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

Abstract

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.

Crowd‐sourced plant occurrence data provide a reliable description of macroecological gradients

“…But even if the current potentials of automated species recognition are not in the direct quantification of species richness, can such data complement professional inventories or be exploited as inputs to more complex analysis. Under the assumption that apps for automated species identification continue to enjoy broad user uptake and sufficient information comes together (Bonnet et al 2020), we envisage that analyses like the one presented here could offer novel perspectives for macroecological research. One idea would be to co‐interpret the derived with the emerging multivariate satellite derived data cubes that continuously describe the states and processes of land‐ecosystems globally (Mahecha et al 2020).…”

“…plants, insects or birds directly in the field (Kumar et al 2012, Affouard et al 2017, Van Horn et al 2018, Wäldchen and Mäder 2018a, Jones 2020). The voluntarily shared ancillary information on time and location could soon turn such mobile observations into an invaluable resource for different monitoring tasks (Bonnet et al 2020). Consequently, the questions discussed in the existing literature on automated species identification mainly revolve around the accuracy of the competing algorithmic approaches for automated species identification (Nguyen et al 2018, Wäldchen and Mäder 2018b, Jones 2020, Villon et al 2020).…”

Perspectives on Citizen Science Data Quality

“…In addition, increasing transparency about pitfalls that have compromised the quality of CSD can avoid a cycle of repeating failures in CS research (Balázs et al, 2021). Enabling volunteers to contribute to transparent validation of observations also contributes to the improvement of CSD quality and to the motivation of contributors (Bonnet et al, 2020).…”

Towards ecological science for all by all

“…Although wide ranging and varied, as a collection these articles go some way to addressing the two perspectives intended for this Special Feature; the contribution of citizen science to the advancement of ecological knowledge and the contribution of community‐based perspectives to citizen science. Among these 19 papers are 16 that present original quantitative or qualitative research, a practice‐based article (Bonnet et al., 2021), a perspective (Palmer et al., 2021) and a literature review (Winch et al., 2021).…”