Convolutional Neural Networks to Estimate Dry Matter Yield in a Guineagrass Breeding Program Using UAV Remote Sensing

Forage dry matter is the main source of nutrients in the diet of ruminant animals. Thus, this trait is evaluated in most forage breeding programs with the objective of increasing the yield. Novel solutions combining unmanned aerial vehicles (UAVs) and computer vision are crucial to increase the efficiency of forage breeding programs, to support high-throughput phenotyping (HTP), aiming to estimate parameters correlated to important traits. The main goal of this study was to propose a convolutional neural network (CNN) approach using UAV-RGB imagery to estimate dry matter yield traits in a guineagrass breeding program. For this, an experiment composed of 330 plots of full-sib families and checks conducted at Embrapa Beef Cattle, Brazil, was used. The image dataset was composed of images obtained with an RGB sensor embedded in a Phantom 4 PRO. The traits leaf dry matter yield (LDMY) and total dry matter yield (TDMY) were obtained by conventional agronomic methodology and considered as the ground-truth data. Different CNN architectures were analyzed, such as AlexNet, ResNeXt50, DarkNet53, and two networks proposed recently for related tasks named MaCNN and LF-CNN. Pretrained AlexNet and ResNeXt50 architectures were also studied. Ten-fold cross-validation was used for training and testing the model. Estimates of DMY traits by each CNN architecture were considered as new HTP traits to compare with real traits. Pearson correlation coefficient r between real and HTP traits ranged from 0.62 to 0.79 for LDMY and from 0.60 to 0.76 for TDMY; root square mean error (RSME) ranged from 286.24 to 366.93 kg·ha−1 for LDMY and from 413.07 to 506.56 kg·ha−1 for TDMY. All the CNNs generated heritable HTP traits, except LF-CNN for LDMY and AlexNet for TDMY. Genetic correlations between real and HTP traits were high but varied according to the CNN architecture. HTP trait from ResNeXt50 pretrained achieved the best results for indirect selection regardless of the dry matter trait. This demonstrates that CNNs with remote sensing data are highly promising for HTP for dry matter yield traits in forage breeding programs.

[1]  Stefan Hinz,et al.  Review on Convolutional Neural Networks (CNN) in vegetation remote sensing , 2021, ISPRS Journal of Photogrammetry and Remote Sensing.

[2]  L. Jorge,et al.  A Review on Deep Learning in UAV Remote Sensing , 2021, Int. J. Appl. Earth Obs. Geoinformation.

[3]  Lúcio André de Castro Jorge,et al.  Deep Learning Applied to Phenotyping of Biomass in Forages with UAV-Based RGB Imagery , 2020, Sensors.

[4]  Prakash Lakshmanan,et al.  High-Throughput Phenotyping of Indirect Traits for Early-Stage Selection in Sugarcane Breeding , 2019, Remote. Sens..

[5]  Dharmendra Saraswat,et al.  Evaluating remotely sensed plant count accuracy with differing unmanned aircraft system altitudes, physical canopy separations, and ground covers , 2017 .

[6]  Changying Li,et al.  Convolutional Neural Networks for Image-Based High-Throughput Plant Phenotyping: A Review , 2020, Plant phenomics.

[7]  Georg Bareth,et al.  Estimating Barley Biomass with Crop Surface Models from Oblique RGB Imagery , 2018, Remote. Sens..

[8]  R. L. Thorndike.  Who belongs in the family? , 1953 .

[9]  Dong Hwan Kim,et al.  An automated, high-throughput plant phenotyping system using machine learning-based plant segmentation and image analysis , 2018, PloS one.

[10]  Lingxian Zhang,et al.  Estimating above ground biomass of winter wheat at early growth stages using digital images and deep convolutional neural network , 2019, European Journal of Agronomy.

[11]  L. Jank,et al.  The value of improved pastures to Brazilian beef production , 2014, Crop and Pasture Science.

[12]  Jonathan Li,et al.  A Machine Learning Framework to Predict Nutrient Content in Valencia-Orange Leaf Hyperspectral Measurements , 2020, Remote. Sens..

[13]  Mauro dos Santos de Arruda,et al.  A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery , 2020, ISPRS Journal of Photogrammetry and Remote Sensing.

[14]  Jiri Matas,et al.  Fine-grained recognition of plants from images , 2017, Plant Methods.

[15]  Kevin F. Smith,et al.  Prospects for Measurement of Dry Matter Yield in Forage Breeding Programs Using Sensor Technologies , 2019, Agronomy.

[16]  Joshua A. Udall,et al.  Breeding for Quantitative Traits in Plants , 2003 .

[17]  Margaret R. Krause,et al.  Aerial high‐throughput phenotyping enables indirect selection for grain yield at the early generation, seed‐limited stages in breeding programs , 2020 .

[18]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[19]  J. Araus,et al.  Field high-throughput phenotyping: the new crop breeding frontier. , 2014, Trends in plant science.

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  Ce Yang,et al.  A review on plant high-throughput phenotyping traits using UAV-based sensors , 2020, Comput. Electron. Agric..

[22]  M. Zaman-Allah,et al.  Translating High-Throughput Phenotyping into Genetic Gain , 2018, Trends in plant science.

[23]  Wenzhun Huang,et al.  Two-stage plant species recognition by local mean clustering and Weighted sparse representation classification , 2017, Cluster Computing.

[24]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[25]  Nithya Rajan,et al.  Unmanned Aerial Vehicles for High-Throughput Phenotyping and Agronomic Research , 2016, PloS one.

[26]  Yang Lu,et al.  Identification of rice diseases using deep convolutional neural networks , 2017, Neurocomputing.

[27]  Gota Morota,et al.  Statistical Methods for the Quantitative Genetic Analysis of High-Throughput Phenotyping Data. , 2019, Methods in molecular biology.

[28]  Janne Heiskanen,et al.  Classification of Tree Species in a Diverse African Agroforestry Landscape Using Imaging Spectroscopy and Laser Scanning , 2017, Remote. Sens..

[29]  Brian R. Cullis,et al.  On the design of early generation variety trials with correlated data , 2006 .

[31]  Naira Hovakimyan,et al.  Modeling yield response to crop management using convolutional neural networks , 2020, Comput. Electron. Agric..

[32]  Tzu-Tsung Wong,et al.  Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation , 2015, Pattern Recognit..

[33]  S. Chapman,et al.  A Direct Comparison of Remote Sensing Approaches for High-Throughput Phenotyping in Plant Breeding , 2016, Front. Plant Sci..

[34]  Selection strategies for increasing the yield of high nutritional value leaf mass in Urochloa hybrids , 2020, Euphytica.

[35]  Farid Melgani,et al.  Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective , 2018, GigaScience.

[36]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[38]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[39]  J. A. R. Nunes,et al.  Visual selection of Urochloa ruziziensis genotypes for green biomass yield , 2019 .

[40]  Brian R. Cullis,et al.  Accounting for natural and extraneous variation in the analysis of field experiments , 1997 .

[41]  Wei Guo,et al.  High-Throughput Phenotyping of Sorghum Plant Height Using an Unmanned Aerial Vehicle and Its Application to Genomic Prediction Modeling , 2017, Front. Plant Sci..

[42]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..