1. Fast and accurate estimates of wildlife abundance are an essential component of efforts to conserve ecosystems in the face of rapid environmental change. A widely used method for estimating species abundance involves flying aerial transects, taking photographs, counting animals within the images, then inferring total population size based on a statistical estimate of species density in the region. The intermediate task of manually counting the aerial images is highly labour intensive and is often the limiting step in making a population estimate.2. Here we assess the use of two novel approaches to perform this task by deploying both citizen scientists and deep learning to count aerial images of the 2015 survey of wildebeest (Connochaetes taurinus) in Serengeti National Park, Tanzania.3. Through the use of the online platform Zooniverse, we collected multiple non-expert counts by citizen scientists and used three different aggregation methods to obtain a single count for the survey images. We also counted the images by developing a bespoke deep learning method via the use of a convolutional neural network. The results of both approaches were then compared. 4. After filtering of the citizen science counts, both approaches provided highly accurate total estimates. The deep learning method was far faster and appears to be a more reliable and predictable approach, however we note that citizen science volunteers played an important role when creating training data for the algorithm. Notably, our results show that accurate, species-specific, automated counting of aerial wildlife images is now possible.
Accurate and on-demand animal population counts are the holy grail for wildlife conservation organizations throughout the world because they enable fast and responsive adaptive management policies. While the collection of image data from camera traps, satellites, and manned or unmanned aircraft has advanced significantly, the detection and identification of animals within images remains a major bottleneck since counting is primarily conducted by dedicated enumerators or citizen scientists. Recent developments in the field of computer vision suggest a potential resolution to this issue through the use of rotation-invariant object descriptors combined with machine learning algorithms. Here we implement an algorithm to detect and count wildebeest from aerial images collected in the Serengeti National Park in 2009 as part of the biennial wildebeest count. We find that the per image error rates are greater than, but comparable to, two separate human counts. For the total count, the algorithm is more accurate than both manual counts, suggesting that human counters have a tendency to systematically over or under count images. While the accuracy of the algorithm is not yet at an acceptable level for fully automatic counts, our results show this method is a promising avenue for further research and we highlight specific areas where future research should focus in order to develop fast and accurate enumeration of aerial count data. If combined with a bespoke image collection protocol, this approach may yield a fully automated wildebeest count in the near future.
Even though over many years the IUCN has considered the African buffalo and waterbuck and abundant species in Africa with no conservation concern, the situation is rapidly changing. Using aerial counts in wet and dry season in 2010 and 2013, this study assessed the trend, population status and distribution of the African buffalo and common waterbuck in the Northern Tanzania and Southern Kenya borderland. Both species were rare in the borderland, with the Amboseli region had the highest number of buffalo (241.5 ± 29.9), followed by Magadi/Namanga (58.0 ± 22.0), West Kilimanjaro (38.8 ± 34.9), and lastly Lake Natron (14.5 ± 9.0) areas. In terms of density, Amboseli also led with 0.03 ± 0.00 (buffalo per km 2), but rest had similar densities of 0.01 ± 0.00 buffalo per km 2. In terms of percent changes in buffalo, Amboseli area had a positive increase (+10.59 ± 27.71), but with a negative growth of −17.12 in the dry season. All other changes in all locations had negative (decline) buffalo numbers over time. For waterbuck numbers, Amboseli area also led with 12.3 ± 3.9 waterbuck), followed by Magadi/Namanga (10.3 ± 3.7.0), Lake Natron (3.8 ± 3.4), and lastly West Kilimanjaro (0.5 ± 0.5) areas. In terms of waterbuck density, they were low and less than 0.00 ± 0.00 per km 2. For percent changes in waterbuck numbers, Magadi/Namanga had higher positive change (+458.33 ± 291.67), but all other locations had negative (decline) changes with the worst being West Kilimanjaro and Lake Natron areas. Further, buffalo number was dependent (p = 0.008) on the season, with numbers being higher in the wet season than dry season.
Among the nine sub-species of giraffes, the Maasai giraffe is the most widespread and common in Northern and Southern Kenya. Although it's considered by the IUCN to be a species of no conservation concern, they have been reported to have declined in some of their range areas mostly due to bush meat activities, habitat fragmentation and loss. There are also concerns recent climatic changes especially prevalence of droughts is increasingly becoming another threat to their survival. In this regard, this study examined the status and trend of the Maasai giraffe in the Kenya-Tanzania border after the 2007 to 2009 drought. Amboseli had the highest giraffe number (averaging 2, 062.5 ± 534.7 giraffes), followed by a distant Lake Natron area (725.8 ± 129.4 giraffes), Magadi/Namanga (669.5 ± 198.0 giraffes), and lastly West Kilimanjaro area (236.5 ± 47.8 giraffes). Further, the proportion of giraffes were highest in Amboseli (55.09% ± 5.65%) followed by Lake Natron area (20.98% ± 3.42%), Magadi/Namanga area (16.35% ± 3.83%), and lastly West Kilimanjaro (7.58% ± 2.12%). But in terms of population growth after droughts, giraffe had positive growth in all locations in the borderland, with Magadi leading (+339.82 ± 329.99) followed Lake Natron area (+37.62 ± 83.27), Amboseli area (+38.11 ± 7.09), and lastly West Kilimanjaro (+3.21 ± 57.95.27). Their wet season population and density was much higher than that of the dry season. However, though the species was widely spread in the borderland, they seemed to avoid the region between Lake Magadi and Amboseli which is traversed by the Nairobi-Namanga highway both in wet and dry season. There is a need to develop a collaborative management framework for cross-border
This study discusses the conflict between Maasai pastoralists and African wild dogs (Lycaon pictus) over livestock before and after the Maasai were evicted from the Serengeti National Park (SNP) in 1959. We surveyed 181 randomly selected households from six villages in the eastern Serengeti ecosystem. A semi-structured questionnaire was used to acquire the required information from the respondents. We found that males had a greater awareness of local wild dog presence and livestock-derived conflict than females, and reported more frequently to have chased and killed wild dogs that attacked their livestock. Moreover, the conflict existed before 1959, decreased during the 1990s, but increased from 2000 onwards. This increase is attributed to the growth in human, livestock and wild dog populations in the area. This study recommends that to foster their coexistence, the continued escalation in livestock numbers needs to cease while simultaneously protecting the region's wild prey populations.
Management of invasive species, whether prevention, population reduction, or eradication, requires assessment of the invasive species' population status and an assessment of the probability of success of management options. Perceptions of a species' permanence in an environment or lack thereof frequently drives how limited time, financial, and personnel resources are allocated to such efforts. Language we use to describe a non-native species' status largely defines these perceptions and sets boundaries, real or perceived, to potential management actions. Here we discuss the use of a particular term-"established"when confronting management decisions for invasive species. Our objective is to contribute to bridging the gap between the realms of conceptual development and management with respect to use of the term "established". We find that although there are benefits of polysemy and synonymy to conceptual development they present an additional challenge to managers who must weigh the costs, benefits, and potential for success of particular management actions. We also examine how existing conceptual frameworks might be augmented to bridge the theoretical-practical gap, such as more precisely defining potential management actions and explicitly including assessment of risk.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.