Detecting Intra-Field Variation in Rice Yield With Unmanned Aerial Vehicle Imagery and Deep Learning
Authors:
Open Access
- 23 March 2022
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 13, 716506
Abstract
Unmanned aerial vehicles (UAVs) equipped with multispectral sensors offer high spatial and temporal resolution imagery for monitoring crop stress at early stages of development. Analysis of UAV-derived data with advanced machine learning models could improve real-time management in agricultural systems, but guidance for this integration is currently limited. Here we compare two deep learning-based strategies for early warning detection of crop stress, using multitemporal imagery throughout the growing season to predict field-scale yield in irrigated rice in eastern Arkansas. Both deep learning strategies showed improvements upon traditional statistical learning approaches including linear regression and gradient boosted decision trees. First, we explicitly accounted for variation across developmental stages using a 3D convolutional neural network (CNN) architecture that captures both spatial and temporal dimensions of UAV images from multiple time points throughout one growing season. 3D-CNNs achieved low prediction error on the test set, with a Root Mean Squared Error (RMSE) of 8.8% of the mean yield. For the second strategy, a 2D-CNN, we considered only spatial relationships among pixels for image features acquired during a single flyover. 2D-CNNs trained on images from a single day were most accurate when images were taken during booting stage or later, with RMSE ranging from 7.4 to 8.2% of the mean yield. A primary benefit of convolutional autoencoder-like models (based on analyses of prediction maps and feature importance) is the spatial denoising effect that corrects yield predictions for individual pixels based on the values of vegetation index and thermal features for nearby pixels. Our results highlight the promise of convolutional autoencoders for UAV-based yield prediction in rice.Keywords
This publication has 37 references indexed in Scilit:
- A visible band index for remote sensing leaf chlorophyll content at the canopy scaleInternational Journal of Applied Earth Observation and Geoinformation, 2013
- Remote Sensing Leaf Chlorophyll Content Using a Visible Band IndexAgronomy Journal, 2011
- Value of Using Different Vegetative Indices to Quantify Agricultural Crop Characteristics at Different Growth Stages under Varying Management PracticesRemote Sensing, 2010
- Yield Editor: Software for Removing Errors from Crop Yield MapsAgronomy Journal, 2007
- Remote estimation of canopy chlorophyll content in cropsGeophysical Research Letters, 2005
- Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leavesJournal of Plant Physiology, 2003
- Green revolution: the way forwardNature Reviews Genetics, 2001
- Field water management to save water and increase its productivity in irrigated lowland riceAgricultural Water Management, 2001
- Remote estimation of chlorophyll content in higher plant leavesInternational Journal of Remote Sensing, 1997
- Red and photographic infrared linear combinations for monitoring vegetationRemote Sensing of Environment, 1979