Wind Energy Facilities Research Articles

White-Nose Syndrome Pathogen Pseudogymnoascus destructans Detected in Migratory Tree-Roosting Bats.

White-nose syndrome (WNS) is an emerging fungal epizootic disease that has caused large-scale mortality in several species of North American bats. The fungus that causes WNS, Pseudogymnoascus destructans (Pd), has also been detected in bat species without diagnostic signs of WNS. Although these species could play a role in WNS spread, understanding of the spatial and temporal extents of Pd occurrence on WNS-resistant species is limited. This study evaluated the presence of Pd on 272 individuals of three species of migratory tree-roosting bats: hoary (Lasiurus cinereus), eastern red (Lasiurus borealis), and silver-haired (Lasionycteris noctivagans) bats, obtained opportunistically during summer and autumn from throughout much of their ranges in North America. We also compared tissue sampling protocols (i.e., tissue swabbing, fur swabbing, and DNA extraction of excised wing tissue). We detected Pd on three eastern red bats from Illinois and Ohio, US, one silver-haired bat from West Virginia, US, and one hoary bat from New York, US, all via DNA extracted from wing tissue of carcasses. These results document the first publicly reported detections of Pd on a hoary bat and on migratory bats during the autumn migratory period, and demonstrate the potential for using carcasses salvaged at wind-energy facilities to monitor for Pd.

A Closer Look at the Environmental Impact of Solar and Wind Energy.

Moving towards a sustainable society implies constant improvement in the way energy is supplied and consumed, with wider implementation of solar and wind energy facilities in stand‐alone or hybrid configurations. The goal of this work is to evaluate the lifecycle performance (construction and operation‐related impact) of large‐scale solar and wind energy systems and to compare it with conventional coal and natural gas fossil fuel plants under similar conditions. Environmental analyses of energy conversion systems today usually neglect the construction‐related environmental impact of fossil fuel plants, because it is significantly smaller than the impact related to the operation of the plant. However, the construction of large‐scale renewable plants implies the use of rare materials, transport‐related emissions, and other environmentally impactful activities. The plants evaluated here are configured and compared for similar emissions and similar power output. It is found that the life‐cycle environmental impact of the renewable plants could, in some specific cases, exceed that of the fossil fuel plants. Understanding the reasons behind this and the possible limitations of the different technologies can help plan for sustainable energy systems in the future. Finally, solutions to minimize the impact of renewable energy are proposed for more environmentally friendly implementation and future research.

Performance Analysis for the Most Convenient Wind Turbine Selection in Wind Energy Facility

Performance Analysis for the Most Convenient Wind Turbine Selection in Wind Energy Facility

Problems Applying a Model for Red-Tailed Hawks and American Crows to Golden Eagles

In the 13(1) issue of the Journal of Fish and Wildlife Management , Dwyer and Mojica (2022) tested the usefulness of a 2014 model, based on Southern California Edison (SCE) data, for assessing avian electrocution risk of power poles to predict electrocution risk for golden eagles Aquila chrysaetos (Dwyer et al. 2014). They suggested that if the 2014 model is applicable to golden eagles, it could be used by the U.S. Fish and Wildlife Service (USFWS) when determining appropriate compensatory mitigation for incidental take permits issued under the Bald and Golden Eagle Protection Act. Power pole retrofits currently serve as mitigation for several types of golden eagle take permits including but not limited to wind energy facilities, mining construction and operators, electric utility operators, and nest disturbance.

Monitoring Raptor Movements with Satellite Telemetry and Avian Radar Systems: An Evaluation for Synchronicity

Avian radar technologies have the potential to serve an important role in the quantification of bird movements and determining patterns of bird use in areas where human–wildlife conflicts might occur (e.g., airports, wind energy facilities). Ground-truthing studies are needed to help wildlife managers understand the biological meaning of radar information, as the capabilities and limitations of these technologies are relatively unknown. We conducted a study to evaluate the efficacy of three X-band marine radar sensors for tracking red-tailed hawks (Buteo jamaicensis) on or near the airfield at Chicago’s O’Hare International Airport from September 2010 to May 2014. Specific information regarding red-tailed hawk locations derived from satellite telemetry was used to determine how frequently the three radar sensors provided corresponding tracks of these avian targets (i.e., synchronized monitoring). We examined various factors (e.g., bird altitude and distance to the radar) to determine if they had any influence on the frequency of synchronicity between satellite telemetry locations and radar tracks. We found evidence that as the distance between a hawk and the radars increased, the radars’ ability to detect and track known avian targets decreased. Overall, the frequency of synchronization events for red-tailed hawks was low. Of the 1977 red-tailed hawk locations that should have been visible to the radar sensors, 51 of these bird movements were tracked by at least one of the radar sensors (2.6%). This study provides a new methodology for evaluating the performance of radar systems for tracking birds and determining what factors might influence overall performance.

Efficacy and cost of acoustic-informed and wind speed-only turbine curtailment to reduce bat fatalities at a wind energy facility in Wisconsin.

Current research estimates hundreds of thousands of turbine-related bat fatalities in North America annually. In an effort to reduce impacts of wind energy production on bat populations, many facilities implement operational curtailment strategies that limit turbine blade rotation during conditions when nighttime wind speeds are low. Incorporating real-time bat activity data into wind speed-only curtailment (WOC) strategies may increase operational flexibility by allowing turbines to operate normally when bats are not present near turbines. We evaluated costs and benefits of implementing the Turbine Integrated Mortality Reduction (TIMR) system, an approach that informs a curtailment-triggering algorithm based on wind speed and real-time bat acoustic data, compared to a WOC strategy in which turbines were curtailed below 4.5 meters per second (m/s) at a wind energy facility in Fond Du Lac County, Wisconsin. TIMR is a proprietary system and we had no access to the acoustic data or bat call analysis software. Operational parameters for the TIMR system were set to allow curtailment at all wind speeds below 8.0 m/s during the study period when bats were acoustically detected. Overall, the TIMR system reduced fatalities by 75% compared to control turbines, while the WOC strategy reduced fatalities by 47%. An earlier analysis of the same TIMR data neglected to account for carcasses occurring outside the plot boundary and estimated an 84.5% fatality reduction due to the TIMR system. Over the study period, bat activity led to curtailment of TIMR turbines during 39.4% of nighttime hours compared to 31.0% of nighttime hours for WOC turbines, and revenue losses were approximately 280% as great for TIMR turbines as for turbines operated under the WOC strategy. The large cost difference between WOC and TIMR was driven by the 4.5 m/s versus 8.0 m/s wind speed thresholds for curtailment, but our study site has a relatively low average wind speed, which may also have contributed; other wind operators considering the TIMR system will need to consider their ability to absorb production losses in relation to their need to reduce bat fatality rates.

Wind speed prediction based on multi-variable Capsnet-BILSTM-MOHHO for WPCCC

To additional understand the wind speed prediction of every wind energy facility in several geographical locations and environments within the Wind Power Centralized Control Center (WPCCC), this paper proposes a variable short wind speed prediction model of Capsule Neural Network (Capsnet) and bidirectional Long and Short Term Memory Network (BILSTM) combined with Multi-Object Harris Hawk optimization (MOHHO). The method selects four typical location wind farms within the wind farm hub and uses their historical wind speed information and multidimensional meteorologic variables as inputs to the model, then extract the spatial features of the multifaceted temporal variables by Capsnet and apply BILSTM to simulate the time dependence of the capsule layer outputs, and at last transfer the four pre-trained models to the wind farm hub victimization the transfer learning and MOHHO optimization algorithm to weight the four sets of prediction results, to get the wind speed prediction results of any wind farm underneath the jurisdiction of the centralized center. Once examination of the experimental results, it's shown that the model has high prediction accuracy.

Seasonal variation in age, sex, and reproductive status of Mexican free‐tailed bats

AbstractIn North America, Mexican free‐tailed bats (Tadarida brasiliensis mexicana) consume vast numbers of insects contributing to the economic well‐being of society. Mexican free‐tailed bats have declined due to historic guano mining, roost destruction, and bioaccumulation of organochlorine pesticides. Long‐distance migrations and dense congregations at roosts exacerbate these declines. Wind energy development further threatens bat communities worldwide and presents emerging challenges to bat conservation. Effective mitigation of bat mortality at wind energy facilities requires baseline data on the biology of affected populations. We collected data on age, sex, and reproductive condition of Mexican free‐tailed bats at a cave roost in eastern Nevada located 6 km from a 152‐MW industrial wind energy facility. Over 5 years, we captured 46,353 Mexican free‐tailed bats. Although just over half of the caught individuals were nonreproductive adult males (53.6%), 826 pregnant, 892 lactating, 10,101 post‐lactating, and 4327 nonreproductive adult females were captured. Juveniles comprised 11.5% of captures. Female reproductive phenology was delayed relative to conspecific roosts at lower latitudes, likely due to cooler temperatures. Roost use by reproductive females and juvenile bats demonstrates this site is a maternity roost, with significant ecological and conservation value. To our knowledge, no other industrial scale wind energy facilities exist in such proximity to a heavily used bat roost in North America. Given the susceptibility of Mexican free‐tailed bats to wind turbine mortality and the proximity of this roost to a wind energy facility, these data provide a foundation from which differential impacts on demographic groups can be assessed.

Comparison of the Home Ranges of Mountain Hawk-Eagles during Different Phases of Wind Farm Construction

Raptors are long-lived apex predators with a lower rate of breeding success than smaller birds. Therefore, their responses to the construction of wind farms must be documented to assess the impact of wind energy on birds. We estimated the home ranges of three pairs of Mountain Hawk-Eagle Nisaetus nipalensis orientalis before, during, and after construction of a wind energy facility to assess changes in home range. We also compared altitude, inclination, and land cover composition of habitats within home ranges during the construction phase. For one pair, the home range of which included wind farm construction, the distance from the home range to the construction area during the first year of construction increased significantly compared with that during pre-construction, but there was no significant difference between the post-construction and construction phase. It is thought that the construction of a wind farm within the home range caused the displacement, and that displacement began during the first phase of construction and continuing during the second phase and afterwards. Because the birds moved about 500 m away from the wind farm during the construction and post-construction phases but succeeded in breeding, we think that the distance of 500 m may be meaningful in terms of mitigating disturbance. The nest trees of all three successful breeding pairs were more than 1.3 km from the closest wind turbine, perhaps indicative that impact on breeding is light if construction takes place this far away from breeding sites. No significant differences in either land cover or inclination within home ranges were found during the construction phase, which might explain why all birds bred successfully during the second construction phase. After construction, all three pairs continued to use areas with similar habitat.

An Updated Review of Hypotheses Regarding Bat Attraction to Wind Turbines.

Simple SummaryThe rapid development of wind energy facilities has increased bat mortality due to wind turbine blade strikes. Patterns of bat activity and mortality at wind energy facilities suggest that bats are attracted to wind turbines. It has been more than a decade since a comprehensive review of the various attraction hypotheses was published, highlighting the need to revisit and assess progress in the testing of these ideas. In this review, we discuss the most prominent attraction hypotheses, summarize the current state of knowledge, and briefly outline remaining questions. Identifying the causes of bat interactions with wind turbines is critical to developing effective impact minimization strategies. Patterns of bat activity and mortalities at wind energy facilities suggest that bats are attracted to wind turbines based on bat behavioral responses to wind turbines. For example, current monitoring efforts suggest that bat activity increases post-wind turbine construction, with bats making multiple passes near wind turbines. We separated the attraction hypothesis into five previously proposed explanations of bat interactions at or near wind turbines, including attraction based on noise, roost sites, foraging and water, mating behavior, and lights, and one new hypothesis regarding olfaction, and provide a state of the knowledge in 2022. Our review indicates that future research should prioritize attraction based on social behaviors, such as mating and scent-marking, as this aspect of the attraction hypothesis has many postulates and remains the most unclear. Relatively more data regarding attraction to wind turbines based on lighting and noise emission exist, and these data indicate that these are unlikely attractants. Analyzing attraction at the species-level should be prioritized because of differences in foraging, flight, and social behavior among bat species. Lastly, research assessing bat attraction at various scales, such as the turbine or facility scale, is lacking, which could provide important insights for both wind turbine siting decisions and bat mortality minimization strategies. Identifying the causes of bat interactions with wind turbines is critical for developing effective impact minimization strategies.

Effects of turbine height and cut-in speed on bat and swallow fatalities at wind energy facilities

Understanding the relationship between the height of wind turbines and wildlife fatalities is important for informing and mitigating wildlife collisions as ever taller and denser arrays of wind turbines are erected across the landscape. We examined relationships between turbine height and fatalities of bats and swallows at 811 turbines in Ontario, Canada, ranging from 119 to 186 m tall. We accounted for cut-in speeds, operational mitigation, and taller turbines projecting carcasses farther from the turbine base than shorter turbines. Fatalities of hoary bats ( Lasiurus cinereus Palisot de Beauvois, 1796), silver-haired bats ( Lasionycteris noctivagans Le Conte, 1831), and big brown bats ( Eptesicus fuscus Palisot de Beauvois, 1796) increased with increased maximum blade height of turbines. In contrast, fatalities of little brown bat ( Myotis lucifugus Le Conte, 1831) and eastern red bat ( Lasiurus borealis Müller, 1776) decreased with increased turbine height. Fatalities of purple martins ( Progne subis Linnaeus, 1758) and tree swallows ( Tachycineta bicolor Vieillot, 1808) were higher at taller turbines than shorter turbines. However, fatalities of cliff swallow ( Petrochelidon pyrrhonota Vieillot, 1817) and barn swallow ( Hirundo rustica Linnaeus, 1758) were not associated with turbine height. Our results suggest that varying flight height among species may be one factor affecting collision risk.

Selecting auditory alerting stimuli for eagles on the basis of auditory evoked potentials.

Development of wind energy facilities results in interactions between wildlife and wind turbines. Raptors, including bald and golden eagles, are among the species known to incur mortality from these interactions. Several alerting technologies have been proposed to mitigate this mortality by increasing eagle avoidance of wind energy facilities. However, there has been little attempt to match signals used as alerting stimuli with the sensory capabilities of target species like eagles. One potential approach to tuning signals is to use sensory physiology to determine what stimuli the target eagle species are sensitive to even in the presence of background noise, thereby allowing the development of a maximally stimulating signal. To this end, we measured auditory evoked potentials of bald and golden eagles to determine what types of sounds eagles can process well, especially in noisy conditions. We found that golden eagles are significantly worse than bald eagles at processing rapid frequency changes in sounds, but also that noise effects on hearing in both species are minimal in response to rapidly changing sounds. Our findings therefore suggest that sounds of intermediate complexity may be ideal both for targeting bald and golden eagle hearing and for ensuring high stimulation in noisy field conditions. These results suggest that the sensory physiology of target species is likely an important consideration when selecting auditory alerting sounds and may provide important insight into what sounds have a reasonable probability of success in field applications under variable conditions and background noise.

Timing and Weather Offer Alternative Mitigation Strategies for Lowering Bat Mortality at Wind Energy Facilities in Ontario.

Simple SummaryWind farms represent one of the largest sources of anthropogenic mortality for bats. Wind proponents attempt to mitigate these effects via operational curtailment, such that wind energy is not produced on nights with low wind speeds during the late summer and fall. Our study modeled bat activity and mortality on two timescales (nightly and seasonally) and in response to a range of weather variables. We showed that bat mortality risks could be lowered and opportunities for wind energy production can be increased by focusing curtailment efforts to the periods of the night and year when bats are most active and by considering a wider range of weather variables, compared to standard curtailment strategies.Relatively high mortality of migratory bats at wind energy facilities has prompted research to understand the underlying spatial and temporal factors, with the goal of developing more effective mitigation approaches. We examined acoustic recordings of echolocation calls at 12 sites and post-construction carcass survey data collected at 10 wind energy facilities in Ontario, Canada, to quantify the degree to which timing and regional-scale weather predict bat activity and mortality. Rain and low temperatures consistently predicted low mortality and activity of big brown bats (Eptesicus fuscus) and three species of migratory tree bats: hoary bat (Lasiurus cinereus), eastern red bat (L. borealis), and silver-haired bat (Lasionycteris noctivagans). Bat activity occurred in waves with distinct peaks through the season; regardless of seasonal timing, most activities occurred in the first half of the night. We conclude that wind energy facilities could adopt a novel and more effective curtailment strategy based on weather and seasonal and nocturnal timing that would minimize mortality risks for bats while increasing the opportunities for power generation, relative to the mitigation strategy of increasing cut-in wind speed to 5.5 m/s.

The Use of Intrinsic Markers for Studying the Migratory Movements of Bats.

Simple SummaryMigratory bats species are among the most heavily impacted by the erection of wind energy facilities, with many individuals killed at wind turbines each year. Bat carcasses may be collected and used for a variety of biological studies. In this paper, we review the use of intrinsic markers—chemical signatures in bat tissues that can provide information about that animal’s life history—to study bat movements across the landscape. In doing so, we aim to provide our audience with a better understanding of the currently available literature and, more importantly, the areas of this field that need expansion. We emphasize the applications of intrinsic markers that have not been used extensively to study migratory bat species (i.e., trace elements, contaminants, strontium isotopes), and provide a workflow for researchers interested in conducting studies of this type.Mortality of migratory bat species at wind energy facilities is a well-documented phenomenon, and mitigation and management are partially constrained by the current limited knowledge of bat migratory movements. Analyses of biochemical signatures in bat tissues (“intrinsic markers”) can provide information about the migratory origins of individual bats. Many tissue samples for intrinsic marker analysis may be collected from living and dead bats, including carcasses collected at wind energy facilities. In this paper, we review the full suite of available intrinsic marker analysis techniques that may be used to study bat migration, with the goal of summarizing the current literature and highlighting knowledge gaps and opportunities. We discuss applications of the stable isotopes of hydrogen, oxygen, nitrogen, carbon, sulfur; radiogenic strontium isotopes; trace elements and contaminants; and the combination of these markers with each other and with other extrinsic markers. We further discuss the tissue types that may be analyzed for each and provide a synthesis of the generalized workflow required to link bats to origins using intrinsic markers. While stable hydrogen isotope techniques have clearly been the leading approach to infer migratory bat movement patterns across the landscape, here we emphasize a variety of lesser used intrinsic markers (i.e., strontium, trace elements, contaminants) that may address new study areas or answer novel research questions.

Attitudes of Communities in Rural Areas towards the Development of Wind Energy

The objective of the study was to demonstrate attitudes towards wind energy facilities in the area of the Korsze Commune. The results of the study were processed using structure indices calculated from the respondents’ answers, which were analyzed in terms of social and economic factors. The study revealed that both the NIMBY syndrome and the lack of civic engagement influence attitudes towards renewable energy technologies in rural areas. The NIMBY (“not in my backyard”) term describes negative public attitudes towards proposed development projects. However, some trends towards more pronounced attitudes can be observed, depending on socioeconomic conditions. The research results imply that the measures taken to promote renewable energy technologies should be designed differently depending on the socioeconomic situation of the targeted audience. Young people might be reached via social media appropriate to their age, and through campaigns promoting local investments. For older people, traditional ways of communication can be used, but the information transmitted should include specific benefits for the whole society as well as for individual households. The conducted research revealed that, despite the fact that many authors deny the occurrence of NIMBY syndrome in relation to the wind energy, the NIMBY problem has occurred in the Korsze Commune. The biggest challenge in the survey was the unwillingness of the residents to participate in it, which only confirms the lack of social involvement.

Acoustic Exposure to Turbine Operation Quantifies Risk to Bats at Commercial Wind Energy Facilities

ABSTRACTTurbine‐related bat mortality at commercial wind energy facilities may threaten populations of migratory tree‐roosting bat species in North America. Industry stakeholders and regulatory agencies alike are investigating strategies to reduce risk of population‐level consequences as the wind energy industry grows. Bats collide with turbines only when turbine rotors are spinning and curtailing turbine operation at low wind speeds can effectively reduce bat fatality rates. Nonetheless, few quantitative data exist to determine appropriate threshold wind speeds below which turbine operations should be curtailed. Carcass monitoring is labor‐intensive and does not provide information on factors linked to bat fatality rates on any scale finer than nightly. We tested whether acoustic bat data recorded at turbine nacelles could provide a more precise and sensitive measure of fatality risk to bats by analyzing acoustics, weather, turbine operation, and carcass data collected at 2 commercial wind energy facilities in West Virginia over 7 years. Each wind facility implemented several distinct curtailment treatments during our study, allowing us to compare fatality rates and acoustic bat activity across multiple operational strategies. We found that bat passes exposed to turbine operation explained close to 80% of the variation in carcass‐based estimates of bat fatality rates and accounted for significant variation in raw carcass counts per turbine and probability of finding bat carcasses during individual turbine searches. Conversely, bat activity occurring when turbines were not operating had little or no relationship to fatality rates. We also found that patterns in bat activity exposure could be predicted accurately among turbines and years. Our results demonstrate that measuring exposure of acoustic bat activity provides a quantitative basis for designing, evaluating, and adaptively managing curtailment strategies. This is an important advance towards using curtailment to reduce bat fatality rates strategically while allowing for increased generation of renewable energy. © 2021 The Authors. Wildlife Society Bulletin published by Wiley Periodicals LLC on behalf of The Wildlife Society.

A review of the effectiveness of operational curtailment for reducing bat fatalities at terrestrial wind farms in North America.

Curtailment of turbine operations during low wind conditions has become an operational minimization tactic to reduce bat mortality at terrestrial wind energy facilities. Site-specific studies have demonstrated that bat activity is higher during lower wind speeds and that operational curtailment can effectively reduce fatalities. However, the exact nature of the relationship between curtailment cut-in speed and bat fatality reduction remains unclear. To evaluate the efficacy of differing curtailment regimes in reducing bat fatalities, we examined data from turbine curtailment experiments in the United States and Canada in a meta-analysis framework. We used multiple statistical models to explore possible linear and non-linear relationships between turbine cut-in speed and bat fatality. Because the overall sample size for this meta-analysis was small (n = 36 control-treatment studies from 17 wind farms), we conducted a power analysis to assess the number of control-treatment curtailment studies needed to understand the relationship between fatality reduction and change in cut-in speed. We also identified the characteristics of individual curtailment field studies that may influence their power to detect fatality reductions, and in turn, contribute to future meta-analyses. We found strong evidence that implementing turbine curtailment reduces fatality rates of bats at wind farms; the estimated fatality ratio across all studies was 0.37 (p < 0.001), or a 63% decrease in fatalities. However, the nature of the relationship between the magnitude of treatment and reduction in fatalities was more difficult to assess. Models that represented the response ratio as a continuous variable (e.g., with a linear relationship between the change in cut-in speed and fatalities) and a categorical variable (to allow for possible non-linearity in this relationship) both had substantial support when compared using AICc. The linear model represented the best fit, likely due to model simplicity, but the non-linear model was the most likely without accounting for parsimony and suggested fatality rates decreased when the difference in curtailment cut-in speeds was 2m/s or larger. The power analyses showed that the power to detect effects in the meta-analysis was low if fatality reductions were less than 50%, which suggests that smaller increases in cut-in speed (i.e., between different treatment categories) may not be easily detectable with the current dataset. While curtailment is an effective operational mitigation measure overall, additional well-designed curtailment studies are needed to determine precisely whether higher cut-in speeds can further reduce bat fatalities.

Understanding Attitudes towards Renewable Energy Technologies and the Effect of Local Experiences

For the planning of the energy transition, decision-makers need to be aware of the public attitudes towards renewable energy technologies (RETs) and the impacts of such energy facilities from a population’s perspective. To facilitate the comparison of RET attitudes, a uniform survey design was used for four case studies (onshore wind, offshore wind, waste-to-energy, and biomass power) situated in the region of Flanders, Belgium. The survey analysis showed differences between the energy facilities with regard to the perceived impact on population health (combustion facilities were perceived more negatively) and landscape impact (wind energy facilities were perceived more negatively). All groups recognized the contribution of the RET facility to the economic development of the region. The effect of such local experiences on the overall evaluation of energy technologies was investigated using ordinal regression models. Personal experiences were found to be more meaningful predictors than socio-economic population characteristics or the proximity to the energy facility. In all investigated energy neighborhoods, the personal relationship of the participants to the landscape was a significant predictor of technology attitude. This points to the importance of investigating place attachment rather than pure visibility to understand the acceptability of land use for energy provision.

A Temporal Boosted YOLO-Based Model for Birds Detection around Wind Farms.

Object detection for sky surveillance is a challenging problem due to having small objects in a large volume and a constantly changing background which requires high resolution frames. For example, detecting flying birds in wind farms to prevent their collision with the wind turbines. This paper proposes a YOLOv4-based ensemble model for bird detection in grayscale videos captured around wind turbines in wind farms. In order to tackle this problem, we introduce two datasets—(1) Klim and (2) Skagen—collected at two locations in Denmark. We use Klim training set to train three increasingly capable YOLOv4 based models. Model 1 uses YOLOv4 trained on the Klim dataset, Model 2 introduces tiling to improve small bird detection, and the last model uses tiling and temporal stacking and achieves the best mAP values on both Klim and Skagen datasets. We used this model to set up an ensemble detector, which further improves mAP values on both datasets. The three models achieve testing mAP values of 82%, 88%, and 90% on the Klim dataset. mAP values for Model 1 and Model 3 on the Skagen dataset are 60% and 92%. Improving object detection accuracy could mitigate birds’ mortality rate by choosing the locations for such establishment and the turbines location. It can also be used to improve the collision avoidance systems used in wind energy facilities.

Evidence of absence regression: a binomial N-mixture model for estimating fatalities at wind energy facilities.

Estimating bird and bat fatalities caused by wind-turbine facilities is challenging when carcasses are rare and produce counts that are either exactly or very near zero. The rarity of found carcasses is exacerbated when live members of a particular species are rare and when carcasses degrade quickly, are removed by scavengers, or are not detected by observers. With few observed carcass counts, common statistical methods like logistic, Poisson, or negative binomial regression are unreliable (statistically biased) and often fail to provide answers (i.e., fail to converge). Here, we propose a binomial N-mixture model that estimates fatality rates as well as the total number of carcasses when rates are expanded. Our model extends the "evidence of absence" model by relating carcass deposition rates to study covariates and by incorporating terms that naturally scale counts from facilities of different sizes. Our model, which we call Evidence of Absence Regression (EoAR), can estimate the total number of birds or bats killed at a single wind energy facility or a fleet of wind energy facilities based on covariate values. Furthermore, with accurate prior distributions the model's results are extremely robust to sparse data and unobserved combinations of covariate values. In this paper, we describe the model, show its low bias and high precision via computer simulation, and apply it to bat carcass counts observed at 21 wind energy facilities in Iowa.