Author(s): Likith Muni Narakala; Manoj Yadav; Ghanshyam Giri; Hitesh Upreti; Gopal Das Singhal

Linked Author(s): Gopal Das Singhal

Keywords: Canopy temperature Artificial neural networks irrigation scheduling

Abstract: Efficient irrigation management is crucial for sustaining crop yields in water-scarce regions, with plant-based indicators, such as canopy temperature (Tc), offering promising solutions for water stress assessment. This study aims to enhance the Tc predictions using artificial neural networks (ANNs), leveraging meteorological and soil moisture data collected for wheat crop during the two cropping seasons: 2021-22,2022-23 at the Water Management Research Laboratory, Shiv Nadar Institution of Eminence (SNIoE). Five input configurations were tested, progressively reducing soil moisture depth layers, to identify the optimal combination of predictors. The best-performing model, combination C4, which included vapor pressure deficit (VPD), air temperature (Ta), net radiation (Rn), wind speed (U), and soil moisture at 10 cm (SD10), achieved least MAE of 1.13 during training and 1.27 while testing. These results underscore the importance of integrating shallow soil moisture data with meteorological parameters to improve Tc prediction accuracy, advancing CWSI reliability for irrigation scheduling. This ANN-based approach demonstrates a potential tool for water management practices, paving the way for further research in diverse agro-climatic contexts.

DOI:

Year: 2025