Comment on “Pollination supply models from a local to global scale”: convolutional neural networks can improve pollination supply models at a global scale

• Published in: Web ecology 2024-11, Vol.24 (2), p.81-96
• Main Authors: Allen-Perkins, Alfonso, Giménez-García, Angel, Magrach, Ainhoa, Galeano, Javier, Tarquis, Ana María, Bartomeus, Ignasi
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Artificial neural networks; Bayesian analysis; Complex variables; Correlation coefficient; Correlation coefficients; Crops; Deep learning; Habitat utilization; Habitats; Hypotheses; Land cover; Learning algorithms; Machine learning; Mathematical models; Neural networks; Plant reproduction; Pollination; Pollinators; Predictions; Rankings; Regression analysis; Regression models
• ISSN: 1399-1183; 2193-3081; 1399-1183
• DOI: 10.5194/we-24-81-2024

Tools to predict pollinator activity at regional scales generally rely on land cover maps, combined with human-inferred mechanistic rules and/or expert knowledge. Recently, Giménez-García et al. (2023) showed that, using large pollinator datasets, different environmental variables, and machine learning models, those predictions can be enhanced but at the cost of losing model interpretability. Here, we complement this work by exploring the potential of using advanced machine learning techniques to directly infer wild-bee visitation rates across different biomes only from land cover maps and available pollinator data while maintaining a mechanistic interpretation. In particular, we assess the ability of convolutional neural networks (CNNs), which are deep learning models, to infer mechanistic rules able to predict pollinator habitat use. At a global scale, our CNNs achieved a rank correlation coefficient of 0.44 between predictions and observations of pollinator visitation rates, doubling that of the previous human-inferred mechanistic models presented in Giménez-García et al. (2023) (0.17). Most interestingly, we show that the predictions depend on both landscape composition and configuration variables, with prediction rules being more complex than those of traditional mechanistic processes. We also demonstrate how CNNs can improve the predictions of our previous data-driven models that did not use land cover maps by creating a new model that combined the predictions of our CNN with those of our best regression model based on environmental variables, a Bayesian ridge regressor. This new ensemble model improved the overall rank correlation from 0.56 to 0.64.