Early Prediction of Soybean Traits through Color and Texture Features of Canopy RGB Imagery.

Global crop production is facing the challenge of a high projected demand, while the yields of major crops are not increasing at sufficient speeds. Crop breeding is an important way to boost crop productivity, however its improvement rate is partially hindered by the long crop generation cycles. If end-season crop traits such as yield can be predicted through early-season phenotypic measurements, crop selection can potentially be made before a full crop generation cycle finishes. This study explored the possibility of predicting soybean end-season traits through the color and texture features of early-season canopy images. Six thousand three hundred and eighty-three images were captured at V4/V5 growth stage over 6039 soybean plots growing at four locations. One hundred and forty color features and 315 gray-level co-occurrence matrix-based texture features were derived from each image. Another two variables were also introduced to account for location and timing differences between the images. Five regression and five classification techniques were explored. Best results were obtained using all 457 predictor variables, with Cubist as the regression technique and Random Forests as the classification technique. Yield (RMSE = 9.82, R2 = 0.68), Maturity (RMSE = 3.70, R2 = 0.76) and Seed Size (RMSE = 1.63, R2 = 0.53) were identified as potential soybean traits that might be early predictable.

Wheat Height Estimation Using LiDAR in Comparison to Ultrasonic Sensor and UAS.

As one of the key crop traits, plant height is traditionally evaluated manually, which can be slow, laborious and prone to error. Rapid development of remote and proximal sensing technologies in recent years allows plant height to be estimated in more objective and efficient fashions, while research regarding direct comparisons between different height measurement methods seems to be lagging. In this study, a ground-based multi-sensor phenotyping system equipped with ultrasonic sensors and light detection and ranging (LiDAR) was developed. Canopy heights of 100 wheat plots were estimated five times during a season by the ground phenotyping system and an unmanned aircraft system (UAS), and the results were compared to manual measurements. Overall, LiDAR provided the best results, with a root-mean-square error (RMSE) of 0.05 m and an R² of 0.97. UAS obtained reasonable results with an RMSE of 0.09 m and an R² of 0.91. Ultrasonic sensors did not perform well due to our static measurement style. In conclusion, we suggest LiDAR and UAS are reliable alternative methods for wheat height evaluation.

Field-Based Scoring of Soybean Iron Deficiency Chlorosis Using RGB Imaging and Statistical Learning.

Iron deficiency chlorosis (IDC) is an abiotic stress in soybean that can cause significant biomass and yield reduction. IDC is characterized by stunted growth and yellowing and interveinal chlorosis of early trifoliate leaves. Scoring IDC severity in the field is conventionally done by visual assessment. The goal of this study was to investigate the usefulness of Red Green Blue (RGB) images of soybean plots captured under the field condition for IDC scoring. A total of 64 soybean lines with four replicates were planted in 6 fields over 2 years. Visual scoring (referred to as Field Score, or FS) was conducted at V3-V4 growth stage; and concurrently RGB images of the field plots were recorded with a high-throughput field phenotyping platform. A second set of IDC scores was done on the plot images (displayed on a computer screen) consistently by one person in the office (referred to as Office Score, or OS). Plot images were then processed to remove weeds and extract six color features, which were used to train computer-based IDC scoring models (referred to as Computer Score, or CS) using linear discriminant analysis (LDA) and support vector machine (SVM). The results showed that, in the fields where severe IDC symptoms were present, FS and OS were strongly positively correlated with each other, and both of them were strongly negatively correlated with yield. CS could satisfactorily predict IDC scores when evaluated using FS and OS as the reference (overall classification accuracy > 81%). SVM models appeared to outperform LDA models; and the SVM model trained to predict IDC OS gave the highest prediction accuracy. It was anticipated that coupling RGB imaging from the high-throughput field phenotyping platform with real-time image processing and IDC CS models would lead to a more rapid, cost-effective, and objective scoring pipeline for soybean IDC field screening and breeding.