Related Experiment Video
Updated: May 25, 2026
10:17
Laboratory Protocol for Genetic Gut Content Analyses of Aquatic Macroinvertebrates Using Group-specific rDNA Primers
Published on: October 5, 2017
Automated discovery of food webs from ecological data using logic-based machine learning
David A Bohan1, Geoffrey Caron-Lormier, Stephen Muggleton
1Rothamsted Research, West Common, Harpenden, Herts, United Kingdom. weed.dynamics@gmail.com
Plos One
|January 14, 2012
Summary
Machine learning, using a logic-based approach called A/ILP, can generate plausible food webs from field data. This method helps understand agricultural ecosystems and their responses to environmental change.
Area of Science:
- Ecology
- Computational Biology
- Machine Learning
Background:
- Food webs are crucial for understanding energy transfer in ecosystems, but studying them is challenging due to the large number of species involved.
- Traditional food web analysis is limited in scope, necessitating innovative approaches for comprehensive ecosystem study.
Purpose of the Study:
- To demonstrate the capability of a logic-based Machine Learning approach, Abductive Inductive Logic Programming (A/ILP), in generating plausible food webs from field sample data.
- To apply A/ILP to invertebrate data from arable fields in Great Britain to hypothesize trophic links and test the method's efficacy.
Main Methods:
- Utilized Vortis suction sampling to collect invertebrate data from arable fields across Great Britain.
- Applied a logic-based Machine Learning technique (A/ILP) to analyze the collected sample data and infer food web structures.
- Focused on identifying hypothesized trophic links, including predator-prey relationships and intra-guild predation.
Main Results:
- Hypothesized links among 45 invertebrate species/taxa, representing a significant portion of the sampled individuals.
- Identified detritivore Collembola as key prey and generalist/omnivorous carabid beetles as dominant predators.
- Revealed the significant predatory role of carabid larvae, including high-probability intra-guild predation, and validated many links with existing literature.
Conclusions:
- A/ILP Machine Learning can generate plausible and testable food webs from sample data, independent of prior assumptions.
- The approach offers a powerful tool for extending and testing theories of agricultural ecosystem dynamics and function.
- This method can contribute to developing broader theories on ecosystem responses to environmental change.
Related Concept Videos
00:48Optimal Foraging
How animals obtain and eat their food is called foraging behavior. Foraging can include searching for plants and hunting for prey and depends on the species and environment.
02:02Ecological Niches
All organisms have a position within an ecosystem. The complete set of living and nonliving factors—including food resources, climate, and terrain—that define the position of a given organism are collectively referred to as the organism’s ecological niche.
01:28Automatic Processing and Automatic Social Behavior
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...