Search

Common buckwheat (Fagopyrum esculentum Moench.) is one of the most important orphan crops worldwide. Various research efforts have been done to improve cultivation methods to enhance important agronomic traits such as productivity and biotic/abiotic resistance. One important aspect is the seed trait, which has not been extensively studied due to the time-consuming and tedious nature of its examination. Despite this, understanding seed traits is crucial for meeting consumer needs and optimizing crop yields. Therefore, the aim of the study is to investigate the inheritance of common buckwheat seed traits—such as shape, size, and coat color—using an image-based approach. This method allows for the analysis of a large number of seeds with a level of accuracy and precision that was previously unattainable. The results indicate that seed coat color is inherited maternally. Notably, the parameters in size had substantial increases acting like overdominance. The number of seeds that were harvested from F1s of each cross differed a lot depending on the cross combinations and pin/thrum type. In addition, seed size had large reduction in F1s from the different seed-sized parents, especially in thrum type. These may show that there could be cross barriers. The results revealed trends of maternal inheritance for seed shape and coat color in buckwheat, an area that has not been extensively studied. These findings could support buckwheat breeding efforts, helping to address market needs and food demands in the face of significant climate change.

Although plant disease recognition has witnessed a significant improvement with deep learning in recent years, a common observation is that current deep learning methods with decent performance tend to suffer in real-world applications. We argue that this illusion essentially comes from the fact that current plant disease recognition datasets cater to deep learning methods and are far from real scenarios. Mitigating this illusion fundamentally requires an interdisciplinary perspective from both plant disease and deep learning, and a core question arises. What are the characteristics of a desired dataset? This paper aims to provide a perspective on this question. First, we present a taxonomy to describe potential plant disease datasets, which provides a bridge between the two research fields. We then give several directions for making future datasets, such as creating challenge-oriented datasets. We believe that our paper will contribute to creating datasets that can help achieve the ultimate objective of deploying deep learning in real-world plant disease recognition applications. To facilitate the community, our project is publicly available at https://github.com/xml94/PPDRD with the information of relevant public datasets. [ABSTRACT FROM AUTHOR]