MSGID: 1:317/3 64a3a07e   
   PID: hpt/lnx 1.9.0-cur 2019-01-08   
   TID: hpt/lnx 1.9.0-cur 2019-01-08   
    Counting Africa's largest bat colony    
    Artificial intelligence and computer vision provide most accurate   
   estimate yet    
      
     Date:   
         July 3, 2023   
     Source:   
         Max-Planck-Gesellschaft   
     Summary:   
         Artificial intelligence and computer vision provide most accurate   
         estimate yet.   
      
      
         Facebook Twitter Pinterest LinkedIN Email   
      
   ==========================================================================   
   FULL STORY   
   ==========================================================================   
   Once a year, a small forest in Zambia becomes the site of one of the   
   world's greatest natural spectacles. In November, straw-colored fruit   
   bats migrate from across the African continent to a patch of trees in   
   Kasanka National Park. For reasons not yet known, the bats converge for   
   three months in a small area of the park, forming the largest colony of   
   bats anywhere in Africa. The exact number of bats in this colony, however,   
   has never been known. Estimates range anywhere from 1 to 10 million. A new   
   method developed by the Max Planck Institute of Animal Behavior (MPI-AB)   
   has counted the colony with the greatest accuracy yet. The method uses   
   GoPro cameras to record bats and then applies artificial intelligence   
   (AI) to detect animals without the need for human observers. The method,   
   published in the journal Ecosphere, produced an overall estimate of   
   between 750,000 and 1,000,000 bats in Kasanka -- making the colony the   
   largest for bats by biomass anywhere in the world.   
      
   "We've shown that cheap cameras, combined with AI, can be used to monitor   
   large animal populations in ways that would otherwise be impossible," says   
   Ben Koger who is first author on the paper. "This approach will change   
   what we know about the natural world and how we work to maintain it in   
   the face of rapid human development and climate change."  Africa's secret   
   gardeners Even amongst the charismatic fauna of the African continent,   
   the straw-colored fruit bat shines bright. By some estimates, it's   
   the most abundant mammal anywhere on the continent. And, by traveling   
   up to two thousand kilometers every year, it's also the most extreme   
   long-distance migrant of any flying fox.   
      
   From an environmental perspective, these merits matter a lot. By   
   dispersing seeds as they fly over vast distances, the fruit bats are   
   cardinal reforesters of degraded land -- making them a "keystone"   
   species on the African continent.   
      
   Scientists have long sought to estimate colony sizes of this important   
   species, but the challenges of manually counting very large populations   
   have led to widely fluctuating numbers. That's always frustrated Dina   
   Dechmann, a biologist from the MPI-AB, who has studied straw-colored   
   fruit bats for over 10 years.   
      
   Concerned that she has witnessed a decline in numbers of these fruit bats   
   over her career, Dechmann wanted a tool that could accurately reveal if   
   populations were changing. That is, she needed a way of counting bats   
   that was reproducible and comparable across time.   
      
   "Straw-colored fruit bats are the secret gardeners of Africa," says   
   Dechmann.   
      
   "They connect the continent in ways that no other seed disperser does. A   
   loss of the species would be devastating for the ecosystem. So, if the   
   population is decreasing at all, we urgently need to know."  Dechmann   
   began talking to longtime collaborators Roland Kays from NC State   
   University and Teague O'Mara from Southeastern Louisiana University,   
   as well as Kasanka Trust, the Zambian conservation organization   
   responsible for managing Kasanka National Park and protecting its colony   
   of bats. Together, they wondered if advances in computer vision and   
   artificial intelligence could improve the accuracy and efficiency of   
   counting large and complex bat populations. To find out, they approached   
   Ben Koger, then a doctoral student at the MPI-AB, who was an expert in   
   using automated approaches to create ecological datasets.   
      
   Accurate and comparable bat counts Koger worked to devise a method that   
   could be used by scientists and conservation managers to efficiently   
   quantify the complex system. His method comprised two main steps. First,   
   nine GoPro cameras were set up evenly around the colony to record the   
   bats as they left the roost at dusk. Second, Koger trained deep learning   
   models to automatically detect and count bats in the videos. To test the   
   method's accuracy, the team manually counted bats in a sample of clips and   
   found the AI was 95% accurate -- it even worked well in dark conditions.   
      
   "Using more sophisticated technology to monitor a colony as giant as   
   Kasanka's could be prohibitively expensive because you'd need so much   
   equipment," says Koger. "But we could show that cheap cameras paired with   
   our custom software algorithms did very well at detecting and counting   
   bats at our study site. This is hugely important for monitoring the   
   site in the future."  Recording bats over five nights, the new method   
   counted an average of between around 750,000 and 1,000,000 animals per   
   night. This result falls below previous counts at Kasanka, and the authors   
   state that the study might not have caught the peak of bat migration,   
   and some animals might have arrived after the count period. Even so,   
   the study's estimate makes Kasanka's colony the heaviest congregation   
   of bats anywhere in the world.   
      
   Says Dechmann: "This is a game-changer for counting and conserving large   
   populations of animals. Now, we have an efficient and reproducible way of   
   monitoring animals over time. If we use this same method to census animals   
   every year, we can actually say if the population is going up or down."   
   For the Kasanka colony, which is facing threats from agriculture and   
   constriction, Dechmann says that the need for accurate monitoring has   
   never been more urgent than now.   
      
   "It's easy to assume that losing a few animals here and there from large   
   populations won't make a dent. But if we are to maintain the ecosystem   
   services provided by these animals, we need to maintain their populations   
   at meaningful levels. The Kasanka colony isn't just one of many; it's   
   a sink colony of bats from across the subcontinent. Losing this colony   
   would be devastating for Africa as a whole."   
       * RELATED_TOPICS   
             o Plants_&_Animals   
                   # Wild_Animals # Nature # Extreme_Survival # Animals   
             o Computers_&_Math   
                   # Artificial_Intelligence # Math_Puzzles # Mathematics #   
                   Computer_Modeling   
       * RELATED_TERMS   
             o Computer_vision o Artificial_intelligence o Artificial_reef   
             o Computing_power_everywhere o Bioinformatics o Game_theory   
             o Computer_security o The_evolution_of_human_intelligence   
      
   ==========================================================================   
      
    Print   
      
    Email   
      
    Share   
   ==========================================================================   
   ****** 1 ****** ***** 2 ***** **** 3 ****   
   *** 4 *** ** 5 ** Breaking this hour   
   ==========================================================================   
       * Screens_More_Versatile_Than_LED:_Fins_and_...   
      
       * GM_Pig_Heart_in_a_Human_Patient:_Update *   
       Multiple_Sclerosis_Severity * Wind_Farm_Noise_and_Road_Traffic_Noise   
       * Mavericks_and_Horizontal_Gene_Transfer *   
       Early_Reading_for_Pleasure:_Brains,_...   
      
       * New_Light_Shed_On_Evolution_of_Animals *   
       Gullies_On_Mars_from_Liquid_Meltwater?   
       * DNA_Organization_in_Real-Time *   
       How_the_Cat_Nose_Knows_What_It's_Smelling   
      
   Trending Topics this week   
   ==========================================================================   
   PLANTS_&_ANIMALS Birds Animal_Learning_and_Intelligence Molecular_Biology   
   EARTH_&_CLIMATE Water Weather Climate FOSSILS_&_RUINS Dinosaurs   
   Early_Mammals Origin_of_Life   
      
      
   ==========================================================================   
      
   Strange & Offbeat   
   ==========================================================================   
   PLANTS_&_ANIMALS   
   Squash_Bugs_Are_Attracted_to_and_Eat_Each_Other's_Poop_to_Stock_Their   
   Microbiome How_Urea_May_Have_Been_the_Gateway_to_Life   
   Octopus_Sleep_Is_Surprisingly_Similar_to_Humans_and_Contains_a_Wake-Like_Stage   
   EARTH_&_CLIMATE   
   Turning_Old_Maps_Into_3D_Digital_Models_of_Lost_Neighborhoods   
   Orangutans_Can_Make_Two_Sounds_at_the_Same_Time,_Similar_to_Human_Beatboxing,   
   Study_Finds Do_Hummingbirds_Drink_Alcohol?_More_Often_Than_You_Think   
   FOSSILS_&_RUINS Newly_Discovered_Jurassic_Fossils_in_Texas   
   Megalodon_Was_No_Cold-Blooded_Killer   
   'We're_All_Asgardians':_New_Clues_About_the_Origin_of_Complex_Life   
   Story Source: Materials provided by Max-Planck-Gesellschaft. Note:   
   Content may be edited for style and length.   
      
      
   ==========================================================================   
   Journal Reference:   
      1. Benjamin Koger, Edward Hurme, Blair R. Costelloe, M. Teague O'Mara,   
         Martin Wikelski, Roland Kays, Dina K. N. Dechmann. An automated   
         approach for counting groups of flying animals applied to one of   
         the world's largest bat colonies. Ecosphere, 2023; 14 (6) DOI:   
         10.1002/ecs2.4590   
   ==========================================================================   
      
   Link to news story:   
   https://www.sciencedaily.com/releases/2023/07/230703133110.htm   
      
   --- up 1 year, 18 weeks, 10 hours, 50 minutes   
    * Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1:317/3)   
   SEEN-BY: 15/0 106/201 114/705 123/120 153/7715 218/700 226/30 227/114   
   SEEN-BY: 229/110 112 113 307 317 400 426 428 470 664 700 291/111 292/854   
   SEEN-BY: 298/25 305/3 317/3 320/219 396/45 5075/35   
   PATH: 317/3 229/426