Human–Machine Scientific Discovery

Abstract

Humanity is facing existential, societal challenges related to food security, ecosystem conservation, antimicrobial resistance, etc, and Artificial Intelligence (AI) is already playing an important role in tackling these new challenges. Most current AI approaches are limited when it comes to ‘knowledge transfer’ with humans, i.e. it is difficult to incorporate existing human knowledge and also the output knowledge is not human comprehensible. In this chapter we demonstrate how a combination of comprehensible machine learning, text-mining and domain knowledge could enhance human-machine collaboration for the purpose of automated scientific discovery where humans and computers jointly develop and evaluate scientific theories. As a case study, we describe a combination of logic-based machine learning (which included human-encoded ecological background knowledge) and text-mining from scientific publications (to verify machine-learned hypotheses) for the purpose of automated discovery of ecological interaction networks (food-webs) to detect change in agricultural ecosystems using the Farm Scale Evaluations (FSEs) of genetically modified herbicide-tolerant (GMHT) crops dataset. The results included novel food-web hypotheses, some confirmed by subsequent experimental studies (e.g. DNA analysis) and published in scientific journals. These machine-leaned food-webs were also used as the basis of a recent study revealing resilience of agro-ecosystems to changes in farming management using GMHT crops.

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

“…Inductive Logic Programming (ILP) is a subfield of symbolic artificial intelligence, which works based on inductive reasoning to detect generalisations, rules, or models [13,18]. In this method, the system learns from training examples with the help of background information and using logic programming [24]. Indeed, the primary purpose of ILP [13], like the other types of machine learning, is to induce a model/ hypothesis that can generalise training examples but, unlike them, uses logic programs to represent data and learns relations [2].…”

“…An automated software tool, for example, should be able to learn from a small number of interactions with the user in order to be efficiently customised with every new user's requirement. Inductive Logic Programming (ILP) and, in particular, Meta Interpretive Learning (MIL) can learn human-readable hypotheses from a small amount of training data [17,24]. This capability is very promising for medical and industrial usage, especially when we do not have access to a large amount of training data.…”

Holo-omic applications to unveil microbiome shaping sustainable horticultural production

“…These tools allow us to connect the identified positive and negative interactions and the ecological mechanisms. Explainable machine learning can link inferred interaction networks to ecological mechanisms (Tamaddoni-Nezhad et al, 2021). Several horticultural crops-microbiome interactions (i.e., mutualism, competition) affect the frequency of different species in different ways (Song et al, 2020;Venkataram et al, 2023).…”

The functional microbiome of grapevine throughout plant evolutionary history and lifetime

“…Explainable machine learning can associate ecological mechanisms with the inferred interaction networks (Tamaddoni-Nezhad et al, 2021). Different interaction types, such as competition and mutualism, lead to different changes in species frequency (Fig.…”