Tree-level almond yield estimation from high resolution aerial imagery with convolutional neural network

Minmeng Tang; Dennis Lee Sadowski; Chen Peng; Stavros G Vougioukas; Brandon Klever; Sat Darshan S Khalsa; Patrick H Brown; Yufang Jin

doi:10.3389/fpls.2023.1070699

Tree-level almond yield estimation from high resolution aerial imagery with convolutional neural network

Front Plant Sci. 2023 Feb 15:14:1070699. doi: 10.3389/fpls.2023.1070699. eCollection 2023.

Authors

Minmeng Tang¹, Dennis Lee Sadowski², Chen Peng², Stavros G Vougioukas², Brandon Klever¹, Sat Darshan S Khalsa³, Patrick H Brown³, Yufang Jin¹

Affiliations

¹ Department of Land, Air, and Water Resources, University of California, Davis, Davis, CA, United States.
² Department of Biological and Agricultural Engineering, University of California, Davis, Davis, CA, United States.
³ Department of Plant Sciences, University of California, Davis, Davis, CA, United States.

Abstract

Introduction: Estimating and understanding the yield variability within an individual field is critical for precision agriculture resource management of high value tree crops. Recent advancements in sensor technologies and machine learning make it possible to monitor orchards at very high spatial resolution and estimate yield at individual tree level.

Methods: This study evaluates the potential of utilizing deep learning methods to predict tree-level almond yield with multi-spectral imagery. We focused on an almond orchard with the 'Independence' cultivar in California, where individual tree harvesting and yield monitoring was conducted for ~2,000 trees and summer aerial imagery at 30cm was acquired for four spectral bands in 2021. We developed a Convolutional Neural Network (CNN) model with a spatial attention module to take the multi-spectral reflectance imagery directly for almond fresh weight estimation at the tree level.

Results: The deep learning model was shown to predict the tree level yield very well, with a R2 of 0.96 (±0.002) and Normalized Root Mean Square Error (NRMSE) of 6.6% (±0.2%), based on 5-fold cross validation. The CNN estimation captured well the patterns of yield variation between orchard rows, along the transects, and from tree to tree, when compared to the harvest data. The reflectance at the red edge band was found to play the most important role in the CNN yield estimation.

Discussion: This study demonstrates the significant improvement of deep learning over traditional linear regression and machine learning methods for accurate and robust tree level yield estimation, highlighting the potential for data-driven site-specific resource management to ensure agriculture sustainability.

Keywords: CNN; UAV/drone; almond; deep learning; multispectral imagery; yield prediction.

Grants and funding

This study is supported by funding from the Almond Board of California (HORT-66) and the US-Israel Binational Agricultural Research and Development Fund (BARD IS-5430-21).