IoT in Agriculture Conference | EPA 2026 Call for Papers

Earth Precision Agriculture

IoT in Agriculture Conference Track

Bridge the silos of proprietary networks and build the intelligent, secure, and interoperable IoT ecosystems, driving the next generation of smart farming

About the IoT in Agriculture Conference Track

The IoT in Agriculture Conference Track invites researchers to submit papers on the Internet of Things, AIoT, edge computing, sensor networks, and cybersecurity in smart farming. The conference takes place August 10–14, 2026, in Calgary, Canada.

The Internet of Things (IoT) and AI track at EPA 2026 is dedicated to the foundational networks, intelligent algorithms, and secure architectures that make smart farming possible. As precision agriculture increasingly depends on heterogeneous networks of connected devices, from soil moisture sensors and UAVs to edge gateways and cloud analytics platforms, the integration of Artificial Intelligence (AIoT) has become critical for real-time decision making.

This track provides a rigorous platform for researchers, engineers, and policymakers to share cutting-edge contributions that address the fragmentation of proprietary agri-IoT silos and the challenges of deploying AI at the edge. We convene experts working in TinyML, federated learning, geospatial IoT standards, cybersecurity, and energy-harvesting sensor networks. The track emphasizes how intelligent, secure, and scalable architectures collectively generate richer, more actionable insights across the entire food value chain.

We invite submissions that explore a wide range of IoT, AI, and connected systems research, including but not limited to:

Interoperability, Standards, and Spatiotemporal Analytics

This sub-track focuses on frameworks, protocols, standards, and system integration approaches that support interoperable, transparent, and scalable agricultural IoT ecosystems. It emphasizes open architectures, reusable data models, and standards-based methods that enable seamless communication across sensors, platforms, and services.

Geospatial IoT Standards: Novel approaches to implementing and extending open geospatial standards for connecting IoT devices over the web, enabling location-aware architectures in agricultural deployments.
Interoperable Architectures for Agricultural IoT: Methods, frameworks, and system designs for linking sensors, devices, farm platforms, and cloud services into unified, vendor-neutral ecosystems that improve integration and long-term scalability.
Standardized Data Models and APIs for Smart Farming: Common schemas, metadata frameworks, ontologies, and service interfaces that enhance data exchange, interoperability, and reuse across agricultural information systems.

Artificial Intelligence of Things (AIoT) and Edge Intelligence

TinyML and On-Device AI for Agricultural Sensors: Deploying lightweight machine learning models directly on resource-constrained microcontrollers for real-time crop disease detection, pest identification, and microclimate analysis without cloud reliance.
Federated Learning for Privacy-Preserving Smart Farming: Collaborative machine learning approaches that train models across distributed farm edge devices while keeping raw agricultural data localized, ensuring farmer data privacy and sovereignty.
Large Language Models (LLMs) for IoT Data Interpretation: Integrating generative AI and LLMs with IoT sensor streams to provide conversational interfaces and explainable agronomic recommendations directly to farmers.
AI-Driven Predictive Maintenance for Farm Machinery: Utilizing IoT vibration, acoustic, and thermal sensors combined with deep learning to predict equipment failures in tractors, harvesters, and irrigation pumps before they occur.

IoT Security, Privacy, and Trust

Cybersecurity for Agricultural IoT Infrastructure: Novel intrusion detection systems, zero-trust architectures, and lightweight cryptographic protocols designed specifically to protect vulnerable rural sensor networks from cyberattacks.
Blockchain and Distributed Ledger Technology in Agri-Food IoT: Integration of IoT data with blockchain to ensure immutable, tamper-proof records, securing data from the sensor level through the supply chain for traceability and food safety applications.
Data Sovereignty and Governance in Agri-IoT: Exploration of policy, regulatory frameworks, and ownership challenges of agricultural data, including the impact of the EU's European Interoperability Framework for Smart Farming.

Connectivity, Energy, and Hardware Innovations

Energy Harvesting for Battery-Free Agricultural Sensors: Sustainable IoT solutions utilizing solar, kinetic, RF, or thermal energy harvesting to power remote field sensors, reducing maintenance costs and environmental impact (Green IoT).
LPWAN, Satellite IoT, and 6G for Rural Connectivity: Studies on foundational network layers (LoRaWAN, NB-IoT, LTE-M) and emerging LEO satellite IoT or 6G networks that facilitate reliable data exchange in remote, off-grid agricultural environments.
Underground and Underwater IoT Sensing: Development of specialized sensor networks for continuous root-zone soil health monitoring, groundwater quality assessment, and smart aquaculture applications.

Digital Twins, IoT, and Real-Time Farm Systems

This sub-track focuses on integrating IoT technologies with digital twin frameworks in agriculture. It emphasizes connected sensing infrastructures, real-time data synchronization, and intelligent system architectures that link physical farm environments with their virtual representations for monitoring, simulation, and decision support.

Agricultural Digital Twins Architecture: Architectures, frameworks, and IoT infrastructures required to build and maintain digital twins in agriculture, including the continuous synchronization of data between physical farm systems and their virtual representations.
Real-Time IoT Data Integration for Digital Twins: Methods and platforms for collecting, integrating, and managing real-time sensor, machine, and geospatial data streams that support digital twin operation, situational awareness, and decision-making.
IoT-Enabled Farm Monitoring and Simulation: Approaches for using connected devices, sensor networks, and dynamic agricultural data to model, monitor, and simulate interactions among crops, soils, weather, machinery, and livestock.