Exploring and Predicting Plant-Arthropod Interactions: Hierarchical Modelling of Species Communities and Graph Neural Network Approaches
Bibliographic record
Abstract
The world's biodiversity is encountering unprecedented threats, with more than one million plant and animal species at risk of extinction as of 2022. In this thesis, we explore the interactions between plants and arthropods, beginning with an investigation of environmental influences on arthropods using joint species distribution modelling. Our results demonstrate that incorporating specific plants significantly improves model performance, highlighting the importance of considering plant diversity when studying arthropod communities. We then focus on predicting plant-arthropod interactions using Graph Neural Networks (GNN) adapted to our dyadic data. Our proposed approach encompasses different model architectures and choices of arthropod features. We find that GNN-based systems achieve moderate performance, which could potentially be improved by integrating higher-quality data and features. Together, the insights gained from the distributional modelling of species communities and GNN models of dyadic data provide a deeper understanding of plant-arthropod interactions and their complex interplay with diverse factors. This research contributes to the broader knowledge of biodiversity and ecosystem functioning, with potential applications in ecological research and conservation efforts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".