Content uploaded by Julien Minet
Author content
All content in this area was uploaded by Julien Minet on Oct 06, 2017
Content may be subject to copyright.
A preview of the PDF is not available
Crowdsourcing for agricultural applications: A review of uses and opportunities for a farmsourcing approach
Abstract and Figures
Abstract Crowdsourcing, understood as outsourcing tasks or data collection by a large group of non-professionals, is increasingly used in scientific research and operational applications. In this paper, we reviewed crowdsourcing initiatives in agricultural science and farming activities and further discussed the particular characteristics of this approach in the field of agriculture. On-going crowdsourcing initiatives in agriculture were analysed and categorised according to their crowdsourcing component. We identified eight types of agricultural data and information that can be generated from crowdsourcing initiatives. Subsequently we described existing methods of quality control of the crowdsourced data. We analysed the profiles of potential contributors in crowdsourcing initiatives in agriculture, suggested ways for increasing farmers’ participation, and discussed the on-going initiatives in the light of their target beneficiaries. While crowdsourcing is reported to be an efficient way of collecting observations relevant to environmental monitoring and contributing to science in general, we pointed out that crowdsourcing applications in agriculture may be hampered by privacy issues and other barriers to participation. Close connections with the farming sector, including extension services and farm advisory companies, could leverage the potential of crowdsourcing for both agricultural research and farming applications. This paper coins the term of farmsourcing as a professional crowdsourcing strategy in farming activities and provides a source of recommendations and inspirations for future collaborative actions in agricultural crowdsourcing.
Figures - uploaded by Julien Minet
Author content
All figure content in this area was uploaded by Julien Minet
Content may be subject to copyright.
... In 2019, the Food Price Crowdsourcing in Africa (FPCA) initiative was launched by the JRC and collaborating institutions to curate commodity prices through volunteer submissions, beginning with a pilot implementation in northern Nigeria [21][22][23]. The crowdsourcing approach leverages "citizen science" principles, engaging volunteers (paid or unpaid) to submit data at regular or irregular intervals, which can then be aggregated across locations and time [24]. This method assumes that the diversity of volunteer contributors yields rich, minimally biased data, as submissions are decentralized and independent, offering a robust quasi-sampling of the population at scale [22,23]. ...
... AI-imputed and crowdsourced price data show strong agreeement with traditional price surveys Challenging perceptions: Crowdsourced price data and AI-imputed data as viable alternatives to the gold standard As efforts to apply crowdsourcing for high-frequency, large-volume data collection gain momentum [24,43], a common perception persists that citizen volunteers may not be able to submit data as credible as that from trained enumerators [17]. However, the strong relationship between conventional enumerator-submitted prices and crowdsourced prices challenges this notion, showing that high-frequency price datasets from citizens or market actors can be both useful and valid. ...
Continuous access to up-to-date food price data is crucial for monitoring food security and responding swiftly to emerging risks. However, in many food-insecure countries, price data is often delayed, lacks spatial detail, or is unavailable during crises when markets may become inaccessible, and rising prices can rapidly exacerbate hunger. Recent innovations, such as AI-driven data imputation and crowdsourcing, present new opportunities to generate continuous, localized price data. This paper evaluates the reliability of these approaches by comparing them to traditional enumerator-led data collection in northern Nigeria, a region affected by conflict, food insecurity, and data scarcity. The analysis examines crowdsourced prices for two staple food commodities, maize and rice, submitted daily by volunteers through a smartphone application over 36 months (2019–2021), and compares them with data collected concurrently by trained enumerators during the final eight months of 2021. Additionally, the crowdsourced dataset is compared to AI-imputed prices from the World Bank’s Real-Time Prices (RTP) database. Data from the alternative methods reflected similar price inflation trends during the COVID-19 pandemic. Pearson’s correlation coefficients indicate strong statistical agreement between crowdsourced and enumerator-collected prices (r = 0.94 for yellow and white maize, r = 0.96 for Indian rice, and r = 0.78 for Thailand rice). Furthermore, the crowdsourced data shows a high correlation with the AI-imputed prices (r = 0.99 for maize, and r = 0.94 for rice). The results from additional statistical tests of normality and paired means shows that the discrepancies between price datasets are consistent with measurement error rather than differences in actual price dynamics. Further tests of equivalence confirmed that enumerator and crowdsourced prices represent the same underlying market processes for specific commodity subtypes, and connotes that crowdsourced price data is a credible reference for validating AI-imputed estimates. The results support the use of AI imputation and crowdsourcing methods to improve price data collection and track market dynamics in near real time. These data innovations can be particularly valuable in areas that are underrepresented in national aggregate data due to limited monitoring capacity, and where high-frequency local data can aid targeted interventions.
... Moreover, ICT has proven instrumental in fostering communication and collaboration among farmers, extension workers, and other stakeholders [13]. Virtual forums, social media groups, and messaging apps enable knowledge sharing, peer-to-peer learning, and the formation of virtual communities of practice [14]. Furthermore, empirical evidence suggests a positive correlation between ICT adoption and increased agricultural productivity [15]. ...
... Int J Adv Appl Sci, Vol.14, No. 1, March 2025: 46-52 BIOGRAPHIES OF AUTHORS Chris Sugihono is a PhD student in the Extension and Development Communication Study Program at the Graduate School, Universitas Gadjah Mada (UGM). He currently works at the Indonesian Agency for Agricultural Instrument Standardization, Ministry of Agriculture. ...
The world's swift digitization has profoundly transformed how farmers and extension workers operate, learn, and communicate. This study explores how information and communication technologies (ICT) adoption transforms agricultural extension practices in North Maluku, Indonesia. Using a qualitative approach, the study gathered and analyzed data from fifteen extension workers through interviews, observation, documentation, and focus group discussions from November 2022 to March 2023. The findings reveal ICT adoption has transformed the extension workers’ strategies in five areas: i) coordination and collaboration, ii) digital learning, iii) virtual group dynamics, iv) promotion and mobilization, and v) online consultation and monitoring. However, ICT adoption has not replaced traditional extension methods, such as demonstration plots, field schools, and field trips. The use of ICT is not always in line with the deterministic view that technology automatically changes society. In contrast, recursive patterns in practice adaptation create complex dynamics in which extension workers' decisions continue to play a key role in the evolution of agricultural extension. These findings enrich practical and policy debates regarding harnessing ICT potential for enhanced agricultural extension in Indonesia. Additionally, they advance theoretical discussions on the merits of the technological determinism perspective in analyzing ICT utilization.
... It involves collecting raw measurements of environmental variables, noting geographical features, and recording visual observations. This collaborative approach allows for the gathering of diverse data from a large number of contributors, contributing to a better understanding of agricultural and environmental conditions [18]. Several crowdsourcing-related agricultural applications have been developed and utilized in various countries. ...
With the increase in urbanization and the growth of the economy, car ownership increases significantly, and at the same time demand for parking increases causing several issues like traffic congestion and resource wastage. There's a critical significance of accurate parking demand estimation in the context of urban planning, addressing those issues. It emphasizes the emerging role of crowdsourced data as a novel solution for more efficient and cost-effective parking demand estimation. This review discusses the benefits of crowdsourcing, including real-time data and minimal infrastructure requirements, while acknowledging challenges like data accuracy, user privacy, and potential biases. Furthermore, it provides a comprehensive overview of the subject matter and it suggests future directions for improvement, proposing the integration of advanced technologies like Google APIs and IoT to augment parking demand estimation models and address the limitations associated with crowdsourced data.
... Regarding agriculture research, CSOF involves new elements, based on new digital technologies, that were absent in former participatory research in agriculture ( Van de Gevel et al., 2020). They aim to help handling uncertainty by collecting large databases supporting a more efficient and effective scientific knowledge (see Ruck et al. (2024) for a review of approaches) but also by enabling knowledge production 'on the field', directly by farmers, thus supporting learning from participants (Couvet & Prevot, 2015;Minet et al., 2017;Ryan et al., 2018). Hence, this growing methodology claims to reconcile formal research with informal knowledge, thanks to studies based on farmer's observations and to knowledge production directly on the farms. ...
As for any innovation, integrating farmland biodiversity into agricultural practices is a complex process, leading to decisions made under uncertainty, due to the difficulty of foreseeing the consequences of decisions. This uncertainty comes under many different forms, depending among others on the type of environmental innovation in agriculture, in a continuum from Efficiency/Substitution‐Based Agriculture (ESBA) to Biodiversity‐Based Agriculture (BBA). To handle this uncertainty, new knowledge production tools, some of which rely on citizen science on farms (CSOF), are developed. They aim to support decision‐making by collecting large databases but also by enabling knowledge production ‘on the field’, directly by farmers. Yet, the ability of CSOF to actually meet these challenges has little been studied. It is now necessary to understand how new biodiversity knowledge production tools are designed and used.
Using a user‐centred approach, we analysed a CSOF monitoring scheme, the Farmland Biodiversity Observatory (FBO), wherein farmers monitored biodiversity in their fields (3558 fields, from 2011 to 2023, still ongoing). As insiders in the research group, and using an exploratory approach based on 32 interviews, we observed an operational limitation of the scientific knowledge produced, which fails at producing technical recommendations to protect biodiversity locally. While this led to a difficulty to offer prescriptive practices, some participants shifted to non‐prescriptive knowledge, that is, they accepted high uncertainty and used FBO to gain knowledge and navigate through this uncertainty.
As a theoretical result, we witnessed that shifting to high uncertainty due to the complexity of ecological processes consists in accepting a leap into the unknown. Farmers must trust the action of biodiversity, making themselves ‘vulnerable’ with respect to the possible responses of the ecosystems to a change in farming practices. We identified several factors likely to favour this trust towards biodiversity.
As a practical outcome, our results show that, to work with biodiversity, farmers must move from reduction and control of uncertainty to acceptance and reliance on trust towards biodiversity. The ensuing management recommendation is to favour a clinical and contextual production of knowledge, emerging from individual experience, over a controlled, standardised and statistical production, inherited from industrialization.
Read the free Plain Language Summary for this article on the Journal blog.
... For small farms, cost-effectiveness is essential, necessitating economical automation technologies and AI-powered mobile apps. Open-source platforms and governmental subsidies have facilitated the adoption of these advances by smallholders, yielding substantial returns on investment [69]. Extensive industrial farms may incorporate this technology into vast operations, focusing on economies of scale. ...
Agricultural sustainability is continually undermined by climate change, resource depletion, and the increasing worldwide need for food. Fundamental technologies, including automation, smart greenhouses, and artificial intelligence (AI), are changing modern agricultural methods by providing novel ways to improve sustainability in farming. This review study examines the significance of these technologies in advancing sustainable agricultural systems, particularly their effects on resource optimization, environmental conservation, and economic efficiency. Automation technologies, such as robots, drones, and autonomous vehicles, enhance farm management by enhancing efficiency and minimizing resource waste. Intelligent greenhouses, fitted with IoT sensors and temperature regulation systems, provide precise management of environmental conditions, therefore improving agricultural output while minimizing water and energy use. AI-driven technologies, including machine learning and predictive analytics, enhance crop health monitoring, pest management, and yield prediction, enabling data-informed decision-making. The research analyses the combination of various technologies, focusing their synergies in developing comprehensive smart agricultural systems that promote enduring sustainability. Despite the apparent promise, challenges like substantial initial investment, technological intricacy, and scalability persist. This review continues by addressing future directions, policy implications, and research requirements for promoting the use of these technologies to enhance global agricultural sustainability.
... In this manner, citizens, small farmers and different kinds of organizations can provide data for their own purposes, while contributing to public databases. Data, information and knowledge inputs collected by crowdsourcing may be categorized in eight groups: land-use data, soil data, weather data, crop phenology, data on pests and diseases, yield and data on vegetation status, prices, and general agricultural knowledge (Minet et al., 2017). ...
Digitalization, being one of the major drivers of change in the 21st century, has fundamentally altered the way the global economy and society thought to be developing. The digital transformation of agricultural systems will most certainly have effects on the creation of information and knowledge, the institutional environment and management, as well as relations between stakeholders, both private and public. Digitalization of public services in the agricultural sector is the part of a broader strategy of digital transformation of this economic activity, the expected outcome of which is the transition of traditional agriculture to agriculture 4.0 and digitalization of farms. Timely provision of appropriate information to farmers is essential to increase the efficiency and sustainability of small farms. Strengthening market activities, improving interaction with key stakeholders, better connecting agricultural producers and empowerment through access to information can be considered as the main benefits of ICT application in agriculture. However, critical factors for the success of digitalization of public services in agriculture, such as connectivity, usefulness of information content and the ability to make decisions based on information provided using ICT, affect the success of acceptance of changes, especially in developing countries.Digitalization, being one of the major drivers of change in the 21st century, has fundamentally altered the way the global economy and society thought to be developing. The digital transformation of agricultural systems will most certainly have effects on the creation of information and knowledge, the institutional environment and management, as well as relations between stakeholders, both private and public. Digitalization of public services in the agricultural sector is the part of a broader strategy of digital transformation of this economic activity, the expected outcome of which is the transition of traditional agriculture to agriculture 4.0 and digitalization of farms. Timely provision of appropriate information to farmers is essential to increase the efficiency and sustainability of small farms. Strengthening market activities, improving interaction with key stakeholders, better connecting agricultural producers and empowerment through access to information can be considered as the main benefits of ICT application in agriculture. However, critical factors for the success of digitalization of public services in agriculture, such as connectivity, usefulness of information content and the ability to make decisions based on information provided using ICT, affect the success of acceptance of changes, especially in developing countries.
... It involves collecting raw measurements of environmental variables, noting geographical features, and recording visual observations. This collaborative approach allows for the gathering of diverse data from a large number of contributors, contributing to a better understanding of agricultural and environmental conditions [18]. Several crowdsourcing-related agricultural applications have been developed and utilized in various countries. ...
With the increase in urbanization and the growth of the economy, car ownership increases significantly, and at the same time demand for parking increases causing several issues like traffic congestion and resource wastage. There's a critical significance of accurate parking demand estimation in the context of urban planning, addressing those issues. It emphasizes the emerging role of crowdsourced data as a novel solution for more efficient and cost-effective parking demand estimation. This review discusses the benefits of crowdsourcing, including real-time data and minimal infrastructure requirements, while acknowledging challenges like data accuracy, user privacy, and potential biases. Furthermore, it provides a comprehensive overview of the subject matter and it suggests future directions for improvement, proposing the integration of advanced technologies like Google APIs and IoT to augment parking demand estimation models and address the limitations associated with crowdsourced data.
... It involves collecting raw measurements of environmental variables, noting geographical features, and recording visual observations. This collaborative approach allows for the gathering of diverse data from a large number of contributors, contributing to a better understanding of agricultural and environmental conditions [18]. Several crowdsourcing-related agricultural applications have been developed and utilized in various countries. ...
With the increase in urbanization and the growth of the economy, car ownership increases significantly, and at the same time demand for parking increases causing several issues like traffic congestion and resource wastage. There’s a critical significance of accurate parking demand estimation in the context of urban planning, addressing those issues. It emphasizes the emerging role of crowdsourced data as a novel solution for more efficient and cost-effective parking demand estimation. This review discusses the benefits of crowdsourcing, including real-time data and minimal infrastructure requirements, while acknowledging challenges like data accuracy, user privacy, and potential biases. Furthermore, it provides a comprehensive overview of the subject matter and it suggests future directions for improvement, proposing the integration of advanced technologies like Google APIs and IoT to augment parking demand estimation models and address the limitations associated with crowdsourced data.
Social media has become a transformative force in agricultural extension, fostering real-time communication, peer-to-peer learning, and knowledge dissemination on an unprecedented scale. By leveraging platforms like WhatsApp, Facebook, YouTube, and Twitter, farmers are now able to connect with extension agents, policymakers, and researchers, breaking geographical and literacy barriers. These platforms enable access to information on crop management, pest control, weather forecasts, and market prices, offering real-time solutions that enhance decision-making and productivity. Through farmer-led groups and virtual communities, social media has democratized agricultural knowledge, promoting participatory learning and creating a sense of community. The role of analytics in social media-driven extension has further amplified its impact, allowing policymakers and stakeholders to track engagement, measure campaign outcomes, and refine strategies for greater outreach. Despite challenges such as limited connectivity, misinformation, and digital literacy gaps, social media's potential remains immense. Investments in broadband infrastructure, subsidized smartphones, and training programs can address barriers and ensure inclusivity for smallholder farmers and marginalized groups. Collaborative efforts among governments, private sectors, and NGOs can enhance content quality, moderation, and platform design, tailoring them to diverse linguistic and cultural needs. Emerging technologies such as artificial intelligence, augmented reality, and blockchain present opportunities to personalize advisories and create immersive learning experiences. By promoting gender-sensitive campaigns and incorporating indigenous knowledge, social media can further empower women farmers and preserve traditional practices.
Utilizing Information and Communication Technology (ICT) to grant farmers direct access to information, while also developing models tailored to the specific contexts of both public and private agricultural extension sectors, stands as a pivotal endeavor in modern agriculture. This study uses bibliometric analysis to identify key research areas in ICT-based extension and advisory services (EAS) and to understand patterns and trends within this domain. The Scopus database served as the primary tool for accessing publications, yielding a corpus of 525 articles spanning from 1999 onwards, subsequently analyzed through VOSviewer and R software. The findings unveil that the Sustainability journal claims the highest number of published articles, while the Agricultural Economics journal garners the most citations within this realm. Notably, Aker emerges as the most globally cited author with 405 citations, while China Agricultural University emerges as the institution with the highest publication count concerning ICT-based EAS. India emerges as a frontrunner with 446 publications, while publications originating from the USA receive the highest number of citations, reflecting the nation's substantial endeavors and investments in harnessing ICT for agricultural extension purposes. The co-occurrence analysis of all keywords emphasizes the primary focus of publications on e-agriculture and e-extension. Furthermore, the outcomes of co-citation analysis highlight The Journal of Agricultural Education and Extension as the most referenced journal, with 22 citations and a cumulative link strength of 266, indicative of its profound influence and recurrent citation alongside other scholarly journals. This study uncovers an escalating interest in this field, emphasizing its paramount importance in contemporary agricultural practices. Accordingly, these findings offer crucial insights for guiding future research and shaping evidence-based policies, thereby aiding researchers, policymakers, and practitioners in improving ICT-based EAS in agriculture.
Smart Farming is a development that emphasizes the use of information and communication technology in the cyber-physical farm management cycle. New technologies such as the Internet of Things and Cloud Computing are expected to leverage this development and introduce more robots and artificial intelligence in farming. This is encompassed by the phenomenon of Big Data, massive volumes of data with a wide variety that can be captured, analysed and used for decision-making. This review aims to gain insight into the state-of-the-art of Big Data applications in Smart Farming and identify the related socio-economic challenges to be addressed. Following a structured approach, a conceptual framework for analysis was developed that can also be used for future studies on this topic. The review shows that the scope of Big Data applications in Smart Farming goes beyond primary production; it is influencing the entire food supply chain. Big data are being used to provide predictive insights in farming operations, drive real-time operational decisions, and redesign business processes for game-changing business models. Several authors therefore suggest that Big Data will cause major shifts in roles and power relations among different players in current food supply chain networks. The landscape of stakeholders exhibits an interesting game between powerful tech companies, venture capitalists and often small start-ups and new entrants. At the same time there are several public institutions that publish open data, under the condition that the privacy of persons must be guaranteed. The future of Smart Farming may unravel in a continuum of two extreme scenarios: 1) closed, proprietary systems in which the farmer is part of a highly integrated food supply chain or 2) open, collaborative systems in which the farmer and every other stakeholder in the chain network is flexible in choosing business partners as well for the technology as for the food production side. The further development of data and application infrastructures (platforms and standards) and their institutional embedment will play a crucial role in the battle between these scenarios. From a socio-economic perspective, the authors propose to give research priority to organizational issues concerning governance issues and suitable business models for data sharing in different supply chain scenarios.
Collect Earth is a free and open source software for land monitoring developed by the Food and Agriculture Organization of the United Nations (FAO). Built on Google desktop and cloud computing technologies, Collect Earth facilitates access to multiple freely available archives of satellite imagery, including archives with very high spatial resolution imagery (Google Earth, Bing Maps) and those with very high temporal resolution imagery (e.g., Google Earth Engine, Google Earth Engine Code Editor). Collectively, these archives offer free access to an unparalleled amount of information on current and past land dynamics for any location in the world. Collect Earth draws upon these archives and the synergies of imagery of multiple resolutions to enable an innovative method for land monitoring that we present here: augmented visual interpretation. In this study, we provide a full overview of Collect Earth's structure and functionality, and we present the methodology used to undertake land monitoring through augmented visual interpretation. To illustrate the application of the tool and its customization potential, an example of land monitoring in Papua New Guinea (PNG) is presented. The PNG example demonstrates that Collect Earth is a comprehensive and user-friendly tool for land monitoring and that it has the potential to be used to assess land use, land use change, natural disasters, sustainable management of scarce resources and ecosystem functioning. By enabling non-remote sensing experts to assess more than 100 sites per day, we believe that Collect Earth can be used to rapidly and sustainably build capacity for land monitoring and to substantively improve our collective understanding of the world's land use and land cover.
Accurate landcover maps are fundamental to understanding socio-economic and environmental patterns and processes, but existing datasets contain substantial errors. Crowdsourcing map creation may substantially improve accuracy, but the quality and representativeness of crowdsourced data is hard to verify. We present an open-sourced platform, DIYlandcover, that systematically serves samples of high resolution imagery to an online job market, where workers delineate landcover features of interest. Worker mapping skill is frequently assessed, providing estimates of overall map accuracy and a basis for performance-based payments. An initial trial of DIYlandcover showed that novice workers delineated South African cropland with 91% accuracy, which exceeds current generation global landcover products, while capturing important field geometry data. Given worker payment costs, large area, wall-to-wall mapping may be cost prohibitive, but a potentially promising use of DIYlandcover is to iteratively train and test emerging computer vision algorithms adapted for landcover mapping.
With the ubiquity of advanced web technologies and location-sensing hand held devices, citizens regardless of their knowledge or expertise, are able to produce spatial information. This phenomenon is known as volunteered geographic information (VGI). During the past decade VGI has been used as a data source supporting a wide range of services, such as environmental monitoring, events reporting, human movement analysis, disaster management, etc. However, these volunteer-contributed data also come with varying quality. Reasons for this are: data is produced by heterogeneous contributors, using various technologies and tools, having different level of details and precision, serving heterogeneous purposes, and a lack of gatekeepers. Crowd-sourcing, social, and geographic approaches have been proposed and later followed to develop appropriate methods to assess the quality measures and indicators of VGI. In this article, we review various quality measures and indicators for selected types of VGI and existing quality assessment methods. As an outcome, the article presents a classification of VGI with current methods utilized to assess the quality of selected types of VGI. Through these findings, we introduce data mining as an additional approach for quality handling in VGI.
The integration of local agricultural knowledge deepens the understanding of complex phenomena such as the association between climate variability, crop yields and undernutrition. Participatory Sensing (PS) is a concept which enables laymen to easily gather geodata with standard low-cost mobile devices, offering new and efficient opportunities for agricultural monitoring. This study presents a methodological approach for crop height assessment based on PS. In-field crop height variations of a maize field in Heidelberg, Germany, are gathered with smartphones and handheld GPS devices by 19 participants. The comparison of crop height values measured by the participants to reference data based on terrestrial laser scanning (TLS) results in R2 = 0.63 for the handheld GPS devices and R2 = 0.24 for the smartphone-based approach. RMSE for the comparison between crop height models (CHM) derived from PS and TLS data is 10.45 cm (GPS devices) and 14.69 cm (smartphones). Furthermore, the results indicate that incorporating participants' cognitive abilities in the data collection process potentially improves the quality data captured with the PS approach. The proposed PS methods serve as a fundament to collect agricultural parameters on field-level by incorporating local people. Combined with other methods such as remote sensing, PS opens new perspectives to support agricultural development.
A key global 21st century challenge is to maximize agricultural production while minimizing use of resources such as land, water, and energy to meet rising demand for produce. To meet this challenge, while also adapting to climate change, agriculture will have to become more knowledge intensive and deploy smarter farming techniques. The intention of this study was to: (1) Highlight the opportunity for web-based knowledge exchange to increase farm productivity and thus contribute to achieving food and energy security, (2) Give some examples of online farming information services such as the “CROPROTECT” tool I am developing in the UK, the CABI “Plantwise” Knowledge Bank and the IRRI “Rice Doctor,” and (3) Consider lessons learnt so far. There are huge opportunities to facilitate knowledge exchange through online systems for farmers and people who advise farmers. CROPROTECT is interacting with users to determine priorities in terms of the pests, weeds, and diseases covered and is providing key information to assist with their management. Knowledge is a critical input for farming systems. Crop protection in particular is becoming more difficult due to evolution of pest resistance and changes in legislation. Up to date information can be made rapidly available and shared online through websites and smartphone Apps. Agricultural extension no longer relies solely on physical meetings and printed documents. The capacity to share information via the Internet is tremendous with its potential to reach a wide audience in the farming community, to provide rapid updates and to interact more with the users. However, in an era of information deluge, accessing relevant information and ensuring reliability are essential considerations. There is also a need to bring science and farming communities together to turn information into relevant farming knowledge.
This research introduces the notion of Volunteered Information Sensing (VGI Sensing) as the set of standards, methods and techniques required to streamline georeferenced contents published online by citizens into a timely, reliable and cost-effective source of Geoinformation for Earth Observation purposes.
VGI Sensing is proposed as an emerging sub-field of research at the conjunction of Geographic Information Science, Data Mining and (Web) Knowledge Discovery. It is expected to have many practical applications requiring pervasive and/or real-time geospatial data such as health epidemics, crisis management, environmental monitoring, crime analysis, or socio-economic studies.
After presenting background works and formulating research objectives in the Introduction, this thesis explores the information potential of VGI (Chapter 1) in the context of natural hazards management, then proposes a generic workflow for VGI Sensing (Chapter 2) – which is exemplified to a real-life use case. Technical optimisations of key steps of the VGI Sensing workflow are then studied in details (Chapter 3), and finally, the concept of VGI Sensing is presented in the wider perspective of the Digital Earth Nervous System (Chapter 4).
By doing so, it gives significant contribution to the sub-field of Geomatics that aims at converting information shared on the Internet by citizens as a reliable source of Earth Observation data, and opens perspectives for further research - which are discussed in the final chapter. An additional commentary is then proposed, addressing the questions related to the limitations and ethics of VGI Sensing.
