Improved Accuracy of Phenological Detection in Rice Breeding by Using Ensemble Models of Machine Learning Based on UAV-RGB Imagery

Abstract

Accurate and timely detection of phenology at plot scale in rice breeding trails is crucial for understanding the heterogeneity of varieties and guiding field management. Traditionally, remote sensing studies of phenology detection have heavily relied on the time-series vegetation index (VI) data. However, the methodology based on time-series VI data was often limited by the temporal resolution. In this study, three types of ensemble models including hard voting (majority voting), soft voting (weighted majority voting) and model stacking, were proposed to identify the principal phenological stages of rice based on unmanned aerial vehicle (UAV) RGB imagery. These ensemble models combined RGB-VIs, color space (e.g., RGB and HSV) and textures derived from UAV-RGB imagery, and five machine learning algorithms (random forest; k-nearest neighbors; Gaussian naïve Bayes; support vector machine and logistic regression) as base models to estimate phenological stages in rice breeding. The phenological estimation models were trained on the dataset of late-maturity cultivars and tested independently on the dataset of early-medium-maturity cultivars. The results indicated that all ensemble models outperform individual machine learning models in all datasets. The soft voting strategy provided the best performance for identifying phenology with the overall accuracy of 90% and 93%, and the mean F1-scores of 0.79 and 0.81, respectively, in calibration and validation datasets, which meant that the overall accuracy and mean F1-scores improved by 5% and 7%, respectively, in comparison with those of the best individual model (GNB), tested in this study. Therefore, the ensemble models demonstrated great potential in improving the accuracy of phenology detection in rice breeding.

Satellite Data Reveal Concerns Regarding Mangrove Restoration Efforts in Southern China

“…These boundaries were used as the area of interest for assessing the resilience of MFs in LP-BG. Additionally, we calculated the precision of the mangrove data products for each phase using accuracy (Equation ( 3)) and F1 scores [40,41], as shown in Equations ( 4)-( 6) :…”

Research on Rice Fields Extraction by NDVI Difference Method Based on Sentinel Data

“…The characteristics of the terrain environment, the complexity of land use types and the degree of fragmentation in different study areas necessitate machine learning combined with the phenological characteristics of rice fields to extract rice information [25,26]. However, the extraction accuracy, constraints, and difficulty of different methods vary for different projects and are heavily influenced by the specific study area.…”