UAV-Based Hyperspectral and Ensemble Machine Learning for Predicting Yield in Winter Wheat

Winter wheat is a widely-grown cereal crop worldwide. Using growth-stage information to estimate winter wheat yields in a timely manner is essential for accurate crop management and rapid decision-making in sustainable agriculture, and to increase productivity while reducing environmental impact. UAV remote sensing is widely used in precision agriculture due to its flexibility and increased spatial and spectral resolution. Hyperspectral data are used to model crop traits because of their ability to provide continuous rich spectral information and higher spectral fidelity. In this study, hyperspectral image data of the winter wheat crop canopy at the flowering and grain-filling stages was acquired by a low-altitude unmanned aerial vehicle (UAV), and machine learning was used to predict winter wheat yields. Specifically, a large number of spectral indices were extracted from the spectral data, and three feature selection methods, recursive feature elimination (RFE), Boruta feature selection, and the Pearson correlation coefficient (PCC), were used to filter high spectral indices in order to reduce the dimensionality of the data. Four major basic learner models, (1) support vector machine (SVM), (2) Gaussian process (GP), (3) linear ridge regression (LRR), and (4) random forest (RF), were also constructed, and an ensemble machine learning model was developed by combining the four base learner models. The results showed that the SVM yield prediction model, constructed on the basis of the preferred features, performed the best among the base learner models, with an R2 between 0.62 and 0.73. The accuracy of the proposed ensemble learner model was higher than that of each base learner model; moreover, the R2 (0.78) for the yield prediction model based on Boruta’s preferred characteristics was the highest at the grain-filling stage.

Soybean Yield Preharvest Prediction Based on Bean Pods and Leaves Image Recognition Using Deep Learning Neural Network Combined With GRNN

Soybean yield is a highly complex trait determined by multiple factors such as genotype, environment, and their interactions. The earlier the prediction during the growing season the better. Accurate soybean yield prediction is important for germplasm innovation and planting environment factor improvement. But until now, soybean yield has been determined by weight measurement manually after soybean plant harvest which is time-consuming, has high cost and low precision. This paper proposed a soybean yield in-field prediction method based on bean pods and leaves image recognition using a deep learning algorithm combined with a generalized regression neural network (GRNN). A faster region-convolutional neural network (Faster R-CNN), feature pyramid network (FPN), single shot multibox detector (SSD), and You Only Look Once (YOLOv3) were employed for bean pods recognition in which recognition precision and speed were 86.2, 89.8, 80.1, 87.4%, and 13 frames per second (FPS), 7 FPS, 24 FPS, and 39 FPS, respectively. Therefore, YOLOv3 was selected considering both recognition precision and speed. For enhancing detection performance, YOLOv3 was improved by changing IoU loss function, using the anchor frame clustering algorithm, and utilizing the partial neural network structure with which recognition precision increased to 90.3%. In order to improve soybean yield prediction precision, leaves were identified and counted, moreover, pods were further classified as single, double, treble, four, and five seeds types by improved YOLOv3 because each type seed weight varies. In addition, soybean seed number prediction models of each soybean planter were built using PLSR, BP, and GRNN with the input of different type pod numbers and leaf numbers with which prediction results were 96.24, 96.97, and 97.5%, respectively. Finally, the soybean yield of each planter was obtained by accumulating the weight of all soybean pod types and the average accuracy was up to 97.43%. The results show that it is feasible to predict the soybean yield of plants in situ with high precision by fusing the number of leaves and different type soybean pods recognized by a deep neural network combined with GRNN which can speed up germplasm innovation and planting environmental factor optimization.

Yield prediction model of summer groundnut based on spectral characteristics

Spectral characteristics were studied at pod development stage (75 DAS) in summer groundnut, at Pune, in western Maharashtra plain zone. A simple regression model (yield vs. vegetation index, R2= 0.94) and another multiple regression model (yield vs. B: R, G: R, NIR: R and VI, R2= 0.99) were developed to predict the yields of summer groundnut. The yield prediction model based on spectral ratios at pod development stage (75 DAS) is helpful in forecasting the yield of summer groundnut, one month in advance, in western Maharashtra plain zone.

Evaluating radiation interception pattern and RUE of green gram grown in Lower Gangetic Plains and assessing future yield based on RUE

An experiment was conducted in the Lower Gangetic Plains of West Bengal during 2017 and 2018 with three popular green gram varieties of the region (viz. Samrat, PM05 and Meha). Along with studying the variation of PAR components, a radiation use efficiency (RUE) based equation irrespective of varieties was developed and used to estimate the green gram yield for 2040-2090 period under RCP 4.5 and 8.5 scenarios. Field experimental results showed that almost 33.33 to 52.12% higher yield was recorded in 2017 in comparison to 2018. As observed through pooled experimental data of two years, PM05 produced 3 to 4% higher pod and 4 to 15% more biomass than Samrat and Meha with the highest radiation use efficiency (1.786 g MJ-1). Results also depicted that enhanced thermal condition would cause 9 to 15 days of advancement in maturity. Biomass and yield would also decrease gradually from 2040 to 2090 with an average rate of 7.60-11.70% and 10.19-14.17% respectively. The supporting literature confirms that future yield prediction under projected climate based on “radiation to biomass” conversion efficiency can be used successfully as a method to evaluate climate change impact on crop performance.