Protected areas slow declines unevenly across the tetrapod tree of life.

Protected areas (PAs) are the primary strategy for slowing terrestrial biodiversity loss. Although expansion of PA coverage is prioritized under the Convention on Biological Diversity, it remains unknown whether PAs mitigate declines across the tetrapod tree of life and to what extent land cover and climate change modify PA effectiveness1,2. Here we analysed rates of change in abundance of 2,239 terrestrial vertebrate populations across the globe. On average, vertebrate populations declined five times more slowly within PAs (-0.4% per year) than at similar sites lacking protection (-1.8% per year). The mitigating effects of PAs varied both within and across vertebrate classes, with amphibians and birds experiencing the greatest benefits. The benefits of PAs were lower for amphibians in areas with converted land cover and lower for reptiles in areas with rapid climate warming. By contrast, the mitigating impacts of PAs were consistently augmented by effective national governance. This study provides evidence for the effectiveness of PAs as a strategy for slowing tetrapod declines. However, optimizing the growing PA network requires targeted protection of sensitive clades and mitigation of threats beyond PA boundaries. Provided the conditions of targeted protection, adequate governance and well-managed landscapes are met, PAs can serve a critical role in safeguarding tetrapod biodiversity.

Clustered versus catastrophic global vertebrate declines.

Recent analyses have reported catastrophic global declines in vertebrate populations1,2. However, the distillation of many trends into a global mean index obscures the variation that can inform conservation measures and can be sensitive to analytical decisions. For example, previous analyses have estimated a mean vertebrate decline of more than 50% since 1970 (Living Planet Index2). Here we show, however, that this estimate is driven by less than 3% of vertebrate populations; if these extremely declining populations are excluded, the global trend switches to an increase. The sensitivity of global mean trends to outliers suggests that more informative indices are needed. We propose an alternative approach, which identifies clusters of extreme decline (or increase) that differ statistically from the majority of population trends. We show that, of taxonomic-geographic systems in the Living Planet Index, 16 systems contain clusters of extreme decline (comprising around 1% of populations; these extreme declines occur disproportionately in larger animals) and 7 contain extreme increases (around 0.4% of populations). The remaining 98.6% of populations across all systems showed no mean global trend. However, when analysed separately, three systems were declining strongly with high certainty (all in the Indo-Pacific region) and seven were declining strongly but with less certainty (mostly reptile and amphibian groups). Accounting for extreme clusters fundamentally alters the interpretation of global vertebrate trends and should be used to help to prioritize conservation efforts.

Bending the curve of terrestrial biodiversity needs an integrated strategy.

Increased efforts are required to prevent further losses to terrestrial biodiversity and the ecosystem services that it  provides1,2. Ambitious targets have been proposed, such as reversing the declining trends in biodiversity3; however, just feeding the growing human population will make this a challenge4. Here we use an ensemble of land-use and biodiversity models to assess whether-and how-humanity can reverse the declines in terrestrial biodiversity caused by habitat conversion, which is a major threat to biodiversity5. We show that immediate efforts, consistent with the broader sustainability agenda but of unprecedented ambition and coordination, could enable the provision of food for the growing human population while reversing the global terrestrial biodiversity trends caused by habitat conversion. If we decide to increase the extent of land under conservation management, restore degraded land and generalize landscape-level conservation planning, biodiversity trends from habitat conversion could become positive by the mid-twenty-first century on average across models (confidence interval, 2042-2061), but this was not the case for all models. Food prices could increase and, on average across models, almost half (confidence interval, 34-50%) of the future biodiversity losses could not be avoided. However, additionally tackling the drivers of land-use change could avoid conflict with affordable food provision and reduces the environmental effects of the food-provision system. Through further sustainable intensification and trade, reduced food waste and more plant-based human diets, more than two thirds of future biodiversity losses are avoided and the biodiversity trends from habitat conversion are reversed by 2050 for almost all of the models. Although limiting further loss will remain challenging in several biodiversity-rich regions, and other threats-such as climate change-must be addressed to truly reverse the declines in biodiversity, our results show that ambitious conservation efforts and food system transformation are central to an effective post-2020 biodiversity strategy.

Ongoing over-exploitation and delayed responses to environmental change highlight the urgency for action to promote vertebrate recoveries by 2030.

To safeguard nature, we must understand the drivers of biodiversity loss. Time-delayed biodiversity responses to environmental changes (ecological lags) are often absent from models of biodiversity change, despite their well-documented existence. We quantify how lagged responses to climate and land-use change have influenced mammal and bird populations around the world, while incorporating effects of direct exploitation and conservation interventions. Ecological lag duration varies between drivers, vertebrate classes and body size groupings-e.g. lags linked to climate-change impacts are 13 years for small birds, rising to 40 years for larger species. Past warming and land conversion generally combine to predict population declines; however, such conditions are associated with population increases for small mammals. Positive effects of management (>+4% annually for large mammals) and protected areas (>+6% annually for large birds) on population trends contrast with the negative impact of exploitation (<-7% annually for birds), highlighting the need to promote sustainable use. Model projections suggest a future with winners (e.g. large birds) and losers (e.g. medium-sized birds), with current/recent environmental change substantially influencing abundance trends to 2050. Without urgent action, including effective conservation interventions and promoting sustainable use, ambitious targets to stop declines by 2030 may already be slipping out of reach.

Quantifying reliability and data deficiency in global vertebrate population trends using the Living Planet Index.

Global biodiversity is facing a crisis, which must be solved through effective policies and on-the-ground conservation. But governments, NGOs, and scientists need reliable indicators to guide research, conservation actions, and policy decisions. Developing reliable indicators is challenging because the data underlying those tools is incomplete and biased. For example, the Living Planet Index tracks the changing status of global vertebrate biodiversity, but taxonomic, geographic and temporal gaps and biases are present in the aggregated data used to calculate trends. However, without a basis for real-world comparison, there is no way to directly assess an indicator's accuracy or reliability. Instead, a modelling approach can be used. We developed a model of trend reliability, using simulated datasets as stand-ins for the "real world", degraded samples as stand-ins for indicator datasets (e.g., the Living Planet Database), and a distance measure to quantify reliability by comparing partially sampled to fully sampled trends. The model revealed that the proportion of species represented in the database is not always indicative of trend reliability. Important factors are the number and length of time series, as well as their mean growth rates and variance in their growth rates, both within and between time series. We found that many trends in the Living Planet Index need more data to be considered reliable, particularly trends across the global south. In general, bird trends are the most reliable, while reptile and amphibian trends are most in need of additional data. We simulated three different solutions for reducing data deficiency, and found that collating existing data (where available) is the most efficient way to improve trend reliability, whereas revisiting previously studied populations is a quick and efficient way to improve trend reliability until new long-term studies can be completed and made available.

Anthropogenic predictors of varying Holocene occurrence for Europe's large mammal fauna.

Understanding how species respond to different anthropogenic pressures is essential for conservation planning. The archaeological record has great potential to inform extinction risk assessment by providing evidence on past human-caused biodiversity loss, but identifying specific drivers of past declines from environmental archives has proved challenging. We used 17 684 Holocene zooarchaeological records for 15 European large mammal species together with data on past environmental conditions and anthropogenic activities across Europe, to assess the ability of environmental archives to determine the relative importance of different human pressures in shaping faunal distributions through time. Site occupancy probability showed differing significant relationships with environmental covariates for all species, and nine species also showed significant relationships with anthropogenic covariates (human population density, % cropland, % grazing land). Across-species differences in negative relationships with covariates provide ecological insights for understanding extinction dynamics: some mammals (red deer, aurochs, wolf, wildcat, lynx, pine marten and beech marten) were more vulnerable to past human-environmental interactions, and differing single and synergistic anthropogenic factors influenced likelihood of past occurrence across species. Our results provide new evidence for pre-industrial population fragmentation and depletion in European mammals, and demonstrate the usefulness of historical baselines for understanding species' varying long-term sensitivity to multiple threats.

Achieving a real-time online monitoring system for conservation culturomics.

Environmental monitoring is increasingly shifting toward a set of systems that describe changes in real time. In ecology specifically, a series of challenges have prevented the rollout of real-time monitoring for features such as biodiversity change or ecosystem service provision. Conservation culturomics, a field concerned with interactions between people and nature, is well placed to demonstrate how monitoring might move toward a network of real-time platforms, given its existence exclusively in the digital realm. We examined a set of considerations associated with the development of real-time monitoring platforms for conservation culturomics and introduce a near real-time platform for the Species Awareness Index, a global index of changing biodiversity awareness derived from the rate of change in page views for species on Wikipedia. This platform will update automatically each month, operating in near real time (https://joemillard.shinyapps.io/Real_time_SAI/). There are plans to make the underlying data queryable via an application programing interface independent of the platform. The real-time Species Awareness Index will represent the first real-time and entirely automated conservation culturomic platform and one of the first real-time platforms in the discipline of ecology. Real-time monitoring for culturomics can provide insight into human-nature interactions as they play out in the physical realm and provide a framework for the development of real-time monitoring in ecology. Real-time monitoring metrics can be processed on private virtual machines and hosted on publicly available cloud services. Conservation now needs an online, real-time observatory that can evolve with the structure of the web.

Obtención de un sistema virtual de monitoreo en tiempo real para la culturomía de la conservación Resumen El monitoreo ambiental se enfoca cada vez más en un conjunto de sistemas que describen los cambios en tiempo real. En cuanto a la ecología, una serie de obstáculos ha impedido el despliegue del monitoreo en tiempo real para funciones como el cambio en la biodiversidad o el suministro de servicios ambientales. La culturomía de la conservación, un campo enfocado en las interacciones entre las personas y la naturaleza, es una buena opción para demostrar cómo el monitoreo podría transformarse en una red de plataformas en tiempo real, dado que sólo existe en el ámbito digital. Analizamos una serie de consideraciones asociadas con el desarrollo de plataformas de monitoreo en tiempo real para la culturomía de la conservación e introdujimos una plataforma casi en tiempo real para el Índice de Conciencia de Especies, un índice mundial del cambio en la conciencia sobre la biodiversidad derivado de la tasa de cambio en las visitas a las páginas de Wikipedia de diferentes especies. Esta plataforma se actualizará automáticamente cada mes, por lo que opera casi en tiempo real (https://joemillard.shinyapps.io/Real_time_SAI/). Existen planes para hacer que los datos subyacentes sean consultables por medio de una interfaz de programación de aplicaciones independiente de la plataforma. El Índice de Conciencia de Especies en tiempo real será la primera plataforma de culturomía de la conservación automatizada por completo y en tiempo real, así como una de las primeras plataformas de este tipo para la disciplina de la ecología. El monitoreo en tiempo real de la culturomía puede proporcionar información sobre las interacciones humano-naturaleza conforme se desarrollan en el ámbito físico y también un marco de trabajo para el desarrollo del monitoreo en tiempo real para la ecología. Las medidas del monitoreo en tiempo real pueden procesarse en máquinas virtuales privadas y albergarse en servicios públicos de nubes de almacenamiento. Hoy en día, la conservación necesita un observatorio en línea y en tiempo real que pueda evolucionar con la estructura de la web.

Understanding why racial/ethnic inequities along the HIV care continuum persist in the United States: a qualitative exploration of systemic barriers from the perspectives of African American/Black and Latino persons living with HIV.

BACKGROUND: Racial/ethnic inequities along the HIV care continuum persist in the United States despite substantial federal investment. Numerous studies highlight individual and social-level impediments in HIV, but fewer foreground systemic barriers. The present qualitative study sought to uncover and describe systemic barriers to the HIV care continuum from the perspectives of African American/Black and Latino persons living with HIV (PLWH) with unsuppressed HIV viral load, including how barriers operated and their effects. METHODS: Participants were African American/Black and Latino PLWH with unsuppressed HIV viral load (N = 41). They were purposively sampled for maximum variability on key indices from a larger study. They engaged in semi-structured in-depth interviews that were audio-recorded and professionally transcribed. Data were analyzed using directed content analysis. RESULTS: Participants were 49 years old, on average (SD = 9), 76% were assigned male sex at birth, 83% were African American/Black and 17% Latino, 34% were sexual minorities (i.e., non-heterosexual), and 22% were transgender/gender-nonbinary. All had indications of chronic poverty. Participants had been diagnosed with HIV 19 years prior to the study, on average (SD = 9). The majority (76%) had taken HIV medication in the six weeks before enrollment, but at levels insufficient to reach HIV viral suppression. Findings underscored a primary theme describing chronic poverty as a fundamental cause of poor engagement. Related subthemes were: negative aspects of congregate versus private housing settings (e.g., triggering substance use and social isolation); generally positive experiences with health care providers, although structural and cultural competency appeared insufficient and managing health care systems was difficult; pharmacies illegally purchased HIV medication from PLWH; and COVID-19 exacerbated barriers. Participants described mitigation strategies and evidenced resilience. CONCLUSIONS: To reduce racial/ethnic inequities and end the HIV epidemic, it is necessary to understand African American/Black and Latino PLWH's perspectives on the systemic impediments they experience throughout the HIV care continuum. This study uncovers and describes a number of salient barriers and how they operate, including unexpected findings regarding drug diversion and negative aspects of congregate housing. There is growing awareness that systemic racism is a core determinant of systemic barriers to HIV care continuum engagement. Findings are interpreted in this context.

Exploring behavioral intervention components for African American/Black and Latino persons living with HIV with non-suppressed HIV viral load in the United States: a qualitative study.

BACKGROUND: The persistence of racial/ethnic inequities in rates of engagement along the HIV care continuum signals the need for novel approaches. We developed six behavioral intervention components for use in an optimization trial, grounded in a model that integrates critical race theory, harm reduction, and self-determination theory, designed to address various barriers that African American/Black and Latino persons living with HIV (PLWH) experience to the HIV care continuum. The components were: health education, motivational interviewing sessions, pre-adherence skill building, peer mentorship, focused support groups, and navigation. The present qualitative exploratory study describes participants' perspectives on the components' acceptability, feasibility, and impact. METHODS: Participants were African American/Black and Latino PLWH poorly engaged in HIV care and with non-suppressed HIV viral load in New York City. From a larger trial, we randomly selected 46 participants for in-depth semi-structured interviews. Interviews were audio-recorded and transcribed verbatim, and data were analyzed using directed content analysis. Quantitative data on sociodemographic and background characteristics and components' acceptability and feasibility were also collected. RESULTS: On average, participants were 49 years old and had lived with HIV for 19 years. Most were cisgender-male and African American/Black. Participants reported a constellation of serious social and structural challenges to HIV management including chronic poverty, unstable housing, and stigma. Across components, a non-judgmental and pressure-free approach and attention to structural and cultural factors were seen as vital to high levels of engagement, but lacking in most medical/social service settings. Prominent aspects of individual components included establishing trust (health education); developing intrinsic motivation, goals, and self-reflection (motivational interviewing sessions); learning/practicing adherence strategies and habits (pre-adherence skill building); reducing social isolation via peer role models (peer mentorship); reflecting on salient goals and common challenges with peers without stigma (focused support groups); and circumventing structural barriers to HIV management with support (navigation). Components were found acceptable and feasible. Findings suggested ways components could be improved. CONCLUSIONS: The present study advances research on interventions for African American/Black and Latino PLWH, who experience complex barriers to engagement along the HIV care continuum. Future study of the components is warranted to address racial/ethnic health inequities in HIV.

Global patterns of resilience decline in vertebrate populations.

Maintaining the resilience of natural populations, their ability to resist and recover from disturbance, is crucial to prevent biodiversity loss. However, the lack of appropriate data and quantitative tools has hampered our understanding of the factors determining resilience on a global scale. Here, we quantified the temporal trends of two key components of resilience-resistance and recovery-in >2000 population time-series of >1000 vertebrate species globally. We show that the number of threats to which a population is exposed is the main driver of resilience decline in vertebrate populations. Such declines are driven by a non-uniform loss of different components of resilience (i.e. resistance and recovery). Increased anthropogenic threats accelerating resilience loss through a decline in the recovery ability-but not resistance-of vertebrate populations. These findings suggest we may be underestimating the impacts of global change, highlighting the need to account for the multiple components of resilience in global biodiversity assessments.

Vertebrate population trends are influenced by interactions between land use, climatic position, habitat loss and climate change.

Rapid human-driven environmental changes are impacting animal populations around the world. Currently, land-use and climate change are two of the biggest pressures facing biodiversity. However, studies investigating the impacts of these pressures on population trends often do not consider potential interactions between climate and land-use change. Further, a population's climatic position (how close the ambient temperature and precipitation conditions are to the species' climatic tolerance limits) is known to influence responses to climate change but has yet to be investigated with regard to its influence on land-use change responses over time. Consequently, important variations across species' ranges in responses to environmental changes may be being overlooked. Here, we combine data from the Living Planet and BioTIME databases to carry out a global analysis exploring the impacts of land use, habitat loss, climatic position, climate change and the interactions between these variables, on vertebrate population trends. By bringing these datasets together, we analyse over 7,000 populations across 42 countries. We find that land-use change is interacting with climate change and a population's climatic position to influence rates of population change. Moreover, features of a population's local landscape (such as surrounding land cover) play important roles in these interactions. For example, populations in agricultural land uses where maximum temperatures were closer to their hot thermal limit, declined at faster rates when there had also been rapid losses in surrounding semi-natural habitat. The complex interactions between these variables on populations highlight the importance of taking intraspecific variation and interactions between local and global pressures into account. Understanding how drivers of change are interacting and impacting populations, and how this varies spatially, is critical if we are to identify populations at risk, predict species' responses to future environmental changes and produce suitable conservation strategies.

Shearwaters know the direction and distance home but fail to encode intervening obstacles after free-ranging foraging trips.

While displacement experiments have been powerful for determining the sensory basis of homing navigation in birds, they have left unresolved important cognitive aspects of navigation such as what birds know about their location relative to home and the anticipated route. Here, we analyze the free-ranging Global Positioning System (GPS) tracks of a large sample (n = 707) of Manx shearwater, Puffinus puffinus, foraging trips to investigate, from a cognitive perspective, what a wild, pelagic seabird knows as it begins to home naturally. By exploiting a kind of natural experimental contrast (journeys with or without intervening obstacles) we first show that, at the start of homing, sometimes hundreds of kilometers from the colony, shearwaters are well oriented in the homeward direction, but often fail to encode intervening barriers over which they will not fly (islands or peninsulas), constrained to flying farther as a result. Second, shearwaters time their homing journeys, leaving earlier in the day when they have farther to go, and this ability to judge distance home also apparently ignores intervening obstacles. Thus, at the start of homing, shearwaters appear to be making navigational decisions using both geographic direction and distance to the goal. Since we find no decrease in orientation accuracy with trip length, duration, or tortuosity, path integration mechanisms cannot account for these findings. Instead, our results imply that a navigational mechanism used to direct natural large-scale movements in wild pelagic seabirds has map-like properties and is probably based on large-scale gradients.

The species awareness index as a conservation culturomics metric for public biodiversity awareness.

Although threats to global biodiversity are well known, slowing current rates of biodiversity loss remains a challenge. The Aichi targets set out 20 goals on which the international community should act to alleviate biodiversity decline, 1 of which (Target 1) aims to raise public awareness of the importance of biodiversity. Although conventional indicators for Target 1 are of low spatial and temporal coverage, conservation culturomics metrics show how biodiversity awareness can be quantified at the global scale. Following methods used for the Living Planet Index, we devised a species awareness index (SAI) to measure change in species awareness based on Wikipedia views. We calculated this index at the page level for 41,197 species listed by the International Union for Conservation of Nature (IUCN) across 10 Wikipedia languages and >2 billion views from 1 July 2015 to 30 March 2020. Bootstrapped indices for the page-level SAI showed that overall awareness of biodiversity increased marginally over time, although there were differences among taxonomic classes and languages. Among taxonomic classes, overall awareness increased fastest for reptiles and slowest for amphibians. Among languages, overall species awareness increased fastest for Japanese and slowest for Chinese and German users. Although awareness of species as a whole increased and was significantly higher for traded species, from January 2016 through January 2020, change in awareness appeared not to be strongly related to whether the species is traded or is a pollinator. As a data source for public biodiversity awareness, the SAI could be integrated into the Conservation International Biodiversity Engagement Indicator.

El Índice de Sensibilización de Especie como Medida de Culturomia de la Conservación para la Sensibilización Pública por la Biodiversidad Resumen Aunque las amenazas a la biodiversidad mundial son bien conocidas, reducir las tasas actuales de pérdida de la biodiversidad todavía es un desafío. Los objetivos de Aichi establecieron 20 metas para las cuales debe actuar la comunidad internacional para aliviar la declinación de la biodiversidad. Una de estas metas (Objetivo 1) busca sensibilizar al público sobre la importancia de la biodiversidad. Aunque los indicadores convencionales del Objetivo 1 tienen una baja cobertura espacial y temporal, las medidas de culturomia para la conservación muestran cómo la sensibilización por la biodiversidad puede cuantificarse a escala global. Seguimos los métodos utilizados para el Índice del Planeta Viviente para diseñar un índice de sensibilización de especie (ISE) para medir el cambio en la sensibilización por una especie con base en las vistas en Wikipedia. Calculamos este índice a nivel de página para 41,197 especies incluidas en las listas de la Unión Internacional para la Conservación de la Naturaleza (UICN) en diez diferentes idiomas en Wikipedia y más de 2 mil millones de vistas entre el 1 de julio de 2015 y el 30 de marzo de 2020. Los índices de arranque para el ISE a nivel de página mostraron que la sensibilización general por la biodiversidad incrementó ligeramente con el tiempo, aunque hubo diferencia entre las clasificaciones taxonómicas y los idiomas. Entre las clasificaciones taxonómicas, la sensibilización general incrementó más rápido para los reptiles y más lento para los anfibios. Entre los idiomas, la sensibilización general por especie incrementó más rápido para los usuarios del japonés y más lento para los usuarios del chino y el alemán. Aunque la sensibilización por las especies en su totalidad incrementó y fue significativamente más alta para las especies comercializadas, entre enero de 2016 y enero de 2020 el cambio en la sensibilización pareció no estar relacionado fuertemente con si la especie es un polinizador o es comercializada. Como fuente de información para la sensibilización pública por la biodiversidad, el ISE podría ser integrado dentro del Indicador de Participación Internacional para la Conservación de la Biodiversidad.

Multiyear social stability and social information use in reef sharks with diel fission-fusion dynamics.

Animals across vertebrate taxa form social communities and often exist as fission-fusion groups. Central place foragers (CPF) may form groups from which they will predictably disperse to forage, either individually or in smaller groups, before returning to fuse with the larger group. However, the function and stability of social associations in predatory fish acting as CPFs is unknown, as individuals do not need to return to a shelter yet show fidelity to core areas. Using dynamic social networks generated from acoustic tracking data, we document spatially structured sociality in CPF grey reef sharks at a Pacific Ocean atoll. We show that sharks form stable social groups over multiyear periods, with some dyadic associations consistent for up to 4 years. Groups primarily formed during the day, increasing in size throughout the morning before sharks dispersed from the reef at night. Our simulations suggest that multiple individuals sharing a central place and using social information while foraging (i.e. local enhancement) will outperform non-CPF social foragers. We show multiyear social stability in sharks and suggest that social foraging with information transfer could provide a generalizable mechanism for the emergence of sociality with group central place foraging.

Below the canopy: global trends in forest vertebrate populations and their drivers.

Global forest assessments use forest area as an indicator of biodiversity status, which may mask below-canopy pressures driving forest biodiversity loss and 'empty forest' syndrome. The status of forest biodiversity is important not only for species conservation but also because species loss can have consequences for forest health and carbon storage. We aimed to develop a global indicator of forest specialist vertebrate populations to improve assessments of forest biodiversity status. Using the Living Planet Index methodology, we developed a weighted composite Forest Specialist Index for the period 1970-2014. We then investigated potential correlates of forest vertebrate population change. We analysed the relationship between the average rate of change of forest vertebrate populations and satellite-derived tree cover trends, as well as other pressures. On average, forest vertebrate populations declined by 53% between 1970 and 2014. We found little evidence of a consistent global effect of tree cover change on forest vertebrate populations, but a significant negative effect of exploitation threat on forest specialists. In conclusion, we found that the forest area is a poor indicator of forest biodiversity status. For forest biodiversity to recover, conservation management needs to be informed by monitoring all threats to vertebrates, including those below the canopy.

Bat detective-Deep learning tools for bat acoustic signal detection.

Passive acoustic sensing has emerged as a powerful tool for quantifying anthropogenic impacts on biodiversity, especially for echolocating bat species. To better assess bat population trends there is a critical need for accurate, reliable, and open source tools that allow the detection and classification of bat calls in large collections of audio recordings. The majority of existing tools are commercial or have focused on the species classification task, neglecting the important problem of first localizing echolocation calls in audio which is particularly problematic in noisy recordings. We developed a convolutional neural network based open-source pipeline for detecting ultrasonic, full-spectrum, search-phase calls produced by echolocating bats. Our deep learning algorithms were trained on full-spectrum ultrasonic audio collected along road-transects across Europe and labelled by citizen scientists from www.batdetective.org. When compared to other existing algorithms and commercial systems, we show significantly higher detection performance of search-phase echolocation calls with our test sets. As an example application, we ran our detection pipeline on bat monitoring data collected over five years from Jersey (UK), and compared results to a widely-used commercial system. Our detection pipeline can be used for the automatic detection and monitoring of bat populations, and further facilitates their use as indicator species on a large scale. Our proposed pipeline makes only a small number of bat specific design decisions, and with appropriate training data it could be applied to detecting other species in audio. A crucial novelty of our work is showing that with careful, non-trivial, design and implementation considerations, state-of-the-art deep learning methods can be used for accurate and efficient monitoring in audio.