Monitoring biomass of forages in experimental plots and livestock farms is a time-consuming, expensive, and biased task. Thus, non-destructive, accurate, precise, and quick phenotyping strategies for biomass yield are needed. To promote high-throughput phenotyping in forages, we propose and evaluate the use of deep learning-based methods and UAV (Unmanned Aerial Vehicle)-based RGB images to estimate the value of biomass yield by different genotypes of the forage grass species Panicum maximum Jacq. Experiments were conducted in the Brazilian Cerrado with 110 genotypes with three replications, totaling 330 plots. Two regression models based on Convolutional Neural Networks (CNNs) named AlexNet and ResNet18 were evaluated, and compared to VGGNet—adopted in previous work in the same thematic for other grass species. The predictions returned by the models reached a correlation of 0.88 and a mean absolute error of 12.98% using AlexNet considering pre-training and data augmentation. This proposal may contribute to forage biomass estimation in breeding populations and livestock areas, as well as to reduce the labor in the field.

Forage dry matter is the main source of nutrients in the diet of ruminant animals. Thus, this trait is evaluated in most forage breeding programs with the objective of increasing the yield. Novel solutions combining unmanned aerial vehicles (UAVs) and computer vision are crucial to increase the efficiency of forage breeding programs, to support high-throughput phenotyping (HTP), aiming to estimate parameters correlated to important traits. The main goal of this study was to propose a convolutional neural network (CNN) approach using UAV-RGB imagery to estimate dry matter yield traits in a guineagrass breeding program. For this, an experiment composed of 330 plots of full-sib families and checks conducted at Embrapa Beef Cattle, Brazil, was used. The image dataset was composed of images obtained with an RGB sensor embedded in a Phantom 4 PRO. The traits leaf dry matter yield (LDMY) and total dry matter yield (TDMY) were obtained by conventional agronomic methodology and considered as the ground-truth data. Different CNN architectures were analyzed, such as AlexNet, ResNeXt50, DarkNet53, and two networks proposed recently for related tasks named MaCNN and LF-CNN. Pretrained AlexNet and ResNeXt50 architectures were also studied. Ten-fold cross-validation was used for training and testing the model. Estimates of DMY traits by each CNN architecture were considered as new HTP traits to compare with real traits. Pearson correlation coefficient r between real and HTP traits ranged from 0.62 to 0.79 for LDMY and from 0.60 to 0.76 for TDMY; root square mean error (RSME) ranged from 286.24 to 366.93 kg·ha${}^{-1}$ for LDMY and from 413.07 to 506.56 kg·ha${}^{-1}$ for TDMY. All the CNNs generated heritable HTP traits, except LF-CNN for LDMY and AlexNet for TDMY. Genetic correlations between real and HTP traits were high but varied according to the CNN architecture. HTP trait from ResNeXt50 pretrained achieved the best results for indirect selection regardless of the dry matter trait. This demonstrates that CNNs with remote sensing data are highly promising for HTP for dry matter yield traits in forage breeding programs.

Perennial grass hybrids of Urochloa are evaluated for at least two years during the screening stage trials (SS) and advanced trials (AD) in breeding programs, an expensive and time-consuming process. In this study, we aimed to evaluate the potential for early selection of cultivars in this breeding scheme. We used multiple measurements of agronomic and nutritive value traits of Urochloa humidicola and Urochloa decumbens in the SS, and Urochloa ssp. in the AD. Repeatability coefficient, genetic correlation, selection efficiency (SE), and Spearman correlations were estimated. The results indicated that reliable early selection could be applied, decreasing the evaluation period to one year and a half for SS, and to one year for AD. These results were confirmed by high genetic and rank correlations, and overall SE above 50%. This proposed change in the breeding scheme could save considerable time, labor, and resources and accelerate the release of improved cultivars.

The objective of this work was to estimate genetic parameters for agronomic traits and resistance to spittlebugs in B. decumbens hybrids and to select the ones with best performance. For that, 324 hybrids were evaluated in field plots for agronomic traits and in the greenhouse for resistance to spittlebugs. Genetic variability amongst the hybrids was observed for all traits analyzed. The heritability estimates between genotypes means were higher than 0.52 for all agronomic traits and 0.98 and 0.99 for nymphal survival and nymphal period duration respectively. Hybrids with better performance than cultivar Basilisk for each individual trait were identified and also through a selection index combining all traits. Assigning weights to the different traits in the selection index did not significantly alter the rank for superior hybrids. Those were selected to continue on to the next phases of the breeding program.