Convolutional Neural Networks to Estimate Dry Matter Yield in a Guineagrass Breeding Program Using UAV Remote Sensing

Comparing CNNs and PLSr for estimating wheat organs biophysical variables using proximal sensing

Estimation of biophysical vegetation variables is of interest for diverse applications, such as monitoring of crop growth and health or yield prediction. However, remote estimation of these variables remains challenging due to the inherent complexity of plant architecture, biology and surrounding environment, and the need for features engineering. Recent advancements in deep learning, particularly convolutional neural networks (CNN), offer promising solutions to address this challenge. Unfortunately, the limited availability of labeled data has hindered the exploration of CNNs for regression tasks, especially in the frame of crop phenotyping. In this study, the effectiveness of various CNN models in predicting wheat dry matter, nitrogen uptake, and nitrogen concentration from RGB and multispectral images taken from tillering to maturity was examined. To overcome the scarcity of labeled data, a training pipeline was devised. This pipeline involves transfer learning, pseudo-labeling of unlabeled data and temporal relationship correction. The results demonstrated that CNN models significantly benefit from the pseudolabeling method, while the machine learning approach employing a PLSr did not show comparable performance. Among the models evaluated, EfficientNetB4 achieved the highest accuracy for predicting above-ground biomass, with an R² value of 0.92. In contrast, Resnet50 demonstrated superior performance in predicting LAI, nitrogen uptake, and nitrogen concentration, with R² values of 0.82, 0.73, and 0.80, respectively. Moreover, the study explored multi-output models to predict the distribution of dry matter and nitrogen uptake between stem, inferior leaves, flag leaf, and ear. The findings indicate that CNNs hold promise as accessible and promising tools for phenotyping quantitative biophysical variables of crops. However, further research is required to harness their full potential.

Methodologies Used in Remote Sensing Data Analysis and Remote Sensors for Precision Agriculture

When adopting remote sensing techniques in precision agriculture, there are two main areas to consider: data acquisition and data analysis methodologies [...].

Estimating Grass Sward Quality and Quantity Parameters Using Drone Remote Sensing with Deep Neural Networks

The objective of this study is to investigate the potential of novel neural network architectures for measuring the quality and quantity parameters of silage grass swards, using drone RGB and hyperspectral images (HSI), and compare the results with the random forest (RF) method and handcrafted features. The parameters included fresh and dry biomass (FY, DMY), the digestibility of organic matter in dry matter (D-value), neutral detergent fiber (NDF), indigestible neutral detergent fiber (iNDF), water-soluble carbohydrates (WSC), nitrogen concentration (Ncont) and nitrogen uptake (NU); datasets from spring and summer growth were used. Deep pre-trained neural network architectures, the VGG16 and the Vision Transformer (ViT), and simple 2D and 3D convolutional neural networks (CNN) were studied. In most cases, the neural networks outperformed RF. The normalized root-mean-square errors (NRMSE) of the best models were for FY 19% (2104 kg/ha), DMY 21% (512 kg DM/ha), D-value 1.2% (8.6 g/kg DM), iNDF 12% (5.1 g/kg DM), NDF 1.1.% (6.2 g/kg DM), WSC 10% (10.5 g/kg DM), Ncont 9% (2 g N/kg DM), and NU 22% (11.9 N kg/ha) using independent test dataset. The RGB data provided good results, particularly for the FY, DMY, WSC and NU. The HSI datasets provided advantages for some parameters. The ViT and VGG provided the best results with the RGB data, whereas the simple 3D-CNN was the most consistent with the HSI data.

Deep Learning Regression Approaches Applied to Estimate Tillering in Tropical Forages Using Mobile Phone Images

We assessed the performance of Convolutional Neural Network (CNN)-based approaches using mobile phone images to estimate regrowth density in tropical forages. We generated a dataset composed of 1124 labeled images with 2 mobile phones 7 days after the harvest of the forage plants. Six architectures were evaluated, including AlexNet, ResNet (18, 34, and 50 layers), ResNeXt101, and DarkNet. The best regression model showed a mean absolute error of 7.70 and a correlation of 0.89. Our findings suggest that our proposal using deep learning on mobile phone images can successfully be used to estimate regrowth density in forages.