How citizen scientists contribute to monitor protected areas thanks to automatic plant identification tools

1. Successful monitoring and management of plant resources worldwide needs the involvement of civil society to support natural reserve managers. Because it is difficult to correctly and quickly identify plant species for non‐specialists, the development of recent techniques based on automatic visual identification should facilitate and increase public engagement in citizen science initiatives. 2. Automatic identification platforms are new to most citizen scientists and land managers. Pl@ntNet is such a platform, available since 2013 on web and mobile environments, and now included in several workflows such as invasive alien species management, endemic species monitoring, educational activities and eco‐tourism practices. The successful development of such platforms needs to identify their strengths and weaknesses in order to improve and facilitate their use in all aspects of ecosystem management. 3. Here we present two Pl@ntNet citizen science initiatives used by conservation practitioners in Europe (France) and Africa (Kenya). We discuss various perspectives, including benefits and limitations. Based on the experiences of field managers, we formulate several recommendations for future initiatives. The recommendations are aimed at a diverse group of conservation managers and citizen science practitioners.

[1]  R. R. Newell.  Art and science. , 1950, Stanford medical bulletin.

[2]  E. Donaldson.  A Vision of Will , 1981, Speculum.

[3]  Nozha Boujemaa,et al.  The ImageCLEF 2011 plant images classification task , 2011 .

[4]  Melinda Laituri,et al.  The art and science of multi-scale citizen science support , 2011, Ecol. Informatics.

[5]  Nozha Boujemaa,et al.  The ImageCLEF 2012 Plant Identification Task , 2012, CLEF.

[6]  Nozha Boujemaa,et al.  The imageCLEF plant identification task 2013 , 2013, MAED '13.

[7]  Nozha Boujemaa,et al.  Pl@ntNet mobile app , 2013, ACM Multimedia.

[8]  Itheri Yahiaoui,et al.  Pl@ntNet Mobile 2014: Android port and new features , 2014, ICMR.

[9]  J. Fischer,et al.  Challenges for biodiversity monitoring using citizen science in transitioning social-ecological systems , 2015 .

[10]  Pierre Bonnet,et al.  Plant Identification in an Open-world (LifeCLEF 2016) , 2016, CLEF.

[11]  Lauren V. Weatherdon,et al.  Is citizen science an open science in the case of biodiversity observations , 2017 .

[12]  A. Cox,et al.  Motivations, learning and creativity in online citizen science , 2016 .

[13]  F. Ratnieks,et al.  Data reliability in citizen science: learning curve and the effects of training method, volunteer background and experience on identification accuracy of insects visiting ivy flowers , 2016 .

[14]  Jennifer Preece,et al.  Citizen Science: New Research Challenges for Human–Computer Interaction , 2016, Int. J. Hum. Comput. Interact..

[15]  Margaret Kosmala,et al.  Assessing data quality in citizen science (preprint) , 2016, bioRxiv.

[16]  N. Constant,et al.  Narratives as a mode of research evaluation in citizen science : understanding broader science communication impacts. , 2017 .

[17]  Cara E. Steger,et al.  Safari Science: assessing the reliability of citizen science data for wildlife surveys , 2017 .

[18]  Pierre Bonnet,et al.  Plant Identification Based on Noisy Web Data: the Amazing Performance of Deep Learning (LifeCLEF 2017) , 2017, CLEF.

[19]  J. K. Legind,et al.  Contribution of citizen science towards international biodiversity monitoring , 2017 .

[20]  Jean-Christophe Lombardo,et al.  Pl@ntNet app in the era of deep learning , 2017, ICLR.

[21]  Steve Kelling,et al.  Estimates of observer expertise improve species distributions from citizen science data , 2018 .

[22]  Michael J. O. Pocock,et al.  A Vision for Global Biodiversity Monitoring With Citizen Science , 2018 .

[23]  P. Monestiez,et al.  Species distribution modeling based on the automated identification of citizen observations , 2018, Applications in plant sciences.

[24]  Patrick Mäder,et al.  Machine learning for image based species identification , 2018, Methods in Ecology and Evolution.

[25]  Pierre Bonnet,et al.  Overview of ExpertLifeCLEF 2018: how far Automated Identification Systems are from the Best Experts? , 2018, CLEF.

[26]  L. Cappellato,et al.  Overview of LifeCLEF Plant Identification task 2019: diving into data deficient tropical countries , 2019 .

[27]  Pierre Bonnet,et al.  Overview of LifeCLEF Plant Identification Task 2019: diving into Data Deficient Tropical Countries , 2019, CLEF.

[28]  Stefan Kahl,et al.  Overview of LifeCLEF 2019: Identification of Amazonian Plants, South & North American Birds, and Niche Prediction , 2019, CLEF.

[29]  Jessica L. Oliver,et al.  Opportunities and Risks for Citizen Science in the Age of Artificial Intelligence , 2019, Citizen Science: Theory and Practice.

[30]  B. Zuckerberg,et al.  Tradeoffs and tools for data quality, privacy, transparency, and trust in citizen science , 2019, Biological Conservation.

[31]  Advaith Siddharthan,et al.  Designing online species identification tools for biological recording: the impact on data quality and citizen science learning , 2019, PeerJ.

[32]  Eric Hervet,et al.  Applications for deep learning in ecology , 2019, Methods in Ecology and Evolution.

[33]  R. Dasgupta,et al.  Citizen science and invasive alien species: An analysis of citizen science initiatives using information and communications technology (ICT) to collect invasive alien species observations , 2020 .

[34]  P. Monestiez,et al.  Bias in presence-only niche models related to sampling effort and species niches: Lessons for background point selection , 2020, PloS one.

[35]  Jean-Christophe Lombardo,et al.  Author response for "How citizen scientists contribute to monitor protected areas thanks to automatic plant identification tools" , 2020 .