Remote Sensing in Ecology and Conservation最新文献

{"title":"Monitoring feral pigs ( Sus scrofa ): Complementarity between autonomous sensing methods increases detection probability","authors":"Marina D. A. Scarpelli, Stewart Macdonald, Maryam Golchin, Simon Linke, Jens G. Froese","doi":"10.1002/rse2.70062","DOIUrl":"https://doi.org/10.1002/rse2.70062","url":null,"abstract":"Invasive alien species are a major threat to biodiversity, with significant impacts on threatened species and priority sites. Monitoring is essential to inform appropriate management strategies, and autonomous sensors are increasingly used to address data collection at large spatio‐temporal scales. Feral pigs ( <jats:italic>Sus scrofa</jats:italic> ) are a major threat to native fauna in Australia. Here, the utility of passive acoustic monitoring for detecting feral pigs and its complementarity to camera trap detection was tested. A custom‐built deep‐learning BirdNET recogniser was used to automatically scan sound for pig presence; image data was manually scanned. Detection probabilities and effects of covariates were compared for detections of each method, separately and combined, using multi‐season occupancy models. There was little spatio‐temporal overlap between image and sound detections. Modelled detection probability was the highest when sound and image detections were combined, followed by sound and, lastly, images. Seasonality affected detectability: camera traps were most successful in the Late Wet, when sound detection was poor. Sound detection was more successful in all other seasons, with the highest detection probability in the Late Dry. The intrinsic variation across survey methods along with the effects of environmental factors in species behaviour can be accounted for by combining methods, improving overall detections and providing complementary information on the same species. Autonomous sensors can provide comprehensive data to inform land management decisions, including population control and impact mitigation of invasive species. However, the utility of different sensors is context‐dependent. Combining multiple technologies can harness the strengths of each and mitigate against weaknesses. Increasing technology accessibility and decreasing costs is key to facilitate uptake by land managers.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"51 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147373925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knee height is often right: evaluating device height effects on camera trapping rate","authors":"Jorge Sereno‐Cadierno, Tim R. Hofmeester, Marcus Becker, Alice Bernard, Lizette Moolman, Hervé Fritz, Pelayo Acevedo","doi":"10.1002/rse2.70053","DOIUrl":"https://doi.org/10.1002/rse2.70053","url":null,"abstract":"Camera traps (CTs) are widely used in wildlife monitoring, but sampling design choices can introduce significant biases in trapping rates (TR) that, depending on the evaluated parameter, can be propagated to dependent estimates (e.g., density). This study evaluates the effect of camera height placement on TR across five experiments encompassing 172 paired sampling points (i.e., with a low and a high camera per point) in four biomes across Europe, North America and Africa. We analysed data of 49 vertebrate species, ranging from small mammals and birds to large ungulates and carnivores (0.013–461 kg), using generalised linear and multinomial models to assess how TR varies with body mass and camera height. Our results show that lower camera placements significantly increase TR for small (0–10 kg) and medium‐sized species (11–50 kg), while the opposite is found in larger animals. Simultaneous detections by both high‐ and low‐placed cameras increased with body mass, but small species were often missed by high cameras alone. Camera height introduces systematic biases in TR, affecting its comparability across time and space. For multispecies monitoring, lower cameras (30–50 cm above ground) offer better overall performance, though higher placements may be more suitable for large‐bodied focal species. We recommend consistent, standardised height measurements in long‐term monitoring to ensure reliable TR‐based inferences and validate the recommendation of using target species' shoulder height when monitoring single species. This study provides the most comprehensive cross‐continental evaluation of camera height effects to date and offers empirically grounded guidance for optimising sampling design in wildlife monitoring.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"41 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146215636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lacking data? No worries! How synthetic images can alleviate image scarcity in wildlife surveys: A case study with muskox ( Ovibos moschatus )","authors":"Simon Durand, Samuel Foucher, Alexandre Delplanque, Joëlle Taillon, Jérôme Théau","doi":"10.1002/rse2.70056","DOIUrl":"https://doi.org/10.1002/rse2.70056","url":null,"abstract":"Accurate population estimates are essential for wildlife management, providing critical insights into species abundance and distribution. Traditional survey methods, including visual aerial counts and GNSS telemetry tracking, are widely used to monitor muskox ( <jats:italic>Ovibos moschatus</jats:italic> ) populations in Arctic regions. These approaches are resource‐intensive and constrained by logistical challenges. Advances in remote sensing, artificial intelligence, and high‐resolution aerial imagery offer promising alternatives for wildlife detection. Yet, the effectiveness of deep learning object detection models (ODMs) is often limited by small datasets, making it challenging to train robust ODMs for sparsely distributed species like muskoxen. This study investigates the integration of synthetic imagery, created with diffusion‐based models, to supplement limited training data and improve muskox detection in zero‐shot and few‐shot settings. We compared a baseline model trained solely on real imagery with five zero‐shot (ZS1–ZS5) and five few‐shot (FS1–FS5) models that incorporated progressively more synthetic imagery in the training set. For the zero‐shot models, where no real images were included in the training set, adding synthetic imagery improved detection performance. As more synthetic images were added, performance in precision, recall, and F1 score increased, but eventually plateaued, suggesting diminishing returns when synthetic images exceeded 100% of the baseline model training dataset. For few‐shot models, combining real and synthetic images led to better recall and slightly higher overall accuracy compared with using real images alone, though these improvements were not statistically significant. Our findings demonstrate the potential of synthetic images to train accurate ODMs when data are scarce, offering important perspectives for wildlife monitoring by enabling rare or inaccessible species to be monitored and to increase monitoring frequency. This approach could be used to initiate ODMs without real data and refine it as real images are acquired over time.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"29 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146169709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hyperspectral species maps and LiDAR‐based structured population models show future forest fire frequency may compromise forest resilience","authors":"Jessica McLean, Tommaso Jucker, Alice Rosen, Sean M. McMahon, Roberto Salguero‐Gómez","doi":"10.1002/rse2.70057","DOIUrl":"https://doi.org/10.1002/rse2.70057","url":null,"abstract":"Forest disturbances are accelerating biodiversity loss and altering tree productivity worldwide. Post‐disturbance recovery time, a component of resilience, is critical for identifying vulnerable areas and targeting conservation but varies with environmental conditions. Monitoring recovery at scale requires tracking tree dynamics, yet traditional ground‐based approaches are resource‐intensive. We present a pipeline to parameterize integral projection models (IPMs) using LiDAR data and hyperspectral‐based species maps to assess post‐fire recovery across large, forested areas. Focusing on the fire‐adapted <jats:italic>Picea mariana</jats:italic> , we model passage times to reproductive heights and life expectancy under different fire regimes as indicators of recovery time. To do this, we combined hyperspectral‐based species maps and LiDAR‐based crown heights to track individual tree survival and growth at the Caribou‐Poker Creek Research Watershed (BONA) from 2017 to 2023. We incorporated fire history, aspect, slope, elevation and surrounding canopy height into our models and found partial support for their expected effects on survival and growth. Once accounting for topography and competition, we estimated passage times to reproductive maturity (11–22 years). Life expectancy in the absence of fire is shortest on North‐facing slopes with recent fire (581 years). Sensitivity analyses highlight fire history and aspect as key modulators of population resilience, with elevation exerting strong influence on life expectancy across all conditions. Our results demonstrate that remotely sensed IPMs can effectively quantify forest recovery at scale, revealing that in some contexts, stands of <jats:italic>P. mariana</jats:italic> may not recover between fire disturbances. We discuss the implications of these findings for advancing modelling of resilience and highlight both the challenges and opportunities of using LiDAR and hyperspectral data to build demographic models for forecasting forest dynamics.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"133 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From snapshots to continuous estimates: Augmenting citizen science with computer vision for fish monitoring","authors":"Zhongqi Chen, Timm Haucke, Sara Beery, Keven Bennett, Austin Powell, Lydia Zuehsow, Robert Vincent, Linda Deegan","doi":"10.1002/rse2.70055","DOIUrl":"https://doi.org/10.1002/rse2.70055","url":null,"abstract":"Monitoring fish movement is essential for understanding population dynamics, informing conservation efforts and supporting fisheries management. Traditional methods, such as visual observations by volunteers, are constrained by time limitations, environmental conditions and labour intensity. Recent advancements in computer vision (CV) and deep learning offer promising solutions for automating fish counting from underwater videos, improving efficiency and data resolution. In this study, we developed and applied a deep learning‐based CV system to monitor river herring ( <jats:italic>Alosa</jats:italic> spp.) migration, covering all essential steps from field camera deployment, video annotation to model training and in‐season population counting. We assessed the labelling and training efforts required to achieve good model performance and explored the use of importance sampling to correct biases in CV‐based fish counts. Our results demonstrated that CV models trained on a single site and year showed limited generalization to sites or years unseen during training, while models trained on more diverse labelled data generalized better. We also found that the amount of annotations required is related to dataset complexity. When applied for in‐season fish counting, CV efficiently processed season‐long datasets and produced counts consistent with human review, with some moderate differences under migration pulses that can be adjusted by importance sampling. By providing continuous, high‐resolution monitoring throughout the entire migration season, CV counts offer more reliable run size estimates and greater insight into the spawning migration of river herring. This study demonstrates a scalable, cost‐effective and efficient approach with significant potential for addressing complex ecological questions and supporting conservation strategies and resource management.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"51 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incorporating environmental DNA metabarcoding for improved benthic biodiversity and habitat mapping","authors":"Rylan J. Command, Shreya Nemani, Benjamin Misiuk, Mehrdad Hajibabaei, Nicole Fahner, Emily Porter, Greg Singer, Beverly McClenaghan, Katleen Robert","doi":"10.1002/rse2.70048","DOIUrl":"https://doi.org/10.1002/rse2.70048","url":null,"abstract":"Complex coastal seascapes harbor high marine biodiversity from which humans derive numerous ecosystem services. Maps of benthic habitats are important tools used to inform coastal development and conservation efforts. Seafloor imagery is commonly used to collect information about the distribution of benthic organisms, but these data are often limited to low taxonomic resolutions and may systematically underrepresent local biodiversity. Recent advances in genomics enable rapid and accurate detection of taxa with high taxonomic resolution from environmental DNA (eDNA) extracted from water samples, but there are few examples of broad‐spectrum eDNA biodiversity data in nearshore benthic habitat mapping. We combined an eDNA‐based biodiversity assessment with concurrently collected high‐resolution video ground‐truth data to assess the benefit of metabarcoding data for improving benthic habitat mapping in the sub‐Arctic coastal embayment of Mortier Bay, Newfoundland and Labrador, Canada. Features derived from acoustic bathymetry and backscatter data were used to develop full‐coverage habitat and biodiversity maps using a joint species distribution‐modeling framework. The predicted taxonomic richness spatial patterns were similar between video‐only, eDNA‐only and combined datasets, suggesting diversity patterns were accurately represented by both methods. However, 226 additional taxa (72 species, 109 genera) were identified using eDNA compared to the 46 detected by video ground‐truthing. Averaged over all taxa, the video‐only model performed best in terms of discriminating presences from absences; however, we found that most sessile taxa were better predicted by the combined dataset compared to video data alone. These results highlight the limitations of imagery‐only datasets for biodiversity surveys and demonstrate the utility and limitations of metabarcoding data to improve benthic habitat and diversity maps in complex coastal habitats. This study highlights opportunities to fill gaps that could improve spatial modeling of seafloor assemblages derived from metabarcoding data, including sources and sinks of DNA in the environment and water column properties that control its dispersal.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"28 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Big Bird: A global dataset of birds in drone imagery annotated to species level","authors":"Joshua P. Wilson, Tatsuya Amano, Thomas Bregnballe, Alejandro Corregidor‐Castro, Roxane Francis, Diego Gallego‐García, Jarrod C. Hodgson, Landon R. Jones, César R. Luque‐Fernández, Dominik Marchowski, John McEvoy, Ann E. McKellar, W. Chris Oosthuizen, Christian Pfeifer, Martin Renner, José Hernán Sarasola, Mateo Sokač, Roberto Valle, Adam Zbyryt, Richard A. Fuller","doi":"10.1002/rse2.70059","DOIUrl":"https://doi.org/10.1002/rse2.70059","url":null,"abstract":"Drones are a valuable tool for surveying birds. However, surveys are hampered by the costs of manually detecting birds in the resulting images. Researchers are using computer vision to automate this process, but efforts to date generally target a narrow context, such as a single habitat, and do not identify key attributes such as species. To address this, we collected a diverse dataset of drone‐based bird images from existing studies and our own fieldwork. We labelled the birds in these images, detailing their location, species, posture (resting, flying, or other), age (chick, juvenile, or adult), and sex (male, female, or monomorphic). To demonstrate the usefulness of this dataset, we trained a bird detection and identification computer vision model, compared its performance with manual methods, and identified the main predictors of performance. Thirty‐three researchers contributed 23 865 images, captured using 21 different cameras across 11 countries and all 7 continents. We labelled 4824 of these images, containing 49 990 birds from 101 species. Our model processed images 85 times faster than manual processing and achieved a mean average precision (mAP) of 0.91 ± 0.25 for detection and 0.65 ± 0.33 for classification of species, age, and sex. Performance was predicted by the similarity between test and train images (Estimate = 1.3248, <jats:italic>P</jats:italic> = 0.00021), the number of similar classes (Estimate = −0.0742, <jats:italic>P</jats:italic> = 0.0033), the number of train instances (Estimate = 0.0034, <jats:italic>P</jats:italic> = 0.1019), and the number of pixels on the bird (Estimate = 0.0002, <jats:italic>P</jats:italic> = 0.0462). Our drone‐based bird dataset is the most accurately labelled and biologically, environmentally, and digitally diverse to date, laying the foundation for future research. We provide it and the trained model open‐access and urge researchers to continue to work together to assemble datasets that cover broad contexts and are labelled with key conservation metrics.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"112 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An autonomous network of acoustic detectors to map tiger risk by eavesdropping on prey alarm calls","authors":"Arik Kershenbaum, Andrew Markham, Holly Root‐Gutteridge, Bethany Smith, Casey Anderson, Riley McClaughry, Ramjan Chaudhary, Amogh Vishwakarma, Stephen Cummins, Angela Dassow","doi":"10.1002/rse2.70061","DOIUrl":"https://doi.org/10.1002/rse2.70061","url":null,"abstract":"Tiger ( <jats:italic>Panthera tigris</jats:italic> ) attacks are a frequent source of injuries and fatalities among villagers in Nepal, where many communities make extensive use of dense forests for foraging and grazing of livestock. As conservation efforts have boosted the tiger population in the country, a conflict exists between maintaining traditional practises whilst ensuring human safety and protecting endangered predators. Hence, there is a need for cost‐effective management strategies that do not reduce habitat use by humans or wildlife. Passive acoustic monitoring (PAM) offers a promising approach to mapping tiger presence in real‐time and providing a warning system for villagers. Although tigers vocalize infrequently, their presence triggers alarm calls from prey species, meaning these alarm calls could potentially act as a proxy for detecting tigers. To explore the potential for tracking tigers and other dangerous predators such as leopards using these alarm calls, we designed and tested a PAM system in the Terai region of southern Nepal. We implemented a TinyML low‐memory convolutional neural network (~1000 parameters) for chital deer ( <jats:italic>Axis axis</jats:italic> ) automatic detection—a species that reliably produce loud predator‐specific alarm calls—and deployed a distributed network of 10 autonomous interconnected sensors for continuous operation over 3 months. The network transmits chital deer alarm call events via a cellular‐connected gateway to a remote base station to generate a heatmap of predator risk. Incidences of high predator risk can be used to alert local forest rangers, who can then inform nearby villagers of areas with a higher likelihood of predator presence. The neural net achieved an F1 score of 0.91 in training and 0.72 in the field. We suggest that this proof of concept indicates that automated PAM could be an effective tool for detecting and tracking tigers and other predators and a potentially valuable tool for facilitating human‐wildlife co‐existence.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"23 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146122095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large‐scale characterization of horizontal forest structure from remote sensing optical images","authors":"Xin Xu, Martin Brandt, Xiaowei Tong, Maurice Mugabowindekwe, Yuemin Yue, Sizhuo Li, Qiue Xu, Siyu Liu, Florian Reiner, Kelin Wang, Zhengchao Chen, Yongqing Bai, Rasmus Fensholt","doi":"10.1002/rse2.70058","DOIUrl":"https://doi.org/10.1002/rse2.70058","url":null,"abstract":"Forest structure is an essential variable in forest management and conservation, as it has a direct impact on ecosystem processes and functions. Previous remote sensing studies have primarily focused on the vertical structure of forests, which requires laser point data and may not always be suited to distinguish plantations from old forests. Sub‐meter resolution remote sensing data and tree crown segmentation techniques hold promise in offering detailed information that can support the characterization of forest structure from a horizontal perspective, offering new insights in the tree crown structure at scale. In this study, we generated a dataset with over 5 billion tree crowns and developed a Horizontal Structure Index (HSI) by analyzing spatial relationships among neighboring trees from remote sensing optical images. We first extracted the location and crown size of overstory trees from optical satellite and aerial imagery at sub‐meter resolution. We subsequently calculated the distance between tree crown centers, their angles, the crown size and crown spacing, and linked this information with individual trees. We then used principal component analysis (PCA) to condense the structural information into the HSI and tested it in China, Rwanda and Denmark. Our result showed that the HSI has the potential to distinguish monoculture plantations from other forest types, which provides insights that extend beyond metrics derived from vertical forest structure. The proposed HSI is derived directly from tree‐level attributes and supports a deeper understanding of forest structure from a horizontal perspective, complementing existing remote sensing‐based metrics.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"45 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145993210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning‐based ecological analysis of camera trap images is impacted by training data quality and quantity","authors":"Peggy A. Bevan, Omiros Pantazis, Holly A.I. Pringle, Guilherme Braga Ferreira, Daniel J. Ingram, Emily K. Madsen, Liam Thomas, Dol Raj Thanet, Thakur Silwal, Santosh Rayamajhi, Gabriel J. Brostow, Oisin Mac Aodha, Kate E. Jones","doi":"10.1002/rse2.70052","DOIUrl":"https://doi.org/10.1002/rse2.70052","url":null,"abstract":"Large image collections generated from camera traps offer valuable insights into species richness, occupancy, and activity patterns, significantly aiding biodiversity monitoring. However, the manual processing of these data sets is time‐consuming, hindering analytical processes. To address this, deep neural networks have been widely adopted to automate image labelling, but the impact of classification error on key ecological metrics remains unclear. Here, we analyze data from camera trap collections in an African savannah (82,300 labelled images, 47 species) and an Asian sub‐tropical dry forest (40,308 labelled images, 29 species) to compare ecological metrics derived from expert‐generated species identifications with those generated by deep‐learning classification models. We specifically assess the impact of deep‐ learning model architecture, the proportion of label noise in the training data, and the size of the training data set on three key ecological metrics: species richness, occupancy, and activity patterns. We found that predictions of species richness derived from deep neural networks closely match those calculated from expert labels and remained resilient to up to 10% noise in the training data set (mis‐labelled images) and a 50% reduction in the training data set size. We found that our choice of deep‐learning model architecture (ResNet vs. ConvNext‐T) or depth (ResNet18, 50, 101) did not impact predicted ecological metrics. In contrast, species‐specific metrics were more sensitive; less common and visually similar species were disproportionately affected by a reduction in deep neural network accuracy, with consequences for occupancy and diel activity pattern estimates. To ensure the reliability of their findings, practitioners should prioritize creating large, clean training sets and account for class imbalance across species over exploring numerous deep‐learning model architectures.","PeriodicalId":21132,"journal":{"name":"Remote Sensing in Ecology and Conservation","volume":"88 1","pages":""},"PeriodicalIF":5.5,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145955812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}