i.e. Nashik, Dhule, and Jalgaon where onion is a major rabi crop grown on a large scale, for two consecutive rabi seasons of the year 2020-21 and 2021-22. Multitemporal vegetation indices such as NDVI, NDWI, SAVI, MSAVI2, and RVI were estimated using temporal images of Sentinel 2A satellite during the growth period of onion and week-wise values were obtained by using ERDAS Imagine. Linear regression was applied on VI values versus Kc recommended by MPKV, Rahuri which resulted in linear models. NDWI-Kc model showed the strongest relation with high R2 values. The spatial crop evapotranspiration (ETc) was then calculated by applying this model. For the 2020–21 growing season, the total crop evapotranspiration for onions in Dhule, Jalgaon and Nashik was calculated to be 486.5 mm, 482.7 mm, and 488.7 mm, respectively. Whereas during 2021–22, it was estimated to be 493.7 mm, 473.9 mm, and 477.2 mm, respectively in these districts. For getting water demand crop evapotranspiration values were multiplied by the acreage estimated by remote sensing. Total water demand for rabi onion for the districts Dhule, Jalgaon and Nashik was found to be 70.54 Mm3, 43.8 Mm3 and 693.2 Mm3, respectively and 128.1 Mm3, 33.9 Mm3, and 825.7Mm3 respectively for the years 2020-21 and 2021-22, respectively.

Case Study of Impact Evaluation of Agrivoltaic Structure Sizing on Water Availability for Wheat

Agrivoltaic (AV) Systems are a new solution for cropping conditions improvement by mitigating extreme weather conditions. Indeed, AV Systems affect microclimate, notably Air Temperature, Irradiance or Evapotranspiration that determines Soil Water Availability. To evaluate crop water stress protection and ensure optimized AV Systems sizing, a methodology was developed using a microclimate simulation tool. This paper presents a case study of Wheat focused on Water Availability, from a project located near Orléans, Center France. The methodology uses Irradiance Simulations at crop level by AGRISOLEO software, which has been parameterized with the structures sizing under study and a panel steering algorithm adapted to wheat phenology. The results are used for evapotranspiration modelling following the FAO-56 Penman-Monteith equation. For this case study, results showed that AV Systems under test reduced irradiance up to 40%. This effect may be reduced up to 17% by controlling the panels rotation angle to maximize irradiance during crop’s key development stages. Furthermore, AV Systems reduced Water Stress up to 48%. Microclimate simulation tool demonstrated possibility to assess AV Systems sizing impact on irradiance received by crop and Water Stress protection. Moreover, controlling the solar panels at key development stages of the crop is the central lever in the synergy of dynamic AV Systems. The methodology presented here applies not only to Wheat but to a wider range of crops and climate conditions, hence opening promising perspectives to optimize AV systems sizing and agronomic benefits.

Evaluation of daily crop reference evapotranspiration and sensitivity analysis of FAO Penman-Monteith equation using ERA5-Land reanalysis database in Sicily, Italy

Crop evapotranspiration (ET) is one of the most important components in many hydrological processes. The crop reference evapotranspiration (ETo) represents the atmospheric water demand in each crop type, development stage, and management practices. The Penman-Monteith equation in the version suggested by the Food and Agriculture Organization (FAO56-PM), is one of the most used methods to estimate ETo. In several regions of the world, meteorological observations are not always available. The most recent reanalysis database ERA5-Land, released in 2019, can be useful to overcome this limit. The database provides, with a spatial grid of 0.1° latitude and 0.1° longitude, several hourly climate data such as air temperature, dew point temperature, solar radiation, and wind speed components all at 2.0 m above the soil surface, except wind speed components at 10 m, useful to apply the FAO56-PM equation. The objective of this research is to assess the quality of ERA5-Land climate variables data to estimate daily ETo in Sicily, Italy. The effect of the weather station’s elevation associated with the statistical indicators was also evaluated to verify how the morphology affects the measurements. Finally, the sensitivity analysis of the FAO56-PM equation was carried out to identify which climate variables have the most influence on the ETo estimation. For the period 2006–2015, the comparison between air temperature, global solar radiation, wind speed, and relative air humidity, measured from 39 ground weather stations in Sicily, and ERA5-Land was carried out and then, through FAO56-PM equation daily ETo values were estimated using both databases. The statistical indicators Root Mean Square Error (RMSE) and Mean Bias Error (MBE) confirm the possibility of considering the ERA5-Land a suitable solution to estimate ETo. The sensitivity analysis showed that good ETo estimation depends mainly on the accuracy of the relative air humidity and air temperature data.

Artificial Neural Network for Forecasting Reference Evapotranspiration in Semi-Arid Bioclimatic Regions

A correct determination of irrigation water requirements necessitates an adequate estimation of reference evapotranspiration (ETo). In this study, monthly ETo is estimated using artificial neural network (ANN) models. Eleven combinations of long-term average monthly climatic data of air temperature (min and max), wind speed (WS), relative humidity (RH), and solar radiation (SR) recorded at nine different weather stations in Tunisia are used as inputs to the ANN models to calculate ETo given by the FAO-56 PM (Penman–Monteith) equation. This research study proposes to: (i) compare the FAO-24 BC, Riou, and Turc equations with the universal PM equation for estimating ETo; (ii) compare the PM method with the ANN technique; (iii) determine the meteorological parameters with the greatest impact on ETo prediction; and (iv) determine how accurate the ANN technique is in estimating ETo using data from nearby weather stations and compare it to the PM method. Four statistical criteria were used to evaluate the model’s predictive quality: the determination coefficient (R2), the index of agreement (d), the root mean square error (RMSE), and the mean absolute error (MAE). It is quite evident that the Blaney–Criddle, Riou, and Turc equations underestimate or overestimate the ETo values when compared to the PM method. Values of ETo underestimation ranged from 1.9% to 66.1%, while values of overestimation varied from 0.9% to 25.0%. The comparisons revealed that the ANN technique could be adeptly utilized to model ETo using the available meteorological data. Generally, the ANN technique performs better on the estimates of ETo than the conventional equations studied. Among the meteorological parameters considered, maximum temperature was identified as the most significant climatic parameter in ETo modeling, reaching values of R and d of 0.936 and 0.983, respectively. The research showed that trained ANNs could be used to yield ETo estimates using new data from nearby stations not included in the training process, reaching high average values of R and d values of 0.992 and 0.997, respectively. Very low values of MAE (0.233 mm day−1) and RMSE (0.326 mm day−1) were also obtained.

Innovative approach for predicting daily reference evapotranspiration using improved shallow and deep learning models in a coastal region: A comparative study

Accurate and reliable estimation of Reference Evapotranspiration (ETo) is crucial for water resources management, hydrological processes, and agricultural production. The FAO-56 Penman-Monteith (FAO-56PM) approach is recommended as the standard model for ETo estimation; nevertheless, the absence of comprehensive meteorological variables at many global locations frequently restricts its implementation. This study compares shallow learning (SL) and deep learning (DL) models for estimating daily ETo against the FAO-56PM approach based on various statistic metrics and graphic tool over a coastal Red Sea region, Sudan. A novel approach of the SL model, the Catboost Regressor (CBR) and three DL models: 1D-Convolutional Neural Networks (1D-CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) were adopted and coupled with a semi-supervised pseudo-labeling (PL) technique. Six scenarios were developed regarding different input combinations of meteorological variables such as air temperature (Tmin, Tmax, and Tmean), wind speed (U2), relative humidity (RH), sunshine hours duration (SSH), net radiation (Rn), and saturation vapor pressure deficit (es-ea). The results showed that the PL technique reduced the systematic error of SL and DL models during training for all the scenarios. The input combination of Tmin, Tmax, Tmean, and RH reflected higher performance than other combinations for all employed models. The CBR-PL model demonstrated good generalization abilities to predict daily ETo and was the overall superior model in the testing phase according to prediction accuracy, stability analysis, and less computation cost compared to DL models. Thus, the relatively simple CBR-PL model is highly recommended as a promising tool for predicting daily ETo in coastal regions worldwide which have limited climate data.

Effect of vegetation treatment and water stress on evapotranspiration in bioretention systems

Evapotranspiration is a key hydrological process for reducing stormwater runoff in bioretention systems, regardless of their physical configuration. Understanding the volumes of stormwater that can be returned to the atmosphere via evapotranspiration is, therefore, a key consideration in the design of any bioretention system. This study establishes the evapotranspiration dynamics of three common, structurally different, bioretention vegetation treatments (an Amenity Grass mix, and mono-cultures of Deschampsia cespitosa and Iris sibirica) compared with an un-vegetated control using lab-scale column experiments. Via continuous mass and moisture loss data, observed evapotranspiration rates were compared with those predicted by the FAO-56 Penman–Monteith model for five 14-day dry periods during Spring 2021, Summer 2021, and Spring 2022. Soil moisture reductions over the 14-day trials led to reduced rates of evapotranspiration. This necessitated the use of a soil moisture extraction function alongside a crop coefficient to represent actual evapotranspiration from FAO-56 Penman–Monteith reference evapotranspiration estimates. Crop coefficients (Kc) varied between 0.65 and 2.91, with a value of 1.0 identified as a recommended default value in the absence of treatment-specific empirical data. A continuous hydrological model with Kc=1.0 and a loading ratio of 10:1 showed that evapotranspiration could account for between 1 and 12% of the annual water budget for a bioretention system located in the UK and Ireland, increasing to a maximum of 35% when using the highest Kc observed (2.91).