Reliable automation of bat call identification for eastern New South Wales, Australia, using classification trees and AnaScheme software

• Autorzy: Adams M.D. , Law B. S. , Gibson M. S.
• Języki publikacji: EN

Abstrakty

EN

Accurate and efficient identification of bat (Microchiroptera) echolocation calls has been hampered by poor knowledge of the intraspecific variability in calls (including regional variation), a lack of call parameters for use in separating species and the amount of time required to manually identify individual calls or call sequences. We constructed and tested automated bat call identification keys for three regions in New South Wales, Australia, using over 4,000 reference calls in ≈300 call sequences per region. We used the program AnaScheme to extract time, frequency and shape parameters from calls recorded with the Anabat system. Classification trees were built to separate species using these parameters and provided the decision rules for construction of the keys. An ‘Unknown’ category was included in the keys for sequences that could not be confidently identified to species. The reliability of the keys was tested automatically with AnaScheme, using independent sets of reference call sequences, and keys were refined before further testing on additional test sequences. Regional keys contained 18–19 species or included species groups. We report rates of sequence misidentification (accuracy) and correct identification (detection) relative to all sequences (including ‘unknowns’) used to test each version of a key. Refined versions of the keys were accurate, with total misidentification rates of 0.5–5.3% for the three regions. Additionally, total correct identifications for regions were 56–75% (> 50% for most species), an overall high rate of detection. When ‘unknowns’ were ignored, as is common in many published studies, correct identification for regions increased to 91–99%, rates which compare favourably to the most successful classifiers tested to date. The future use of AnaScheme for automated bat call identification is promising, especially for the large-scale temporal and spatial acoustic sampling to which Anabat is particularly suited.

Słowa kluczowe

EN

bat call; identification; New South Wales; Australia; classification tree; AnaScheme software; call; bat; habitat use; Anabat system; echolocation; identification key; monitoring; regional variation

• Wydawca: -
• Czasopismo: Acta Chiropterologica
• Rocznik: 2010
• Tom: 12
• Numer: 1
• Opis fizyczny: p.231-245,fig.,ref.

Twórcy

autor

Adams M.D.

• Forest Science Centre, Industry and Investment NSW, PO Box 100, Beecroft NSW 2119, Australia

autor

Law B. S.

autor

Gibson M. S.

Bibliografia

• 1. M. D. Adams , B. S. Law , and K. O. French . 2005. Effect of lights on activity levels of forest bats: increasing the efficiency of surveys and species identification. Wildlife Research, 32: 173–182. Google Scholar
• 2. R. M. R. Barclay 1999. Bats are not birds — a cautionary note on using echolocation calls to identify bats: a comment. Journal of Mammalogy, 80: 290–296. Google Scholar
• 3. R. M. R. Barclay , J. H. Fullard , and D. S. Jacobs . 1999. Variation in the echolocation calls of the hoary bat (Lasiurus cinereus): influence of body size, habitat structure, and geographic location. Canadian Journal of Zoology, 77: 530–534. Google Scholar
• 4. O. Berger-Tal , R. Berger-Tal , C. Korine , M. W. Holderied , and M. B. Fenton . 2008. Echolocation calls produced by Kuhl's pipistrelles in different flight situations. Journal of Zoology, 274: 59–64. Google Scholar
• 5. B. J. Betts 1998. Effects of interindividual variation in echo-location calls on identification of big brown and silver-haired bats. Journal of Wildlife Management, 62: 1003–1010. Google Scholar
• 6. S. Biscardi , J. Orprecio , M. B. Fenton , A. Tsoar , and J. M. Ratcliffe . 2004. Data, sample sizes and statistics affect the recognition of species of bats by their echolocation calls. Acta Chiropterologica, 6: 347–363. Google Scholar
• 7. E. R. Britzke 2004. Designing monitoring programs using frequency-division bat detectors: active versus passive sampling. Pp. 79–83, in Bat echolocation research: tools, techniques and analysis ( R. M. Brigham , E. K. V. Kalko , G. Jones , S. Parsons , and H. J. G. A. Limpens , eds.). Bat Conservation International, Austin, Texas, vii + 167 pp. Google Scholar
• 8. H. G. Broders , C. S. Findlay , and L. Zheng . 2004. Effects of clutter on echolocation call structure of Myotis septentrionalis and M. lucifugus. Journal of Mammalogy, 85: 273–281. Google Scholar
• 9. C. Chiu , W. Xian , and C. F. Moss . 2009. Adaptive echolocation behavior in bats for the analysis of auditory scenes. Journal of Experimental Biology, 212: 1392–1404. Google Scholar
• 10. S. Churchill 2009. Australian bats, 2nd edition. Allen and Unwin, Sydney, 256 pp. Google Scholar
• 11. C. Corben , and G. M. Fellers . 2001. Choosing the ‘correct’ bat detector — a reply. Acta Chiropterologica, 3: 253–256. Google Scholar
• 12. D. De'Ath , and K. E. Fabricius . 2000. Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology, 81: 3178–3192. Google Scholar
• 13. A. M. Duffy , L. F. Lumsden , C. R. Caddle , R. R. Chick , and G. R. Newell . 2000. The efficacy of Anabat ultrasonic detectors and harp traps for surveying microchiropterans in south-eastern Australia. Acta Chiropterologica, 2: 127–144. Google Scholar
• 14. M. B. Fenton , and G. P. Bell . 1981. Recognition of species of insectivorous bats by their echolocation calls. Journal of Mammalogy, 62: 233–243. Google Scholar
• 15. J. Fischer , J. Stott , B. S. Law , M. D. Adams , and R. I. Forrester . 2009. Designing effective habitat studies: quantifying multiple sources of variability in bat activity. Acta Chiropterologica, 11: 127–137. Google Scholar
• 16. D. Fukui , N. Agetsuma , and D. A. Hill . 2004. Acoustic identification of eight species of bat (Mammalia: Chiroptera) inhabiting forests of southern Hokkaido, Japan: potential for conservation monitoring. Zoological Science, 21: 947–955. Google Scholar
• 17. W. L. Gannon , M. J. O'Farrell , C. Corben , and E. J. Bedrick . 2004. Call character lexicon and analysis of field recordings of bat echolocation calls. Pp. 478–484, in Echolocation in bats and dolphins ( J. A. Thomas , C. F. Moss , and M. Vater , eds.). The University of Chicago Press, Chicago, xxvii + 604 pp. Google Scholar
• 18. M. Gibson , and L. Lumsden . 2003. The AnaScheme automated bat call identification system. The Australasian Bat Society Newsletter, 20: 24–27. Google Scholar
• 19. E. H. Gillam , and G. F. McCracken . 2007. Variability in the echolocation of Tadarida brasiliensis: effects of geography and local acoustic environment. Animal Behaviour, 74: 277–286. Google Scholar
• 20. D. R. Griffin 1958. Listening in the dark. Yale University Press, New Haven, 415 pp. Google Scholar
• 21. D. R. Griffin , F. A. Webster , and C. R. Michael . 1960. The echolocation of flying insects by bats. Animal Behaviour, 8: 141–154. Google Scholar
• 22. A. Herr , N. I. Klomp , and J. S. Atkinson . 1997. Identification of bat echolocation calls using a decision tree classification system. Complexity International, 4, URL http://www.csu.edu.au/ci/vol4/herr/batcall.html Google Scholar
• 23. D. A. Hill , and F. Greenaway . 2005. Effectiveness of an acoustic lure for surveying bats in British woodlands. Mammal Review, 35: 116–122. Google Scholar
• 24. S. H. Hurlbert 1984. Pseudoreplication and the design of ecological field experiments. Ecological Monographs, 54: 187–211. Google Scholar
• 25. N. Jennings , S. Parsons , and M. J. O. Pocock . 2008. Human vs. machine: identification of bat species from their echolocation calls by humans and by artificial neural networks. Canadian Journal of Zoology, 86: 371–377. Google Scholar
• 26. M. E. Jensen , and L. A. Miller . 1999. Echolocation signals of the bat Eptesicus serotinus recorded using a vertical microphone array: effect of flight altitude on searching signals. Behavioral Ecology and Sociobiology, 47: 60–69. Google Scholar
• 27. G. Jones , and T. Kokurewicz . 1994. Sex and age variation in echolocation calls and flight morphology of Daubenton's bats Myotis daubentonii. Mammalia, 58: 41–50. Google Scholar
• 28. G. Jones , N. Vaughan , and S. Parsons . 2000. Acoustic identification of bats from directly sampled and time expanded recordings of vocalizations. Acta Chiropterologica, 2: 155–170. Google Scholar
• 29. E. K. V. Kalko , and H.-U. Schnitzler . 1993. Plasticity in echolocation signals of European pipistrelle bats in search flight: implications for habitat use and prey detection. Behavioral Ecology and Sociobiology, 33: 415–428. Google Scholar
• 30. B. S. Law , and M. Chidel . 2006. Eucalypt plantings on farms: use by insectivorous bats in south-eastern Australia. Biological Conservation, 133: 236–249. Google Scholar
• 31. B. S. Law , L. Reinhold , and M. Pennay . 2002. Geographic variation in the echolocation calls of Vespadelus spp. (Vespertilionidae) from New South Wales and Queensland, Australia. Acta Chiropterologica, 4: 201–215. Google Scholar
• 32. L. F. Lumsden , and A. F. Bennett . 2005. Scattered Trees in Rural Landscapes: Foraging Habitat for insectivorous bats in south-eastern Australia. Biological Conservation, 122: 205–222. Google Scholar
• 33. W. M. Masters , K. A. S. Raver , and K. A. Kazial . 1995. Sonar signals of big brown bats, Eptesicus fuscus, contain information about individual identity, age and family affiliation. Animal Behaviour, 50: 1243–1260. Google Scholar
• 34. D. J. Milne , M. Armstrong , A. Fisher , T. Flores , and C. R. Pavey . 2004. A comparison of three survey methods for collecting bat echolocation calls and species-accumulation rates from nightly Anabat recordings. Wildlife Research, 31: 57–63. Google Scholar
• 35. K. L. Murray , E. R. Britzke , B. M. Hadley , and L. W. Robbins . 1999. Surveying bat communities: a comparison between mist nets and the Anabat II bat detector system. Acta Chiropterologica, 1: 105–112. Google Scholar
• 36. K. L. Murray , E. R. Britzke , and L. W. Robbins . 2001. Variation in search-phase calls of bats. Journal of Mammaogy, 82: 728–737. Google Scholar
• 37. M. K. Obrist 1995. Flexible bat echolocation: the influence of individual, habitat and conspecifics on sonar signal design. Behavioral Ecology and Sociobiology, 36: 207–219. Google Scholar
• 38. M. K. Obrist , R. Boesch , and P. F. Flückiger . 2004. Variability in echolocation call design of 26 Swiss bat species: consequences, limits and options for automated field identification with a synergetic pattern recognition approach. Mammalia, 68: 307–322. Google Scholar
• 39. M. J. O'Farrell , B. W. Miller , and W. L. Gannon . 1999a. Qualitative identification of free-flying bats using the Anabat detector. Journal of Mammalogy, 80: 11–23. Google Scholar
• 40. M. J. O'Farrell , C. Corben , W. L. Gannon , and B. W. Miller . 1999b. Confronting the dogma: a reply. Journal of Mammalogy, 80: 297–302. Google Scholar
• 41. M. J. O'Farrell , C. Corben , and W. L. Gannon . 2000. Geographic variation in the echolocation calls of the hoary bat (Lasiurus cinereus). Acta Chiropterologica, 2: 185–195. Google Scholar
• 42. E. Papadatou , R. K. Butlin , and J. D. Altringham . 2008. Identification of bat species in Greece from their echolocation calls. Acta Chiropterologica, 10: 127–143. Google Scholar
• 43. H. Parnaby 1992. An interim guide to identification of insectivorous bats of south-eastern Australia. Technical Reports of the Australian Museum, No. 8, 33 pp. Google Scholar
• 44. S. Parsons 1997. Search-phase echolocation calls of the New Zealand lesser short-tailed bat (Mystacina tuberculata) and long-tailed bat (Chalinolobus tuberculatus). Canadian Journal of Zoology, 75: 1487–1494. Google Scholar
• 45. S. Parsons 2001. Identification of New Zealand bats (Chalinolobus tuberculatus and Mystacina tuberculata) in flight from analysis of echolocation calls by artificial neural networks. Journal of Zoology (London), 253: 447–456. Google Scholar
• 46. S. Parsons , and G. Jones . 2000. Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks. The Journal of Experimental Biology, 203: 2641–2656. Google Scholar
• 47. M. Pennay , B. Law , and L. Reinhold . 2004. Bat calls of New South Wales: region based guide to the echolocation calls of Microchiropteran bats. NSW Department of Environment and Conservation, Hurstville. Google Scholar
• 48. D. G. Preatoni , M. Nodari , R. Chirichella , G. Tosi , L. A. Wauters , and A. Martinoli . 2005. Identifying bats from time-expanded recordings of search calls: comparing classification methods. Journal of Wildlife Management, 69: 1601–1614. Google Scholar
• 49. R. D. Redgwell , J. M. Szewczak , G. Jones , and S. Parsons . 2009. Classification of echolocation calls from 14 species of bat by support vector machines and ensembles of neural networks. Algorithms, 2: 907–924. Google Scholar
• 50. L., Reinhold A. Herr , L. Lumsden , T. Reardon , C. Corben , B. Law , P. Prevett , G. Ford , L. Conole , A. Kutt , D. Milne , and G. Hoye . 2001a. Geographic variation in the echolocation calls of Gould's wattled bat Chalinolobus gouldii. Australian Zoologist, 31: 618–624. Google Scholar
• 51. L. Reinhold , B. Law , G. Ford , and M. Pennay . 2001b. Key to the bat calls of south-east Queensland and north-east New South Wales. Forest Ecosystem Research and Assessment Technical Paper 2001–07 , Department of Natural Resources and Mines, Queensland, iii + 62 pp . Google Scholar
• 52. D. Russo , and G. Jones . 2002. Identification of twenty-two bat species (Mammalia: Chiroptera) from Italy by analysis of time-expanded recordings of echolocation calls. Journal of Zoology (London), 258: 91–103. Google Scholar
• 53. Y Shan , D. Paull , and R. I. McKay . 2006. Machine learning of poorly predictable ecological data. Ecological Modelling, 195: 129–138. Google Scholar
• 54. M. D. Skowronski , and J. G. Harris . 2006. Acoustic detection and classification of microchiroptera using machine learning: lessons learned from automatic speech recognition. Journal of the Acoustical Society of America, 119: 1817–1833. Google Scholar
• 55. D. W. Thomas , G. P. Bell , and M. B. Fenton . 1987. Variation in echolocation call frequencies recorded from North American vespertilionid bats: a cautionary note. Journal of Mammalogy, 68: 842–847. Google Scholar
• 56. N. Vaughan , G. Jones , and S. Harris . 1997. Identification of British bat species by multivariate analysis of echolocation call parameters. Bioacoustics, 7: 189–207. Google Scholar
• 57. T. J. Weller , and C. J. Zabel . 2002. Variation in bat detections due to detector orientation in a forest. Wildlife Society Bulletin, 30: 922–930. Google Scholar