In wheat and barley breeding, field phenotyping requires a lot of time and effort, so speeding up and automating these processes play an important role. Image sensing technology, which has developed dramatically with the advent of deep learning methods, makes it possible to acquire various types of information from images quickly with high precision. In this study, we aimed to improve the efficiency of breeding using such image sensing technology. At the first step, we attempted to develop a method for head detection and counting using images of yield trail plots in wheat and barley breeding programs. For developing the method, we used YOLOv4 and created a model using 2,023 training images and 674 validating images for three post-flowering stages. The developed model showed good accuracy with an mAP (mean Average Precision) of 85.13% for untrained data, considered to be robust for images of different wheat and barley types and ripening stages. Using the detection model combined with tracking technology, we attempted to estimate the number of heads from consecutive video frames. By using the output of the model, we tested two types of calculation methods for counting heads: the average number of heads per frame and the total number of unique heads in the video, while changing the detection threshold. As a result, the number of heads based on the total number of unique heads when the threshold was set at 0.35 showed a high correlation with the actual values, with coefficients of determination of 0.726 for barley and 0.510 for wheat. When the estimated number of heads from images was compared with the values obtained by conventional visual measurement, the average correlation coefficient over two years was 0.499 for barley and 0.337 for wheat. Since the method developed in this study is simpler than the conventional method and has excellent reproducibility between replications, it can save labor, and speed up and provide high accuracy in head count surveys of wheat and barley breeding programs.

Acceleration and efficiency improvement are necessary for the breeding of various crops that satisfy various needs, such as environmental adaptability, and for this purpose, the development of prediction and selection technology based on a large amount of breeding data (breeding big data) appears to be effective. To collect and utilize these breeding big data, a system is needed for the unified use of crop-breeding data held by various breeding organizations in Japan. However, there are many undisclosed breeding data for which intellectual property security, such as breeding registration, has not been carried out, and there are many difficulties in unifying and using these data on the assumption that they are publicly available. Thus, by applying secure computation technology that can encrypt and aggregate the data from multiple organizations and process and calculate them while maintaining confidentiality, the unified use of breeding data with high safety and convenience will become possible. For example, it will be possible to encrypt and collect sensitive breeding data held by multiple organizations, such as public laboratories, in each prefecture and seed companies without revealing the data to other organizations, create machine learning and prediction models with the encryption, and make predictions on the basis of the prediction models. Carrying out such integrated analysis using breeding data from multiple organizations will lead to acceleration and efficiency improvement of breeding. In this paper, the process from the registration of rice-breeding data in multiple cultivation areas to the prediction based on the machine learning model built using the breeding data for phenotype prediction was carried out on a secure computation system, and the applicability of the system was evaluated. Specifically, the prediction accuracy and processing performance were compared with the plain text, and confidentiality maintenance was evaluated in the whole process of learning. The results showed that the prediction accuracy was better when using a confidential calculation that can utilize the breeding data of multiple organizations while maintaining the secrecy of each organization’s data from the others in comparison to analysis that uses the data of a single organization. The results also showed that the data can be kept secret throughout AI processing of preprocessing, learning, evaluation, and prediction. Future work is to evaluate the usefulness in an actual use case.

Tohoku Agricultural Research Center, NARO, has bred a new soft winter wheat cultivar, “Nanbukirari”, as a successor to “Nanbukomugi”. “Nanbukirari” was applied for variety registration at the seed and seeding section of MAFF in 2018. “Nanbukirari” is a Japanese noodle cultivar with a slightly low amylose content and excellent texture. “Nanbukirari” has improved on the disadvantages of “Nanbukomugi”, such as having a lower wheat yellow mosaic virus (WYMV) susceptibility, and a longer stem. It also has the advantage of producing a bright yellowish flour. The yield of “Nanbukirari” is about 1.4 times higher than that of “Nanbukomugi”. The snow mold resistance is inferior to that of “Nanbukomugi”, but it is less susceptible to pre-harvest sprouting. It is highly resistant to yellow mosaic virus, which is a significant improvement on “Nanbukomugi”. “Nanbukirari” has a higher milling yield than “Nanbukomugi”, and has excellent milling characteristics. As a slightly-low-amylose cultivar lacking Wx-B1, it has a large amylogram breakdown, which gives it a good noodle texture. “Nanbukirai” flour is yellowish like “Nanbukomugi”, and has better lightness than “Nanbukomugi”. Therefore, “Nanbukirari” is a cultivar that has improved on disadvantages (better yellow mosaic virus resistance and longer stem) and has an advantage (yellowish flour).

Sweetpotato for starch production plays an important role in supporting regional agriculture and the regional economy as a staple crop in southern Kyushu. However, in recent years, the shortage of raw materials for starch has become serious due to the frequent occurrence of disease and pest damage, and a decrease in the cultivation area. In the present study, a variety for starch production, “Konaishin”, with excellent disease and pest resistance and high yield was developed. We evaluated the characteristics of “Konaishin” for several years, and the total yield of “Konaishin” was higher than that of “Shiroyutaka” and “Koganesengan” in all of the five cropping types investigated and was 118–148% of that of “Shiroyutaka”. The starch content of “Konaishin” was higher than that of “Koganesengan” and similar to that of “Shiroyutaka”. The yield of starch of “Konaishin” was higher than that of “Shiroyutaka” and “Koganesengan” and was 116–152% of that of “Shiroyutaka”. “Konaishin” showed slightly strong resistance to stem rot, strong resistance to southern root-knot nematode races SP1, SP2, SP3, and SP4, and slightly strong resistance to race SP6-2, slightly strong resistance to coffee root-lesion nematode, and slightly strong resistance to foot rot. In a field severely infested with foot rot, “Konaishin” had a lower incidence of plants with symptoms of foot rot on the foot of the stem than “Shiroyutaka” and “Koganesengan”. Therefore, cultivation of “Konaishin” was thought to be an effective means of controlling foot rot, which continues to cause serious damage in southern Kyushu. The whiteness and viscosity characteristics of the starch of “Konaishin” were not significantly different from those of “Shiroyutaka”. Therefore, it was considered that the replacement of “Shiroyutaka” with “Konaishin” would proceed smoothly in terms of starch properties. Furthermore, “Konaishin” was also found to be suitable for shochu brewing. “Konaishin” has a higher yield than “Shiroyutaka”, which is the main variety used as a raw material for starch, and is resistant to foot rot and stem rot, as well as resistant to two types of nematodes; therefore, it is expected to contribute to the stable production of starch by expanding its growth in southern Kyushu.

Waxy wheat was bred by the pedigree breeding method in Japan for the first time in the world. However, its usage is limited because a hard and waxy wheat cultivar was not developed. A hard wheat generally has the Glu-D1d gene, which strengthens the gluten. On the other hand, current Japanese waxy wheat cultivars do not have this gene, thus the gluten is weakened. When conventional waxy wheat flour is blended to improve the texture of bread, the strength of gluten in the dough is weakened as a result. Institute of Crop Science, NARO, and Kumamoto Flour Milling co., Ltd. worked together to breed a hard and waxy wheat cultivar, “Mochiharuka”, whose genetic background was the hard wheat cultivar “Yumeshiho”, using the methods of DNA marker selection, continuous backcross, near-isogenic lineage production, and generation promotion in greenhouses. Compared with “Yumeshiho”, the panicles are longer, volume weight and yield are slightly smaller, appearance quality is the same or slightly worse, pre-harvest sprouting is slightly difficult to difficult, and the degree of resistance to wheat yellow mosaic and leaf rust are slightly weak in “Mochiharuka”. The other agronomic traits are equivalent. “Mochiharuka” has little amylose in the endosperm starch and very high-water absorption on Farinogram. The maximum viscosity temperature on an amylogram is low. In a processing test using wheat flour blended with “Mochiharuka”, it was evaluated that the bread has a soft and chewy texture, ramen noodles have strong viscoelasticity, and gyoza-wrappers have a chewy texture. It is expected to lead to commercialization.