Monitoring of Coral Reefs Using Artificial Intelligence: A Feasible and Cost-Effective Approach

被引:108
作者
Gonzalez-Rivero, Manuel [1 ,2 ,3 ,4 ]
Beijbom, Oscar [2 ,5 ]
Rodriguez-Ramirez, Alberto [2 ]
Bryant, Dominic E. P. [3 ,4 ]
Ganase, Anjani [3 ,4 ]
Gonzalez-Marrero, Yeray [2 ]
Herrera-Reveles, Ana [6 ]
Kennedy, Emma, V [2 ]
Kim, Catherine J. S. [3 ,4 ]
Lopez-Marcano, Sebastian [2 ]
Markey, Kathryn [2 ]
Neal, Benjamin P. [2 ,7 ]
Osborne, Kate [1 ]
Reyes-Nivia, Catalina [2 ]
Sampayo, Eugenia M. [3 ,4 ]
Stolberg, Kristin [2 ]
Taylor, Abbie [2 ]
Vercelloni, Julie [2 ,3 ,4 ,8 ,9 ]
Wyatt, Mathew [1 ]
Hoegh-Guldberg, Ove [2 ,3 ,4 ]
机构
[1] Australian Inst Marine Sci, Cape Cleveland, Qld 4810, Australia
[2] Univ Queensland, Global Change Inst, St Lucia, Qld 4072, Australia
[3] Univ Queensland, Sch Biol Sci, St Lucia, Qld 4072, Australia
[4] Univ Queensland, ARC CoE Coral Reef Studies, St Lucia, Qld 4072, Australia
[5] Univ Calif Berkeley, Berkeley Artificial Intelligence Res, Berkeley, CA 94720 USA
[6] Univ Cent Venezuela, Inst Ecol & Zool Trop, Caracas 1051, Miranda, Venezuela
[7] Bigelow Lab Ocean Sci, East Boothbay, ME 04544 USA
[8] Queensland Univ Technol, ARC Ctr Math & Stat Frontiers, Sci & Engn Fac, Brisbane, Qld 4000, Australia
[9] Queensland Univ Technol, Sch Math Sci, Sci & Engn Fac, Brisbane, Qld 4000, Australia
基金
澳大利亚研究理事会;
关键词
coral reefs; monitoring; artificial intelligence; automated image analysis; GREAT-BARRIER-REEF; PLASTICITY; NETWORKS; SCIENCE;
D O I
10.3390/rs12030489
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Ecosystem monitoring is central to effective management, where rapid reporting is essential to provide timely advice. While digital imagery has greatly improved the speed of underwater data collection for monitoring benthic communities, image analysis remains a bottleneck in reporting observations. In recent years, a rapid evolution of artificial intelligence in image recognition has been evident in its broad applications in modern society, offering new opportunities for increasing the capabilities of coral reef monitoring. Here, we evaluated the performance of Deep Learning Convolutional Neural Networks for automated image analysis, using a global coral reef monitoring dataset. The study demonstrates the advantages of automated image analysis for coral reef monitoring in terms of error and repeatability of benthic abundance estimations, as well as cost and benefit. We found unbiased and high agreement between expert and automated observations (97%). Repeated surveys and comparisons against existing monitoring programs also show that automated estimation of benthic composition is equally robust in detecting change and ensuring the continuity of existing monitoring data. Using this automated approach, data analysis and reporting can be accelerated by at least 200x and at a fraction of the cost (1%). Combining commonly used underwater imagery in monitoring with automated image annotation can dramatically improve how we measure and monitor coral reefs worldwide, particularly in terms of allocating limited resources, rapid reporting and data integration within and across management areas.
引用
收藏
页数:22
相关论文
共 48 条
[1]  
[Anonymous], 2009, Artificial intelligence: A modern approach
[2]  
[Anonymous], 7 CRC AUSTR I MAR SC
[3]  
[Anonymous], 2014, Comput. Sci.
[4]  
[Anonymous], 2008, STATE GREAT BARRIER
[5]  
[Anonymous], 2014, NAT COR REEF MON PLA
[6]  
[Anonymous], 2017, P 3 INT C INF TECHN
[7]  
[Anonymous], 2008, A threat to coral reefs multi
[8]  
[Anonymous], SEAVIEW SURVEY PHOTO
[9]  
[Anonymous], ADV NEURAL INFORM PR
[10]  
[Anonymous], 2017, ARXIV170707012