Work

Potential of thermal imaging for yield and soil water content prediction in leafy vegetables

Year: 2025

Type: article

Abstract: In agriculture, water deficit stress is among the main causes of crop yield losses, particularly in leafy vegetables, which are highly sensitive. The need for efficient irrigation management and the early identification of potential yield gaps encourage the development of predictive models and the integration of more precise technologies. From this perspective, infrared radiation cameras in the capture of thermal information have potential for application. The objective of this study was to develop predictive models of yield and soil water content in leafy vegetables crops, specifically lettuce and arugula, by integrating thermal images obtained using infrared radiation cameras. Two experiments were carried out in Piracicaba, São Paulo, Brazil, using lettuce and arugula crops, each with two growing cycles. A randomized complete block design (RCBD) was adopted, with three irrigation levels: 100, 80, and 60 % of crop evapotranspiration replacement. For model development, crop yield was assessed based on shoot biomass at harvest, and soil water content was measured using tensiometry-based sensors. The Crop Water Stress Index (CWSI) and the normalized temperature difference (ΔT) were calculated from thermal images of the plant canopy. Yield prediction models exhibited R2 values of 0.71 and 0.82 using CWSI, and 0.75 and 0.79 using ΔT, for lettuce and arugula, respectively, with a mean RMSE of 4.87 t ha-1. Soil water content prediction models showed R2 values of 0.92 based on CWSI and 0.73 based on ΔT, with a mean RMSE of 0.00428 m3 m-3. The developed models demonstrated good predictive performance, indicating their applicability for irrigation management and for predicting possible early yield gaps in leafy vegetables. CWSI and ΔT values above 0.35 and -0.96 °C, respectively, are recommended as critical thresholds to avoid water deficit stress in lettuce and arugula crops.

Source: Smart Agricultural Technology

DOI: 10.1016/j.atech.2025.101587

Authors: Vinícius Villa e Vila, Silas Alves Souza, Fernando Campos Mendonça, Tamara Maria Gomes, Peterson Ricardo Fiorio, Patricia Angélica Alves Marques

Institution: Universidade de São Paulo

Language: English

Topic: Remote Sensing in Agriculture

Subfield: Ecology

Field: Environmental Science

Domain: Physical Sciences

SDG: Zero hunger

Open Access status: gold

Estimated APC paid: $1,770