Link to home

Cannot retrieve the URL specified in the Content Link property. For more assistance, contact your site administrator.

Predicting ascospore release of Monilinia vaccinii-corymbosi causing mummy berry of blueberry in the Pacific Northwest using machine learning
Dalphy Harteveld: Washingtom State University; Tobin Peever: Washington State University; Jay Pscheidt: Oregon State University; Michael Grant: University of Washington
<div>Mummy berry, caused by <i>M. vaccinii-corymbosi,</i> causes economic losses of highbush blueberry in the US Pacific Northwest. Apothecia develop from mummified berries overwintering on soil surfaces and produce ascospores that infect emerging tissue from floral and vegetative buds. Disease control currently relies on calendar-based fungicide sprays rather than on the disease cycle. To establish a prediction model for ascospore release, apothecial development was tracked in three fields, one in northwestern OR and two in northwestern WA in 2015 and 2016. The environmental factors air and soil temperature, precipitation, soil moisture, leaf wetness, relative humidity and solar radiation were monitored using in-field weather stations and WSU’s Agweathernet. Four modeling approaches were compared: logistic regression, multivariate adaptive regression splines, artificial neural networks and random forest. A supervised learning approach was used to train the models on two data sets: training (70%) and testing (30%). Importance of environmental factors was calculated for each model separately. Soil temperature, soil moisture, and solar radiation were identified as the most important factors influencing ascospore release. Random forest showed the highest accuracy compared to the other models, and was used in the production of an interactive web application aimed at assisting growers in predicting inoculum release in their fields for fungicide optimization and reduced cost.</div>

View Presentation