Can exascale computing and explainable artificial intelligence applied to plant biology deliver on the United Nations sustainable development goals?

Abstract

Humanpopulationgrowthandacceleratedclimatechange necessitateagriculturalimprovementsusingdesignercrop ideotypes(idealizedplantsthatcangrowinniche environments).Diverseandhighlyskilledresearchgroups mustintegrateeffortstobridgethegapsneededtoachieve internationalgoalstowardsustainableagriculture.Giventh e scaleofglobalagriculturalneedsandthebreadthof multiple typesofomicsdataneededtooptimizethese efforts, explainableartificialintelligence(AIwitha decipherable decisionmakingprocessthatprovidesa meaningful explanationtohumans)andexascalecomputing (computers thatcanperform10 18 floating-pointoperations persecond,or exaflops)arecrucial.Accuratephenotyping anddailyresolutionclimatypeassociationsareequally importantfor refiningideotypeproductiontospecific environmentsat variouslevelsofgranularity.We review advancestoward tacklingtechnologicalhurdlestosolve multipleUnitedNations SustainableDevelopmentGoals anddiscussavisionto overcomegapsbetweenresearch andpolicy.

Next-Generation Breeding Strategies for Climate-Ready Crops

“…Recently, Summit, the world's most powerful supercomputer has been launched, which has the capacity to store 27,000 graphical processing units (GPUs) and unfolds an exciting way forward. AI can be a game changer and is pivotal for the next-generation crop revolution in the near future (Streich et al, 2020 ).…”

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

“…Nowadays, graphical processing units (GPUs) are accelerating AI with their ability to process multiple tasks simultaneously due to their large number of processing units and high memory bandwidth. With supercomputers breaking the exascale barrier (performing a quintillion floating-point operations per second) 26 , 27 and the ability of AI to analyze massive amounts of data, researchers can take advantage of big data, rather than relying on smaller representative samples, to extract knowledge and insights without loss of information.…”

“… 28 , 29 , 30 However, learning how to use such data more efficiently, easily, and on a large scale is a key challenge to overcome if the implementation of phenomics to improve on-farm response to climate change is to become a reality. 25 , 26 …”

“…[28][29][30] However, learning how to use such data more efficiently, easily, and on a large scale is a key challenge to overcome if the implementation of phenomics to improve on-farm response to climate change is to become a reality. 25,26 Digital phenomics is at the forefront of this tour-de-force effort. Here, we define it as the use of phenome data and metadata to guide decisions along the entire data analytics cycle.…”

Crop researchers harness artificial intelligence to breed crops for the changing climate

“…To probe the genetic underpinnings of climate adaptation for crop species worldwide, Daniel Jacobson, the chief researcher for computational systems biology at Oak Ridge National Laboratory in TN, has amassed "climatype" data for every square kilometer of land on Earth. Using the Summit supercomputer, they then compared each square kilometer to every other square kilometer to identify similar environments (9). The result can be viewed as a network of GPS points connected by lines that show the degree of environmental similarity between points.…”