New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. the aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. in addition, we correlated the appearance of seeds to their physiological performance. images of soybean seeds and seedlings were used to develop models using low-cost approaches and free-access software. The models developed showed high performance, with overall accuracy reaching 0.94 for seeds and seedling classification. The high precision of the models that were developed based on interactive and traditional machine learning demonstrated that the method can easily be used to classify soybean seeds according to their appearance, as well as to classify soybean seedling vigor quickly and non-subjectively. the appearance of soybean seeds is strongly correlated with their physiological performance.

No abstract

Nitrogen (N) is an essential element frequently associated with environmental issues, and the utilization of leaf clip sensors to adjust N fertilization is a technology of interest. This study aimed to evaluate the indices measured with SPAD and Dualex through the bell pepper crop cycle cultivated under different N doses, to identify the ability of the SPAD and Dualex optical sensors to assess N status and establishing the accuracy of the chlorophyll indices as yield estimators. Bell pepper plants were cultivated for 150 days after transplanting (DAT) in slabs fertigated with 6 different N doses divided into 10 biweekly applications. The indices SPAD, chlorophyll (CHL), flavonoids (FLV), and nitrogen balance index (NBI) were measured over the cycle on the uppermost mature leaves of each treatment. We determined the N content of these leaves and the final commercial yield. An interaction effect was found between N dose and growth stage. The SPAD and CHL indices were not significantly affected by N dose up to 60 DAT. The FLV and NBI indices show an opposite pattern in response to N dose. We found a strong correlation between the SPAD, CHL, and NBI and the N content in the leaves and between these indices and commercial yield in several evaluated dates. However, we did not observe a significant correlation between commercial yield and FLV. Both leaf clip sensors could predict the N status of the leaves and the commercial yield, improving the correlation as the crop development progressed.

No abstract

No abstract