Maize (Zea mays L.) is one of the most consumed grains in the world. Within the context of continuous climate change and the reduced availability of arable land, it is urgent to breed new maize varieties and screen for the desired traits, e.g., high yield and strong stress tolerance. Traditional phenotyping methods relying on manual assessment are time-consuming and prone to human errors. Recently, the application of uncrewed aerial vehicles (UAVs) has gained increasing attention in plant phenotyping due to their efficiency in data collection. Moreover, hyperspectral sensors integrated with UAVs can offer data streams with high spectral and spatial resolutions, which are valuable for estimating plant traits. In this study, we collected UAV hyperspectral imagery over a maize breeding field biweekly across the growing season, resulting in 11 data collections in total. Multiple machine learning models were developed to estimate the grain yield and flowering time of the maize breeding lines using the hyperspectral imagery. The performance of the machine learning models and the efficacy of different hyperspectral features were evaluated. The results showed that the models with the multi-temporal imagery outperformed those with imagery from single data collections, and the ridge regression using the full band reflectance achieved the best estimation accuracies, with the correlation coefficients (r) between the estimates and ground truth of 0.54 for grain yield, 0.91 for days to silking, and 0.92 for days to anthesis. In addition, we assessed the estimation performance with data acquired at different growth stages to identify the good periods for the UAV survey. The best estimation results were achieved using the data collected around the tasseling stage (VT) for the grain yield estimation and around the reproductive stages (R1 or R4) for the flowering time estimation. Our results showed that the robust phenotyping framework proposed in this study has great potential to help breeders efficiently estimate key agronomic traits at early growth stages.

Potato holds significant importance as a staple food crop worldwide, particularly in addressing the needs of a growing population. Accurate estimation of the potato Leaf Area Index (LAI) plays a crucial role in predicting crop yield and facilitating precise management practices. Leveraging the capabilities of UAV platforms, we harnessed their efficiency in capturing multi-source, high-resolution remote sensing data. Our study focused on estimating potato LAI utilizing UAV-based digital red–green–blue (RGB) images, Light Detection and Ranging (LiDAR) points, and hyperspectral images (HSI). From these data sources, we computed four sets of indices and employed them as inputs for four different machine-learning regression models: Support Vector Regression (SVR), Random Forest Regression (RFR), Histogram-based Gradient Boosting Regression Tree (HGBR), and Partial Least-Squares Regression (PLSR). We assessed the accuracy of individual features as well as various combinations of feature levels. Among the three sensors, HSI exhibited the most promising results due to its rich spectral information, surpassing the performance of LiDAR and RGB. Notably, the fusion of multiple features outperformed any single component, with the combination of all features of all sensors achieving the highest R² value of 0.782. HSI, especially when utilized in calculating vegetation indices, emerged as the most critical feature in the combination experiments. LiDAR played a relatively smaller role in potato LAI estimation compared to HSI and RGB. Additionally, we discovered that the RFR excelled at effectively integrating features.

Potato growth depends largely on nitrogen (N) availability in the soil. However, the shallow-root crop coupled with its common cultivation in coarse-textured soils leads to its poor N use efficiency. Fast and accurate estimations of potato tissue N concentrations are urgently needed to assist the decision making in precision fertilization management. Remote sensing has been utilized to evaluate the potato N status by correlating spectral information with lab tests on leaf N concentrations. In this study, a systematic comparison was conducted to quantitatively evaluate the performance of hyperspectral and multispectral images in estimating the potato N status, providing a reference for the trade-off between sensor costs and performance. In the experiment, two potato varieties were planted under four fertilization rates with replicates. UAV images were acquired multiple times during the season with a narrow-band hyperspectral imager. Multispectral reflectance was simulated by merging the relevant narrow bands into broad bands to mimic commonly used multispectral cameras. The whole leaf total N concentration and petiole nitrate-N concentration were obtained from 160 potato leaf samples. A partial least square regression model was developed to estimate the two N status indicators using different groups of image features. The best estimation accuracies were given by reflectance of the full spectra with 2.2 nm narrow, with the coefficient of determination (R²) being 0.78 and root mean square error (RMSE) being 0.41 for the whole leaf total N concentration; while, for the petiole nitrate-N concentration, the 10 nm bands had the best performance (R² = 0.87 and RMSE = 0.13). Generally, the model performance decreased with an increase of the spectral bandwidth. The hyperspectral full spectra largely outperformed all three multispectral cameras, but there was no significant difference among the three brands of multispectral cameras. The results also showed that spectral bands in the visible regions (400–700 nm) were the most highly correlated with potato N concentrations.

Maize (Zea mays L.) silage’s forage quality significantly impacts dairy animal performance and the profitability of the livestock industry. Recently, using uncrewed aerial vehicles (UAVs) equipped with advanced sensors has become a research frontier in maize high-throughput phenotyping (HTP). However, extensive existing studies only consider a single sensor modality and models developed for estimating forage quality are single-task ones that fail to utilize the relatedness between each quality trait. To fill the research gap, we propose MUSTA, a MUlti-Sensory feature fusion model that utilizes MUlti-Task learning and the Attention mechanism to simultaneously estimate dry matter yield and multiple nutritive values for silage maize breeding hybrids in the field environment. Specifically, we conducted UAV flights over maize breeding sites and extracted multi-temporal optical- and LiDAR-based features from the UAV-deployed hyperspectral, RGB, and LiDAR sensors. Then, we constructed an attention-based feature fusion module, which included an attention convolutional layer and an attention bidirectional long short-term memory layer, to combine the multi-temporal features and discern the patterns within them. Subsequently, we employed multi-head attention mechanism to obtain comprehensive crop information. We trained MUSTA end-to-end and evaluated it on multiple quantitative metrics. Our results showed that it is capable of practical quality estimation results, as evidenced by the agreement between the estimated quality traits and the ground truth data, with weighted Kendall’s tau coefficients (τ_w) of 0.79 for dry matter yield, 0.74 for MILK2006, 0.68 for crude protein (CP), 0.42 for starch, 0.39 for neutral detergent fiber (NDF), and 0.51 for acid detergent fiber (ADF). Additionally, we implemented a retrieval-augmented method that enabled comparable prediction performance, even without certain costly features available. The comparison experiments showed that the proposed approach is effective in estimating maize silage yield and nutritional values, providing a digitized alternative to traditional field-based phenotyping.