Thermal-RGB imagery and in-field weather sensing derived sweet cherry wetness prediction model

Authors: RANJAN, RAKESH - Freshwater Institute; SINHA, RAJEEV - Washington State University; KHOT, LAV - Washington State University; WHITING, MATTHEW - Washington State University

Submitted to: Scientia Horticulturae
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/28/2021
Publication Date: 2/27/2022
Citation: Ranjan, R., Sinha, R., Khot, L.R., Whiting, M. 2022. Thermal-RGB imagery and in-field weather sensing derived sweet cherry wetness prediction model. Scientia Horticulturae. 294:110782. https://doi.org/10.1016/j.scienta.2021.110782.
DOI: https://doi.org/10.1016/j.scienta.2021.110782

Interpretive Summary: Rain-induced pre-harvest cracking of fruits has the potential to severely reduce sweet cherry production. Preharvest rain can cause s cracking losses as high as 90% of the total yield, though typically damage rates of 25% will render the crop uneconomical to harvest and sort. The grower’s decision to initiate preventative methods is complicated by the fruit’s sensitivity to cracking and key environmental factors including temperature and wind speed, and the rate and duration of rainfall. An empirical measure of fruit wetness would be thus beneficial. Apart from the cherry cracking, wetness levels and duration can also influence the susceptibility of various fungal diseases including downy mildew and brown rot in grapevine, sweet cherry, peach, and other orchard crops. Hence, a real-time fruit wetness and wetness duration estimation could assist growers in effective crop loss management. Therefore, this study was conducted to develop a thermal-RGB imagery and microclimate sensing derived cherry wetness prediction models for two cracking susceptible sweet cherry cultivars, ‘Selah’ and ‘Skeena’. A stepwise multilinear regression analysis was performed to select a model with the highest prediction power and an optimal number of input variables. The cultivar specific wetness models with fruit surface temperature and three in-field weather parameters (i.e., air temperature, relative humidity, and solar radiation) as predictor variables resulted in best prediction accuracy. Wind velocity and dew point temperature did not contribute significantly to wetness prediction. Results from this study will help inform growers with their decisions to initiate preventative methods to reduce pre-harvest cracking.

Technical Abstract: Rain-induced cracking of sweet cherry (Prunus avium L.) fruit causes substantial economic loss to tree fruit growers annually. Increased fruit surface wetness triggers absorption of water in maturing fruits and leads to fruit cracking. This study was undertaken to develop and evaluate thermal-RGB imagery and in-field weather sensing derived wetness prediction models as tools to help mitigate cracking. We developed two cultivar-specific cherry wetness prediction models, one with only the weather data and other combined with the imagery data derived fruit surface temperature (FST). The suitability and accuracy of such models was validated for two cherry cultivars (cv. ‘Selah’ and ‘Skeena’). The FST and weather data derived model indicated an improved wetness prediction for both the cultivars. Strong relations (R2 = 0.80 and 0.86) and marginal prediction errors (Root Mean Squared Error = 8.7% and 3.5%) were observed between measured and predicted wetness for ‘Selah’ and ‘Skeena’ cultivars, respectively. However, weaker relations (R2= 0.66 and 0.53) were observed, when a model for a particular cultivar was validated against other cultivar, indicating the need of cultivar specific models. Such models can be integrated with a decision support system and crop protection (e.g. rainwater removal, chemical spraying) techniques, for improved crop loss management.