Key message: The growth of UCB-1 pistachio rootstock seedlings in the earliest years is a poor predictor of subsequent growth. Therefore, rogueing during the 1st years of growth is not effective. The UCB-1 hybrid, produced from a controlled cross betweenPistacia atlantica(female) andP. integerrima(male), is the main pistachio rootstock used in the USA. Variation has been observed in orchards planted with seedling UCB-1 rootstocks for over 20 years. Reduced vigor and stunting of some trees are of particular concern to growers due to decreased nut yield. This study was conducted to better understand the growth of non-grafted UCB-1, as well as between UCB-1 rootstock andPistacia verascions in commercial orchards. Phenotypic traits were evaluated in the non-grafted orchard. Grafted tree data were collected for bothP. verafemale scions and their UCB-1 seedling rootstocks in commercial orchards. The uniformity of tree height, trunk caliper, and canopy volume decreased annually during the first 5 years of growth. Individual tree growth was not linear and was poorly synchronized among siblings, causing the population to become increasingly less uniform as it aged. Consequently, growth in the earliest years is a poor predictor of subsequent growth. The strongest correlation was between growth parameters during the later years. There was a significant correlation between rootstock and scion caliper of the grafted trees in commercial orchards, with the least vigorous rootstocks producing the least vigorous scions. These data confirm the need to reliably rogue out seedlings that later will not be vigorous; however, our data show that rogueing based on the 1st years of growth is ineffective. This study suggests the need to develop predictive molecular markers for rootstock vigor.
Monitoring individual tree crown characteristics is an important component of smart agriculture and is crucial for orchard management. We focused on understanding how UAV imagery taken across one growing season can help understand and predict the growth and development of pistachio trees grown from rootstock seedlings. Tree crown characteristics (i.e., height, size, shape, and mean normalized difference vegetation index (NDVI)) were derived using an object-based image analysis method with multispectral Uncrewed Aerial Vehicles (UAV) imagery flown seven times over 472 five-year-old pistachio trees in 2018. These imagery-derived metrics were compared with field-collected tree characteristics (tree height, trunk caliper, crown height, width and volume, and leaf development status) collected over two months in 2018. The UAV method captured seasonal development of tree crowns well. UAV-derived tree characteristics were better correlated with the field tree characteristics when recorded between May and November, with high overall correlations in November. The highest correlation (R2 = 0.774) was found between trunk caliper and June UAV crown size. The weakest correlations between UAV and field traits were found in March and December. Spring leaf development stage was most variable, and mean NDVI values were lowest in March, when leaf development starts. Mean NDVI increased orchard-wide by May, and was consistently high through November. This study showcased the benefits of timely, detailed drone imagery for orchard managers.
Extracting the irregular and complex shapes of individual tree crowns from high-resolution imagery can play a crucial role in many applications, including precision agriculture. We evaluated three CNN models - MASK R-CNN, YOLOv3, and SAM - and compared their tree crown results with OBIA-based reference datasets from UAV imagery for seven dates across one growing season. We found that YOLOv3 performed poorly across all dates; both MASK R-CNN and SAM performed well in May, June, September, and November (Precision, Recall and F1 scores over 0.79). All models struggled in the early season imagery (e.g., March). MASK R-CNN outperformed other models in August (when there was smoke haze) and December (showing end of season red leaf senescence). SAM was the fastest model, and as it required no training, it could cover more area in less time; MASK R-CNN was very accurate and customizable. In this paper, we aimed to contribute insight into which CNN model offers the best balance of accuracy and ease of implementation for orchard management tasks. We also evaluated their applicability within one software ecosystem, ESRI ArcGIS Pro, and showed how such an approach offers users a streamlined, efficient way to detect objects in high resolution UAV imagery.
Extracting the shapes of individual tree crowns from high-resolution imagery can play a crucial role in many applications, including precision agriculture. We evaluated three CNN models—MASK R-CNN, YOLOv3, and SAM—and compared their tree crown results with OBIA-based reference datasets from UAV imagery for seven dates across one growing season. We found that YOLOv3 performed poorly across all dates; both MASK R-CNN and SAM performed well in May, June, September, and November (precision, recall, and F1 scores over 0.79). All models struggled in the early season imagery (e.g., March). MASK R-CNN outperformed other models in August (when there was smoke haze) and December (showing end-of-season variation in leaf color). SAM was the fastest model, and, as it required no training, it could cover more area in less time; MASK R-CNN was very accurate and customizable. In this paper, we aimed to contribute insight into which CNN model offers the best balance of accuracy and ease of implementation for orchard management tasks. We also evaluated its applicability within one software ecosystem, ESRI ArcGIS Pro, and showed how such an approach offers users a streamlined efficient way to detect objects in high-resolution UAV imagery.