Standardised and referenced acoustic monitoring reliably estimates bat fatalities at wind turbines: comments on ‘Limitations of acoustic monitoring at wind turbines to evaluate fatality risk of bats’

Behr, Oliver; Barré, Kévin; Bontadina, Fabio; Brinkmann, Robert; Dietz, Markus; Disca, Thierry; Froidevaux, Jérémy S.P.; Ghanem, Simon J.; Huemer, Senta; Hurst, Johanna; Kaminsky, Stefan K.; Kelm, Volker; Korner‐Nievergelt, Fränzi; Lauper, Mirco; Lintott, Paul R.; Newman, Christian M.; Peterson, Trevor S.; Proksch, Jasmin; Roemer, Charlotte; Schorcht, Wigbert; Nagy, Martina

doi:10.1111/mam.12310

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A standard practice for areas under consideration for wind energy development is to conduct three to twelve months of acoustic monitoring for bat collision risk [ 13 , 14 ]. The value of these pre-construction surveys has recently been questioned [ 15 , 16 ], but acoustic monitoring may still play a role in detection-based operational minimization (a.k.a., “smart curtailment”) in reducing bat mortality at wind energy facilities [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

Automated echolocation classifiers vary in accuracy for northeastern U.S. bat species

Solick,

Hopp,

Chenger

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Acoustic surveys of bat echolocation calls are an important management tool for determining presence and probable absence of threatened and endangered bat species. In the northeastern United States, software programs such as Bat Call Identification (BCID), Kaleidoscope Pro (KPro), and Sonobat can automatically classify ultrasonic detector sound files, yet the programs’ accuracy in correctly classifying calls to species has not been independently assessed. We used 1,500 full-spectrum reference calls with known identities for nine northeastern United States bat species to test the accuracy of these programs using calculations of Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity (SN), Specificity (SP), Overall Accuracy, and No Information Rate. We found that BCID performed less accurately than other programs, likely because it only operates on zero-crossing data and may be less accurate for recordings converted from full-spectrum to zero-crossing. NPV and SP values were high across all species categories for SonoBat and KPro, indicating these programs’ success at avoiding false positives. However, PPV and SN values were relatively low, particularly for individual Myotis species, indicating these programs are prone to false negatives. SonoBat and KPro performed better when distinguishing Myotis species from non-Myotis species. We expect less accuracy from these programs for acoustic recordings collected under normal working conditions, and caution that a bat acoustic expert should verify automatically classified files when making species-specific regulatory or conservation decisions.

show abstract

Section: Introductionmentioning

confidence: 99%

Automated echolocation classifiers vary in accuracy for northeastern U.S. bat species

Solick,

Hopp,

Chenger

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…However, such microphones are stationary and cannot follow a nacelle’s rotational movement. Despite the limited detection area, Behr et al [ 23 ] argue that standardized and referenced acoustic monitoring at WTs’ nacelles can be used for the reliable estimation of bat fatalities as well as for determining curtailment algorithms for the bat-friendly operation of wind turbines.…”

Section: Introductionmentioning

confidence: 99%

Detection and validation of common noctule bats (Nyctalus noctula) with a pulse radar and acoustic monitoring in the proximity of an onshore wind turbine

Krapivnitckaia,

Kreutzfeldt,

Schritt

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

This paper presents the results of bats detected with marine radar and their validation with acoustic detectors in the vicinity of a wind turbine with a hub height of 120 m. Bat detectors are widely used by researchers, even though the common acoustic detectors can cover only a relatively small volume. In contrast, radar technology can overcome this shortcoming by offering a large detection volume, fully covering the rotor-swept areas of modern wind turbines. Our study focused on the common noctule bats (Nyctalus noctula). The measurement setup consisted of a portable X-band pulse radar with a modified radar antenna, a clutter shielding fence, and an acoustic bat detector installed in the wind turbine’s nacelle. The radar’s detection range was evaluated using an analytical simulation model. We developed a methodology based on a strict set of criteria for selecting suitable radar data, acoustic data and identified bat tracks. By applying this methodology, the study data was limited to time intervals with an average duration of 48 s, which is equal to approximately 20 radar images. For these time intervals, 323 bat tracks were identified. The most common bat speed was extracted to be between 9 and 10 m/s, matching the values found in the literature. Of the 323 identified bat tracks passed within 80 m of the acoustic detector, 32% had the potential to be associated with bat calls due to their timing, directionality, and distance to the acoustic bat detector. The remaining 68% passed within the studied radar detection volume but out of the detection volume of the acoustic bat detector. A comparison of recorded radar echoes with the expected simulated values indicated that the in-flight radar cross-section of recorded common noctule bats was mostly between 1.0 and 5.0 cm2, which is consistent with the values found in the literature for similar sized wildlife.

show abstract

“…Acoustic surveillance of bat activity is of great importance for mitigation and curtailment systems of wind turbines [ 17 , 18 ] and for general population monitoring apart from wind energy applications [ 19 ]. Non-invasive acoustic monitoring of bat activity has a long history of improvements regarding hardware, data management and analysis methodology [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Neural Network Design Incorporating Autoencoders for the Classification of Bat Echolocation Sounds

Alipek

Maelzer

Paumen

et al. 2023

Animals

View full text Add to dashboard Cite

Bats are widely distributed around the world, have adapted to many different environments and are highly sensitive to changes in their habitat, which makes them essential bioindicators of environmental changes. Passive acoustic monitoring over long durations, like months or years, accumulates large amounts of data, turning the manual identification process into a time-consuming task for human experts. Automated acoustic monitoring of bat activity is therefore an effective and necessary approach for bat conservation, especially in wind energy applications, where flying animals like bats and birds have high fatality rates. In this work, we provide a neural-network-based approach for bat echolocation pulse detection with subsequent genus classification and species classification under real-world conditions, including various types of noise. Our supervised model is supported by an unsupervised learning pipeline that uses autoencoders to compress linear spectrograms into latent feature vectors that are fed into a UMAP clustering algorithm. This pipeline offers additional insights into the data properties, aiding in model interpretation. We compare data collected from two locations over two consecutive years sampled at four heights (10 m, 35 m, 65 m and 95 m). With sufficient data for each labeled bat class, our model is able to comprehend the full echolocation soundscape of a species or genus while still being computationally efficient and simple by design. Measured classification F1 scores in a previously unknown test set range from 92.3% to 99.7% for species and from 94.6% to 99.4% for genera.

show abstract

Standardised and referenced acoustic monitoring reliably estimates bat fatalities at wind turbines: comments on ‘Limitations of acoustic monitoring at wind turbines to evaluate fatality risk of bats’

Cited by 4 publications

References 16 publications

Automated echolocation classifiers vary in accuracy for northeastern U.S. bat species

Automated echolocation classifiers vary in accuracy for northeastern U.S. bat species

Detection and validation of common noctule bats (Nyctalus noctula) with a pulse radar and acoustic monitoring in the proximity of an onshore wind turbine

An Efficient Neural Network Design Incorporating Autoencoders for the Classification of Bat Echolocation Sounds

Contact Info

Product

Resources

About