Search

Despite significant progress has been made towards crop yield prediction with remote sensing, there exist knowledge gaps on (1) the impacts of temporal resolution of imaging frequencies on yield prediction, (2) transferability of the models among different genotypes and test sites, and (3) translation of these research developments to crop breeding that benefit farmers. Existing research predominantly provides an on-site perspective, frequently missing the complexities of real-world applications. The objectives of this paper are to investigate the transferability and generalization capabilities of yield prediction models for crop breeding across test sites located in North and South Americas. Toward that goal, we tested different machine learning techniques including Random Forest Regressor (RF), Gradient Boosting Regression (GB), and Deep Neural Networks (DNN) for soybean yield prediction with experiments conducted in different climate and growth conditions. A novel transfer learning approach was proposed for genotype selection and categorizing soybean yield for screening high-yield varieties. Furthermore, we studied the effect of temporal resolution on yield prediction, focusing on the critical development stages and optimal aerial survey frequencies for precise yield prediction using large 31,404 sample data. Results demonstrated that the combined dataset of Argentina and United States representing different climate regimes provided the highest performance with an R2 of 0.76 using RF and GB algorithms. The classification approach was proven to be most useful for crop breeding as demonstrated by accurately identifying the high-yielding genotypes. Increasing temporal sampling of key phenological stages significantly improved yield prediction. Although transfer learning yielded promising outcomes across trials within Argentina the efficacy of transferring models from Argentina to the United States was limited, attributed to significant seasonal and climate variations. This study pioneered the use of transfer learning for model adaptability in real-world breeding scenarios, training and transferring models within the South and North Americas, providing actionable insights and strategies for the breeding community, aiming to facilitate improved decision-making for agricultural productivity. [ABSTRACT FROM AUTHOR]

In this paper, a deep convolutional neural network (CNN) is developed to classify the Unmanned Aerial Vehicle (UAV) derived multispectral imagery and normalized digital surface model (DSM) data in urban areas. For this purpose, a multi-input deep CNN (MIDCNN) architecture is designed using 11 parallel CNNs; 10 deep CNNs to extract the features from all possible triple combinations of spectral bands as well as one deep CNN dedicated to the normalized DSM data. The proposed method is compared with the traditional single-input (SI) and double-input (DI) deep CNN designations and random forest (RF) classifier, and evaluated using two independent test datasets. The results indicate that increasing the CNN layers parallelly augmented the classifier's generalization and reduced overfitting risk. The overall accuracy and kappa value of the proposed method are 95% and 0.93, respectively, for the first test dataset, and 96% and 0.94, respectively, for the second test data set. [ABSTRACT FROM AUTHOR]