Nebraska Cooperative Fish & Wildlife Research Unit



Ali Khalighifar, Colorado State University
Benjamin S. Gotthold, U.S. Geological Survey
Erin Adams, U.S. Fish and Wildlife Service
Jenny Barnett, U.S. Fish and Wildlife Service
Laura O. Beard, Wyoming Game and Fish Department
Eric R. Britzke, US Army Engineer Research & Development Center
Paul A. Burger, National Park Service
Kimberly Chase, Florida Fish and Wildlife Conservation Commission
Zackary Cordes, Kansas Department of Wildlife and Parks
Paul M. Cryan, U.S. Geological Survey
Emily Emily, Wildlife Conservation Section, Georgia Department of Natural Resources
Christopher T. Fill, University of Nebraska Lincoln
Scott E. Gibson, Utah Division of Wildlife Resources
G. Scott Haulton, Indiana Department of Natural Resources
Kathryn M. Irvine, U.S. Geological Survey
Lara S. Katz, University of Maine
William L. Kendall, U.S. Geological Survey
Christen A. Long, Bat Conservation International
Oisin Mac Aodha, University of Edinburgh
Tessa McBurney, University of Prince Edward Island
Sara McCarthy, Happy Valley-Goose Bay
Matthew W. McKown, Conservation Metrics, Inc.
Joy O'Keefe, University of Illinois Urbana Champaign
Lucy D. Patterson, Parks Canada Agency
Kristopher A. Pitcher, U.S. Air Force
Matthew Rustand, Bureau of Land Management
Jordi L. Segers, Canadian Wildlife Health Cooperative
Kyle Seppanen, Keweenaw Bay Indian Community Natural Resources Department
Jeremy L. Siemers, Colorado State University
Christian Stratton, Montana State University
Bethany R. Straw, U.S. Geological Survey
Theodore J. Weller, U.S. Department of Agriculture Forest Service
Brian E. Reichert, U.S. Geological Survey

Date of this Version



J Appl Ecol. 2022;00:1–14. DOI: 10.1111/1365-2664.14280


Open access.


  1. Bats play crucial ecological roles and provide valuable ecosystem services, yet many populations face serious threats from various ecological disturbances. The North American Bat Monitoring Program (NABat) aims to use its technology infrastructure to assess status and trends of bat populations, while developing innovative and community-driven conservation solutions.

  2. Here, we present NABat ML, an automated machine-learning algorithm that improves the scalability and scientific transparency of NABat acoustic monitoring. This model combines signal processing techniques and convolutional neural networks (CNNs) to detect and classify recorded bat echolocation calls. We developed our CNN model with internet-based computing resources (‘cloud environment’), and trained it on >600,000 spectrogram images. We also incorporated species range maps to improve the robustness and accuracy of the model for future ‘unseen’ data. We evaluated model performance using a comprehensive, independent, holdout dataset.

  3. NABat ML successfully distinguished 31 classes (30 species and a noise class) with overall weighted-average accuracy and precision rates of 92%, and ≥90% classification accuracy for 19 of the bat species. Using a single cloud-environment computing instance, the entire model training process took <16 h.

  4. Synthesis and applications. Our convolutional neural network (CNN)-based model, NABat ML, classifies 30 North American bat species using their recorded echolocation calls with an overall accuracy of 92%. In addition to providing highly accurate species-level classification, NABat ML and its outputs are compatible with Bayesian and other statistical techniques for measuring uncertainty in classification. Our model is open-source and reproducible, enabling future implementations as software on end-user devices and cloud-based web applications. These qualities make NABat ML highly suitable for applications ranging from grassroots community science initiatives to big-data methods developed and implemented by researchers and professional practitioners. We believe the transparency and accessibility of NABat ML will encourage broad-scale participation in bat monitoring, and enable development of innovative solutions needed to conserve North American bat species.