Yield prediction by machine learning from UAS-based multi-sensor data fusion in soybean

Abstract

Background: Nowadays, automated phenotyping of plants is essential for precise and cost-effective improvement in the efficiency of crop genetics. In recent years, machine learning (ML) techniques have shown great success in the classification and modelling of crop parameters. In this research, we consider the capability of ML to perform grain yield prediction in soybeans by combining data from different optical sensors via RF (Random Forest) and XGBoost (eXtreme Gradient Boosting). During the 2018 growing season, a panel of 382 soybean recombinant inbred lines were evaluated in a yield trial at the Agronomy Center for Research and Education (ACRE) in West Lafayette (Indiana, USA). Images were acquired by the Parrot Sequoia Multispectral Sensor and the S.O.D.A. compact digital camera on board a senseFly eBee UAS (Unnamed Aircraft System) solution at R4 and early R5 growth stages. Next, a standard photogrammetric pipeline was carried out by SfM (Structure from Motion). Multispectral imagery serves to analyse the spectral response of the soybean end-member in 2D. In addition, RGB images were used to reconstruct the study area in 3D, evaluating the physiological growth dynamics per plot via height variations and crop volume estimations. As ground truth, destructive grain yield measurements were taken at the end of the growing season. Results: Algorithms and feature extraction techniques were combined to develop a regression model to predict final yield from imagery, achieving an accuracy of over 90.72% by RF and 91.36% by XGBoost. Conclusions: Results provide practical information for the selection of phenotypes for breeding coming from UAS data as a decision support tool, affording constant operational improvement and proactive management for high spatial precision.

Corn Biomass Estimation by Integrating Remote Sensing and Long-Term Observation Data Based on Machine Learning Techniques

“…Trees are independent in the RF model, which is a more flexible algorithm and is the reason why XGBoost performs better. In this study, the performance of the RF model was comparable to that of the XGBoost model, and this finding is in accordance with the results reported by Herrero-Huerta et al [80]. The RF model outperformed the SVC and ANN models, and the results are similar to those of the studies of An et al, Kayah et al, Xu et al, and Zhu et al [14,[81][82][83], which focused on the performance and accuracy of the RF, SVC, ANN and other models, and the RF model was recommended due to its robustness and accuracy in those studies.…”

Maize Yield Prediction at an Early Developmental Stage Using Multispectral Images and Genotype Data for Preliminary Hybrid Selection

“…Because plant performance is a result of the individual's genetic and environmental conditions, the addition of complementary data types, such as weather, soil, genotype, and field management, can enrich the features that will represent the plant varieties for the model, potentially generating more accurate yield predictions within the field-trial context. Several studies have used multiple data types as input for machine learning models for crop yield prediction in the field [23,24]; however, using hand-crafted features may prevent the model from capturing inter-and cross-modality. In most multimodal deep learning models, each deep learning module specializes in a single data type depicting one aspect of the phenomenon, which are then concatenated and used to inform the prediction [25,26].…”

Comparison of Outdoor Compost Pile Detection Using Unmanned Aerial Vehicle Images and Various Machine Learning Techniques

“…Feng et al [38] attempted urban forest mapping through RF and texture analysis using UAV orthoimages and achieved an accuracy of 73%-90%. Herrero-Huerta et al [39] predicted soybean detection and harvesting rates using RF and eXtreme gradient boosting (XGBoost), and the accuracies of RF and XG-Boost were 90.72% and 91.36%, respectively. Most previous studies achieved less accurate results than the results obtained herein.…”