In-field classification of herbicide-resistant Papaver rhoeas and Stellaria media using an imaging sensor of the maximum quantum efficiency of photosystem II

Reliable in-season and in-field tools for rapidly quantifying herbicide efficacy in dicotyledonous weeds are missing. In this study, the maximum quantum efficiency of photosystem II (F-v/F-m) of susceptible and resistant Papaver rhoeas and Stellaria media populations in response to treatments with acetolactate synthase (ALS) inhibitors were examined. Seedlings (4-6 leafs) were transplanted into the field immediately after the application of the ALS inhibitors florasulam, metsulfuron-methyl and tribenuron-methyl. The F-v/F-m values were assessed 1-7, 9 and 14 days after treatment (DAT). Based on the F-v/F-m values of all fluorescing pixels in the images of herbicide-treated plants, discriminant maximum-likelihood classifiers were created. Based on this classifier, an independent set of images were classified into 'susceptible' or 'resistant' plants. The classifiers' accuracy, false-positive rate and false-negative rate were calculated. The F-v/F-m values of sensitive P. rhoeas and S. media plants decreased within 3 DAT by 28-43%. The F-v/F-m values of the resistant plants of both species were 20% higher than those of the sensitive plants in all herbicide treatments. The classifier separated sensitive and resistant plants 3 DAT with accuracies of 62-100%. False-positive and false-negative classifications decreased with increasing DAT. We conclude that by the assessment of the F-v/F-m value in combination with the classification sensitive and resistant P. rhoeas and S. media populations could be separated 3 DAT. This technique can help to select effective control methods and speed up the monitoring process of susceptible and resistant weeds.