Exploiting Hierarchical Features for Crop Yield Prediction Based on 3-D Convolutional Neural Networks and Multikernel Gaussian Process

Abstract

Accurate and timely prediction of crop yield based on remote sensing data is important for food security. However, crop growth is a complex process, which makes it quite difficult to achieve better performance. To address this problem, a novel 3-D convolutional neural multikernel network is proposed to capture hierarchical features for predicting crop yield. First, a full 3-D convolutional neural network is constructed to maximally explore deep spatial-spectral features from multispectral images. Then, a multikernel learning (MKL) approach is proposed for fusion of intraimage deep spatial-spectral features and intersample spatial consistency features. Specifically, we assign a group of nonlinear kernels for each feature in the MKL framework, which provides a robust way to fit features extracted from different domains. Finally, the probability distribution of prediction results is obtained by a kernel-based method. We evaluate the performance of the proposed method on China wheat yield prediction and offer detailed and systematic analyses of the performance of the proposed method. In addition, our method is compared with several competing methods. Experimental results demonstrate that the proposed method has certain advantages and can provide better prediction performance than the competitive methods.