Prediction of reference crop evapotranspiration: Empirical and machine learning approaches

T. R. Jayashree, N. V.Subba Reddy, U. Dinesh Acharya, Saeid Eslamian

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)


There are several empirical methods for calculating the reference crop evapotranspiration (ET0) from the meteorological parameters. The Penman-Monteith method recommended by the Food and Agriculture Organization (FAO) of the United Nations is the globally accepted and most widely used method for the estimation of ET0 across diverse climatic regimes. The hardships involved in handling a large number of climatic variables and their interdependence make the computation time-consuming and cumbersome. The computational methods involving machine learning techniques have been widely used in modeling ET0 using limited and complete climate datasets. In this article, we have focused on the various empirical methods for ET0 calculations and also the application of various machine learning techniques in predicting ET0 from the climate variables of assorted climatic conditions. The potential of novel deep learning techniques has been discussed along with a case study to model ET0 in the concerned study region.

Original languageEnglish
Title of host publicationHandbook of HydroInformatics
Subtitle of host publicationVolume II: Advanced Machine Learning Techniques
Number of pages16
ISBN (Electronic)9780128219614
ISBN (Print)9780128219508
Publication statusPublished - 01-01-2022

All Science Journal Classification (ASJC) codes

  • Environmental Science(all)


Dive into the research topics of 'Prediction of reference crop evapotranspiration: Empirical and machine learning approaches'. Together they form a unique fingerprint.

Cite this