The leaf area index (LAI) is a biophysical crop parameter of great interest for agronomists and plant breeders. Direct methods for measuring LAI are normally destructive, while indirect methods are either costly or require long pre- and post-processing times. In this study, a novel deep learning-based (DL) model was developed using RGB nadir-view images taken from a high-throughput plant phenotyping platform for LAI estimation of maize. The study took place in a commercial maize breeding trial during two consecutive growing seasons. Ground-truth LAI values were obtained non-destructively using an allometric relationship that was derived to calculate the leaf area of individual leaves from their main leaf dimensions (length and maximum width). Three convolutional neural network (CNN)-based DL model approaches were proposed using RGB images as input. One of the models tested is a classification model trained with a set of RGB images tagged with previously measured LAI values (classes). The second model provides LAI estimates from CNN-based linear regression and the third one uses a combination of RGB images and numerical data as input of the CNN-based model (multi-input model). The results obtained from the three approaches were compared against ground-truth data and LAI estimations from a classic indirect method based on nadir-view image analysis and gap fraction theory. All DL approaches outperformed the classic indirect method. The multi-input_model showed the least error and explained the highest proportion of the observed LAI variance. This work represents a major advance for LAI estimation in maize breeding plots as compared to previous methods, in terms of processing time and equipment costs.

No abstract

No abstract

The water needs for tomato crops are very high and could limit the viability of cultivation in semiarid environments. There is no agreement among works on irrigation regarding the sensibility of the flowering period. In addition, there is a lack of studies about the effects of water stress on fruit and cluster development under severe water stress. The aim of this work was to evaluate the effect of water stress and rehydration during cluster development. The experiment was conducted in a greenhouse (Seville, Spain) in two different growth cycles (autumn 2021 and spring 2022) using three different cultivars. Two irrigation treatments were applied: a control, with full irrigated conditions, and severe stress, without irrigation during the development of the fifth cluster (43 days (autumn) and 21 days (spring) after transplantation) followed by rehydration. Plant height was significantly decreased, by approximately 10%, in the irrigation treatment during the autumn cycle, however, not in spring. A delayed cluster emergence occurred, however, the final number per plant at the end of the experiment was the same when rehydration was applied (73 and 56 days after transplanting). In the autumn cycle, only the fruit size was considerably affected, with more than a 50% reduction on some dates, though not in the first cluster. However, the extremely severe water stress during the spring cycle, with strong defoliation, reduced the number (around 50%) and size (around 40%) of the fruit. Total soluble solids increased only on isolated dates of the harvest in the stress plants. The response of cherry cultivars to water stress was similar in terms of quality parameters. Fruit size was the most sensitive yield component, and no recovery was detected at harvest after rehydration. The effect of severe water stress was different depending on the evaporative demand and, more importantly, on fruit size.