Two-dimensional Deep Regression for Early Yield Prediction of Winter Wheat

TL;DR

This paper introduces Hyper3DNetReg, a CNN model that predicts winter wheat yield using multi-source satellite and ground data, demonstrating improved accuracy over existing methods in early-season predictions.

Contribution

The paper presents a novel 2D deep regression CNN architecture, Hyper3DNetReg, for early yield prediction using multi-source satellite and ground data in precision agriculture.

Findings

Hyper3DNetReg outperforms five baseline methods in yield prediction accuracy.

Radar satellite data combined with ground features improves prediction.

Early-season predictions are feasible with the proposed deep learning approach.

Abstract

Crop yield prediction is one of the tasks of Precision Agriculture that can be automated based on multi-source periodic observations of the fields. We tackle the yield prediction problem using a Convolutional Neural Network (CNN) trained on data that combines radar satellite imagery and on-ground information. We present a CNN architecture called Hyper3DNetReg that takes in a multi-channel input image and outputs a two-dimensional raster, where each pixel represents the predicted yield value of the corresponding input pixel. We utilize radar data acquired from the Sentinel-1 satellites, while the on-ground data correspond to a set of six raster features: nitrogen rate applied, precipitation, slope, elevation, topographic position index (TPI), and aspect. We use data collected during the early stage of the winter wheat growing season (March) to predict yield values during the harvest season (August). We present experiments over four fields of winter wheat and show that our proposed methodology yields better results than five compared methods, including multiple linear regression, an ensemble of feedforward networks using AdaBoost, a stacked autoencoder, and two other CNN architectures.