In the value chain, yields are key information for both growers and other stakeholders in market supply and exports. However, orchard yields are often still based on an extrapolation of tree production which is visually assessed on a limited number of trees; a tedious and inaccurate task that gives no yield information at a finer scale than the orchard plot. In this work, we propose a method to accurately map individual tree production at the orchard scale by developing a trade-off methodology between mechanistic yield modelling and extensive fruit counting using machine vision systems. A methodological toolbox was developed and tested to estimate and map tree species, structure, and yields in mango orchards of various cropping systems (from monocultivar to plurispecific orchards) in the Niayes region, West Senegal. Tree structure parameters (height, crown area and volume), species, and mango cultivars were measured using unmanned aerial vehicle (UAV) photogrammetry and geographic, object-based image analysis. This procedure reached an average overall accuracy of 0.89 for classifying tree species and mango cultivars. Tree structure parameters combined with a fruit load index, which takes into account year and management effects, were implemented in predictive production models of three mango cultivars. Models reached satisfying accuracies with R² greater than 0.77 and RMSE% ranging from 20% to 29% when evaluated with the measured production of 60 validation trees. In 2017, this methodology was applied to 15 orchards overflown by UAV, and estimated yields were compared to those measured by the growers for six of them, showing the proper efficiency of our technology. The proposed method achieved the breakthrough of rapidly and precisely mapping mango yields without detecting fruits from ground imagery, but rather, by linking yields with tree structural parameters. Such a tool will provide growers with accurate yield estimations at the orchard scale, and will permit them to study the parameters that drive yield heterogeneity within and between orchards.

This paper presents results on the detection and identification mango fruits from colour images of trees. We evaluate the behaviour and the performances of the Faster R-CNN network to determine whether it is robust enough to "detect and classify" fruits under particularly heterogeneous conditions in terms of plant cultivars, plantation scheme, and visual information acquisition contexts. The network is trained to distinguish the 'Kent', 'Keitt', and "Boucodiekhal" mango cultivars from 3,000 representative labelled fruit annotations. The validation set composed of about 7,000 annotations was then tested with a confidence threshold of 0.7 and a Non-Maximal-Suppression threshold of 0.25. With a F1-score of 0.90, the Faster R-CNN is well suitable to the simple fruit detection in tiles of 500x500 pixels. We then combine a multi-tiling approach with a Jaccard matrix to merge the different parts of objects detected several times, and thus report the detections made at the tile scale to the native 6,000x4,000 pixel size images. Nonetheless with a F1-score of 0.56, the cultivar identification Faster R-CNN network presents some limitations for simultaneously detecting the mango fruits and identifying their respective cultivars. Despite the proven errors in fruit detection, the cultivar identification rates of the detected mango fruits are in the order of 80%. The ideal solution could combine a Mask R-CNN for the image pre-segmentation of trees and a double-stream Faster R-CNN for detecting the mango fruits and identifying their respective cultivar to provide predictions more relevant to users' expectations.

Plant breeding programs design new crop cultivars which, while developed for distinct populations of environments, are nevertheless grown over large areas during their time in the market. Over its cultivation area, the crop is exposed to highly diverse stress patterns caused by climatic uncertainty and multiple management options, which often leads to decreased expected crop performance. In this study, we aim is to assess how finer spatial management of genetic resources could reduce the yield variance explained by genotype × environment interactions in a set of cropping environments and ultimately improve the efficiency and stability of crop production. We used modeling and simulation to predict the crop performance resulting from the interaction between cultivar growth and development, climate and soil conditions, and management practices. We designed a computational experiment that evaluated the performance of a collection of commercial sunflower cultivars in a realistic population of cropping conditions in France, built from extensive agricultural surveys. Distinct farming locations sharing similar simulated abiotic stress patterns were clustered together to specify environment types. We then used optimization methods to search for cultivars × environments combinations leading to increased yield expectations. Results showed that a single cultivar choice adapted to the most frequent environment-type in the population is a robust strategy. However, the relevance of cultivar recommendations to specific locations was gradually increasing with the knowledge of pedo-climatic conditions. We argue that this approach while being operational on current genetic material could act synergistically with plant breeding as more diverse material could enable access to cultivars with distinctive traits, more adapted to specific conditions. Key message: Crop simulation helps to analyze environmental impacts on crops and provides year-independent context information. This information is of major importance when deciding which cultivar to choose at sowing time.