Abstract: Embodiments of the disclosed technologies are capable of inputting, to a machine-learned classifier that has been created using a set of neural network-based models, multi-band digital image data that represents an aerial view of an agricultural field location containing an horticultural product; outputting, by the classifier, annotated image data, the annotated image data comprising annotation data indicative of individual instances of the horticultural product in the agricultural field location; using the annotated image data, computing a first predicted yield for the agricultural field location; adjusting the first predicted yield by a scaling factor to produce a second predicted yield for the agricultural field location.

Abstract: Systems and methods are provided for use in assessing regions (for example, trials) in fields. One example computer-implemented method includes identifying, by an agricultural computer system, two regions in a field for assessment, where at least one of the two regions is associated with an agricultural trial in the field, and generating an aggregate fitness metric for the two regions. In doing so, the aggregate fitness metric is indicative of a similarity between the two regions in the field. The method also includes determining, by the agricultural computer system, whether the aggregate fitness metric satisfies a defined threshold and, in response to determining that the aggregate fitness metric fails to satisfy the defined threshold, automatically discarding the trial.

Abstract: Embodiments of the disclosed technologies are capable of inputting, to a machine-learned classifier that has been created using a set of neural network-based models, multi-band digital image data that represents an aerial view of an agricultural field location containing an horticultural product; outputting, by the classifier, annotated image data, the annotated image data comprising annotation data indicative of individual instances of the horticultural product in the agricultural field location; using the annotated image data, computing a first predicted yield for the agricultural field location; adjusting the first predicted yield by a scaling factor to produce a second predicted yield for the agricultural field location.