The DOI matches its Crossref record; 78 of the 78 references it cites were found in a registry or an index.
Machine learning algorithms to infer trait‐matching and predict species interactions in ecological networks
Open accessAbstract
Ecologists have long suspected that species are more likely to interact if their traits match in a particular way. For example, a pollination interaction may be more likely if the proportions of a bee's tongue fit a plant's flower shape. Empirical estimates of the importance of trait‐matching for determining species interactions, however, vary significantly among different types of ecological networks. Here, we show that ambiguity among empirical trait‐matching studies may have arisen at least in parts from using overly simple statistical models. Using simulated and real data, we contrast conventional generalized linear models (GLM) with more flexible Machine Learning (ML) models (Random Forest, Boosted Regression Trees, Deep Neural Networks, Convolutional Neural Networks, Support Vector Machines, naïve Bayes, and k‐Nearest‐Neighbor), testing their ability to predict species interactions based on traits, and infer trait combinations causally responsible for species interactions. We found that the best ML models can successfully predict species interactions in plant–pollinator networks, outperforming GLMs by a substantial margin. Our results also demonstrate that ML models can better identify the causally responsible trait‐matching combinations than GLMs. In two case studies, the best ML models successfully predicted species interactions in a global plant–pollinator database and inferred ecologically plausible trait‐matching rules for a plant–hummingbird network from Costa Rica, without any prior assumptions about the system. We conclude that flexible ML models offer many advantages over traditional regression models for understanding interaction networks. We anticipate that these results extrapolate to other ecological network types. More generally, our results highlight the potential of machine learning and artificial intelligence for inference in ecology, beyond standard tasks such as image or pattern recognition.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Significant error reduction of ML and DL with respect to traditional generalized regression models has been reported routinely for species richness and diversity estimation33,34.”
From Perspectives in machine learning for wildlife conservation (2022) · cites this paper as [33]
In the citing paper
“Tree-based techniques have also been used to predict species interactions: for example, regression trees significantly outperformed classical generalized linear models in predicting plant-pollinator interactions33.”
From Perspectives in machine learning for wildlife conservation (2022) · cites this paper as [33]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
(2012) · Cited by 8,009
MissForest—Non-parametric missing value imputation for mixed-type data
Stekhoven, D. J., & Bühlmann, P. (2012) · Bioinformatics · doi:10.1093/bioinformatics/btr597 · Cited by 6,156
ALLOUCHE, O., TSOAR, A., & KADMON, R. (2006) · Journal of Applied Ecology · doi:10.1111/j.1365-2664.2006.01214.x · Cited by 5,172
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340
Cross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure
Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera‐Arroita, G., Hauenstein, S., Lahoz‐Monfort, J. J., Schröder, B., Thuiller, W., et al. (2017) · Ecography · doi:10.1111/ecog.02881 · Cited by 3,689
Self-citationLearning from imbalanced data: open challenges and future directions
Krawczyk, B. (2016) · Progress in Artificial Intelligence · doi:10.1007/s13748-016-0094-0 · Cited by 2,459
Pollination Syndromes and Floral Specialization
Fenster, C. B., Armbruster, W. S., Wilson, P., Dudash, M. R., & Thomson, J. D. (2004) · Annual Review of Ecology Evolution and Systematics · doi:10.1146/annurev.ecolsys.34.011802.132347 · Cited by 2,315
Safeguarding pollinators and their values to human well-being
Potts, S. G., Imperatriz-Fonseca, V., Ngo, H. T., Aizen, M. A., Biesmeijer, J. C., Breeze, T. D., Dicks, L. V., Garibaldi, L. A., Hill, R., Settele, J., et al. (2016) · Nature · doi:10.1038/nature20588 · Cited by 2,138
Predictive learning via rule ensembles
Friedman, J. H., & Popescu, B. E. (2008) · The Annals of Applied Statistics · doi:10.1214/07-aoas148 · Cited by 1,315
Prediction of drug–target interaction networks from the integration of chemical and genomic spaces
Yamanishi, Y., Araki, M., Gutteridge, A., Honda, W., & Kanehisa, M. I. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn162 · Cited by 1,148
Invariant properties in coevolutionary networks of plant–animal interactions
Jordano, P., Bascompte, J., & Olesen, J. M. (2002) · Ecology Letters · doi:10.1046/j.1461-0248.2003.00403.x · Cited by 867
Functional traits, the phylogeny of function, and ecosystem service vulnerability
Díaz, S., Purvis, A., Cornelissen, J. H. C., Mace, G. M., Donoghue, M. J., Ewers, R. M., Jordano, P., & Pearse, W. D. (2013) · Ecology and Evolution · doi:10.1002/ece3.601 · Cited by 644
A method for detecting modules in quantitative bipartite networks
Dormann, C. F., & Strauss, R. (2013) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12139 · Cited by 639
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629
Deep-Learning-Based Drug–Target Interaction Prediction
Wen, M., Zhang, Z., Niu, S., Sha, H., Yang, R., Yun, Y., & Lü, H. (2017) · Journal of Proteome Research · doi:10.1021/acs.jproteome.6b00618 · Cited by 592
Specialization, Constraints, and Conflicting Interests in Mutualistic Networks
Blüthgen, N., Menzel, F., Hovestadt, T., Fiala, B., & Blüthgen, N. (2007) · Current Biology · doi:10.1016/j.cub.2006.12.039 · Cited by 590
Menden, M. P., Iorio, F., Garnett, M. J., McDermott, U., Benes, C. H., Ballester, P. J., & Sáez-Rodríguez, J. (2013) · PLoS ONE · doi:10.1371/journal.pone.0061318 · Cited by 543
Centrality measures and the importance of generalist species in pollination networks
González, A. M. M., Dalsgaard, B., & Olesen, J. M. (2009) · Ecological Complexity · doi:10.1016/j.ecocom.2009.03.008 · Cited by 541
A quantitative review of pollination syndromes: do floral traits predict effective pollinators?
Rosas‐Guerrero, V., Aguilar, R., Martén‐Rodríguez, S., Ashworth, L., Lopezaraiza‐Mikel, M., Bastida, J. M., & Quesada, M. (2014) · Ecology Letters · doi:10.1111/ele.12224 · Cited by 538
He, T., Heidemeyer, M., Ban, F., Cherkasov, A. R., & Ester, M. (2017) · Journal of Cheminformatics · doi:10.1186/s13321-017-0209-z · Cited by 529
Bischl, B., Lang, M., Kotthoff, L., Schratz, P., Schiffner, J., Richter, J., Jones, Z., Casalicchio, G., Gallo, M., & Binder, M. (2013) · doi:10.32614/cran.package.mlr · Cited by 506
Machine learning to classify animal species in camera trap images: Applications in ecology
Tabak, M. A., Norouzzadeh, M. S., Wolfson, D. W., Sweeney, S. J., Vercauteren, K. C., Snow, N. P., Halseth, J. M., Di Salvo, P. A., Lewis, J. S., White, M. D., et al. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13120 · Cited by 504
A global test of the pollination syndrome hypothesis
Ollerton, J., Alarcón, R., Waser, N. M., Price, M. V., Watts, S., Cranmer, L., Hingston, A., Peter, C. I., & Rotenberry, J. (2009) · Annals of Botany · doi:10.1093/aob/mcp031 · Cited by 484
Beyond species: why ecological interaction networks vary through space and time
Poisot, T., Stouffer, D. B., & Gravel, D. (2014) · Oikos · doi:10.1111/oik.01719 · Cited by 475
Janzen, D. H. (1985) · Oikos · doi:10.2307/3565565 · Cited by 469
Cheng, F., & Zhao, Z. (2014) · Journal of the American Medical Informatics Association · doi:10.1136/amiajnl-2013-002512 · Cited by 382
Inferring biotic interactions from proxies
Morales‐Castilla, I., Matias, M. G., Gravel, D., & Araújo, M. B. (2015) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2015.03.014 · Cited by 373
Simple prediction of interaction strengths in complex food webs
Berlow, E. L., Dunne, J. A., Martinez, N. D., Stark, P. B., Williams, R. J., & Brose, U. (2008) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0806823106 · Cited by 352
Higher-order interactions capture unexplained complexity in diverse communities
Mayfield, M. M., & Stouffer, D. B. (2017) · Nature Ecology & Evolution · doi:10.1038/s41559-016-0062 · Cited by 350
Schleuning, M., Fründ, J., & Garcı́a, D. (2014) · Ecography · doi:10.1111/ecog.00983 · Cited by 345
Self-citationThe dimensionality of ecological networks
Eklöf, A., Jacob, U., Kopp, J. C., Bosch, J., Castro‐Urgal, R., Chacoff, N. P., Dalsgaard, B., de Sassi, C., Galetti, M., Guimarães, P. R., et al. (2013) · Ecology Letters · doi:10.1111/ele.12081 · Cited by 339
Dehling, D. M., Jordano, P., Schaefer, H. M., Böhning‐Gaese, K., & Schleuning, M. (2016) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2015.2444 · Cited by 282
Self-citationDrug-Drug Interaction Extraction via Convolutional Neural Networks
Liu, S., Tang, B., Chen, Q., & Wang, X. (2016) · Computational and Mathematical Methods in Medicine · doi:10.1155/2016/6918381 · Cited by 262
Vizentin‐Bugoni, J., Maruyama, P. K., & Sazima, M. (2014) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2013.2397 · Cited by 261
Inferring food web structure from predator–prey body size relationships
Gravel, D., Poisot, T., Albouy, C. P., Velez, L., & Mouillot, D. (2013) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12103 · Cited by 261
Maglianesi, M. A., Blüthgen, N., Böhning‐Gaese, K., & Schleuning, M. (2014) · Ecology · doi:10.1890/13-2261.1 · Cited by 250
Self-citationA common framework for identifying linkage rules across different types of interactions
Bartomeus, Í., Gravel, D., Tylianakis, J. M., Aizen, M. A., Dickie, I. A., & Bernard‐Verdier, M. (2016) · Functional Ecology · doi:10.1111/1365-2435.12666 · Cited by 250
Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile
van Laarhoven, T., & Marchiori, E. (2013) · PLoS ONE · doi:10.1371/journal.pone.0066952 · Cited by 249
Visualizing the Effects of Predictor Variables in Black Box Supervised Learning ModelsPreprint
Apley, D. W., & Zhu, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.08468 · Cited by 247
Statistically reinforced machine learning for nonlinear patterns and variable interactions
Ryo, M., & Rillig, M. C. (2017) · Ecosphere · doi:10.1002/ecs2.1976 · Cited by 223
Towards global data products of Essential Biodiversity Variables on species traits
Kissling, W. D., Walls, R., Bowser, A., Jones, M., Kattge, J., Agosti, D., Amengual, J., Basset, A., van Bodegom, P. M., Cornelissen, J. H. C., et al. (2018) · Nature Ecology & Evolution · doi:10.1038/s41559-018-0667-3 · Cited by 217
Garibaldi, L. A., Bartomeus, Í., Bommarco, R., Klein, A., Cunningham, S. A., Aizen, M. A., Boreux, V., Garratt, M. P. D., Carvalheiro, L. G., Kremen, C., et al. (2015) · Journal of Applied Ecology · doi:10.1111/1365-2664.12530 · Cited by 208
Self-citationTari, L., Anwar, S., Liang, S., Cai, J. J., & Baral, C. R. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq382 · Cited by 179
Mutualistic networks: moving closer to a predictive theory
Valdovinos, F. S. (2019) · Ecology Letters · doi:10.1111/ele.13279 · Cited by 171
Predicting novel trophic interactions in a non‐native world
Pearse, I. S., & Altermatt, F. (2013) · Ecology Letters · doi:10.1111/ele.12143 · Cited by 167
Dehling, D. M., Töpfer, T., Schaefer, H. M., Jordano, P., Böhning‐Gaese, K., & Schleuning, M. (2014) · Global Ecology and Biogeography · doi:10.1111/geb.12193 · Cited by 166
Self-citationStang, M., Klinkhamer, P. G. L., & van der Meijden, E. (2006) · Oecologia · doi:10.1007/s00442-006-0585-y · Cited by 161
A convolutional neural network for detecting sea turtles in drone imagery
Gray, P. C., Fleishman, A. B., Klein, D. J., McKown, M., Bézy, V. S., Lohmann, K. J., & Johnston, D. W. (2018) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13132 · Cited by 158
Olito, C., & Fox, J. W. (2014) · Oikos · doi:10.1111/oik.01439 · Cited by 142
Empirical Evaluation of Neutral Interactions in Host-Parasite Networks
Canard, E., Mouquet, N., Mouillot, D., Stanko, M., Miklisová, D., & Gravel, D. (2014) · The American Naturalist · doi:10.1086/675363 · Cited by 136
A novel heterogeneous network-based method for drug response prediction in cancer cell lines
Zhang, F., Wang, M., Xi, J., Yang, J., & Li, A. (2018) · Scientific Reports · doi:10.1038/s41598-018-21622-4 · Cited by 125
Rayhan, F., Ahmed, S., Shatabda, S., Farid, D. M., Mousavian, Z., Dehzangi, A., & Rahman, M. S. (2017) · Scientific Reports · doi:10.1038/s41598-017-18025-2 · Cited by 121
The growing ubiquity of algorithms in society: implications, impacts and innovations
Olhede, S. C., & Wolfe, P. J. (2018) · Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rsta.2017.0364 · Cited by 120 · cited 1×
“In recent years, also in response to issues such as fairness and discrimination (see Olhede & Wolfe 2018), techniques aiming at interpreting fitted ML models have emerged (e.g. Guidotti et al. 2018).”
BackgroundRodgers, A. D., Zhu, H., Fourches, D., Rusyn, I., & Tropsha, A. (2010) · Chemical Research in Toxicology · doi:10.1021/tx900451r · Cited by 116
Weinstein, B. G., & Graham, C. H. (2017) · Ecology Letters · doi:10.1111/ele.12730 · Cited by 113
Effect of flower shape and size on foraging performance and trade‐offs in a tropical hummingbird
Temeles, E. J., Koulouris, C. R., Sander, S. E., & Kress, W. J. (2009) · Ecology · doi:10.1890/08-0695.1 · Cited by 110
Trait matching and phylogeny as predictors of predator–prey interactions involving ground beetles
Brousseau, P., Gravel, D., & Handa, I. T. (2017) · Functional Ecology · doi:10.1111/1365-2435.12943 · Cited by 108
The spatial scaling of species interaction networks
Galiana, N., Lurgi, M., López, B. C., Fortin, M., Leroux, S., Cazelles, K., Gravel, D., & Montoya, J. M. (2018) · Nature Ecology & Evolution · doi:10.1038/s41559-018-0517-3 · Cited by 108
Multispecies interactions across trophic levels at macroscales: retrospective and future directions
Kissling, W. D., & Schleuning, M. (2015) · Ecography · doi:10.1111/ecog.00819 · Cited by 102
Self-citationFang, J., Yang, R., Gao, L., Zhou, D., Yang, S., Liu, A., & Du, G. (2013) · Journal of Chemical Information and Modeling · doi:10.1021/ci400331p · Cited by 99
How can an understanding of plant–pollinator interactions contribute to global food security?
Bailes, E. J., Ollerton, J., Pattrick, J. G., & Glover, B. J. (2015) · Current Opinion in Plant Biology · doi:10.1016/j.pbi.2015.06.002 · Cited by 95
Danieli‐Silva, A., de Souza, J. M. T., Donatti, A. J., Campos, R. P., Vicente‐Silva, J., Freitas, L., & Varassin, I. G. (2011) · Oikos · doi:10.1111/j.1600-0706.2011.19089.x · Cited by 92
Maglianesi, M., Blüthgen, N., Böhning-Gaese, K., & Schleuning, M. (2015) · Ecography · doi:10.1111/ecog.01538 · Cited by 90
Self-citationFisher, A., Rudin, C. D., & Dominici, F. (2018) · arXiv (Cornell University) · Cited by 86
Fenster, C. B., Reynolds, R. J., Williams, C. W., Makowsky, R., & Dudash, M. R. (2015) · Evolution · doi:10.1111/evo.12639 · Cited by 73
Functionally specialised birds respond flexibly to seasonal changes in fruit availability
Bender, I. M. A., Kissling, W. D., Böhning‐Gaese, K., Hensen, I., Kühn, I., Wiegand, T., Dehling, D. M., & Schleuning, M. (2017) · Journal of Animal Ecology · doi:10.1111/1365-2656.12683 · Cited by 69
Self-citationEcological interactions and the Netflix problem
Desjardins-Proulx, P., Laigle, I., Poisot, T., & Gravel, D. (2017) · PeerJ · doi:10.7717/peerj.3644 · Cited by 62
Inferring predator–prey interactions in food webs
Pomeranz, J. P. F., Thompson, R. M., Poisot, T., & Harding, J. S. (2018) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13125 · Cited by 61
Identifying a common backbone of interactions underlying food webs from different ecosystems
Mora, B. B., Gravel, D., Gilarranz, L. J., Poisot, T., & Stouffer, D. B. (2018) · Nature Communications · doi:10.1038/s41467-018-05056-0 · Cited by 46
Aderhold, A., Husmeier, D., Lennon, J. J., Beale, C. M., & Smith, V. A. (2012) · Ecological Informatics · doi:10.1016/j.ecoinf.2012.05.002 · Cited by 45
Hu, J. S., Li, Y., Yang, J.-Y., Shen, H., & Yu, D. (2015) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2015.11.007 · Cited by 36
Murúa, M., & Espíndola, A. (2014) · Plant Biology · doi:10.1111/plb.12225 · Cited by 30
Boreux, V., & Klein, A. (2019) · Figshare · doi:10.6084/m9.figshare.9980471 · Cited by 2
Self-citationMaglianesi, M. A., Blüthgen, N., Böhning‐Gaese, K., & Schleuning, M. (2016) · Figshare · doi:10.6084/m9.figshare.3560895 · Cited by 1
Self-citation
Research works printed but not linked: 4
- Cristianini N., 2000, An introduction to support vector machines
- Faegri K., 1979, The principles of pollination ecology
- Pichler M., 2019, Zenodo
- R Core Team, 2019, R: A language and environment for statistical computing
Cited by
Sorted by citations
Perspectives in machine learning for wildlife conservation
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-27980-y · Cited by 740
The effects of defaunation on plants’ capacity to track climate change
Fricke, E. C., Ordóñez, A., Rogers, H. S., & Svenning, J. (2022) · Science · doi:10.1126/science.abk3510 · Cited by 260
Pollination syndromes in the 21 st century: where do we stand and where may we go?
Dellinger, A. S. (2020) · New Phytologist · doi:10.1111/nph.16793 · Cited by 239
Cautionary notes on the use of co-occurrence networks in soil ecology
Goberna, M., & Verdú, M. (2021) · Soil Biology and Biochemistry · doi:10.1016/j.soilbio.2021.108534 · Cited by 255
Trait-Based Assessments of Climate-Change Impacts on Interacting Species
Schleuning, M., Neuschulz, E. L., Albrecht, J., Bender, I. M. A., Bowler, D. E., Dehling, D. M., Fritz, S. A., Hof, C., Mueller, T., Nowak, L., et al. (2020) · Trends in Ecology & Evolution · doi:10.1016/j.tree.2019.12.010 · Cited by 206
Self-citation
Metadata
- Authors
- Pichler, M., Boreux, V., Klein, A., Schleuning, M., & Hartig, F.
- Affiliations
- University of Regensburg (DE)
- University of Freiburg (DE)
- Senckenberg Biodiversity and Climate Research Centre (DE)
- Corresponding author
- Pichler, Maximilian
- Venue
- Methods in Ecology and Evolution
- Publisher
- Wiley
- Published
- 2019-11-19
- Volume
- 11
- Issue
- 2
- Pages
- 281-293
- ISSN
- 2041-210X (ISSN-L)
- OpenAlex
- W2970584612
- Cited by
- 149
- References
- 78
- Citations by year
- 2026: 20 · 2025: 29 · 2024: 24 · 2023: 21 · 2022: 23 · 2021: 19 · 2020: 13
- FWCI
- 10.77
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Methods in Ecology and Evolution (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Life Sciences › Agricultural and Biological Sciences › Ecology, Evolution, Behavior and Systematics › Plant and animal studies
- Physical Sciences › Environmental Science › Nature and Landscape Conservation › Ecology and Vegetation Dynamics Studies
- Life Sciences › Agricultural and Biological Sciences › Insect Science › Insect and Arachnid Ecology and Behavior
- Keywords
- trait matching, species interactions, ecological networks, plant-pollinator networks, machine learning, generalized linear models, random forest, boosted regression trees, deep neural network, convolutional neural networks, support vector machine, naive Bayes, k-nearest neighbors, trait combinations, plant-hummingbird interactions, interaction prediction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
