Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain

Precise determination of the reference evapotranspiration (ET0) is vital to studying the hydrological cycle. In addition, it plays a significant role in properly managing and allocating water resources in agriculture. The objective of this research was to examine the effectiveness of five different...

Full description

Saved in:
Bibliographic Details
Main Authors: Semin Topaloğlu Paksoy, Deniz Levent Koç
Format: Article
Language:English
Published: Faculty of Agriculture, Ankara University 2025-01-01
Series:Journal of Agricultural Sciences
Subjects:
Online Access:https://dergipark.org.tr/en/download/article-file/3917755
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832576140104957952
author Semin Topaloğlu Paksoy
Deniz Levent Koç
author_facet Semin Topaloğlu Paksoy
Deniz Levent Koç
author_sort Semin Topaloğlu Paksoy
collection DOAJ
description Precise determination of the reference evapotranspiration (ET0) is vital to studying the hydrological cycle. In addition, it plays a significant role in properly managing and allocating water resources in agriculture. The objective of this research was to examine the effectiveness of five different data-driven techniques, including artificial neural networks "multilayer perceptron" (ANN), gene expression programming (GEP), random forest (RF), support vector machine "radial basis function" (SVM), and multiple linear regression (MLR) to model the daily ET0. These methods were also compared with Hargreaves-Samani (HS), Oudin, Ritchie, Makkink (MAK), and Jensen Haise (JH) empirical models and their calibrated versions. The empirical models JH and MAK performed better than the models HS and Oudin after being calibrated by linear regression. All data-driven methods with four inputs were superior to the original and calibrated empirical models. Generally, data-driven models provided increased accuracy and enhanced generalization in predicting daily reference evapotranspiration compared to empirical models. The RF and ANN methods generally demonstrated better estimation accuracy than other data-driven methods. The performance of the RF and ANN models that utilized Tmax, Tmin, and Rs inputs, as well as those that incorporated Tmax, Tmin, Rs, and U2 inputs, proved to be superior to their corresponding MLR-based and GEP-based models for predicting ET0 in the Adana plain, which is characterized by a Mediterranean climate. Nevertheless, the GEP and MLR methods have the advantage of utilizing explicit algebraic equations, making them more convenient to apply, especially in the context of agricultural irrigation practices.
format Article
id doaj-art-8eebf07f51fd4f0d9e8943000ed78290
institution Kabale University
issn 1300-7580
language English
publishDate 2025-01-01
publisher Faculty of Agriculture, Ankara University
record_format Article
series Journal of Agricultural Sciences
spelling doaj-art-8eebf07f51fd4f0d9e8943000ed782902025-01-31T10:57:51ZengFaculty of Agriculture, Ankara UniversityJournal of Agricultural Sciences1300-75802025-01-0131120722910.15832/ankutbd.148120745Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plainSemin Topaloğlu Paksoy0https://orcid.org/0000-0003-1693-0184Deniz Levent Koç1https://orcid.org/0000-0002-4495-3060ÇUKUROVA ÜNİVERSİTESİ, İKTİSADİ VE İDARİ BİLİMLER FAKÜLTESİ, EKONOMETRİ BÖLÜMÜ, EKONOMETRİ PR.ÇUKUROVA ÜNİVERSİTESİ, ZİRAAT FAKÜLTESİ, TARIMSAL YAPILAR VE SULAMA BÖLÜMÜPrecise determination of the reference evapotranspiration (ET0) is vital to studying the hydrological cycle. In addition, it plays a significant role in properly managing and allocating water resources in agriculture. The objective of this research was to examine the effectiveness of five different data-driven techniques, including artificial neural networks "multilayer perceptron" (ANN), gene expression programming (GEP), random forest (RF), support vector machine "radial basis function" (SVM), and multiple linear regression (MLR) to model the daily ET0. These methods were also compared with Hargreaves-Samani (HS), Oudin, Ritchie, Makkink (MAK), and Jensen Haise (JH) empirical models and their calibrated versions. The empirical models JH and MAK performed better than the models HS and Oudin after being calibrated by linear regression. All data-driven methods with four inputs were superior to the original and calibrated empirical models. Generally, data-driven models provided increased accuracy and enhanced generalization in predicting daily reference evapotranspiration compared to empirical models. The RF and ANN methods generally demonstrated better estimation accuracy than other data-driven methods. The performance of the RF and ANN models that utilized Tmax, Tmin, and Rs inputs, as well as those that incorporated Tmax, Tmin, Rs, and U2 inputs, proved to be superior to their corresponding MLR-based and GEP-based models for predicting ET0 in the Adana plain, which is characterized by a Mediterranean climate. Nevertheless, the GEP and MLR methods have the advantage of utilizing explicit algebraic equations, making them more convenient to apply, especially in the context of agricultural irrigation practices.https://dergipark.org.tr/en/download/article-file/3917755reference evapotranspirationdata-driven approachesempirical modelscalibrationadana plain
spellingShingle Semin Topaloğlu Paksoy
Deniz Levent Koç
Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain
Journal of Agricultural Sciences
reference evapotranspiration
data-driven approaches
empirical models
calibration
adana plain
title Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain
title_full Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain
title_fullStr Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain
title_full_unstemmed Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain
title_short Daily reference evapotranspiration prediction using empirical and data-driven approaches: A case study of Adana plain
title_sort daily reference evapotranspiration prediction using empirical and data driven approaches a case study of adana plain
topic reference evapotranspiration
data-driven approaches
empirical models
calibration
adana plain
url https://dergipark.org.tr/en/download/article-file/3917755
work_keys_str_mv AT semintopaloglupaksoy dailyreferenceevapotranspirationpredictionusingempiricalanddatadrivenapproachesacasestudyofadanaplain
AT denizleventkoc dailyreferenceevapotranspirationpredictionusingempiricalanddatadrivenapproachesacasestudyofadanaplain