Agricultural producers have many incentives to clear small natural areas from their fields, as this can expand their cultivated land base. However, natural areas can play a role in delivering ecosystem services that improve crop productivity (e.g., by providing habitat for beneficial arthropods, that deliver pollination or pest control). We assessed the impact of landscape complexity on adjacent canola (Brassica napus) yield at both the field- and subfield-level using remotely sensed products. Fields with higher landscape complexity generally had higher mean yields. However, fields surrounded mostly by either crop or non-crop covers had lower yields, possibly due to a lack of ecosystem services (i.e., pollination or natural pest control services) or a strong yield-reducing edge effect. At the subfield-level, we found evidence of a boost in yield between 30 and 100 m from the field edge towards its center, as well as a potential yield-stabilizing effect at the same range.

Precision yield data is commonly recorded by modern combine harvesters and can be used to help growers optimize their operations. However, there have been very few attempts to predict variation in yield within a given field using multispectral satellite data. We used a precision yield dataset gathered in canola (Brassica napus L.) crops in central Alberta, Canada, and a time series of medium-resolution Sentinel-2 data collected over the growing season. Using two mapping methods, random forest regression and functional data analysis, we were able to predict crop yield to within 12-16% accuracy of actual yield, and to capture within-field variation. Our results demonstrate that time series of medium-resolution multispectral imagery is capable of mapping small-scale variation in crop yields, presenting new research and management applications for these techniques.