Deep learning models map rapid plant species changes from citizen science and remote sensing data.

Anthropogenic habitat destruction and climate change are reshaping the geographic distribution of plants worldwide. However, we are still unable to map species shifts at high spatial, temporal, and taxonomic resolution. Here, we develop a deep learning model trained using remote sensing images from California paired with half a million citizen science observations that can map the distribution of over 2,000 plant species. Our model-Deepbiosphere-not only outperforms many common species distribution modeling approaches (AUC 0.95 vs. 0.88) but can map species at up to a few meters resolution and finely delineate plant communities with high accuracy, including the pristine and clear-cut forests of Redwood National Park. These fine-scale predictions can further be used to map the intensity of habitat fragmentation and sharp ecosystem transitions across human-altered landscapes. In addition, from frequent collections of remote sensing data, Deepbiosphere can detect the rapid effects of severe wildfire on plant community composition across a 2-y time period. These findings demonstrate that integrating public earth observations and citizen science with deep learning can pave the way toward automated systems for monitoring biodiversity change in real-time worldwide.

A Mixed Methods Approach to Understanding the Public Health Impact of a School-Based Citizen Science Program to Reduce Arsenic in Private Well Water.

BACKGROUND: Exposure to arsenic (As) in well water is a well-documented public health issue for Maine and New Hampshire, as well as for other states in the United States and abroad. Arsenic contamination of well water in these locations is primarily attributed to metasedimentary bedrock that leaches As into groundwater. However, As can also enter groundwater reserves from soils contaminated by the historical use of arsenical pesticides. Approximately half of the households in Maine and New Hampshire rely on private wells, many of which have elevated As. Arsenic exposure has been associated with an increased risk of cancer, cardiovascular disease, reduced infection resistance, and lower intelligence quotient in children. Despite these known health impacts, well water testing and treatment are not universal. OBJECTIVES: We have approached the problem of low well water testing rates in Maine and New Hampshire communities by developing the All About Arsenic (AAA) project, which engages secondary school teachers and students as citizen scientists in collecting well water samples for analysis of As and other toxic metals and supports their outreach efforts to their communities. METHODS: We assessed this project's public health impact by analyzing student data relative to existing well water quality datasets in both states. In addition, we surveyed private well owners who contributed well water samples to the project to determine the actions taken to mitigate As in well water. RESULTS: Students collected 3,070 drinking water samples for metals testing, and 752 exceeded New Hampshire's As standard of 5 ppb. The AAA data has more than doubled the amount of information available to public health agencies about well water quality in multiple municipalities across both states. Students also collected information about well types and treatment systems. Their data reveal that some homeowners did not know what type of wells they had or whether they had filtration systems. Those with filtration systems were often unaware of the type of system, what the system was filtering for, or whether the system was designed to remove As. Through interviews with pilot survey participants, we learned that some had begun mitigating their exposure to As and other toxic metals in response to test results from the AAA project. DISCUSSION: A school-based approach to collecting and analyzing private well water samples can successfully reach communities with low testing rates for toxic elements, such as As and other metals. Importantly, information generated through the program can impact household decision-making, and students can influence local and state policymaking by sharing information in their communities. https://doi.org/10.1289/EHP13421.

A Model for Engaging Citizen Scientists: A Community-Partnered Research Collaboration to Address Inequities for Black Birthing People.

PURPOSE: Co-creation of a citizen-science research initiative with a collaborative team of community members and university-based scientists to address regional disparities in maternal and fetal health outcomes for Black birthing people. DESCRIPTION: Citizen scientist-led projects, where community members actively contribute to each discovery step, from setting a research agenda to collecting data and disseminating results, can extend community participatory research initiatives and help reconceptualize traditional research processes. The Pregnancy Collaborative is a citizen-science research initiative and one of nine scientific committees of The Pittsburgh Study-a longitudinal, community-partnered study designed to bring together collaborators to improve child thriving. ASSESSMENT: Ten community members and five university-based scientists participated during all phases of developing a citizen-scientist collaboration over an initial two-and-a-half-year period. Phases include forming the Pregnancy Collaborative and group research ethics training; co-creating a research agenda grounded in shared principles; and community-partnered data collection, analysis, and dissemination. These phases produced three key co-designed products: (1) a mission and vision statement of the Pregnancy Collaborative, (2) a Collaborative-endorsed research agenda, and (3) a citizen-scientist-executed research survey. CONCLUSION: Lessons learned from the formation of the Pregnancy Collaborative highlight the importance of equitable power distribution through bidirectional knowledge sharing and by centering intellectual effort, lived experience, and tools and resources of those affected by health inequities. Using a citizen science approach to co-designing and executing research helps us move maternal health inequity work from "research on" to "research with."

Validation of Citizen Science Meteorological Data: Can They Be Considered a Valid Help in Weather Understanding and Community Engagement?

Citizen science has emerged as a potent approach for environmental monitoring, leveraging the collective efforts of volunteers to gather data at unprecedented scales. Within the framework of the I-CHANGE project, MeteoTracker, a citizen science initiative, was employed to collect meteorological measurements. Through MeteoTracker, volunteers contributed to a comprehensive dataset, enabling insights into local weather patterns and trends. This paper presents the analysis and the results of the validation of such observations against the official Italian civil protection in situ weather network, demonstrating the effectiveness of citizen science in generating valuable environmental data. The work discusses the methodology employed, including data collection and statistical analysis techniques, i.e., time-series analysis, spatial and temporal interpolation, and correlation analysis. The overall analysis highlights the high quality and reliability of citizen-generated data as well as the strengths of the MeteoTracker platform. Furthermore, our findings underscore the potential of citizen science to augment traditional monitoring efforts, inform decision-making processes in environmental research and management, and improve the social awareness about environmental and climate issues.

A citizen science approach to develop a digital intervention to reduce HIV stigma and promote HIV self-testing among adolescents and young adults: a mixed methods analysis from Kazakhstan.

INTRODUCTION: Kazakhstan has one of the fastest-growing HIV epidemics in the world, with increasing rates among adolescents and young adults (AYA). Innovative strategies are needed to increase HIV testing uptake and decrease HIV stigma among AYA. Citizen science, defined as the active engagement of the general public in scientific research tasks, promotes and facilitates community engagement throughout the research process. This citizen science study used crowdsourcing to engage AYA in Kazakhstan to develop a digital intervention to reduce HIV stigma and promote HIV self-testing. Our objectives in this paper are to describe the approach used, its feasibility and acceptability, and AYA motivations for and lessons learned collaborating on the study. METHODS: From October 2021 to July 2022, in collaboration with a Community Collaborative Research Board and a Youth Advisory Board, we developed an open call requesting multimedia submissions to reduce HIV testing stigma. Eligible submissions were separated by age group (13-19 or 20-29 years) and judged by a panel composed of AYA (n = 23), healthcare professionals (n = 12), and representatives from the local government and non-governmental organizations (n = 17). Each entry was reviewed by at least four judges and ranked on a 5-point scale. The top 20 open call contestants were asked to submit self-recordings sharing their motivation for and experience participating in the contest and lessons learned. Descriptive statistics were calculated for quantitative data. Qualitative data were coded using open coding. RESULTS: We received 96 submissions from 77 youth across Kazakhstan. Roughly, three-quarters (n = 75/96) of entries met judging eligibility criteria. Of the eligible entries, over half (n = 39/75) scored 3.5 or higher on a 5-point scale (70.0%). The most frequent types of entries were video (n = 36/96, 37.5%), image (n = 28/96, 29.2%) and text (n = 24/96, 25.0%). AYA's primary motivations for collaborating on the study included a desire to improve society and help youth. The main challenges included creating content to address complex information using simple language, finding reliable information online and technological limitations. CONCLUSIONS: Crowdsourcing was feasible and highly acceptable among AYA in Kazakhstan. Citizen science approaches hold great promise for addressing the increasingly complex health and social challenges facing communities today.

Defining community-led monitoring and its role in programme-embedded learning: lessons from the Citizen Science Project in Malawi and South Africa.

INTRODUCTION: Programme Science (PS) and community-led monitoring (CLM) intersect in unexpected and promising ways. This commentary examines a CLM initiative in Malawi and South Africa to highlight the crucial role of CLM in bolstering the PS framework. By leveraging data sources often overlooked by conventional research and evaluation approaches, CLM emerges as a pivotal element in enhancing programme effectiveness. This paper delineates the fundamental principles of CLM, presents programme outcomes derived from CLM methodologies and contextualizes these findings within the broader framework of PS. DISCUSSION: The Citizen Science Project implements CLM continuously at 33 health facilities: 14 in Malawi (eight in Kasungu District and six in Dedza District), and 19 in South Africa (all in the West Rand District), representing a total catchment area of 989,848 people. Monitoring indicators are developed in an iterative process with community groups. The indicators are unique to each country, but both focus on the uptake of health services (quantitative) and barriers to access (qualitative). Monthly clinic records surveys capture 34 indicators in Malawi and 20 in South Africa and are supplemented by qualitative interviews with care recipients and healthcare workers. Qualitative interviews provide additional granularity and help confirm and explain the more macro trends in service coverage as described in quantitative data. The resulting data analysis reveals key themes that help stakeholders and decision-makers to solve problems collaboratively. Noteworthy outcomes include a substantial increase in multi-month dispensing of antiretroviral therapy (ART) during COVID-19 (from 6% to 31%) with a subsequent recovery surpassing of HIV service benchmarks in Malawi post-pandemic. CONCLUSIONS: While quantifying direct impact remains challenging due to the project's design, CLM proves to be a robust methodology that generates credible data and produces impactful outcomes. Its potential extends beyond the health sector, empowering community leadership and fostering interventions aligned with community needs. As CLM continues to evolve, its integration into PS promises to improve relevance, quality and impact across diverse disciplines.

Fostering citizen-engaged HIV implementation science.

INTRODUCTION: Successful implementation of evidence-based practices depends on contextual factors like stakeholder engagement, the socio-political environment, resource availability, and stakeholders' felt needs and preferences. Nevertheless, inequities in implementation exist and undermine efforts to address HIV in marginalized key populations. Implementation science shows promise in addressing such inequities in the HIV response, but can be limited without meaningful engagement from citizens or communities. DISCUSSION: We define the concept of a citizen-engaged HIV implementation science as one that involves citizens and communities deeply in HIV implementation science activities. In this commentary, we discuss how citizen science approaches can be leveraged to spur equity in HIV implementation science. Drawing on three areas previously defined by Geng and colleagues that serve to drive impactful implementation science in the HIV response, we discuss how citizens can be engaged when considering "whose perspectives?", "what questions are being asked?" and "how are questions asked?". With respect to "whose perspectives?" a citizen-engaged HIV implementation science would leverage participatory methods and tools, such as co-creation, co-production and crowdsourcing approaches, to engage the public in identifying challenges, solve health problems and implement solutions. In terms of "what questions are being asked?", we discuss how efforts are being made to synthesize citizen or community-led approaches with existing implementation science frameworks and approaches. This also means that we ensure communities have a say in interrogating and deconstructing such frameworks and adapting them to local contexts through participatory approaches. Finally, when considering "how are questions asked?", we argue for the development and adoption of broad, guiding principles and frameworks that account for dynamic contexts to promote citizen-engaged research in HIV implementation science. This also means avoiding narrow definitions that limit the creativity, innovation and ground-up wisdom of local citizens. CONCLUSIONS: By involving communities and citizens in the development and growth of HIV implementation science, we can ensure that our implementation approaches remain equitable and committed to bridging divides and ending AIDS as a public health threat. Ultimately, efforts should be made to foster a citizen- and community-engaged HIV implementation science to spur equity in our global HIV response.

Quantification of litter in cities using a smartphone application and citizen science in conjunction with deep learning-based image processing.

Cities are a major source of litter pollution. Determination of the abundance and composition of plastic litter in cities is imperative for effective pollution management, environmental protection, and sustainable urban development. Therefore, here, a multidisciplinary approach to quantify and classify the abundance of litter in urban environments is proposed. In the present study, litter data collection was integrated via the Pirika smartphone application and conducted image analysis based on deep learning. Pirika was launched in May 2018 and, to date, has collected approximately one million images. Visual classification revealed that the most common types of litter were cans, plastic bags, plastic bottles, cigarette butts, cigarette boxes, and sanitary masks, in that order. The top six categories accounted for approximately 80 % of the total, whereas the top three categories accounted for more than 60 % of the total imaged litter. A deep-learning image processing algorithm was developed to automatically identify the top six litter categories. Both precision and recall derived from the model were higher than 75 %, enabling proper litter categorization. The quantity of litter derived from automated image processing was also plotted on a map using location data acquired concurrently with the images by the smartphone application. Conclusively, this study demonstrates that citizen science supported by smartphone applications and deep learning-based image processing can enable the visualization, quantification, and characterization of street litter in cities.

Emerging technologies in citizen science and potential for insect monitoring.

Emerging technologies are increasingly employed in environmental citizen science projects. This integration offers benefits and opportunities for scientists and participants alike. Citizen science can support large-scale, long-term monitoring of species occurrences, behaviour and interactions. At the same time, technologies can foster participant engagement, regardless of pre-existing taxonomic expertise or experience, and permit new types of data to be collected. Yet, technologies may also create challenges by potentially increasing financial costs, necessitating technological expertise or demanding training of participants. Technology could also reduce people's direct involvement and engagement with nature. In this perspective, we discuss how current technologies have spurred an increase in citizen science projects and how the implementation of emerging technologies in citizen science may enhance scientific impact and public engagement. We show how technology can act as (i) a facilitator of current citizen science and monitoring efforts, (ii) an enabler of new research opportunities, and (iii) a transformer of science, policy and public participation, but could also become (iv) an inhibitor of participation, equity and scientific rigour. Technology is developing fast and promises to provide many exciting opportunities for citizen science and insect monitoring, but while we seize these opportunities, we must remain vigilant against potential risks. This article is part of the theme issue 'Towards a toolkit for global insect biodiversity monitoring'.

Willingness to participate in in-the-moment surveys triggered by online behaviors.

Surveys are a fundamental tool of empirical research, but they suffer from errors: in particular, respondents can have difficulties recalling information of interest to researchers. Recent technological developments offer new opportunities to collect data passively (i.e., without participant's intervention), avoiding recall errors. One of these opportunities is registering online behaviors (e.g., visited URLs) through tracking software ("meter") voluntarily installed by a sample of individuals on their browsing devices. Nevertheless, metered data are also affected by errors and only cover part of the objective information, while subjective information is not directly observable. Asking participants about such missing information by means of web surveys conducted in the moment an event of interest is detected by the meter has the potential to fill the gap. However, this method requires participants to be willing to participate. This paper explores the willingness to participate in in-the-moment web surveys triggered by online activities recorded by a participant-installed meter. A conjoint experiment implemented in an opt-in metered panel in Spain reveals overall high levels of willingness to participate among panelists already sharing metered data, ranging from 69% to 95%. The main aspects affecting this willingness are related to the incentive levels offered. Limited differences across participants are observed, except for household size and education. Answers to open questions also confirm that the incentive is the key driver of the decision to participate, whereas other potential problematic aspects such as the limited time to participate, privacy concerns, and discomfort caused by being interrupted play a limited role.

Using citizen science to test for acoustic niche partitioning in frogs.

The acoustic niche hypothesis proposes that to avoid interference with breeding signals, vocal species should evolve to partition acoustic space, minimising similarity with co-occurring signals. Tests of the acoustic niche hypothesis are typically conducted using a single assemblage, with mixed outcomes, but if the process is evolutionarily important, a pattern of reduced acoustic competition should emerge, on average, over many communities. Using a continental-scale dataset derived from audio recordings collected by citizen scientists, we show that frogs do partition acoustic space. Differences in calls were predominately caused by differences in spectral, rather than temporal, features. Specifically, the 90% frequency bandwidths of observed frog assemblages overlapped less than expected, and there was greater distance between dominant frequencies than expected. To our knowledge, this study is the first to use null models to test for acoustic niche partitioning over a large geographic scale.

Applying citizen science to engage families affected by ovarian cancer in developing genetic service outreach strategies.

Citizen science (CS) approaches involving non-professional researchers (citizens) as research collaborators has been used infrequently in health promotion generally and specifically, in cancer prevention. Standardized CS approaches may be especially useful for developing communication interventions to encourage families to consider cancer genetic services. We engaged survivors of ovarian cancer and their close relatives as CS collaborators to collect and help interpret data to inform content for a website, printed invitation materials, and short-message reminders. We applied an implementation quality framework, and posed four research questions regarding the feasibility of CS: recruitment, data collection, data quality and evaluation of the experience. CS members were recruited through three networks: clinical sites, local and national cancer support organizations, and online ovarian cancer patient support groups. The professional research team operationalized theory-aligned CS tasks, five data collection options, question banks/scripts for creating surveys, structured interviews, online training and ongoing support from research coaches. 14 CS members agreed to the 12-week and 20-hour commitment for an honorarium. CS members opted to do both qualitative and quantitative assessments. CS members collected 261 surveys and 39 structured interviews. The largest number of surveys were collected for Task 1 (n = 102) to assess survivors' reactions to different possible options for motivating survivors to visit a study website; 77% of this data were complete (i.e., no missing values). Data collected for tasks 2, 3, 4, and 5 (e.g., assessment of survivors' and relatives' respective communication preferences) ranged from 10 to 58 surveys (80% to 84% completeness). All data were collected within the specified time frame. CSs reported 17 hours of work on average and regarded the experience positively. Our experience suggests that CS engagement is feasible, can yield comprehensive quantitative and qualitative data, and is achievable in a relatively a short timeline.

Cannabis use and suicidal ideation among youth: Can we democratize school policies using digital citizen science?

BACKGROUND: School policies and programs are important in preventing Cannabis use among youth. This study uses an innovative digital citizen science approach to determine the association between Cannabis use and suicidal ideation among youth while investigating how school health policies mediate this association. METHODS: The study engaged 818 youth (aged 13-18 years) and 27 educators as citizen scientists via their own smartphones. Youths responded to time-triggered validated surveys and ecological momentary assessments to report on a complex set of health behaviours and outcomes. Similarly, educators' reported on substance misuse and mental health school policies and programs. Multivariable logistic regression modeling and mediation analyses were employed. RESULTS: 412 youth provided data on substance misuse and suicidal ideation. Cannabis use and other factors such as bullying, other illicit drug use, and youth who identified as females or other gender were associated with increased suicidal ideation. However, school policies and programs for substance misuse prevention did not mediate the association between Cannabis use and suicidal ideation. CONCLUSIONS: In the digital age, it is critical to reimagine the role of schools in health policy interventions. Digital citizen science not only provides an opportunity to democratize school policymaking and implementation processes, but also provides a voice to vulnerable youth.

Web-based citizen science as a tool in conservation research: A case study of prey delivery by the Lesser Spotted Eagle.

Citizen science is increasingly contributing to ecology and conservation research, mostly by the extensive collection of field data. Although webcams attract numerous observers, they have been underused in this respect. We used prey delivery records deposited by citizen scientists in an internet forum linked to webcams to explore the diet composition and food provisioning in a forest-dwelling raptor of conservation concern, the Lesser Spotted Eagle (Clanga pomarina). Four pairs were studied throughout the breeding season. Most of the identified prey items were mammals (62.1%), followed by frogs (31.2%), birds (6.6%) and fish (0.1%). Among mammals, voles accounted for 84.6%, moles 12.1%, water voles 2.4% and weasels 0.4%. Frogs were the most frequently detected prey item in the spring, with a slight increase towards the end of the season, the proportion of mammals increased during the breeding season, and birds were hunted mostly in the middle of the breeding season. However, exact temporal patterns differed between nests. The food delivery rate of males increased over time but decreased somewhat before fledging the young. Females started hunting in mid-summer and their rapidly increasing effort compensated for a reduced male hunting intensity. The data collected by citizen scientists via webcams reflected the general patterns detected in earlier studies, supporting the reliability of crowd-sourced web-based data collection in avian foraging ecology.

A community-powered search of machine learning strategy space to find NMR property prediction models.

The rise of machine learning (ML) has created an explosion in the potential strategies for using data to make scientific predictions. For physical scientists wishing to apply ML strategies to a particular domain, it can be difficult to assess in advance what strategy to adopt within a vast space of possibilities. Here we outline the results of an online community-powered effort to swarm search the space of ML strategies and develop algorithms for predicting atomic-pairwise nuclear magnetic resonance (NMR) properties in molecules. Using an open-source dataset, we worked with Kaggle to design and host a 3-month competition which received 47,800 ML model predictions from 2,700 teams in 84 countries. Within 3 weeks, the Kaggle community produced models with comparable accuracy to our best previously published 'in-house' efforts. A meta-ensemble model constructed as a linear combination of the top predictions has a prediction accuracy which exceeds that of any individual model, 7-19x better than our previous state-of-the-art. The results highlight the potential of transformer architectures for predicting quantum mechanical (QM) molecular properties.

Children and young people's contributions to public involvement and engagement activities in health-related research: A scoping review.

BACKGROUND: There has been an increasing interest in how children and young people can be involved in patient and public involvement and engagement (PPIE) in health research. However, relatively little robust evidence exists about which children and young people are reported as being involved or excluded from PPIE; the methods reported as being used to involve them in PPIE; and the reasons presented for their involvement in PPIE and what happens as a result. We performed a scoping review to identify, synthesise and present what is known from the literature about patient and public involvement and engagement activities with children and young people in health related research. METHODS: Relevant studies were identified by searches in Scopus, Medline, CINAHL, Cochrane and PsychInfo databases, and hand checking of reference lists and grey literature. An adapted version of the Guidance for Reporting Involvement of Patients and the Public (GRIPP2) was used as a framework to collate the data. Two reviewers independently screened articles and decisions were consensually made. MAIN FINDINGS: A total of 9805 references were identified (after duplicates were removed) through the literature search, of which 233 full-text articles were assessed for eligibility. Forty studies published between 2000 and 2019 were included in the review. The review reveals ambiguities in the quality of reporting of PPIE with children with clear reporting on demographics and health conditions. The review found that children and young people were commonly involved in multiple stages of research but there was also significant variation in the level at which children and young people were involved in PPIE. Evaluation of the impact of children and young people's involvement in PPIE was limited. CONCLUSIONS: Consultation, engagement and participation can all offer children and young people worthwhile ways of contributing to research with the level, purpose and impact of involvement determined by the children and young people themselves. However, careful decisions need to be made to ensure that it is suited to the context, setting and focus so that the desired PPIE impacts are achieved. Improvements should be made to the evaluation and reporting of PPIE in research. This will help researchers and funders to better understand the benefits, challenges and impact of PPIE with children and young people on health research.

Citizen science and niche modeling to track and forecast the expansion of the brown marmorated stinkbug Halyomorpha halys (Stål, 1855).

Halyomorpha halys (Stål, 1855), the Brown Marmorated StinkBug (BMSB) is a highly successful invasive species native to eastern Asia that managed to spread into North America and Europe in recent decades. We set up a citizen science survey to monitor BMSB expansion in France in 2012 and analyzed the data it yielded between 2012 and 2019 to examine the local expansion of the insect. These data were gathered with occurrences form various sources (GBIF, literature) to calibrate a species niche model and assess potential current BMSB range. We evaluated the potential changes to the BMSB range due to climate change by projecting the model according to 6 global circulation models (GCM) and the shared socio-economic pathways SSP245 in two time periods 2021-2040 and 2041-2060. Citizen science allowed to track BMSB expansion in France and provided information about its phenology and its habitat preferences. The model highlighted the potential for further range expansion in Europe and illustrated the impact of climate change. These results could help managing the current BMSB invasion and the framework of this survey could contribute to a better preparedness of phytosanitary authorities either for the BMSB or other invasive pests.

Citizen science with colour blindness: A case study on the Forel-Ule scale.

Many citizen science projects depend on colour vision. Examples include classification of soil or water types and biological monitoring. However, up to 1 in 11 participants are colour blind. We simulate the impact of various forms of colour blindness on measurements with the Forel-Ule scale, which is used to measure water colour by eye with a 21-colour scale. Colour blindness decreases the median discriminability between Forel-Ule colours by up to 33% and makes several colour pairs essentially indistinguishable. This reduces the precision and accuracy of citizen science data and the motivation of participants. These issues can be addressed by including uncertainty estimates in data entry forms and discussing colour blindness in training materials. These conclusions and recommendations apply to colour-based citizen science in general, including other classification and monitoring activities. Being inclusive of the colour blind increases both the social and scientific impact of citizen science.