Version 1
: Received: 4 November 2024 / Approved: 5 November 2024 / Online: 5 November 2024 (10:29:29 CET)
How to cite:
Iqbal, M.; Wijeratne, L. O. H.; Waczak, J.; Dewage, P. M.; Balagopal, G.; Lary, D. J. IoT Based Sensing for Assessing Ambient Environmental Conditions and Air Quality Influences on Avian Vocal Behavior and Diversity. Preprints2024, 2024110281. https://doi.org/10.20944/preprints202411.0281.v1
Iqbal, M.; Wijeratne, L. O. H.; Waczak, J.; Dewage, P. M.; Balagopal, G.; Lary, D. J. IoT Based Sensing for Assessing Ambient Environmental Conditions and Air Quality Influences on Avian Vocal Behavior and Diversity. Preprints 2024, 2024110281. https://doi.org/10.20944/preprints202411.0281.v1
Iqbal, M.; Wijeratne, L. O. H.; Waczak, J.; Dewage, P. M.; Balagopal, G.; Lary, D. J. IoT Based Sensing for Assessing Ambient Environmental Conditions and Air Quality Influences on Avian Vocal Behavior and Diversity. Preprints2024, 2024110281. https://doi.org/10.20944/preprints202411.0281.v1
APA Style
Iqbal, M., Wijeratne, L. O. H., Waczak, J., Dewage, P. M., Balagopal, G., & Lary, D. J. (2024). IoT Based Sensing for Assessing Ambient Environmental Conditions and Air Quality Influences on Avian Vocal Behavior and Diversity. Preprints. https://doi.org/10.20944/preprints202411.0281.v1
Chicago/Turabian Style
Iqbal, M., Gokul Balagopal and David J. Lary. 2024 "IoT Based Sensing for Assessing Ambient Environmental Conditions and Air Quality Influences on Avian Vocal Behavior and Diversity" Preprints. https://doi.org/10.20944/preprints202411.0281.v1
Abstract
This study introduces a new approach to monitoring avian diversity and vocal behavior, as well as assessing their responses to environmental factors using IoT-based sensors. We utilized BirdNet, a deep learning model for identifying bird species by their vocalizations, to data from our MINTS-AI environmental sensors deployed across Dallas, Texas. The study investigates how ambient temperature, humidity, light intensity, and particulate matter concentrations affect bird behavior. The results show a positive correlation between bird diversity and temperature during winter, with a Pearson coefficients of 0.65 (2023) and 0.80 (2024), and R2 values of 0.43 and 0.64, respectively. In contrast, during summer, a negative correlation was found with Pearson coefficients of -0.63 (2023) and -0.34 (2024), with corresponding R2 values of 0.40 and 0.11. Machine learning models further highlighted species such as the Northern Mockingbird and Mississippi Kite as particularly sensitive to temperature changes. Humidity analysis revealed significant correlations of vocal activity for species like the Canada Goose and House Finch, indicating that vocal activity may depend on moisture levels. Light intensity also showed strong influences on species such as the Northern Mockingbird and Scissor-tailed Flycatcher, linking variations in light to vocal behavior. However, no significant relationship was found between particulate matter (PM2.5) concentrations and bird behavior. This methodology offers a new way to explore the effects of climate change on bird behavior over time, given adequate long-term data. These findings emphasize the important role of environmental changes in shaping bird populations and their ecological interactions.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
