Deep learning convolutional neural networks (CNNs) have gained popularity in recent years for their ability to classify images with high levels of accuracy. In agriculture, they have been applied for disease identification, crop growth monitoring, animal behaviour tracking, and weed classification. Datasets traditionally consisting of thousands of images of each desired target are required to train CNNs. A recent survey of Nova Scotia wild blueberry (Vaccinium angustifolium Ait.) fields, however, determined that there are more than 200 unique species of weeds present. Collecting an image dataset containing thousands of images of each weed species to train a CNN would therefore be time-consuming and impractical. Meta deep learning allows for classification of images using a small number of labelled training examples, typically one or five images per class. To achieve this, the CNN is pre-trained using a standard dataset containing thousands of generic images. A support dataset containing a small number of images per class is provided for additional training of the specific target identities. A Siamese Convolutional Neural Network (SNN) then uses the features learned by the CNN to differentiate between the classes in the support dataset. In this study, a SNN will be trained to identify six species of weeds using the Keras-TensorFlow deep learning framework. The CNN training dataset will contain three weed classes with 800 images per class collected in April through June during the 2019 and 2020 field seasons. Support datasets containing one, five, and ten images per species were collected in April through July 2021 to train the SNN. Future work will involve using meta deep learning to identify common diseases in the wild blueberry crop including Monilinia blight (Monilinia vaccinii-corymbosi) and Botrytis blight (Botrytis cinerea). The trained SNNs will be deployed in a downloadable smartphone application and an online web-based application to facilitate streamlined delivery of pest identification and management information to wild blueberry growers.