Human-computer collaborative learning in citizen science

Lead Research Organisation: Open University
Department Name: Faculty of Sci, Tech, Eng & Maths (STEM)


This project explores the potential for collaborative learning between humans and machines within the framework of environmental citizen science. The term `citizen science' encompasses public participation in science and scientific communication to the public. Although not new, citizen science has gained renewed attention because of the opportunities arising from citizens' access to digital technologies in terms of data collection and annotation. While the vast majority of citizen science projects are aimed at data gathering, we instead propose a transformational shift to a new citizen science in which the public and technology are regarded not just as sensors or data recorders, but as a collective and empowered human--artificial intelligence that can help each other in science learning.

We will focus on the task of species identification from images. Citizen science projects such as iSpot invite the public to submit photos of wildlife. These are identified to species level and verified before being contributed to science. We will explore artificial intelligence as a means to automatically identify species in images. While this can save human effort, we are concerned about impact this might have on nature lovers. The introduction of technology is often associated with concerns of de-skilling. For naturalists, the honing of species identification skills is a key motivator of the recording activity. Hence, designing technology that provides opportunities for learning for both citizens and machines is essential, as is co-creating the technology to ensure that it is not only user friendly but responds to their motivations. Our approach will involve citizens collaborating with AI to arrive at
a species identification. AI will narrow down the choices and inform the citizen about how to distinguish the options. The citizen in turn will through providing an identification help the machine in its learning. We will study this learning interplay with respect to collaborative species identification, but will also explore technologies that foster wider science learning, environmental consciousness and data literacy through better communication of complex citizen science data. For this we will develop technology for Natural Language Generation that can communicate complex data through language.

Our proposed work programme seeks to bring about quantifiable benefits to (a) science, e.g., through the production of new knowledge and through monitoring key scientific processes at challenging temporal-spatial scales; (b) diverse stakeholders including the citizens themselves, e.g., through meaningful science learning for sustainability in formal and informal education contexts; and (c) wider society, e.g., through better societal understanding of current sustainability issues, leading to individual and societal action in support of the environment.

Planned Impact

We hope to achieve the following impacts through this research:

1. On Primary Schools and Secondary Schools

Citizen science practice, and notably technology, has been minimally promoted within formal education. We will unfold how the proposed collaborative learning technologies can be applied to citizen science in formal education settings and quantify the benefits to students and teachers.
We wish to see more schools take up citizen science and outdoor learning as means to enthuse students about science and technology. We expect this to lead to better learning outcomes for schools, and a more involved and engaged student community.

2. On Universities

We will demonstrate how citizen science can enhance STEM teaching in universities, and encourage its uptake within our universities. Citizen science is increasingly being viewed as a complementary approach to traditional science learning and research and offers several benefits, such as opportunities for students to work with their local communities, engage with technology, and involve themselves in designing and testing tools. It also allows academics to integrate their research with their teaching, which makes for a more stimulating student experience.

3. On Students

Through taking part in citizen science, students will develop the most important Science, Technology, Engineering and Mathematics (STEM) skills, including intellectual curiosity, problem solving,creativity, statistics and data-driven decision making. We will in particular engage with students in primary and secondary schools. While secondary school students can learn science and data skills in greater depth, it is important to get primary school students enthusiastic about science and technology. We are particularly conscious about the take-up of STEM subjects by girls and are keen to reach out to younger students who still need to decide which subjects to retain or drop in secondary school.

4. On Society and the Environment

The 2030 Agenda for Sustainable Development Goals (SDGs) explicitly argues for the need to ``take urgent and significant action to reduce the degradation of natural habitats, halt the loss of biodiversity and, by 2020, protect and prevent the extinction of threatened species''.
Yet, the most recent State of Nature report concludes that the UK has lost significantly more nature over the long term than the global average and is among the world's most nature depleted countries.
In the decades that nature has been in decline, so too has our connection with it. Fewer than a quarter of British children regularly use their local patch of nature and many suffer from `Nature Deficit Disorder', impacting education and physical and emotional health.
Research that promotes science learning through increased interaction with nature thus has multiple benefits to society. It contributes to health and learning outcomes for individuals and the development of a scientific temperament and pro-environmental attitudes in society.

Or research promotes actionable citizen science, whereby individuals, schools and communities can maintain and repair their habitats in the context of pollinating species. Using our developed technologies, students and teachers will build the knowledge and skills required to collect data, enhance habitats and gain the confidence to become passionate environmental stewards. We will encourage students to, through creative campaigns, share their knowledge about insects, the scientific process and planting for pollinators with members of their local and online communities.

The school-based campaigns will also build the capacity to collect high-quality data about changing pollinator populations and the availability of high-quality habitats.


10 25 50
Description Widespread concern over declines in pollinating insects has led to numerous recommendations of which "pollinator-friendly" plants to grow to help turn urban environments into valuable habitats for such important wildlife. Through analysis of the data gathered through our citizen science project BeeWatch, we discovered that much of the plant use recorded on our project did not reflect practitioner recommendations. We concluded that generic "pollinator-friendly" lists fail to recognise the stark differences among species and pollinator groups or adapt to changing phenology or gardening practices. Or findings, published in Nature Scientific Reports, call for the increased use of up-to-date dynamic planting recommendations driven by live (citizen science) data to support pollinator-friendly management of garden spaces, and in the process transformative personal learning journeys through gardening.
Exploitation Route The Royal Horticultural Society will use the information from the study to further improve its recommendations for bumblebee-friendly plantings, and to inform future research.
Sectors Environment

Description The Covid situation limited our access to schools and we were unable to roll out our actionable pollinator citizen science programme through site visits. Instead, we invested effort into creating a collection of online resources on Pollinator Citizen Science, with interactive AI-enhanced elements based on our research. This provided a timely way for families and schools to explore our research and engage in science learning, and allowed schools to continue participation in X-Polli:Nation without requiring visits from us. While the materials are accessible without registration, we know 93 users have attempted the embedded quizzes and over 600 users have used our interactive species identification tool. We have also demonstrated these resources at the European Citizen Science Association Annual Conference 2020, and they were showcased during Bees' Needs Week 2020, a public engagement event coordinated by DEFRA.
First Year Of Impact 2020
Sector Creative Economy,Education,Environment
Impact Types Societal

Description Online Open Course Materials aimed at Primary Schools
Geographic Reach National 
Policy Influence Type Influenced training of practitioners or researchers
Description DECIDE - Delivering Enhanced Biodiversity Information with Adaptive Citizen Science and Intelligent Digital Engagements
Amount £94,282 (GBP)
Funding ID NE/V003194/1 
Organisation Natural Environment Research Council 
Sector Public
Country United Kingdom
Start 06/2020 
End 07/2022
Title Human - AI collaborative interface for biological species identification from images 
Description A Web Tool whereby members of the public can learn how to identify different species of Bumblebee and Butterfly using a key and getting help from Artificial Intelligence technologies such as image recognition. 
Type Of Material Computer model/algorithm 
Year Produced 2020 
Provided To Others? Yes  
Impact This tool is incorporated into an online collection of course materials on Pollinator Citizen Science ( It was publicised as part of DEFRA's Bees' Needs Week 2020 ( 
Description Interview for local news 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Media (as a channel to the public)
Results and Impact Following a press release and a video posted on University of Aberdeen's Twitter account (, we gave an interview to the Press and Journal leading to media coverage ( The research was also reported in the Evening Express (
Year(s) Of Engagement Activity 2021
Description Invited talk at the Green Data Conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact The PI (Siddharthan) was an invited speaker at the 2019 Green Data Conference, London, organised by the Environmental Industries Commission and sponsored by UKRI and NERC. Siddharthan addressed a diverse audience from industry, government bodies, academia and the third sector alongside other speakers that included the NERC head of digital environment, deputy director of DEFRA, executive director of the Environmental Industries Commission and vice president of the World Resources Institute. There was a lively discussion that followed in which we explored topical issues around Artificial Intelligence and Citizen Science for environmental monitoring.
Year(s) Of Engagement Activity 2019
Description Workshop at European Citizen Science Association Annual Conference 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact We demonstrated our AI-enabled Biological Species Identification tools of described the X-Polli:Nation (cross-pollination) citizen science project that the tools is embedded in. This engagement has sparked new engagements with pollinator citizen science groups in Europe.
Year(s) Of Engagement Activity 2020