PREPs: An Open-Source Software for High-Throughput Field Plant Phenotyping.

An open-source software for field-based plant phenotyping, Precision Plots Analyzer (PREPs), was developed using Window.NET. The software runs on 64-bit Windows computers. This software allows the extraction of phenotypic traits on a per-microplot basis from orthomosaic and digital surface model (DSM) images generated by Structure-from-Motion/Multi-View-Stereo (SfM-MVS) tools. Moreover, there is no need to acquire skills in geographical information system (GIS) or programming languages for image analysis. Three use cases illustrated the software's functionality. The first involved monitoring the growth of sugar beet varieties in an experimental field using an unmanned aerial vehicle (UAV), where differences among varieties were detected through estimates of crop height, coverage, and volume index. Second, mixed varieties of potato crops were estimated using a UAV and varietal differences were observed from the estimated phenotypic traits. A strong correlation was observed between the manually measured crop height and UAV-estimated crop height. Finally, using a multicamera array attached to a tractor, the height, coverage, and volume index of the 3 potato varieties were precisely estimated. PREPs software is poised to be a useful tool that allows anyone without prior knowledge of programming to extract crop traits for phenotyping.

High-Throughput Yield Prediction of Diallele Crossed Sugar Beet in a Breeding Field Using UAV-Derived Growth Dynamics.

Data-driven techniques could be used to enhance decision-making capacity of breeders and farmers. We used an RGB camera on an unmanned aerial vehicle (UAV) to collect time series data on sugar beet canopy coverage (CC) and canopy height (CH) from small-plot breeding fields including 20 genotypes per season over 3 seasons. Digital orthomosaic and digital surface models were created from each flight and were converted to individual plot-level data. Plot-level data including CC and CH were calculated on a per-plot basis. A multiple regression model was fitted, which predicts root weight (RW) (r = 0.89, 0.89, and 0.92 in the 3 seasons, respectively) and sugar content (SC) (r = 0.79, 0.83, and 0.77 in the 3 seasons, respectively) using individual time point CC and CH data. Individual CC and CH values in late June tended to be strong predictors of RW and SC, suggesting that early season growth is critical for obtaining high RW and SC. Coefficient of parentage was not a strong factor influencing SC. Integrals of CC and CH time series data were calculated for genetic analysis purposes since they are more stable over multiple growing seasons. Calculations of general combining ability and specific combining ability in F1 offspring demonstrate how growth curve quantification can be used in diallel cross analysis and yield prediction. Our simple yet robust solution demonstrates how state-of-the-art remote sensing tools and basic analysis methods can be applied to small-plot breeder fields for selection purpose.

Improved Field-Based Soybean Seed Counting and Localization with Feature Level Considered.

Developing automated soybean seed counting tools will help automate yield prediction before harvesting and improving selection efficiency in breeding programs. An integrated approach for counting and localization is ideal for subsequent analysis. The traditional method of object counting is labor-intensive and error-prone and has low localization accuracy. To quantify soybean seed directly rather than sequentially, we propose a P2PNet-Soy method. Several strategies were considered to adjust the architecture and subsequent postprocessing to maximize model performance in seed counting and localization. First, unsupervised clustering was applied to merge closely located overcounts. Second, low-level features were included with high-level features to provide more information. Third, atrous convolution with different kernel sizes was applied to low- and high-level features to extract scale-invariant features to factor in soybean size variation. Fourth, channel and spatial attention effectively separated the foreground and background for easier soybean seed counting and localization. At last, the input image was added to these extracted features to improve model performance. Using 24 soybean accessions as experimental materials, we trained the model on field images of individual soybean plants obtained from one side and tested them on images obtained from the opposite side, with all the above strategies. The superiority of the proposed P2PNet-Soy in soybean seed counting and localization over the original P2PNet was confirmed by a reduction in the value of the mean absolute error, from 105.55 to 12.94. Furthermore, the trained model worked effectively on images obtained directly from the field without background interference.

Effects of Different Types of Additional Fertilizers on Root-associated Microbes of Napa Cabbage Grown in an Andosol Field in Japan.

The effects of different types of additional fertilizations (a compound fertilizer and Chiyoda-kasei) on the root-associated microbes of napa cabbage grown in an Andosol field were investigated by molecular community ana-lyses. Most of the closest known species of the bacterial sequences whose relative abundance significantly differed among fertilizers were sensitive to nitrogen fertilization and/or related to the geochemical cycles of nitrogen. The fungal community on the roots of napa cabbage was dominated by two genera, Bipolaris and Olpidium. The relative abundance of these two genera was affected by the types of fertilizers to some extent and showed a strong negative correlation.

A Weakly Supervised Deep Learning Framework for Sorghum Head Detection and Counting.

The yield of cereal crops such as sorghum (Sorghum bicolor L. Moench) depends on the distribution of crop-heads in varying branching arrangements. Therefore, counting the head number per unit area is critical for plant breeders to correlate with the genotypic variation in a specific breeding field. However, measuring such phenotypic traits manually is an extremely labor-intensive process and suffers from low efficiency and human errors. Moreover, the process is almost infeasible for large-scale breeding plantations or experiments. Machine learning-based approaches like deep convolutional neural network (CNN) based object detectors are promising tools for efficient object detection and counting. However, a significant limitation of such deep learning-based approaches is that they typically require a massive amount of hand-labeled images for training, which is still a tedious process. Here, we propose an active learning inspired weakly supervised deep learning framework for sorghum head detection and counting from UAV-based images. We demonstrate that it is possible to significantly reduce human labeling effort without compromising final model performance (R 2 between human count and machine count is 0.88) by using a semitrained CNN model (i.e., trained with limited labeled data) to perform synthetic annotation. In addition, we also visualize key features that the network learns. This improves trustworthiness by enabling users to better understand and trust the decisions that the trained deep learning model makes.

Easy MPE: Extraction of Quality Microplot Images for UAV-Based High-Throughput Field Phenotyping.

Microplot extraction (PE) is a necessary image processing step in unmanned aerial vehicle- (UAV-) based research on breeding fields. At present, it is manually using ArcGIS, QGIS, or other GIS-based software, but achieving the desired accuracy is time-consuming. We therefore developed an intuitive, easy-to-use semiautomatic program for MPE called Easy MPE to enable researchers and others to access reliable plot data UAV images of whole fields under variable field conditions. The program uses four major steps: (1) binary segmentation, (2) microplot extraction, (3) production of ∗.shp files to enable further file manipulation, and (4) projection of individual microplots generated from the orthomosaic back onto the raw aerial UAV images to preserve the image quality. Crop rows were successfully identified in all trial fields. The performance of the proposed method was evaluated by calculating the intersection-over-union (IOU) ratio between microplots determined manually and by Easy MPE: the average IOU (±SD) of all trials was 91% (±3).

Visible Light Image-Based Method for Sugar Content Classification of Citrus.

Visible light imaging of citrus fruit from Mie Prefecture of Japan was performed to determine whether an algorithm could be developed to predict the sugar content. This nondestructive classification showed that the accurate segmentation of different images can be realized by a correlation analysis based on the threshold value of the coefficient of determination. There is an obvious correlation between the sugar content of citrus fruit and certain parameters of the color images. The selected image parameters were connected by addition algorithm. The sugar content of citrus fruit can be predicted by the dummy variable method. The results showed that the small but orange citrus fruits often have a high sugar content. The study shows that it is possible to predict the sugar content of citrus fruit and to perform a classification of the sugar content using light in the visible spectrum and without the need for an additional light source.

An overview of challenges in modeling heat and mass transfer for living on Mars.

Engineering a life-support system for living on Mars requires the modeling of heat and mass transfer. This report describes the analysis of heat and mass transfer phenomena in a greenhouse dome, which is being designed as a pressurized life-support system for agricultural production on Mars. In this Martian greenhouse, solar energy will be converted into chemical energy in plant biomass. Agricultural products will be harvested for food and plant cultivation, and waste materials will be processed in a composting microbial ecosystem. Transpired water from plants will be condensed and recycled. In our thermal design and analysis for the Martian greenhouse, we addressed the question of whether temperature and pressure would be maintained in the appropriate range for humans as well as plants. Energy flow and material circulation should be controlled to provide an artificial ecological system on Mars. In our analysis, we assumed that the greenhouse would be maintained at a subatmospheric pressure under 1/3-G gravitational force with 1/2 solar light intensity on Earth. Convection of atmospheric gases will be induced inside the greenhouse, primarily by heating from sunlight. Microclimate (thermal and gas species structure) could be generated locally around plant bodies, which would affect gas transport. Potential effects of those environmental factors are discussed on the phenomena including plant growth and plant physiology and focusing on transport processes. Fire safety is a crucial issue and we evaluate its impact on the total gas pressure in the greenhouse dome.