A primer on artificial intelligence in plant digital phenomics: embarking on the data to insights journey

Antoine L. Harfouche; Farid Nakhle; Antoine H. Harfouche; Orlando G. Sardella; Eli Dart; Daniel Jacobson

doi:10.1016/j.tplants.2022.08.021

A primer on artificial intelligence in plant digital phenomics: embarking on the data to insights journey

Antoine L. Harfouche, Farid Nakhle, Antoine H. Harfouche, Orlando G. Sardella, Eli Dart, Daniel Jacobson

Computational and Predictive Biology

Research output: Contribution to journal › Review article › peer-review

27 Scopus citations

Abstract

Artificial intelligence (AI) has emerged as a fundamental component of global agricultural research that is poised to impact on many aspects of plant science. In digital phenomics, AI is capable of learning intricate structure and patterns in large datasets. We provide a perspective and primer on AI applications to phenome research. We propose a novel human-centric explainable AI (X-AI) system architecture consisting of data architecture, technology infrastructure, and AI architecture design. We clarify the difference between post hoc models and 'interpretable by design' models. We include guidance for effectively using an interpretable by design model in phenomic analysis. We also provide directions to sources of tools and resources for making data analytics increasingly accessible. This primer is accompanied by an interactive online tutorial.

Original language	English
Pages (from-to)	154-184
Number of pages	31
Journal	Trends in Plant Science
Volume	28
Issue number	2
DOIs	https://doi.org/10.1016/j.tplants.2022.08.021
State	Published - Feb 2023

Funding

The authors are grateful to the editor and three anonymous reviewers for their constructive and insightful comments which greatly helped to improve the manuscript. Partial support for this work was provided by the EU FP7 project WATBIO (grant 311929 ); the EU H2020 project EMPHASIS-PREP and its Italian node PHEN-ITALY (grant 739514 ); and an Italian Ministry of University and Research Brain Gain Professorship to A.L.H,; as well as the Center for Bioenergy Innovation , a US Department of Energy (DOE) Bioenergy Research Center, the Plant–Microbe Interface Science Focus Area (SFA), and the integrated Pennycress Resilience Project, all supported by the Biological and Environmental Research in the DOE Office of Science; the Oak Ridge Leadership Computing Facility , a DOE Office of Science User Facility supported under contract DE-AC05-00OR22725 ; and the DOE, Laboratory Directed Research and Development funding ORNL AI Initiative project ID 10875 at the Oak Ridge National Laboratory .

Keywords

AI system architecture
black box models
data analytics
digital phenomics
explainable artificial intelligence
interpretable by design models

Access to Document

10.1016/j.tplants.2022.08.021

Cite this

@article{b24df23412004ac5a6448b99cd644b3c,

title = "A primer on artificial intelligence in plant digital phenomics: embarking on the data to insights journey",

abstract = "Artificial intelligence (AI) has emerged as a fundamental component of global agricultural research that is poised to impact on many aspects of plant science. In digital phenomics, AI is capable of learning intricate structure and patterns in large datasets. We provide a perspective and primer on AI applications to phenome research. We propose a novel human-centric explainable AI (X-AI) system architecture consisting of data architecture, technology infrastructure, and AI architecture design. We clarify the difference between post hoc models and 'interpretable by design' models. We include guidance for effectively using an interpretable by design model in phenomic analysis. We also provide directions to sources of tools and resources for making data analytics increasingly accessible. This primer is accompanied by an interactive online tutorial.",

keywords = "AI system architecture, black box models, data analytics, digital phenomics, explainable artificial intelligence, interpretable by design models",

author = "Harfouche, {Antoine L.} and Farid Nakhle and Harfouche, {Antoine H.} and Sardella, {Orlando G.} and Eli Dart and Daniel Jacobson",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier Ltd",

year = "2023",

month = feb,

doi = "10.1016/j.tplants.2022.08.021",

language = "English",

volume = "28",

pages = "154--184",

journal = "Trends in Plant Science",

issn = "1360-1385",

publisher = "Cell Press",

number = "2",

}

TY - JOUR

T1 - A primer on artificial intelligence in plant digital phenomics

T2 - embarking on the data to insights journey

AU - Harfouche, Antoine L.

AU - Nakhle, Farid

AU - Harfouche, Antoine H.

AU - Sardella, Orlando G.

AU - Dart, Eli

AU - Jacobson, Daniel

PY - 2023/2

Y1 - 2023/2

N2 - Artificial intelligence (AI) has emerged as a fundamental component of global agricultural research that is poised to impact on many aspects of plant science. In digital phenomics, AI is capable of learning intricate structure and patterns in large datasets. We provide a perspective and primer on AI applications to phenome research. We propose a novel human-centric explainable AI (X-AI) system architecture consisting of data architecture, technology infrastructure, and AI architecture design. We clarify the difference between post hoc models and 'interpretable by design' models. We include guidance for effectively using an interpretable by design model in phenomic analysis. We also provide directions to sources of tools and resources for making data analytics increasingly accessible. This primer is accompanied by an interactive online tutorial.

AB - Artificial intelligence (AI) has emerged as a fundamental component of global agricultural research that is poised to impact on many aspects of plant science. In digital phenomics, AI is capable of learning intricate structure and patterns in large datasets. We provide a perspective and primer on AI applications to phenome research. We propose a novel human-centric explainable AI (X-AI) system architecture consisting of data architecture, technology infrastructure, and AI architecture design. We clarify the difference between post hoc models and 'interpretable by design' models. We include guidance for effectively using an interpretable by design model in phenomic analysis. We also provide directions to sources of tools and resources for making data analytics increasingly accessible. This primer is accompanied by an interactive online tutorial.

KW - AI system architecture

KW - black box models

KW - data analytics

KW - digital phenomics

KW - explainable artificial intelligence

KW - interpretable by design models

UR - http://www.scopus.com/inward/record.url?scp=85138810775&partnerID=8YFLogxK

U2 - 10.1016/j.tplants.2022.08.021

DO - 10.1016/j.tplants.2022.08.021

M3 - Review article

C2 - 36167648

AN - SCOPUS:85138810775

SN - 1360-1385

VL - 28

SP - 154

EP - 184

JO - Trends in Plant Science

JF - Trends in Plant Science

IS - 2

ER -

A primer on artificial intelligence in plant digital phenomics: embarking on the data to insights journey

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this