Skip to main content
ARS Home » Pacific West Area » Kimberly, Idaho » Northwest Irrigation and Soils Research » Research » Publications at this Location » Publication #307918

Research Project: Soil and Water Conservation for Northwestern Irrigated Agriculture

Location: Northwest Irrigation and Soils Research

Title: Evaluation of neural network modeling to predict non-water-stressed leaf temperature in wine grape for calculation of crop water stress index

Author
item King, Bradley - Brad
item Shellie, Krista

Submitted to: Agricultural Water Management
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/12/2015
Publication Date: 1/26/2016
Publication URL: http://handle.nal.usda.gov/10113/61967
Citation: King, B.A., Shellie, K. 2016. Evaluation of neural network modeling to predict non-water-stressed leaf temperature in wine grape for calculation of crop water stress index. Agricultural Water Management. 167:38-52.

Interpretive Summary: Precision irrigation management in wine grape production is hindered by the lack of a reliable method to easily quantify and monitor vine water status. Mild to moderate water stress is desirable in wine grape for controlling vine vigor and optimizing fruit yield and quality. A crop water stress index (CWSI) that effectively monitors plant water status has not been widely adopted in wine grape because of the need to measure well-watered and non-transpiring leaf temperature under identical environmental conditions. In this study, we calculated a daily CWSI for the wine grape cultivars Syrah and Malbec (Vitis vinifera L.) by estimating well-watered leaf temperature with an artificial neural network model and non-transpiring leaf temperature based on the cumulative probability of the measured difference between ambient air and deficit-irrigated grapevine leaf temperature. We evaluated the reliability of this methodology by comparing the calculated CWSI to midday leaf water potential and irrigation amount in replicated plots of grape vines provided with 30, 70 or 100% of their estimated evapotranspiration demand. Predicted and measured well-watered leaf temperature had correlation coefficients of 0.91 and 0.86 for ‘Syrah’ and ‘Malbec’, respectively. Non-transpiring leaf temperature for both cultivars was estimated as air temperature plus 15 degrees Celsius. Calculated daily CWSI consistently differentiated between deficit irrigation amounts, irrigation events, and rainfall and explained between 51 and 70% of the variability in midday leaf water potential. The methodology used to calculate a daily CWSI for wine grape in this study provided a real-time indicator of vine water status that could be automated for use as a decision-support tool in a precision irrigation system.

Technical Abstract: Precision irrigation management in wine grape production is hindered by the lack of a reliable method to easily quantify and monitor vine water status. Mild to moderate water stress is desirable in wine grape for controlling vine vigor and optimizing fruit yield and quality. A crop water stress index (CWSI) that effectively monitors plant water status has not been widely adopted in wine grape because of the need to measure well-watered and non-transpiring leaf temperature under identical environmental conditions. In this study, we calculated a daily CWSI for the wine grape cultivars Syrah and Malbec (Vitis vinifera L.) by estimating well-watered leaf temperature with an artificial neural network (NN) model and non-transpiring leaf temperature based on the cumulative probability of the measured difference between ambient air and deficit-irrigated grapevine leaf temperature. We evaluated the reliability of this methodology by comparing the calculated CWSI to midday leaf water potential and irrigation amount in replicated plots of above ground, drip-irrigated vines provided with 30, 70 or 100% of their estimated evapotranspiration demand under warm, semiarid field conditions in southwestern Idaho USA. Infrared and environmental sensors were used to monitor leaf temperature and weather conditions throughout berry development. The input variables for the NN model with lowest error were 15-minute average values for air temperature, relative humidity, solar radiation and wind speed collected between 13:00 and 15:00 MDT. A feed-forward perceptron NN model was developed for each cultivar because of their difference in well-watered leaf temperature. Predicted and measured well-watered leaf temperature had correlation coefficients of 0.91 and 0.86 for ‘Syrah’ and ‘Malbec’, respectively. Non-transpiring leaf temperature for both cultivars was air temperature plus 15 degrees Celsius. The daily CWSI consistently differentiated between deficit irrigation amounts, irrigation events, and rainfall and explained between 51 and 70% of the variability in midday leaf water potential. The methodology used to calculate a daily CWSI for wine grape in this study provided a real-time indicator of vine water status that could be automated for use as a decision-support tool in a precision irrigation system.