PhD Project: AI-Driven Soil Insight and Precision Management Using Weed Indicators

Wetsus, in collaboration with Leiden University, is offering a PhD research position focused on utilizing weed plant communities as practical bio-indicators of soil status. The project integrates high-resolution optical sensing, plant trait analysis, soil measurements, and interpretable machine learning to create transparent frameworks for soil characterization and field heterogeneity mapping. The successful candidate will design and conduct interdisciplinary experimentation, perform field campaigns, analyze complex soil and spectral datasets, and construct predictive spatial decision-support tools. Applicants are expected to work collaboratively across institutional boundaries and contribute actively to advancing sustainable agricultural practices.

• Develop an AI-enabled framework linking weed species composition and functional traits to soil properties and agroecosystem outcomes
• Extract quantitative plant traits from spectral and high-resolution imaging data
• Analyze soil physicochemical properties and microbiome datasets
• Construct and validate predictive models that infer soil conditions from plant indicators
• Apply interpretable machine learning techniques to quantify feature importance and evaluate trait-soil interactions
• Conduct interdisciplinary experimentation and field campaigns for data collection
• Investigate plant-soil feedback processes to forecast crop performance, disease risk, and environmental stress
• Build spatial decision-support tools to help farmers estimate soil variability through weed observations