Join the Meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision.

Corteva Agriscience is a leading global agricultural solutions company based on deep integration of technology and science. Corteva’s core innovation drivers are proprietary seed products and differentiated crop protection, and has sights set on the next horizon of value from gene editing, biologicals, and advanced decision science.

A central theme of innovation at Corteva is the transformative role of artificial intelligence across the entire R&D pipeline. AI has already delivered an increase in the speed of time to discovery and significantly improved development timelines, and manufacturing productivity. Corteva is expanding its capabilities, from leveraging GenAI for creating regulatory documents to an AI-powered agronomy tool for its sales team.

This focus on innovation underpins a robust pipeline of new seed and crop protection products. The overarching goal is to leverage the latest technological capabilities to accelerate AI-guided discovery and fully embed data-driven solutions from the laboratory to the farm.

Artificial intelligence and machine learning are reshaping agricultural research by enabling new approaches to plant phenotyping and precision agriculture. This talk presents recent advances in 3D plant reconstruction using Neural Radiance Fields (NeRFs) and related learning-based methods for generating high-fidelity visualizations of plant growth. These techniques support scalable, real-time analysis of complex plant structures, offering efficient alternatives to traditional, equipment-intensive approaches. The session will also highlight how immersive Virtual Reality (VR) environments, combined with AI-driven reconstructions, create new opportunities for collaborative research, allowing distributed teams to virtually analyze, monitor, and interact with crops. By integrating machine learning with visualization and interaction technologies, this work advances precision agriculture and lowers barriers to access, providing both researchers and practitioners with flexible, data-driven tools for breeding, monitoring, and decision-making.

The emergence of multi-modal AI foundation models presents a paradigm shift opportunity for cyber-agricultural systems by enabling the integration of diverse data types such as imagery, text, and time-series signals. This talk will explore the core concepts, recent advancements, and domain-specific challenges in building and applying multi-modal models to agricultural problems. I will focus on a few of our recent success stories, driving progress in this space, with applications ranging from crop monitoring and yield prediction to sustainable crop management. I will also discuss some practical considerations such as data curation, computational requirements, and model evaluation in the context of Ag foundation models.

Anomaly detection is transforming manufacturing and surveillance, but what about agriculture? Can AI actually detect plant diseases and pest damage early enough to make a difference?

This talk demonstrates how anomaly detection identifies and localizes crop problems using coffee leaf health as our primary example. We'll start with the foundational theory, then examine how these models detect rust and miner damage in leaf imagery.

The session includes a comprehensive hands-on workflow using the open-source FiftyOne computer vision toolkit, covering dataset curation, patch extraction, model training, and result visualization. You'll gain both theoretical understanding of anomaly detection in computer vision and practical experience applying these techniques to agricultural challenges and other domains.