Skip to main content

Using TreeNet, a Machine Learning Approach to Better Understand Factors that Influence Elevated Blood Lead Levels in Wintering Golden Eagles in the Western United States

Abstract

Environmental contaminants like lead (Pb) can pose a threat to wildlife populations, particularly raptors. However, the sources and consequences associated with exposure are often complex and difficult to assess. Machine learning models are suitable for prediction and for gaining biologically meaningful insight into the potential impacts of Pb on wildlife populations. However, despite their potential, they are often under-utilized in the field of ecology. We used TreeNet, a machine learning algorithm, and six variables to investigate the incidence of elevated blood lead levels (eBLL; >0.20 ppm wet weight) in a population of wintering Golden Eagles captured in Idaho (winter 1989–90 through winter 1997–98). Our best model had 76.7% accuracy overall in predicting the presence or absence of eBLL in an independent sample of wintering eagles from the study area. TreeNet results were also corroborated by traditional statistical analyses done in an earlier study and the findings of others, but provided additional information not revealed by those analyses. All six variables were important for predicting the incidence of Pb contamination in eagles and were characterized by multiple complex interactions. Winter of capture had the greatest influence on predicting eagles with eBLL, followed by time of day captured. Month in which an eagle was captured, gender, valley of capture and age class were all about equally important to model prediction. Eagles with eBLL were most likely to be captured later in the day and during the months of December and January. The evidence from our analysis agrees with results from other areas by indicating that the primary source of Pb to the eagles in our study area was most likely related to Pb contaminated carcasses or offal from hunter-killed animals. However, female Golden Eagles, in our study area, and especially adult females, were more likely to have eBLL than males; similar gender differences have been reported for other avian species but not previously for Golden Eagles. Juveniles were least likely of the free-ranging eagles captured during winter to have eBLL and no nestlings and eagles sampled during summer had eBLL. Our results help to identify members of the population most at risk to contaminants, highlighting gender and age related differences that may be of broader geographic and population-level importance. Lastly, our results provide information potentially relevant for informing future population models, conservation efforts and direction for further research.

Keywords

  • Golden eagles
  • Aquila chrysaetos
  • Contaminants
  • Pb contamination
  • Data mining
  • Predictive modeling
  • TreeNet®
  • Machine learning
  • Stochastic gradient boosting
  • Modeling

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-96978-7_12
  • Chapter length: 18 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   169.00
Price excludes VAT (USA)
  • ISBN: 978-3-319-96978-7
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   219.99
Price excludes VAT (USA)
Fig. 12.1
Fig. 12.2
Fig. 12.3
Fig. 12.4
Fig. 12.5

References

  • Abatzoglou JT, Kolden CA (2011) Climate change in western US deserts: potential for increased wildfire and invasive annual grasses. Rangel Ecol Manag 64:471–478

    CrossRef  Google Scholar 

  • Bedrosian B, Craighead D (2009) Blood lead levels of Bald and Golden Eagles sampled during and after hunting seasons in the greater yellowstone ecosystem. In: Watson RT, Fuller M, Pokras M, Hunt WG (eds) Ingestion of Lead from Spent Ammunition: Implications for Wildlife and Humans. The Peregrine Fund, Boise. ID, USA https://doi.org/10.4080/ILSA.2009.0209

  • Bedrosian B, Craighead D, Crandall R (2012) Lead exposure in bald eagles from big game hunting, the continental implications and successful mitigation efforts. PLoS One 7:e51978

    CAS  CrossRef  Google Scholar 

  • Cade TJ (2007) Exposure of California condors to lead from spent ammunition. J Wildl Manag 71:2125–2133

    CrossRef  Google Scholar 

  • Church ME, Gwiazda R, Risebrough RW, Sorenson K, Chamberlain CP, Farry S, Heinrich W, Rideout BA, Smith DR (2006) Ammunition is the principal source of lead accumulated by California condors re-introduced to the wild. Environ Sci Technol 40:6143–6150

    CAS  CrossRef  Google Scholar 

  • Collij LE, Heeman F, Kuijer JP, Ossenkoppele R, Benedictus MR, Möller C, Verfaillie SC, Sanz-Arigita EJ, van Berckel BN, van der Flier WM, others (2016) Application of machine learning to arterial spin labeling in mild cognitive impairment and Alzheimer disease. Radiology 281:865–875

    CrossRef  Google Scholar 

  • Cooper GF, Aliferis CF, Ambrosino R, Aronis J, Buchanan BG, Caruana R, Fine MJ, Glymour C, Gordon G, Hanusa BH, others (1997) An evaluation of machine-learning methods for predicting pneumonia mortality. Artif Intell Med 9:107–138

    CAS  CrossRef  Google Scholar 

  • Copeland HE, Pocewicz A, Kiesecker JM (2011) Geography of energy development in western North America: potential impacts on terrestrial ecosystems, chapter 2. In: Naugle DE (ed) Energy development and wildlife conservation in western North America. Island Press, Washington, DC, USA, pp 7–22

    CrossRef  Google Scholar 

  • Craig EH, Craig TH (1998) Lead and Mercury levels in golden and bald eagles and annual movements of golden eagles wintering in East Central Idaho, 1990–1997, Technical Bulletin No. 98–12. Idaho Bureau of Land Management, Boise, ID, USA

    Google Scholar 

  • Craig E, Huettmann F (2009) Using “Blackbox” algorithms such as TreeNET and Random Forests for data-mining and for finding meaningful patterns, relationships and outliers in complex ecological data: an overview, an example using Golden Eagle satellite data and an outlook for a promising future. In: Wang H (ed) Intelligent data analysis: developing new methodologies through pattern discovery and recovery. IGI Global, Hershey, PA, USA pp 65–84

    Google Scholar 

  • Craig TH, Connelly JW, Craig EH, Parker TL (1990) Lead concentrations in golden and bald eagles. Wilson Bull 102:130–133

    Google Scholar 

  • Craighead D, Bedrosian B (2008) Blood lead levels of common ravens with access to big-game offal. J Wildl Manag 72:240–245

    CrossRef  Google Scholar 

  • Cruz JA, Wishart DS (2006) Applications of machine learning in cancer prediction and prognosis. Cancer Informat 2:59–78

    CrossRef  Google Scholar 

  • Cruz-Martinez L, Redig PT, Deen J (2012) Lead from spent ammunition: a source of exposure and poisoning in bald eagles. Human–Wildlife Interact 6:11 https://digitalcommons.usu.edu/hwi/vol6/iss1/11

  • Cutler DR, Edwards TC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88:2783–2792

    CrossRef  Google Scholar 

  • Dennison PE, Brewer SC, Arnold JD, Moritz MA (2014) Large wildfire trends in the western United States, 1984–2011. Geophys Res Lett 41:2928–2933

    CrossRef  Google Scholar 

  • Ecke F, Singh NJ, Arnemo JM, Bignert A, Helander B, Berglund AMM, Borg H, Bröjer C, Holm K, Lanzone M, others (2017) Sublethal lead exposure alters movement behavior in free-ranging golden eagles. Environ Sci Technol 51:5729–5736

    CAS  CrossRef  Google Scholar 

  • Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77:802–813

    CAS  CrossRef  Google Scholar 

  • Finkelstein ME, Doak DF, George D, Burnett J, Brandt J, Church M, Grantham J, Smith DR (2012) Lead poisoning and the deceptive recovery of the critically endangered California condor. Proc Natl Acad Sci 109:11449–11454

    CAS  CrossRef  Google Scholar 

  • Fisher IJ, Pain DJ, Thomas VG (2006) A review of lead poisoning from ammunition sources in terrestrial birds. Biol Conserv 131:421–432

    CrossRef  Google Scholar 

  • Friedman J (2002) Stochastic gradient boosting: non-linear methods and data mining. Comput Stat Data Anal 38:367–378

    CrossRef  Google Scholar 

  • Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232

    CrossRef  Google Scholar 

  • Friedman J, Hastie T, Tibshirani R, others (2000) Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann Stat 28:337–407

    CrossRef  Google Scholar 

  • Fry M, Sorenson K, Grantham J, Burnett J, Brandt J, Koenig M (2009) Lead intoxication kinetics in condors from California. In: Watson RT, Fuller M, Pokras M, Hunt WG (eds) Ingestion of Lead from Spent Ammunition: Implications for Wildlife and Humans. The Peregrine Fund, Boise. ID, USA, https://doi.org/10.4080/ilsa.2009.0301

  • Grier JW (1980) Modeling approaches to bald eagle population dynamics. Wildl Soc Bull 8:316–322

    Google Scholar 

  • Guisan A, Zimmermann NE, Elith J, Graham CH, Phillips S, Peterson AT (2007) What matters for predicting the occurrences of trees: techniques, data or species’ characteristics? Ecol Monogr 77:615–630

    CrossRef  Google Scholar 

  • Haig SM, D’Elia J, Eagles-Smith C, Fair JM, Gervais J, Herring G, Rivers JW, Schulz JH (2014) The persistent problem of lead poisoning in birds from ammunition and fishing tackle. Condor 116:408–428. https://doi.org/10.1650/CONDOR-14-36.1

    CrossRef  Google Scholar 

  • Halley DJ, Gjershaug JO (1998) Inter-and intra-specific dominance relationships and feeding behaviour of golden eagles Aquila chrysaetos and sea eagles Haliatetus albicilla at carcasses. Ibis 140:295–301

    CrossRef  Google Scholar 

  • Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction, 2nd edn. Springer, New York, NY, USA

    Google Scholar 

  • Henny CJ (2003) Effects of mining lead on birds: a case history at Coeur d’Alene Basin, Idaho. In: Hoffman DJ, Rattner BA, Burton GA Jr, Cairns J Jr (eds) Handbook of ecotoxicology, 2nd edn. Lewis Publishers, Boca Raton, FL, USA pp 755–766

    Google Scholar 

  • Herring G, Eagles-Smith CA, Wagner MT (2016) Ground squirrel shooting and potential lead exposure in breeding avian scavengers. PLoS One 11:e0167926

    CrossRef  Google Scholar 

  • Herring G, Eagles-Smith CA, Buck J (2017) Characterizing golden eagle risk to lead and anticoagulant rodenticide exposure: a review. J Raptor Res 51:273–292. https://doi.org/10.3356/JRR-16-19.1

    CrossRef  Google Scholar 

  • Hoffman SW, Smith JP (2003) Population trends of migratory raptors in western North America, 1977–2001. Condor 105:397–419

    CrossRef  Google Scholar 

  • Hoffman DJ, Pattee OH, Wiemeyer SN, Mulhern B (1981) Effects of lead shot ingestion on δ-aminolevulinic acid dehydratase activity, hemoglobin concentration, and serum chemistry in bald eagles. J Wildl Dis 17:423–431

    CAS  CrossRef  Google Scholar 

  • Hu Y, Cheng H (2013) Application of stochastic models in identification and apportionment of heavy metal pollution sources in the surface soils of a large-scale region. Environ Sci Technol 47:3752–3760. https://doi.org/10.1021/es304310k

    CAS  CrossRef  PubMed  Google Scholar 

  • Hunt WG (2012) Implications of sublethal lead exposure in avian scavengers. J Raptor Res 46:389–393

    CrossRef  Google Scholar 

  • Hunt WG, Burnham W, Parish CN, Burnham KK, Mutch B, Oaks JL (2006) Bullet fragments in deer remains: implications for lead exposure in avian scavengers. Wildl Soc Bull 34:167–170

    CrossRef  Google Scholar 

  • Knopper LD, Mineau P, Scheuhammer AM, Bond DE, McKinnon DT (2006) Carcasses of shot Richardson’s ground squirrels may pose lead hazards to scavenging hawks. J Wildl Manag 70:295–299

    CrossRef  Google Scholar 

  • Knudby A, Brenning A, Ledrew E (2010) New approaches to modelling fish–habitat relationships. Ecol Model 221:503–511

    CrossRef  Google Scholar 

  • Kochert MN, Steenhof K, Carpenter LB, Marzluff JM (1999) Effects of fire on golden eagle territory occupancy and reproductive success. J Wildl Manag 63:773–780

    CrossRef  Google Scholar 

  • Kochert MN, Steenhof KM, McIntyre CL, Craig EH (2002) Golden Eagle (Aquila chrysaetos), version 2.0. In: Poole AF, Gill FB (eds) The Birds of North America. Cornell Lab of Ornithology, Ithaca, NY, USA. https://doi.org/10.2173/bna.684

  • Kramer JL, Redig PT (1997) Sixteen years of lead poisoning in eagles, 1980–95: an epizootiologic view. J Raptor Res 31:327–332

    Google Scholar 

  • Legagneux P, Suffice P, Messier J-S, Lelievre F, Tremblay JA, Maisonneuve C, Saint-Louis R, Bêty J (2014) High risk of lead contamination for scavengers in an area with high moose hunting success. PLoS One 9:e111546

    CrossRef  Google Scholar 

  • Lemhi County History Committee (1992) Centennial history of Lemhi County, Idaho, vol 1. Lemhi County History Committee, Salmon, ID, USA

    Google Scholar 

  • Liu C, Berry PM, Dawson TP, Pearson RG (2005) Selecting thresholds of occurrence in the prediction of species distributions. Ecography 28:385–393

    CrossRef  Google Scholar 

  • Millsap BA, Zimmerman GS, Sauer JR, Nielson RM, Otto M, Bjerre E, Murphy R (2013) Golden eagle population trends in the western United States: 1968–2010. J Wildl Manag 77:1436–1448. https://doi.org/10.1002/jwmg.588

    CrossRef  Google Scholar 

  • Moradi E, Pepe A, Gaser C, Huttunen H, Tohka J, Initiative ADN, others (2015) Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects. NeuroImage 104:398–412

    CrossRef  Google Scholar 

  • Newton I (1989) Sparrowhawk. In: Newton I (ed) Lifetime reproduction in birds. Academic, London, England, pp 279–296

    Google Scholar 

  • Pain DJ, Bavoux C, Burneleau G (1997) Seasonal blood lead concentrations in marsh harriers Circus aeruginosus from Charente-maritime, France: relationship with the hunting season. Biol Conserv 81:1–7

    CrossRef  Google Scholar 

  • Pain DJ, Fisher IJ, Thomas VG (2009) A global update of lead poisoning in terrestrial birds from ammunition sources. In: Watson RT, Fuller M, Pokras M, Hunt WG (eds) Ingestion of Lead from Spent Ammunition: Implications for Wildlife and Humans. The Peregrine Fund, Boise, ID, USA. https://doi.org/10.4080/ilsa.2009.0108

  • Pattee OH (1984) Eggshell thickness and reproduction in American kestrels exposed to chronic dietary lead. Arch Environ Contam Toxicol 13:29–34

    CAS  CrossRef  Google Scholar 

  • Pattee OH, Bloom PH, Scott JM, Smith MR (1990) Lead hazards within the range of the California condor. Condor 92:931–937

    CrossRef  Google Scholar 

  • Powers DMW (2011) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. J Mach Learn Technol 2:37–63

    Google Scholar 

  • Shipp MA, Ross KN, Tamayo P, Weng AP, Kutok JL, Aguiar RC, Gaasenbeek M, Angelo M, Reich M, Pinkus GS, others (2002) Diffuse large B-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning. Nat Med 8:68–74

    CAS  CrossRef  Google Scholar 

  • Sriram TV, Rao MV, Narayana GS, Kaladhar DSVGK, VT (2013) Intelligent Parkinson disease prediction using machine learning algorithms. Int J Eng Innov Technol 3:212–215

    Google Scholar 

  • Stauber E, Finch N, Talcott PA, Gay JM (2010) Lead poisoning of bald (Haliaeetus leucocephalus) and golden (Aquila chrysaetos) eagles in the US inland Pacific northwest region-an 18-year retrospective study: 1991–2008. J Avian Med Surg 24:279–287

    CrossRef  Google Scholar 

  • Thessen AE (2016) Adoption of machine learning techniques in ecology and earth science. PeerJ PrePrints 4:e1720v1. https://doi.org/10.7287/peerj.preprints.1720v1

    CrossRef  Google Scholar 

  • Umpleby JB (1913) Geology and ore deposits of Lemhi County, Idaho (No. Bulletin 528). Department of the Interior, United States Geological Survey, Government Printing Office, Washington, DC, USA

    Google Scholar 

  • USFWS (1986) Final supplemental environmental impact statement on the use of lead shot for hunting migratory birds. Office of Migratory Bird Management, Washington, DC, USA

    Google Scholar 

  • USFWS (2016) Bald and golden eagles: population demographics and estimation of sustainable take in the United States, 2016 update. USFWS, Division of Migratory Bird Management, Washington, DC, USA

    Google Scholar 

  • Wang Q, Xie Z, Li F (2015) Using ensemble models to identify and apportion heavy metal pollution sources in agricultural soils on a local scale. Environ Pollut 206:227–235. https://doi.org/10.1016/j.envpol.2015.06.040

    CAS  CrossRef  PubMed  Google Scholar 

  • Wayland M, Bollinger T (1999) Lead exposure and poisoning in bald eagles and golden eagles in the Canadian prairie provinces. Environ Pollut 104:341–350

    CAS  CrossRef  Google Scholar 

  • Wayland M, Wilson LK, Elliott JE, Miller MJR, Bollinger T, McAdie M, Langelier K, Keating J, Froese JMW (2003) Mortality, morbidity, and lead poisoning of eagles in western Canada, 1986–98. J Raptor Res 37:8–18

    Google Scholar 

Download references

Acknowledgments

Many individuals have provided technical support for this project. We would particularly like to acknowledge the contributions of R. Craig, J. Craig, H. Craig McFarland and F. Huettmann. This project was partially funded by Aquila Environmental. Original funding for earlier aspects of this research was provided by the U.S. Bureau of Land Management, U.S. Geological Survey, University of Alaska Fairbanks, E-WHALE Lab, Western Ecological Studies Team, Idaho Department of Fish and Game, Golden Eagle Chapter of the Audubon Society, and The Idaho Wildlife Society. Trapping, banding and blood sample collection were authorized by the state of Idaho and the USGS Bird Banding Laboratory (Laurel, MD; permit no. 06714). Any use of trade, product, or firm names is for descriptive purposes only and does not imply endorsement by the U.S. Government.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Erica H. Craig .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

Craig, E.H., Craig, T.H., Fuller, M.R. (2018). Using TreeNet, a Machine Learning Approach to Better Understand Factors that Influence Elevated Blood Lead Levels in Wintering Golden Eagles in the Western United States. In: Humphries, G., Magness, D., Huettmann, F. (eds) Machine Learning for Ecology and Sustainable Natural Resource Management. Springer, Cham. https://doi.org/10.1007/978-3-319-96978-7_12

Download citation