# Pesticide Detection

> Field-level residue screening for Diuron, MCPA, and related compounds - targeting EU MRL compliance verification for export-grade produce.

- Canonical URL: https://spectrify.ai/research-pipeline/pesticide-detection

- Sector: Sector 02 · Environmental & Industrial
- Status: Emails Sent
- Tags: NIR, Pesticides, MRL, EU Compliance, Food Safety

Pesticide maximum residue limits (MRLs) are among the leading causes of export rejections for Sri Lankan agricultural products in EU and Japanese markets. Diuron and MCPA are both regulated at very low MRL thresholds (0.05 mg/kg for tea in the EU) and are commonly detected in compliance failures. Current MRL testing requires full analytical chemistry laboratory infrastructure (LC-MS/MS), takes 5–10 business days, and costs significantly per sample - making routine pre-export screening economically impractical for small and medium exporters.

## What We've Established

### NIR for Pesticide Screening - State of Research

Direct NIR detection of pesticides at MRL-relevant concentrations (sub-ppm) in agricultural matrices is technically challenging and has been demonstrated only in controlled laboratory conditions, not at operational sensitivity thresholds. The more practical approach is using NIR as a first-pass triage tool: flagging samples for full LC-MS/MS analysis rather than replacing it. This screening application requires less sensitivity and is achievable with current NIR technology.

### Market Demand Confirmed

The EU's pesticide residue monitoring programme has resulted in over 20 documented rejections of Sri Lankan tea and spice consignments in the past three years. Exporters are actively seeking pre-shipment screening options. Initial outreach to three export-focused testing laboratories confirmed commercial interest in a rapid triage solution.

## Technical Approach

First-pass screening model: flag samples with spectral profiles deviating from a clean-sample reference distribution. This approach requires a large set of authenticated clean samples (negative controls) and deliberately contaminated samples at and above MRL thresholds. A collaborative data collection with a pesticide testing laboratory is the proposed path to generating a calibration dataset.

## Where We Stand

Initial contact has been made with potential laboratory collaboration partners. Awaiting confirmation of interest and discussion of data-sharing terms for reference sample preparation.

## Next Steps

- Confirm laboratory partnership for spiked sample preparation and reference LC-MS/MS analysis
- Define the screening sensitivity and specificity targets acceptable for a triage application
- Design a structured calibration dataset covering Diuron, MCPA, and the three most common co-detected compounds

## Related Projects

- [Asbestos Analysis](https://spectrify.ai/research-pipeline/asbestos-analysis) (Proposal Sent): Spectral identification of three asbestos fibre types - Chrysotile, Amosite, and Crocidolite - in field samples. Proposal submitted to industrial partner for site monitoring applications.
- [Black Pepper & Spices](https://spectrify.ai/research-pipeline/black-pepper-spices) (Early Exploration): Spectral signature mapping for black pepper and mixed spices - dataset acquisition phase. Adulteration detection and grade classification are primary targets.
- [Total Polyphenols (TPP)](https://spectrify.ai/research-pipeline/total-polyphenols-tpp) (Model Ready): Total polyphenol profiling for black tea - the leading proxy for antioxidant quality and a primary auction pricing signal.

[Research Pipeline](https://spectrify.ai/research-pipeline)