Jan Bauwens on Tackling Pest Challenges and Sustainability
STELAR is conducting a series of interviews to share insights and practical applications in AI and data-driven innovation. This interview explores how technologies like IoT and AI can enhance precision pest control while promoting sustainability. To understand this topic better, the STELAR project interviewed Jan Bauwens, an IoT Research Engineer at ILVO (Flanders Research Institute for Agriculture, Fisheries, and Food).
ILVO is a member of the OpenAgri project consortium, which aims to bridge the gap between the availability of Agricultural Digital Solutions (ADSs) and their adoption by EU farmers. Through initiatives like SIP-3, OpenAgri is exploring innovative approaches to precision pest control.
To discover how Jan’s work is contributing to these efforts and addressing important challenges in sustainable farming, continue reading.
Exploring Our Guest's Motivation and Background
Can you share a bit about your background and what inspired you to pursue a career in data science and technology, particularly in the agricultural sector?
My background is in the field of IoT, with a particular focus on wireless communication between constrained devices. This specialisation was also the core of my PhD research, where I explored efficient and reliable data exchange in resource-limited environments. Over the years, I have gained hands-on experience across the entire IoT ecosystem, from writing low-level firmware for edge devices to designing and managing the cloud infrastructure necessary for large-scale monitoring and control.
In the past year, I transitioned to a role as an IoT Research Engineer at ILVO. My previous company had an ongoing collaboration with ILVO, which introduced me to their work, but I had no prior experience in the agricultural sector. However, I quickly recognised the potential of IoT in precision farming. The ability to leverage real-time sensor data, optimise resource usage, and improve decision-making through connected technologies presented an exciting challenge – one where my expertise could make a meaningful impact.
OpenAgri SIP-3: Advancing AI-Driven Precision Pest Control
In the OpenAgri project, you have been involved in SIP-3, which focuses on precision pest control and sustainability. Can you elaborate on your role and the key challenges you are addressing?
At ILVO, we lead the SIP-3 pilot focusing on precision pest control and sustainability, specifically targeting the Colorado Potato Beetle, which poses significant challenges due to its rapid infestation and resistance to many pesticides. By deploying UAVs equipped with high-resolution RGB cameras, we collect detailed imagery that feeds into advanced AI models for accurate pest detection. The resulting prescription maps enable targeted interventions, such as Variable Rate Application, reducing chemical inputs and operational costs.
Additionally, the data generated helps farmers comply with monitoring, verification, and reporting requirements for CAP eco-schemes, as well as facilitates agrochemical registration processes. Through these efforts, ILVO aims to provide a robust, data-driven strategy that addresses the beetle’s threat while promoting sustainable agricultural practices in Flanders.
How do AI-driven models and sensor technologies help in detecting and preventing pest outbreaks more efficiently than traditional methods?
AI-driven models and sensor technologies can offer precise, timely insights into larval stages of the Colorado Potato Beetle. By analysing high-resolution imagery from a brief 20-minute drone flight, these systems can scan extensive areas efficiently and detect early infestations that might be missed through traditional scouting. This targeted detection allows for precise interventions, reducing the need for broad chemical applications and mitigating the risk of pesticide resistance.
Sustainability is one of several benefits of SIP-3. How do the AI-powered solutions in the project help reduce environmental impact while also maintaining high agricultural productivity?
The AI-powered solutions in SIP-3 focus on detecting and treating pest infestations at a highly localised level, rather than relying on broad, one-size-fits-all treatments. By analysing drone-captured imagery, the system can identify precisely where the larvae are present, enabling targeted pesticide application rather than spraying entire fields.
This significantly cuts down on chemical use and associated runoff risks, lessening environmental impact. At the same time, growers maintain robust yields because they can intervene promptly – preventing widespread damage – while preserving the ecological balance essential for long-term farm productivity.
AI and Data Science in Future Farming
Both OpenAgri and STELAR emphasise the power of data-driven solutions in agriculture. In your experience, what are the biggest opportunities and challenges in leveraging AI, machine learning, and sensor data for improving farming practices?
Data-driven solutions offer immense potential to optimise farming practices through real-time monitoring, predictive analytics, and more precise resource allocation. Access to robust datasets and advanced AI models can significantly improve yield predictions, pest detection, and climate adaptation strategies, all while reducing input costs and environmental impact.
However, these advantages come with notable challenges. Collecting high-quality, consistent data requires ongoing investment in technology infrastructure and training, which can be a hurdle for small-scale farms. Connectivity can also be a significant issue in rural areas, where limited internet access makes it harder to transmit and update large datasets in real time.
Data interoperability and privacy considerations demand thoughtful approaches to ensure different platforms work seamlessly while safeguarding sensitive information. Beyond the technical aspects, achieving broad adoption depends on demonstrating clear value and easing concerns around the time and learning required to integrate new tools into existing workflows.
Looking ahead, what do you see as the most promising advancements in AI and data science for sustainable agriculture, and how do you think they will shape precision farming in the next decade?
Emerging AI techniques, coupled with increasingly sophisticated sensor technologies, are set to transform precision farming over the coming decade. Enhanced computer vision solutions and edge computing capabilities will allow drones and autonomous field machinery to detect and address pest infestations or crop stress in near real time.
Meanwhile, advances in machine learning algorithms – especially for predictive analytics – will enable farmers to anticipate issues like drought, disease spread, or nutrient deficiencies before they escalate, improving both yields and sustainability. These innovations will be further supported by the growing adoption of Internet of Things (IoT) devices, which continuously collect granular data to refine models and drive more precise interventions.
As these tools become more accessible and user-friendly, they will help farmers of all sizes optimise inputs, reduce environmental impacts, and adapt more effectively to changing climate conditions, ultimately making agriculture more resilient, productive, and resource-efficient. Additionally, a key challenge in this domain is translating the vast amounts of data – originating from diverse sources – into a format that is both accessible and actionable for farmers and their advisors. Many end-users lack formal IT training, making it crucial to present complex insights in an intuitive way.
To address this, we leverage Large Language Models (LLMs) and AI agents to process and expose data in a more understandable manner. By integrating these technologies, we would empower users to interpret information effectively and make informed decisions that best suit their specific environments, ultimately enhancing efficiency and sustainability in agriculture.
Conclusion
This interview highlights how AI, IoT, and data-driven solutions are influencing the future of precision pest control and sustainable farming. Through initiatives like OpenAgri’s SIP-3, researchers are developing targeted, efficient strategies that reduce chemical use, improve pest detection, and support regulatory compliance. However, widespread adoption depends on addressing challenges such as data interoperability, connectivity, and ease of use for farmers.
As advancements in AI and sensor technologies continue, making these tools more accessible and practical will be essential for ensuring long-term agricultural resilience. To stay updated on innovative approaches in smart farming, follow our Blog and LinkedIn page.
