{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T17:04:21Z","timestamp":1793293461911,"version":"4.5.0"},"reference-count":42,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T00:00:00Z","timestamp":1693872000000},"content-version":"vor","delay-in-days":4,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Ecology and Evolution"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Camera traps have become in situ sensors for collecting information on animal abundance and occupancy estimates. When deployed over a large landscape, camera traps have become ideal for measuring the health of ecosystems, particularly in unstable habitats where it can be dangerous or even impossible to observe using conventional methods. However, manual processing of imagery is extremely time and labor intensive. Because of the associated expense, many studies have started to employ machine\u2010learning tools, such as convolutional neural networks (CNNs). One drawback for the majority of networks is that a large number of images (millions) are necessary to devise an effective identification or classification model. This study examines specific factors pertinent to camera trap placement in the field that may influence the accuracy metrics of a deep\u2010learning model that has been trained with a small set of images. False negatives and false positives may occur due to a variety of environmental factors that make it difficult for even a human observer to classify, including local weather patterns and daylight. We transfer\u2010trained a CNN to detect 16 different object classes (14 animal species, humans, and fires) across 9576 images taken from camera traps placed in the Chernobyl Exclusion Zone. After analyzing wind speed, cloud cover, temperature, image contrast, and precipitation, there was not a significant correlation between CNN success and ambient conditions. However, a possible positive relationship between temperature and CNN success was noted. Furthermore, we found that the model was more successful when images were taken during the day as well as when precipitation was not present. This study suggests that while qualitative site\u2010specific factors may confuse quantitative classification algorithms such as CNNs, training with a dynamic training set can account for ambient conditions so that they do not have a significant impact on CNN success.<\/jats:p>","DOI":"10.1002\/ece3.10454","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T08:47:42Z","timestamp":1693903662000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["The successes and pitfalls: Deep\u2010learning effectiveness in a Chernobyl field camera trap application"],"prefix":"10.1002","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9615-2142","authenticated-orcid":false,"given":"Rachel E.","family":"Maile","sequence":"first","affiliation":[{"name":"Department of Biological Sciences University of South Carolina  Columbia South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew T.","family":"Duggan","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences University of South Carolina  Columbia South Carolina USA"},{"name":"K. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology Cornell University  Ithaca New York USA"},{"name":"Department of Natural Resources and the Environment Cornell University  Ithaca New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2235-4868","authenticated-orcid":false,"given":"Timothy A.","family":"Mousseau","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences University of South Carolina  Columbia South Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"e_1_2_10_2_1","article-title":"TensorFlow: Large\u2010scale machine learning on heterogeneous systems","volume":"1603","author":"Abadi M.","year":"2015","journal-title":"Arxiv"},{"key":"e_1_2_10_3_1","article-title":"Efficient pipeline for camera trap image review","volume":"1907","author":"Beery S.","year":"2019","journal-title":"Arxiv"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2021.666182"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469\u20107998.2006.00102.x"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.7970"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep26062"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.07.017"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.09.260"},{"key":"e_1_2_10_10_1","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1007\/978-3-030-33676-9","volume-title":"Pattern recognition: 41st DAGM German conference","author":"Fink G. A.","year":"2019"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0067940"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2017.07.004"},{"key":"e_1_2_10_13_1","unstructured":"Google Earth Pro 7.3.6.9285. (2022).Chernobyl Ukraine 51.2763\u00b0\u2009N 30.2219\u00b0\u2009E elevation 122M."},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/258619"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0006\u20103207(94)00057\u2010W"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1009.5718"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-ecolsys-110218-024827"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/jhered\/esu040"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13280\u2010015\u20100713\u20101"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1719367115"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1367943003003172"},{"key":"e_1_2_10_22_1","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/978-4-431-99495-4","volume-title":"Camera traps in animal ecology","author":"O'Connell A. F.","year":"2011"},{"key":"e_1_2_10_23_1","article-title":"An introduction to convolutional neural networks","volume":"1511","author":"O'Shea K.","year":"2015","journal-title":"Arxiv"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.4404\/hystrix\u201024.2\u20108789"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365\u20102664.2008.01473.x"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13364\u2010019\u201000451\u20104"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.6147"},{"key":"e_1_2_10_29_1","doi-asserted-by":"crossref","unstructured":"Schneider S. Taylor G. W. &Kremer S.(2018).Deep learning object detection methods for ecological camera trap data.2018 15th conference on computer and robot vision (CRV).https:\/\/doi.org\/10.1109\/crv.2018.00052","DOI":"10.1109\/CRV.2018.00052"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2014.2330900"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2015.26"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/ece3.6692"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210x.13120"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305143"},{"key":"e_1_2_10_35_1","unstructured":"Tzutalin D.(2015).LabelImg.Git code. Retrieved fromhttps:\/\/github.com\/tzutalin\/labelImg"},{"issue":"1","key":"e_1_2_10_36_1","article-title":"Camera trapping for conservation: A guide to best\u2010practices","volume":"1","author":"Wearn O. R.","year":"2017","journal-title":"WWF Conservation Technology Series"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/rse2.20"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210x.13576"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/2041\u2010210X.13099"},{"key":"e_1_2_10_40_1","unstructured":"World Weather. (2022).World Weather Forecasts | World Weather Online. Retrieved fromhttps:\/\/www.worldweatheronline.com\/country.aspx"},{"key":"e_1_2_10_41_1","article-title":"How transferable are features in deep neural networks?","author":"Yosinski J.","year":"2014","journal-title":"arXIV"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/1687\u20105281\u20102013\u201052"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2016.2594138"}],"container-title":["Ecology and Evolution"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ece3.10454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T09:24:20Z","timestamp":1705483460000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ece3.10454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":42,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10.1002\/ece3.10454"],"URL":"https:\/\/doi.org\/10.1002\/ece3.10454","archive":["Portico"],"relation":{},"ISSN":["2045-7758","2045-7758"],"issn-type":[{"value":"2045-7758","type":"print"},{"value":"2045-7758","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"2022-09-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e10454"}}