Wine growers prefer cultivars with looser bunch architecture because of the decreased risk for bunch rot. As a consequence, grapevine breeders have to select seedlings and new cultivars with regard to appropriate bunch traits. Bunch architecture is a mosaic of different single traits which makes phenotyping labor-intensive and time-consuming. In the present study, a fast and high-precision phenotyping pipeline was developed. The optical sensor Artec Spider 3D scanner (Artec 3D, L-1466, Luxembourg) was used to generate dense 3D point clouds of grapevine bunches under lab conditions and an automated analysis software called 3D-Bunch-Tool was developed to extract different single 3D bunch traits, i.e., the number of berries, berry diameter, single berry volume, total volume of berries, convex hull volume of grapes, bunch width and bunch length. The method was validated on whole bunches of different grapevine cultivars and phenotypic variable breeding material. Reliable phenotypic data were obtained which show high significant correlations (up to r² = 0.95 for berry number) compared to ground truth data. Moreover, it was shown that the Artec Spider can be used directly in the field where achieved data show comparable precision with regard to the lab application. This non-invasive and non-contact field application facilitates the first high-precision phenotyping pipeline based on 3D bunch traits in large plant sets.

Remote sensing data represent one of the most important sources for automized yield prediction. High temporal and spatial resolution, historical record availability, reliability, and low cost are key factors in predicting yields around the world. Yield prediction as a machine learning task is challenging, as reliable ground truth data are difficult to obtain, especially since new data points can only be acquired once a year during harvest. Factors that influence annual yields are plentiful, and data acquisition can be expensive, as crop-related data often need to be captured by experts or specialized sensors. A solution to both problems can be provided by deep transfer learning based on remote sensing data. Satellite images are free of charge, and transfer learning allows recognition of yield-related patterns within countries where data are plentiful and transfers the knowledge to other domains, thus limiting the number of ground truth observations needed. Within this study, we examine the use of transfer learning for yield prediction, where the data preprocessing towards histograms is unique. We present a deep transfer learning framework for yield prediction and demonstrate its successful application to transfer knowledge gained from US soybean yield prediction to soybean yield prediction within Argentina. We perform a temporal alignment of the two domains and improve transfer learning by applying several transfer learning techniques, such as ${\mathrm{L}}^2$-SP, BSS, and layer freezing, to overcome catastrophic forgetting and negative transfer problems. Lastly, we exploit spatio-temporal patterns within the data by applying a Gaussian process. We are able to improve the performance of soybean yield prediction in Argentina by a total of 19% in terms of RMSE and 39% in terms of ${\mathrm{R}}^2$ compared to predictions without transfer learning and Gaussian processes. This proof of concept for advanced transfer learning techniques for yield prediction and remote sensing data in the form of histograms can enable successful yield prediction, especially in emerging and developing countries, where reliable data are usually limited.

In grapevine breeding, loose grape bunch architecture is one of the most important selection traits, contributing to an increased resilience towards Botrytis bunch rot. Grape bunch architecture is mainly influenced by the berry number, berry size, the total berry volume, and bunch width and length. For an objective, precise, and high-throughput assessment of these architectural traits, the 3D imaging sensor Artec^® Spider was applied to gather dense point clouds of the visible side of grape bunches directly in the field. Data acquisition in the field is much faster and non-destructive in comparison to lab applications but results in incomplete point clouds and, thus, mostly incomplete phenotypic values. Therefore, lab scans of whole bunches (360°) were used as ground truth. We observed strong correlations between field and lab data but also shifts in mean and max values, especially for the berry number and total berry volume. For this reason, the present study is focused on the training and validation of different predictive regression models using 3D data from approximately 2000 different grape bunches in order to predict incomplete bunch traits from field data. Modeling concepts included simple linear regression and machine learning-based approaches. The support vector machine was the best and most robust regression model, predicting the phenotypic traits with an R² of 0.70–0.91. As a breeding orientated proof-of-concept, we additionally performed a Quantitative Trait Loci (QTL)-analysis with both the field modeled and lab data. All types of data resulted in joint QTL regions, indicating that this innovative, fast, and non-destructive phenotyping method is also applicable for molecular marker development and grapevine breeding research.

Behavioral analysis of animals in the wild plays an important role for ecological research and conservation and has been mostly performed by researchers. We introduce an action detection approach that automates this process by detecting animals and performing action recognition on the detected animals in camera trap videos. Our action detection approach is based on SWIFT (segmentation with filtering of tracklets), which we have already shown to successfully detect and track animals in wildlife videos, and MAROON (mask-guided action recognition), an action recognition network that we are introducing here. The basic ideas of MAROON are the exploitation of the instance masks detected by SWIFT and a triple-stream network. The instance masks enable more accurate action recognition, especially if multiple animals appear in a video at the same time. The triple-stream approach extracts features for the motion and appearance of the animal. We evaluate the quality of our action recognition on two self-generated datasets, from an animal enclosure and from the wild. These datasets contain videos of red deer, fallow deer and roe deer, recorded both during the day and night. MAROON improves the action recognition accuracy compared to other state-of-the-art approaches by an average of 10 percentage points on all analyzed datasets and achieves an accuracy of $69.16\%$ on the Rolandseck Daylight dataset, in which 11 different action classes occur. Our action detection system makes it possible todrasticallyreduce the manual work of ecologists and at the same time gain new insights through standardized results.