LWV23117 INnovations for Smart Plant Insect Resistance Evaluation and testing (INSPIRE) (TS-02-226-004)

The quantification of pests is crucial for pest monitoring, crop protection, plant breeding, and variety testing. Traditional methods for testing insect resistance in plants are manual and categorical, leading to subjectivity and errors. Manual phenotyping for insect resistance is time-consuming and costly. Although automated phenotyping has improved the evaluation of plant traits, quantifying plant-insect resistance traits remains challenging. This includes assessing plant morphological traits like damage response, oviposition, survival rates, developmental stages, and physical defensive structures such as trichomes. Current methods often rely on categorical data, limiting the depth of analysis and requiring trained personnel to ensure data quality.

Artificial intelligence (AI) offers a solution by enabling rapid and objective data generation, enhancing plant selection and resistance analysis. AI can overcome the challenges of quantifying complex plant-insect interactions through image analysis, potentially improving pest management strategies. This project aims to develop phenotyping technologies using mobile phone imaging to enhance insect resistance testing. AI-based algorithms will be integrated with various image acquisition hardware setups to accelerate insect quantification and plant-insect resistance determination.

The data generated will be essential for exploring new insect resistance traits, testing biological control agent efficacy, plant selection, and diagnostics. Rapid phenotyping tools can significantly reduce labor costs and accelerate data acquisition and analysis, addressing insect-related challenges posed by climate change.

In conclusion, incorporating AI in phenotyping technologies can revolutionize pest management and plant breeding by providing efficient, accurate, and cost-effective solutions for insect resistance testing.