Daily Reference Evapotranspiration Estimation using Linear Regression and ANN Models

Mallikarjuna, P.; Jyothy, S. Aruna; Reddy, K. Chandrasekhar

doi:10.1007/s40030-013-0030-2

Cited by 15 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They put forward these models for regions with similar climatic conditions. The regression models developed earlier by Mallikarjuna et al for the same area, utilizing the same explanatory variables, also showed a satisfactory performance in ETo estimation at daily scale (i.e., R 2 between 89.1-97% and RMSE between 0.26-0.49 mm d −1 ) [50]. Khoshravesh et al applied nonlinear and Bayesian regression models for three arid regions in Iran, and the best results they yielded were R 2 > 95% and a RMSE of about 4.00 mm d −1 [51].…”

Section: Introductionsupporting

confidence: 58%

Multiple Linear Regression Models with Limited Data for the Prediction of Reference Evapotranspiration of the Peloponnese, Greece

Dimitriadou

Nikolakopoulos

2022

Hydrology

View full text Add to dashboard Cite

The aim of this study was to investigate the utility of multiple linear regression (MLR) for the estimation of reference evapotranspiration (ETo) of the Peloponnese, Greece, for two representative months of winter and summer during 2016–2019. Another objective was to test the number of inputs needed for satisfactorily accurate estimates via MLR. Datasets from sixty-two meteorological stations were exploited. The available independent variables were sunshine hours (N), mean temperature (Tmean), solar radiation (Rs), net radiation (Rn), wind speed (u2), vapour pressure deficit (es − ea), and altitude (Z). Sixteen MLR models were tested and compared to the corresponding ETo estimates computed by FAO-56 Penman–Monteith (FAO PM) in a previous study, via statistical indices of error and agreement. The MLR5 model with five input variables outperformed the other models (RMSE = 0.28 mm d−1, adj. R2 = 98.1%). Half of the tested models (two to six inputs) exhibited very satisfactory predictions. Models of one input (e.g., N, Rn) were also promising. However, the MLR with u2 as the sole input variable presented the worst performance, probably because its relationship with ETo cannot be linearly described. The results indicate that MLR has the potential to produce very good predictive models of ETo for the Peloponnese, based on the literature standards.

show abstract

Section: Introductionsupporting

confidence: 58%

Multiple Linear Regression Models with Limited Data for the Prediction of Reference Evapotranspiration of the Peloponnese, Greece

Dimitriadou

Nikolakopoulos

2022

Hydrology

View full text Add to dashboard Cite

show abstract

“…It is a semi-empirical model. Different regions have different meteorological and hydrological elements and need to be tested and evaluated at specific locations to improve the accuracy of model predictions [35][36][37] . In addition, there are more suitable evapotranspiration models to estimate evapotranspiration in the study area.…”

Section: Discussionmentioning

confidence: 99%

Analysis of the variation in potential evapotranspiration and surface wet conditions in the Hancang River Basin, China

Zhang

Wang

2021

Sci Rep

View full text Add to dashboard Cite

Evapotranspiration is an important component of the water cycle, and possible trends in evapotranspiration can, among others, influence water management and agricultural production. Potential evapotranspiration (ETp) is a measure of the ability of the atmosphere to remove water from the surface through the processes of evaporation and transpiration. It plays an important role in assessing regional dry–wet conditions and variations in meteorological conditions. This study analyzed the change trends of monthly ETp and surface dryness and wetness in the Hancang River Basin and, through principal component analysis and correlation analysis, explored the main meteorological factors that affected ETp and the interactions between meteorological factors; ETp values were estimated using the FAO-56 Penman–Monteith method. The results showed that there was a large gap in ETp between different months in the Hancang River Basin, with a trend of first increasing and then decreasing within a year. The highest monthly evapotranspiration was 114.119 mm (July), and the lowest was 42.761 mm (January). The maximum relative humidity index was 0.822 (August), and the minimum was -0.979 (January). The average temperature, precipitation, average relative humidity, and solar radiation are positive factors that affect ETp, while average air pressure is a negative factor that affects ETp. This study provides a reference for the wet conditions of small watersheds and for countermeasures to address climate change.

show abstract

“…The findings revealed that the SVM performed better than the other models in predicting ET 0 with a higher accuracy (99%). In addition, several studies in the literature (Kim et al., 2022; Mallikarjuna et al., 2012; Wen et al., 2015) used NN, RF, SVM, and LR for ET 0 estimation reportingly found SVM, NN, and LR performed the best.…”

Section: Discussionmentioning

confidence: 99%

Reference evapotranspiration prediction using machine learning models: An empirical study from minimal climate data

Shaloo,

Kumar,

Bisht

et al. 2023

Agronomy Journal

View full text Add to dashboard Cite

The scarcity of climatic data is the biggest challenge for developing countries and the development of models for reference evapotranspiration (ET0) estimation with limited datasets is crucial. Therefore, the current investigation assessed the efficacy of four machine learning (ML) models viz., Linear Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Neural Networks (NN) to predict ET0 based on minimal climate data in comparison with the standard FAO‐56 Penman‐Monteith (PM) method. The data on daily climate parameters were collected for the period 2000−2021, including maximum and minimum temperature (Tmax, Tmin), mean relative humidity (RH), wind speed (WS) and sunshine hours (SSH). The performance of the developed models considering different input combinations was evaluated by using several statistical performance measures. The results showed that the SVM model performed better than the other ML models during training (R2 = 0.985; mean absolute error [MAE] = 0.170 mm/d; mean square error [MSE] = 0.052 mm/d; root mean square error [RMSE] = 0.229 mm/d; mean absolute percentage error [MAPE] = 5.72%,) and testing stages (R2 = 0.985; MAE = 0.168 mm/d; MSE = 0.050 mm/d; RMSE = 0.224 mm/d; MAPE = 5.91%) under full dataset scenario. The best performance of the models to estimate was with Tmax, RH. Ws, SSH and Tmin. The results of the current study are substantial as it offers an approach to estimate ET0 in semi‐arid data scarce region.This article is protected by copyright. All rights reserved

show abstract

Daily Reference Evapotranspiration Estimation using Linear Regression and ANN Models

Cited by 15 publications

References 10 publications

Multiple Linear Regression Models with Limited Data for the Prediction of Reference Evapotranspiration of the Peloponnese, Greece

Multiple Linear Regression Models with Limited Data for the Prediction of Reference Evapotranspiration of the Peloponnese, Greece

Analysis of the variation in potential evapotranspiration and surface wet conditions in the Hancang River Basin, China

Reference evapotranspiration prediction using machine learning models: An empirical study from minimal climate data

Contact Info

Product

Resources

About