Machine learning-powered soil organism identification and sorting platform
A high-throughput identification and sorting platform that uses a large-bore flow cytometer with custom sensors and machine learning to count, sort, and identify soil organisms including nematodes, fungal spores, and microarthropods directly from raw soil samples at rates up to 1,000 organisms per minute.
Overview
This technology addresses a critical bottleneck in soil ecology and agricultural diagnostics by enabling rapid, automated identification and sorting of soil organisms directly from raw samples. Traditional manual identification of soil organisms is slow, labor-intensive, and requires specialized expertise. The platform combines a large-bore flow cytometer with a custom sensor suite and machine learning algorithms to process soil samples at industrial scale, identifying organisms to species level without culturing or extensive sample preparation.
The system has demonstrated the ability to identify live nematodes of 14 species with approximately 90% sensitivity and specificity, and has resolved, counted, and separated two species of fungal spores and select microarthropods under 500 micrometers in diameter. These capabilities make the platform relevant for soil health assessment, agricultural research, biodiversity monitoring, and ecosystem studies.
Technical specifications
Core capabilities:
- Large-bore flow cytometer captures high-resolution photographs of each soil organism
- Custom sensor suite generates over 8,000 data points per organism using laser-based detection
- Machine learning algorithms classify organisms to species level
- Processing rate of up to 1,000 organisms per minute
- Capability to physically sort and separate identified organisms for downstream analysis
- Validated performance on nematodes, fungal spores, and microarthropods
Key advantages:
- Eliminates need for manual microscopy and expert identification
- Works directly on raw soil samples with minimal preparation
- Provides both identification and physical separation of target organisms
- Scalable architecture suitable for diagnostic and research applications
Technology readiness level
The technology has been validated through prior laboratory work demonstrating accurate species-level identification of nematodes and separation of fungal spores and microarthropods. Current development efforts focus on expanding the suite of identifiable organisms, with priority on additional nematode species, and improving machine learning classification performance through a hybrid processing pipeline designed to reduce classification times while increasing accuracy. The team is seeking partnership to develop the platform into performant diagnostics at scale, indicating readiness for collaborative development toward commercial or field-deployable diagnostic systems.
About Cornell University
Cornell University is a comprehensive private, land-grant research university with campuses in Ithaca and New York City, combining significant scale with cross-disciplinary breadth. Industry connects through open-access user facilities and prototyping labs, pilot-scale testbeds, and a research and technology park that provide pathways from discovery to demonstration. A statewide extension network and integration with a major hospital system enable real-world deployment, while a graduate campus embedded in New York City’s tech corridor provides direct access to startups, venture investors, and corporate R&D teams. Research is supported by competitive federal funding from agencies such as the National Science Foundation, National Institutes of Health, the Department of Energy, and the U.S. Department of Agriculture. A dedicated technology transfer office streamlines IP management, licensing, startup formation, and corporate partnerships across campuses.
delivered to your inbox.