PhytoOracle: Scalable, modular phenomics data processing pipelines

Abstract

As phenomics data volume and dimensionality increase due to advancements in sensor technology, there is an urgent need to develop and implement scalable data processing pipelines. Current phenomics data processing pipelines lack modularity, extensibility, and processing distribution across sensor modalities and phenotyping platforms. To address these challenges, we developed PhytoOracle (PO), a suite of modular, scalable pipelines for processing large volumes of field phenomics RGB, thermal, PSII chlorophyll fluorescence 2D images, and 3D point clouds. PhytoOracle aims to (i) improve data processing efficiency; (ii) provide an extensible, reproducible computing framework; and (iii) enable data fusion of multi-modal phenomics data. PhytoOracle integrates open-source distributed computing frameworks for parallel processing on high-performance computing, cloud, and local computing environments. Each pipeline component is available as a standalone container, providing transferability, extensibility, and reproducibility. The PO pipeline extracts and associates individual plant traits across sensor modalities and collection time points, representing a unique multi-system approach to addressing the genotype-phenotype gap. To date, PO supports lettuce and sorghum phenotypic trait extraction, with a goal of widening the range of supported species in the future. At the maximum number of cores tested in this study (1,024 cores), PO processing times were: 235 minutes for 9,270 RGB images (140.7 GB), 235 minutes for 9,270 thermal images (5.4 GB), and 13 minutes for 39,678 PSII images (86.2 GB). These processing times represent end-to-end processing, from raw data to fully processed numerical phenotypic trait data. Repeatability values of 0.39-0.95 (bounding area), 0.81-0.95 (axis-aligned bounding volume), 0.79-0.94 (oriented bounding volume), 0.83-0.95 (plant height), and 0.81-0.95 (number of points) were observed in Field Scanalyzer data. We also show the ability of PO to process drone data with a repeatability of 0.55-0.95 (bounding area).

CyVerse: Cyberinfrastructure for open science

“…Moving computations to the edge with the Internet of Things (IoT), Machine Learning (ML), and generative AI for remote sensing using platforms such as sUAS, and integrated sensor networks streaming real and near real-time data are all areas where CyVerse is already involved. Applying CyVerse’s cyberinfrastructure capabilities to the most pressing challenges our society faces include, but are not limited to: adapting to and developing better strategies for resilience to climate change, exploring Genotype by Environment = Phenotype (G×E = P) in both agricultural and natural settings [ 89 , 90 ], using ML and AI for monitoring Earth system processes and studying human health, and developing precision medicine and synthetic biological approaches to life science (See S1 Text for explicit examples).…”

Quantifying Leaf Symptoms of Sorghum Charcoal Rot in Images of Field-Grown Plants Using Deep Neural Networks

“…However, simply providing access to the code and models is not enough. It is equally important to provide integration into web applications and phenotyping workflow managers, such as PhytoOracle, to enable the computationally-efficient deployment of these models to large image datasets (Gonzalez et al 2023). Increasing the accessibility and integration of training models, images, and results is of paramount importance; it empowers a wider range of users to leverage these models, fostering innovation and progress.…”

AgTC and AgETL: open-source tools to enhance data collection and management for plant science research

“…Enterprise Breeding System is an open-source software for breeding programs that enables management of germplasm trials and nurseries as well as data management and analysis ( CGIAR Excellence in Breeding Platform, 2022 ). More recently, PhytoOracle was released to provide a suite of tools that integrates open-source distributed computing frameworks for processing lettuce and sorghum phenotypic traits from RGB, thermal, PSII chlorophyll fluorescence, and 3D laser scanner datasets ( Gonzalez et al., 2023 ). For a comprehensive recent review of digital tools developed for field-based plant data collection and management, we refer the reader to Dipta et al.…”