Can sensor technologies help to safeguard the future of beekeeping in South Africa?
A blog by James Godber, a Frontier Tech Hub Implementing Partner.
This post captures learning from the first Sprint of our pilot — ‘Harnessing sensor technologies to improve beekeeping productivity in South Africa’.
Despite contributing considerably to the economy and providing employment, beekeeper numbers in South Africa are declining and the sector is failing to attract new entrants. To help address this challenge, we are investigating how the internet-of-things (IoT) could be used to provide beekeepers with real-time data from in-hive sensors.
The aim of the pilot is to adapt current UK technology to improve beekeeping practices, increase productivity and ultimately create a viable income opportunity for underserved groups in the KwaZulu Natal and Western Cape Provinces. The technology has been implemented in Europe, so the pilot will explore how it can be adapted and tailored to the South African context. KwaZulu Natal and Western Cape Provinces were chosen as its where the African honeybee (Apis mellifera scutellate) and Capensis bee (Apis mellifera capensis) resides, respectively. By gathering data from both provinces, it will help shed light on whether there is any variation in the optimal behaviours and hive conditions for different species in different regions of the country, meaning that tailored insights could be provided to beekeepers in different locations.
In addition to this, sub-optimal pollination presents a major threat to biodiversity and food production, so creating more jobs and supporting the growth of the beekeeping sector has the potential to generate transformational impacts in the areas of conservation and food security.
This work is being delivered by an innovative partnership including AgriSound, pollination management technologists, Crop Health and Protection (CHAP), a UK Agri-Tech Innovation Centre, and Cropimpi, a South Africa-based R&D organisation. The pilot is supported by the Frontier Tech Hub, an initiative funded by UK aid from the Foreign, Commonwealth and Development Office (FCDO).
About the technology
AgriSound’s hive monitoring systems are designed to provide users with completely new insights into the status and behaviour of their bee colonies.
Small, wireless sensors (see Figure 1A) are placed inside each hive. These collect data on multiple important metrics: sound / colony acoustics, temperature and humidity. In addition, the sensors monitor light to detect if/when a hive has been opened, and includes an accelerometer, to detect if a hive has been moved. This is important as theft of hives has been identified as a major problem in South Africa.
The data from the sensors is transmitted via Bluetooth to a battery-powered Gateway Unit (see Figure 1B). The Gateway Unit then transmits the data via a 3G/4G mobile network to a User Dashboard (see Figure 1C) which can be viewed on a phone, tablet or personal computer.
Figure 1: (A) The in-hive sensor unit is wireless with on-board power and takes seconds to install. (B) The Gateway Unit collects data wirelessly from the in-hive sensors — ideally it is placed 20m from the hives with clear line of sight. (C) The User Dashboard enables beekeepers to view their hive data and insights to support decision-making.
As well as monitoring the colonies, this technology provides an opportunity to share in the combined data and knowledge from AgriSound’s global network of monitored hives. AgriSound continuously analyse the aggregated bee data to identify new behaviours or health indicators, which they then add to the User Dashboard for the benefit of all of their customers. They also provide email updates with hints and tips on how to get the best from the monitors, and articles describing the latest research into bee health and behaviour. Access to this information will allow beekeepers in this project to continuously improve their practices. The impacts of this are not yet fully recognised, however, and will be reviewed at the end of the project.
Sprint 1: Kicking off our first phase of work
For our first sprint we decided to initially focus on KwaZulu Natal province, where the Africa honeybee is present.
For Sprint 1, we set out to explore three critical questions:
1. Would it be possible to identify a diverse user group of 25 people with an interest in beekeeping to take part in the pilot? This is important to understand whether there are any barriers to adoption for different end users and also to inform learnings about the business viability of the AgriSound technology among different user groups.
2. Could IoT sensors be installed in 100 hives, and successfully begin transmitting data, especially in more rural areas?
3. Could online training support users to learn the basics of beekeeping and how to begin using the dashboard to capture insights on their hives?
To answer these questions, the team tapped into networks across the province to identify potential participants, installed and tested sensors in a range of different locations, and developed online training materials for the pilot user group.
Sprint 1: What we achieved
Over a period of 3 months, 25 participants with diverse backgrounds and from different locations across KwaZulu Natal province were identified to take part in the pilot.
The aim was to capture a wide demographic including different ages, genders, business sizes, literacy levels and income brackets in order to maximise learning around barriers to adoption (e.g. computer literacy), accessibility of the technology, as well as market demand. Participant ages ranged from 19 to 80 years old, there was a 60% male to 40% female gender split across the group, and around 12% of participants identified themselves as having a disability.
Figure 2: Participant demographics (A) Age; (B) Gender; and (C) Disability
A series of online training modules were developed and delivered to the participants, covering topics including components and installation, hive health and tips for beekeeping. The training content was informed by insights captured as part of a participant onboarding survey, which included questions around specific beekeeping skills, prior knowledge and experience (see Figure 3), as well as how participants generate income from beekeeping.
Figure 3: Percentage of participants that (A) have previous experience; (B) Know about queen replacement; (C) Merging of colonies; and (D) Ventilation of hives.
Figure 4: Profitability
After viewing the online training content, participants were asked to complete a quiz. This was used to determine how effective the training was and demonstrated a 100% completion rate with an average score of 80%. The data from both the onboarding survey and the quiz will act as a useful baseline, and follow-up surveys will be conducted in the coming months to determine if the devices have increased participant hive production and business profitability.
In total, 100 AgriSound in-hive sensors were deployed to the 25 beekeepers, across different locations in KwaZulu Natal province. This involved first testing 3G/4G connectivity in the locations, then verifying the IoT devices were functioning and transmitting data, before installing the wireless sensors and Gateway Units.
The yellow dots in Figure 5 showcase where the devices were deployed in KwaZulu Natal, while the blue dots demonstrate where further devices will be deployed in the Western Cape Province in Sprint 2.
Figure 5: In-hive sensor deployment across KwaZulu Natal (KZN)
Figure 6: Project team members from AgriSound, Cropimpi and CHAP deploying in-hive sensors in KwaZulu Natal (KZN)
Lessons Learned and Next Steps
During this first sprint, the team was able to validate several critical assumptions that are key to the overall success of the solution. For example, there appears to be demand for improving beekeeping practices from across a range of different user groups and geographies. In addition, 3G/4G connectivity is typically sufficient to enable the IoT devices to function in different locations including rural settings.
The team also generated important learning on several aspects of the device installation and user training processes, which will support further iteration and testing in the next sprint:
In a small number of instances, battery or connectivity issues were detected with the in-hive devices. This highlighted the importance of testing and trialling the devices before deployment to ensure good connectivity and ensure installation can be completed as efficiently as possible.
Once devices were installed, some participants needed some additional technical support regarding the user interface. Going forward, we will ensure sufficient training is provided to reflect this learning.
The team also learned the importance of tailoring training materials and content to end users in order to maximise effectiveness and uptake of the training. This was gathered during the feedback session. As such, content will be iterated to include basic beekeeping information (e.g. hive health, temperature etc.), as well as video interviews with experts, all offered in a variety of different local languages along with subtitles.
In Sprint 1 we chose to focus on KwaZulu Natal due to time and budget constraints.
In Sprint 2, the focus will be on continuing to gather data from the deployed in-hive sensor devices in KwaZulu Natal on topics such as bee behaviours, hive conditions, productivity, practices, income and species based algorithms. In parallel, we will also be identifying, deploying devices and providing training to new participant beekeepers across the Western Cape Province (WCP), with some modifications to the processes and materials, building on the learning described above from Sprint 1.
Expanding the pilot to this second region will provide further learning opportunities because there is a different species of bee in WCP (Capensis bees, compared with African Honeybees in KZN, respectively). This will shed light on whether there is any variation in the optimal behaviours and hive conditions for different species in different regions of the country, meaning that tailored insights could be provided to beekeepers in different locations.
The team have also created a new questionnaire ahead of Sprint 2 to capture feedback on the use of the technology. Data will continue to be gathered regarding profitability and harvesting during follow up interviews.
Finally, the project team will also be organising multiple dissemination events during Sprint 2 for a wide range of stakeholders to showcase and exhibit the results of the project. These events will take place in Cape Town and also at the Honey Festival in KwaZulu Natal. This will include a showcase of the technology, an overview of the project, initial key findings (e.g., behaviours, hive conditions, productivity, practices, income, species-based algorithms), case studies from beekeeper participants and an opportunity to identify future potential collaborators and investors. We plan to conduct a feedback questionnaire after the dissemination events to help inform the development of the business case (e.g. usability and affordability).
Further details:
If you are interested in learning more about this project, please contact CHAP at enquiries@chap-solutions.co.uk or visit www.chap-solutions.co.uk
About AgriSound:
AgriSound Limited was launched in January 2020 and is based in York. The company was founded by Casey Woodward, an experienced agri-tech innovation expert, with an aim to bring modern technology to insect monitoring. AgriSound has created special smart sensors and listening devices to monitor insects across a range of environments including beekeeping, farming, educational and corporate sites, with the aim of deploying sensors across the planet to transform how people monitor insect activity and make a positive impact on biodiversity.
Since its establishment, AgriSound has partnered with a number of companies and projects, including M&S, Tesco, WWF, Dyson Farming, Innocent Drinks, National Trust Scotland and Royal Horticultural Society to spread the message worldwide and is continually looking for opportunities to branch out further.
For more information, visit the AgriSound website: https://www.agrisound.io/
Instagram: https://www.instagram.com/agrisoundtech/
Twitter: https://twitter.com/AgriSoundTech
LinkedIn: https://www.linkedin.com/company/agrisound/
About Cropimpi:
Cropimpi is an Agricultural Research and Development Company based in South Africa. Cropimpi specialises crop protection trials, demonstration sites for agricultural products, viability projects, business establishment, business development and training. They have assisted many international companies to enter the South African crop protection market by assisting with independent trial work for registration purposes. As part of their social responsibility Cropimpi has an enterprise development section that specialises in teaching rural farmers in their native language to farm sustainably to ensure food security. These charitable training sessions also showcase newer farming technologies like hydroponics for water conservation. Clients include Bayer, Villa, Farmers Agricare, Rolfes Agri and various smaller companies.
About CHAP:
Crop Health and Protection (CHAP), funded by Innovate UK, is one of four UK Agri-Tech Centres. CHAP’s vision is for UK Agri-Tech innovation and expertise to drive sustainable farming systems which deliver economic, environmental, and societal benefits across the globe. CHAP acts as a unique, independent nexus between UK government, researchers and industry, building innovation networks to identify and accelerate cutting-edge solutions to drive incremental, transformative and disruptive changes in sustainable crop productivity.
For more information, contact Senior International Business Development Manager, Dr Jenna Ross OBE — jenna.ross@chap-solutions.co.uk
If you’d like to dig in further…
⛴️ Read about the pilot’s deployment of AgriSound sensors in the KwaZulu Natal province — “Buzzworthy success: first phase of international project paves the way for future of beekeeping in South Africa”
