Using Machine Learning to Identify Associations between the Environment, Occurrence, and Outcomes of Songbird Displacements at Supplemental Feeders
Abstract
:Simple Summary
Abstract
1. Introduction
2. Materials and Methods
2.1. Data Collection
2.2. Feeding Displacements
2.3. Random Forest
3. Results
3.1. Species Involvement
3.2. Displacement Occurrence Model
3.3. What Is Associated with Who Is Displaced?
3.4. What Is Associated with Who Displaces?
4. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A
No Displace | Yes Displace | Class Error | ||
---|---|---|---|---|
Pre-downsample | No Displace | 24,795 | 3 | 0.01% |
Yes Displace | 668 | 0 | 100.00% | |
Post 1:100 Downsample | No Displace | 339 | 329 | 49.25% |
Yes Displace | 172 | 496 | 25.75% |
Downsample Model. | OOB Error Pre-Downsample | OOB Error Post-Downsample | No Displacement Error | Yes Displacement Error | |
---|---|---|---|---|---|
1:100 | 2.63% | Mean | 35.74% | 46.35% | 25.13% |
SD | 0.014 | 0.020 | 0.017 | ||
1:200 | 2.54% | Mean | 35.93% | 46.59% | 25.27% |
SD | 0.014 | 0.021 | 0.017 |
OOB Error | AMGO | BCCH | ETTI | HOFI | HOSP | NOCA | SOSP | Class Error | ||
---|---|---|---|---|---|---|---|---|---|---|
“What predicts who is displaced?” | 7.63% | AMGO | 30 | 0 | 1 | 1 | 1 | 2 | 0 | 14.29% |
BCCH | 0 | 41 | 1 | 0 | 0 | 3 | 2 | 12.77% | ||
ETTI | 2 | 1 | 57 | 0 | 2 | 3 | 2 | 14.93% | ||
HOFI | 1 | 0 | 0 | 17 | 6 | 2 | 1 | 37.04% | ||
HOSP | 0 | 0 | 2 | 1 | 317 | 1 | 4 | 2.46% | ||
NOCA | 2 | 0 | 1 | 0 | 4 | 47 | 1 | 14.55% | ||
SOSP | 0 | 0 | 0 | 1 | 3 | 0 | 108 | 3.57% | ||
“What predicts who displaces?” | 7.04% | AMGO | 20 | 0 | 1 | 1 | 0 | 2 | 1 | 20.00% |
BCCH | 0 | 68 | 1 | 0 | 2 | 1 | 1 | 6.85% | ||
ETTI | 3 | 1 | 25 | 0 | 3 | 3 | 1 | 30.56% | ||
HOFI | 3 | 1 | 0 | 32 | 3 | 0 | 0 | 17.95% | ||
HOSP | 1 | 0 | 2 | 0 | 353 | 0 | 0 | 0.84% | ||
NOCA | 1 | 1 | 0 | 1 | 5 | 64 | 0 | 11.11% | ||
SOSP | 0 | 0 | 1 | 3 | 3 | 1 | 59 | 11.94% |
References
- Grossman, G.D. Food, fights, and burrows: The adaptive significance of intraspecific aggression in the bay goby (Pisces: Gobiidae). Oecologia 1980, 45, 261–266. [Google Scholar] [CrossRef] [PubMed]
- Kontiainen, P.H.; Pietiäinen, K.; Huttunen, P.; Karell, H.; Kolunen, K.; Brommer, J.E. Aggressive Ural owl mothers recruit more offspring. Behav. Ecol. 2009, 20, 789e796. [Google Scholar] [CrossRef]
- Peiman, K.S.; Robinson, B.W. Ecology and evolution of resource-related heterospecific aggression. Q. Rev. Biol. 2010, 85, 133–158. [Google Scholar] [CrossRef] [PubMed]
- Wood, K.A.; Stillman, R.A.; Goss-Custard, J.D. The effect of kleptoparasite and host numbers on the risk of food-stealing in an avian assemblage. J. Avian Biol. 2015, 46, 589–596. [Google Scholar] [CrossRef]
- Collias, N.E. Aggressive behavior among vertebrate animals. Physiol. Zool. 1944, 17, 83–123. [Google Scholar] [CrossRef]
- Marcellini, D. Acoustic and visual display behavior of gekkonid lizards. Am. Zool. 1977, 17, 251–260. [Google Scholar] [CrossRef]
- Szamado, S. How threat displays work: Species-specific fighting techniques, weaponry and proximity risk. Anim. Behav. 2008, 76, 1455–1463. [Google Scholar] [CrossRef]
- Zamudio, K.R.; Sinervo, B. Polygyny, mate-guarding, and posthumous fertilization as alternative male mating strategies. Proc. Natl. Acad. Sci. USA 2000, 97, 14427–14432. [Google Scholar] [CrossRef]
- Fashing, P.J. Male and female strategies during intergroup encounters in guerezas (Colobus guereza): Evidence for resource defense mediated through males and a comparison with other primates. Behav. Ecol. Sociobiol. 2001, 50, 219–230. [Google Scholar] [CrossRef]
- Hyman, J.; Hughes, M.; Nowicki, S.; Searcy, W. Individual variation in the strength of territory defense in male song sparrows: Correlates of age, territory tenure, and neighbor aggressiveness. Behaviour 2004, 141, 15–27. [Google Scholar] [CrossRef]
- Vogel, E.R.; Munch, S.B.; Janson, C.H. Understanding escalated aggression over food resources in white-faced capuchin monkeys. Anim. Behav. 2007, 74, 71–80. [Google Scholar] [CrossRef]
- Caldwell, G.S.; Glickman, S.E.; Smith, E.R. Seasonal aggression independent of seasonal testosterone in wood rats. Proc. Natl. Acad. Sci. USA 1984, 81, 5255–5257. [Google Scholar] [CrossRef] [PubMed]
- Sandell, M.I.; Smith, H.G. Female aggression in the European starling during the breeding season. Anim. Behav. 1997, 53, 13–23. [Google Scholar] [CrossRef]
- Knell, R.J. Population density and the evolution of male aggression. J. Zool. 2009, 27, 83–90. [Google Scholar] [CrossRef]
- Samplonius, J.M. Interspecific aggression declines seasonally in breeding great tits Parus major. Ethology 2019, 125, 159–163. [Google Scholar] [CrossRef]
- Wingfield, J.C.; Ball, G.F.; Dufty, A.M.; Hegner, R.E.; Ramenofsky, M. Testosterone and aggression in birds. Am. Sci. 1987, 75, 602–608. [Google Scholar]
- Ketterson, E.D.; Nolan, V. Adaptation, exaptation, and constraint: A hormonal perspective. Am. Nat. 1999, 154, 4–24. [Google Scholar] [CrossRef]
- Hau, M.; Stoddard, S.T.; Soma, K.K. Territorial aggression and hormones during the non-breeding season in a tropical bird. Horm. Behav. 2004, 45, 40–49. [Google Scholar] [CrossRef]
- Dingemanse, N.J.; Both, C.; Drent, P.J.; Tinbergen, J.M. Fitness consequences of avian personalities in a fluctuating environment. Proc. R. Soc. B Biol. Sci. 2004, 271, 847–852. [Google Scholar] [CrossRef]
- Duckworth, R.A. Behavioural correlations across breeding contexts provide a mechanism for a cost of aggression. Behav. Ecol. 2006, 17, 1011–1019. [Google Scholar] [CrossRef]
- Smith, B.R.; Blumstein, D.T. Fitness consequences of personality: A meta-analysis. Behav. Ecol. 2008, 19, 448–455. [Google Scholar] [CrossRef] [Green Version]
- Grether, G.F.; Anderson, C.N.; Drury, J.P.; Kirschel, A.N.; Losin, N.; Okamoto, K.; Peiman, K.S. The evolutionary consequences of interspecific aggression. Ann. N. Y. Acad. Sci. 2013, 1289, 48–68. [Google Scholar] [CrossRef] [PubMed]
- Wilson, A.J.; Gelin, U.; Perron, M.C.; Réale, D. Indirect genetic effects and the evolution of aggression in a vertebrate system. Proc. R. Soc. B Biol. Sci. 2009, 276, 533–541. [Google Scholar] [CrossRef] [PubMed]
- Tilman, D.; Kareiva, P. Spatial Ecology: The Role of Space in Population Dynamics and Interspecific Interactions; Princeton University Press: Chicago, IL, USA, 2018. [Google Scholar]
- Wojczulanis-Jakubas, K.; Kulpińska, M.; Minias, P. Who bullies whom at a garden feeder? Interspecific agonistic interactions of small passerines during a cold winter. J. Ethol. 2015, 33, 159–163. [Google Scholar] [CrossRef]
- Miller, E.T.; Bonter, D.N.; Eldermire, C.; Freeman, B.G.; Greig, E.I.; Harmon, L.J.; Lisle, C.; Hochachka, W.M. Fighting over food unites the birds of North America in a continental dominance hierarchy. Behav. Ecol. 2017, 28, 1454–1463. [Google Scholar] [CrossRef]
- Francis, M.L.; Plummer, K.E.; Lythgoe, B.A.; Macallan, C.; Currie, T.E.; Blount, J.D. Effects of supplementary feeding on interspecific dominance hierarchies in garden birds. PLoS ONE 2018, 13, e0202152. [Google Scholar] [CrossRef]
- Sih, A.; Bell, A.M. Insights for behavioral ecology from behavioral syndromes. Adv. Study Behav. 2008, 38, 227–281. [Google Scholar]
- Tryjanowski, P.; Møller, A.P.; Morelli, F.; Biaduń, W.; Brauze, T.; Ciach, M.; Czechowski, P.; Czyż, S.; Dulisz, B.; Golawski, A.; et al. Urbanization affects neophilia and risk-taking at bird-feeders. Sci. Rep. 2016, 6, 28575. [Google Scholar] [CrossRef]
- Jokimäki, J.; Suhonen, J.; Kaisanlahti-Jokimäki, M.L. Differential long-term population responses of two closely related human-associated sparrow species with respect to urbanization. Birds 2021, 2, 230–249. [Google Scholar] [CrossRef]
- Noble, G.K. The role of dominance in the social life of birds. Auk 1939, 56, 263–273. [Google Scholar] [CrossRef]
- Robinson, S.K.; Terborgh, J. Interspecific aggression and habitat selection by Amazonian birds. J. Anim. Ecol. 1995, 64, 1–11. [Google Scholar] [CrossRef]
- Pasch, B.; Bolker, B.M.; Phelps, S.M. Interspecific dominance via vocal interactions mediates altitudinal zonation in neotropical singing mice. Am. Nat. 2013, 182, E161–E173. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Galbraith, J.A.; Jones, D.N.; Beggs, J.R.; Parry, K.; Stanley, M.C. Urban bird feeders dominated by a few species and individuals. Front. Ecol. Evol. 2017, 5, 81. [Google Scholar] [CrossRef]
- Jokimäki, J.; Kaisanlahti-Jokimäki, M.L.; Suhonen, J. Long-Term Winter Population Trends of Corvids in Relation to Urbanization and Climate at Northern Latitudes. Animals 2022, 12, 1820. [Google Scholar] [CrossRef] [PubMed]
- Jokimäki, J.; Kaisanlahti-Jokimäki, M.L. The role of residential habitat type on the temporal variation of wintering bird assemblages in northern Finland. Ornis Fenn. 2012, 89, 20. [Google Scholar]
- Suhonen, J.; Jokimäki, J. Temporally stable species occupancy frequency distribution and abundance–occupancy relationship patterns in urban wintering bird assemblages. Front. Ecol. Evol. 2019, 7, 129. [Google Scholar] [CrossRef]
- Finney, S.K.; Wanless, S.; Harris, M.P. The effect of weather conditions on the feeding behaviour of a diving bird, the Common Guillemot Uria aalge. J. Avian Biol. 1999, 30, 23–30. [Google Scholar] [CrossRef]
- Amininasab, S.M.; Kingma, S.A.; Birker, M.; Hildenbrandt, H.; Komdeur, J. The effect of ambient temperature, habitat quality and individual age on incubation behaviour and incubation feeding in a socially monogamous songbird. Behav. Ecol. Sociobiol. 2016, 70, 1591–1600. [Google Scholar] [CrossRef]
- Philson, C.S.; Ray, A.; Foltz, S.L.; Davis, J.E. Programmable Automated System for Songbird Ecobehavioral Research (PASSER): Using flexible computer-integrated feeders to conduct high resolution studies of environment–behavior dynamics in songbirds. Ecol. Evol. 2018, 8, 12522–12532. [Google Scholar] [CrossRef]
- Jorde, D.G.; Krapu, G.L.; Crawford, R.D.; Hay, M.A. Effects of weather on habitat selection and behavior of mallards wintering in Nebraska. Condor 1984, 86, 258–265. [Google Scholar] [CrossRef]
- Sergio, F. From individual behaviour to population pattern: Weather-dependent foraging and breeding performance in black kites. Anim. Behav. 2003, 66, 1109–1117. [Google Scholar] [CrossRef]
- Hernandez-Pliego, J.; Rodriguez, C.; Dell’Omo, G.; Bustamante, J. Combined use of tri-axial accelerometers and GPS reveals the flexible foraging strategy of a bird in relation to weather conditions. PLoS ONE 2017, 12, e0177892. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Biau, G. Analysis of a random forests model. J. Mach. Learn. Res. 2012, 13, 1063–1095. [Google Scholar]
- Cutler, D.R.; Edwards, T.C., Jr.; Beard, K.H.; Cutler, A.; Hess, K.T.; Gibson, J.; Lawler, J.J. Random forests for classification in ecology. Ecology 2007, 88, 2783–2792. [Google Scholar] [CrossRef]
- Fox, E.W.; Hill, R.A.; Leibowitz, S.G.; Olsen, A.R.; Thornbrugh, D.J.; Weber, M.H. Assessing the accuracy and stability of variable selection methods for random forest modeling in ecology. Environ. Monit. Assess. 2017, 189, 1–20. [Google Scholar] [CrossRef]
- Valletta, J.J.; Torney, C.; Kings, M.; Thornton, A.; Madden, J. Applications of machine learning in animal behaviour studies. Anim. Behav. 2017, 124, 203–220. [Google Scholar] [CrossRef]
- Hong, W.; Kennedy, A.; Burgos-Artizzu, X.P.; Zelikowsky, M.; Navonne, S.G.; Perona, P.; Anderson, D.J. Automated measurement of mouse social behaviors using depth sensing, video tracking, and machine learning. Proc. Natl. Acad. Sci. USA 2015, 112, E5351–E5360. [Google Scholar] [CrossRef]
- Ellison, G.; Wolfenden, A.; Kahana, L.; Kisingo, A.; Jamieson, J.; Jones, M.; Bettridge, C.M. Sleeping Site Selection in the Nocturnal Northern Lesser Galago (Galago senegalensis) Supports Antipredator and Thermoregulatory Hypotheses. Int. J. Primatol. 2019, 40, 276–296. [Google Scholar] [CrossRef]
- Adelman, J.S.; Moyers, S.C.; Farine, D.R.; Hawley, D.M. Feeder use predicts both acquisition and transmission of a contagious pathogen on a North American songbird. Proc. R. Soc. B Biol. Sci. 2015, 282, 20151429. [Google Scholar] [CrossRef]
- R Core Team. R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria, 2018; Available online: https://www.R-project.org/ (accessed on 11 March 2018).
- Liaw, A.; Wiener, M. Classification and Regression by randomForest. R News 2002, 2, 18–22. [Google Scholar]
- Pelletier, T.A.; Carstens, B.C. Geographical range size and latitude predict population genetic structure in a global survey. Biol. Lett. 2018, 14, 20170566. [Google Scholar] [CrossRef]
- Janitza, S.; Hornung, R. On the overestimation of random forest’s out-of-bag error. PLoS ONE 2018, 13, e0201904. [Google Scholar] [CrossRef] [PubMed]
- Zuckerberg, B.; Bonter, D.N.; Hochachka, W.M.; Koenig, W.D.; DeGaetano, A.T.; Dickinson, J.L. Climatic constraints on wintering bird distributions are modified by urbanization and weather. J. Anim. Ecol. 2011, 80, 403–413. [Google Scholar] [CrossRef]
- Shedd, D.H. Aggressive interactions in wintering house finches and purple finches. Wilson Bull. 1990, 102, 174–178. [Google Scholar]
- Tryjanowski, P.; Skórka, P.; Sparks, T.H.; Biaduń, W.; Brauze, T.; Hetmański, T.; Martyka, R.; Indykiewicz, P.; Myczko, L.; Kunysz, P.; et al. Urban and rural habitats differ in number and type of bird feeders and in bird species consuming supplementary food. Environ. Sci. Pollut. Res. 2015, 22, 15097–15103. [Google Scholar] [CrossRef] [PubMed]
- Arnott, G.; Elwood, R.W. Information gathering and decision making about resource value in animal contests. Anim. Behav. 2008, 76, 529–542. [Google Scholar] [CrossRef]
- Arnott, G.; Elwood, R.W. Assessment of fighting ability in animal contests. Anim. Behav. 2009, 77, 991–1004. [Google Scholar] [CrossRef]
- Chapin, K.J.; Peixoto, P.E.C.; Briffa, M. Further mismeasures of animal contests: A new framework for assessment strategies. Behav. Ecol. 2019, 30, 1177–1185. [Google Scholar] [CrossRef]
- Briffa, M.; Lane, S.M.; Chapin, K.J.; Peixoto, P.E.C. Using ternary plots to investigate continuous variation in animal contest strategies. Anim. Behav. 2020, 167, 85–99. [Google Scholar] [CrossRef]
- Dingemanse, N.J.; Kazem, A.J.N.; Réale, D.; Wright, J. Behavioural reaction norms: Animal personality meets individual plasticity. Trends Ecol. Evol. 2010, 25, 81–89. [Google Scholar] [CrossRef] [PubMed]
- Thys, B.; Pinxten, R.; Raap, T.; De Meester, G.; Rivera-Gutierrez, H.F.; Eens, M. The female perspective of personality in a wild songbird: Repeatable aggressiveness relates to exploration behaviour. Sci. Rep. 2017, 7, 7656. [Google Scholar] [CrossRef] [PubMed] [Green Version]
Measure’s Name in Models | Model | Definition | Why We Used It |
---|---|---|---|
Species | Displacement occurrence | First bird on the feeder | Accounts for species present on the feeder |
Temperature | Both | Ambient; ℃ | Important predictor of songbird feeding behavior [39,40] |
Humidity | Both | Relative; percent | Important predictor of songbird feeding behavior [39,40] |
Time of Day | Both | Time of day; 24 h clock | Important predictor of songbird feeding behavior [39,40] |
Previous bird | Both | Last bird on the feeder before current feeding event | Accounts for influence of the prior species on the feeder |
Y/N prior 2min | Both | Yes/No that there was a bird present at the feeder in the 2 min prior to the current feeding event | Accounts for temporal effects of the prior species on the feeder |
Y/N prior 5min | Both | Yes/No that there was a bird present at the feeder in the 5 min prior to the current feeding event | Accounts for temporal effects of the prior species on the feeder |
Y/N prior 10min | Both | Yes/No that there was a bird present at the feeder in the 10 min prior to the current feeding event | Accounts for temporal lag effect of the prior species on the feeder |
Y/N prior 20min | Both | Yes/No that there was a bird present at the feeder in the 20 min prior to the current feeding event | Accounts for temporal lag effect of the prior species on the feeder |
Site | Both | Location of the feeder | Accounts for the influence of the location of our feeders |
Displaced or Displacer | Role prediction | Species of the displaced/displacer (opposite of the model’s response variable) | Measure of who the displaced/displacer is in the model |
Y/N each species | Role prediction | Binary measure for the presence of each species in the 15min prior to a displacement event | Accounts for the presence or instance of each of our seven most common species prior to a displacement event |
n Species 15min | Role prediction | Number of times each species was present in the 15min prior to a displacement | Accounts for the frequency of visits of each species prior to a displacement event |
15min Count | Role prediction | Number of birds present in the 15min prior to a displacement | Accounts for the overall quantity of birds at the feeder prior to a displacement |
15min Freq. | Role prediction | The most frequent species seen at the feeder in the 15min prior to a displacement event | Accounts for the influence, or lack therefore, of the most frequent species at the feeder prior to a displacement event |
Scheme 1333. | n Total Feedings | n Displaced | % Displaced | Most Freq. Displaced By | n Displacer | % Displacer | Most Freq. Displaced | % Intraspecific |
---|---|---|---|---|---|---|---|---|
AMGO | 1333 | 35 | 2.63% | AMGO | 25 | 1.88% | AMGO | 45.71% |
BCCH | 2067 | 47 | 2.27% | ETTI | 73 | 3.53% | ETTI | 25.53% |
ETTI | 1479 | 67 | 4.53% | BCCH | 36 | 2.43% | BCCH | 4.48% |
HOFI | 1063 | 27 | 2.54% | HOFI | 39 | 3.67% | HOSP | 33.33% |
HOSP | 6511 | 325 | 4.99% | HOSP | 356 | 5.47% | HOSP | 82.15% |
NOCA | 6341 | 55 | 0.87% | NOCA | 72 | 1.14% | NOCA | 38.18% |
SOSP | 5164 | 112 | 2.17% | HOSP | 67 | 1.30% | HOSP | 19.64% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Philson, C.S.; Pelletier, T.A.; Foltz, S.L.; Davis, J.E. Using Machine Learning to Identify Associations between the Environment, Occurrence, and Outcomes of Songbird Displacements at Supplemental Feeders. Birds 2022, 3, 306-319. https://doi.org/10.3390/birds3030021
Philson CS, Pelletier TA, Foltz SL, Davis JE. Using Machine Learning to Identify Associations between the Environment, Occurrence, and Outcomes of Songbird Displacements at Supplemental Feeders. Birds. 2022; 3(3):306-319. https://doi.org/10.3390/birds3030021
Chicago/Turabian StylePhilson, Conner S., Tara A. Pelletier, Sarah L. Foltz, and Jason E. Davis. 2022. "Using Machine Learning to Identify Associations between the Environment, Occurrence, and Outcomes of Songbird Displacements at Supplemental Feeders" Birds 3, no. 3: 306-319. https://doi.org/10.3390/birds3030021