Estimation of crop evapotranspiration using statistical and machine learning techniques with limited meteorological data: a case study in Udham Singh Nagar, India

Satpathi, Anurag; Danodia, Abhishek; Nain, Ajeet Singh; Dhyani, Makrand; Vishwakarma, Dinesh Kumar; Dewidar, Ahmed Z.; Mattar, Mohamed A.

doi:10.1007/s00704-024-04953-3

Cited by 4 publications

(1 citation statement)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks (ANNs) provide an alternative to empirical models for predicting hydrological resources and ET estimates without the need for predefined model frameworks (Maier et al, 2010;Kisi and Sanikhani, 2015;Park et al, 2016;Kisi et al, 2017;Granata, 2019a;Cemek et al, 2023;Satpathi et al, 2024 ).…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks Estimate Evapotranspiration For Miscanthus × Giganteus As Effectively As Empirical Model But With Fewer Inputs

Sungur,

Moore,

Bernacchi

et al. 2024

Preprint

View full text Add to dashboard Cite

Estimating actual evapotranspiration (ET) is particularly crucial for addressing how vegetation affects the water balance of ecosystems. ET estimation can be complex with empirical models due to their many parameters and reliance on aridity. In contrast, artificial neural networks (ANNs) could potentially estimate ET with fewer and more common meteorological parameters. In this study, we trained two ANNs, one using a feed-forward approach (FFN) and the other a nonlinear auto-regressive network (NARX), to predict ET and compared them to the commonly used empirical model Granger and Gray (GG). We trained our models on a nine-year eddy covariance (EC) dataset for Miscanthus × giganteus (M. × giganteus) from Illinois (UIEF), then tested them using out-of-sample data from both UIEF and a different location in Iowa (SABR) to compare the accuracy of FFN, NARX, and GG models in estimating daily ET. A combination of air temperature (Ta) and solar radiation (Rs) was chosen as inputs due to the highest R2 for FFN (R2= 0.79, 0.81, and 0.79 for training, testing, and validation, respectively) and only Ta for NARX (R2= 0.70 for out-of-sample validation). The predictive power of the FFN model was superior to the NARX and GG models at the UIEF site (R2= 0.84, 0.70, and 0.83 for out-of-sample validation, respectively). Our analysis showed that ANN approaches are as accurate as empirical approaches for estimating ET but use fewer inputs.

show abstract