Measuring Neonicotinoid Pesticides in Tap Water

In an upcoming talk at the American Chemical Society Fall 2026 Meeting, which will take place from August 23^rd to the 27^th, Shiqing Cai, a researcher at the University of Wisconsin-Madison, will deliver a presentation titled, “Quantitative Analysis of Neonicotinoids in Tap Water Using Concentration-dependent SERS and Machine Learning.” Cai’s talk will describe a novel method that combines laser-based spectroscopy with machine learning (ML) to detect and measure neonicotinoid pesticides in tap water at concentrations far below levels typically captured by conventional testing.¹

What are some of the details surrounding Cai’s method?

Cai’s technique pairs surface-enhanced Raman spectroscopy (SERS) with a random forest ML model to quantify neonicotinoids, which are a class of systemic insecticides widely used in agriculture that has been repeatedly detected in water supplies.^1,2 These insecticides have drawn scrutiny from environmental and public health researchers over their persistence in water systems and potential ecological effects, including on pollinator populations.¹

This challenge formed the central focus of the study that Cai and the rest of the team pursued. The talk will outline the experimental procedure of this study and discuss what the results mean for future research in this area. In the study, water samples were mixed with citrate-coated gold nanoparticles and potassium sulfate, which is a combination that causes the nanoparticles to cluster into "hotspots" that amplify the Raman signal of target molecules.¹ The researchers tested the method across a concentration range spanning four orders of magnitude, from 10 micromolar down to 0.001 micromolar, to map how the spectral signal changes with concentration.¹

An important component to this study was that the team did not rely on a single characteristic peak for the analysis. Instead, Cai and the team built an automated workflow to detect and select the most informative peaks across the spectra before feeding those features into a ML model trained to predict concentration.¹ The model achieved a coefficient of determination (R²) of approximately 0.99 on both training and validation data, with a root mean square error of roughly 0.001 to 0.002 and a mean absolute error below 0.001.¹ This indicates the predictions closely tracked actual concentrations, including at the lowest, environmentally relevant levels tested.

What is the significance of the results?

Cai will explain during the presentation that the study helped address a persistent limitation of SERS-based detection: although the technique is highly sensitive, raw spectral signals do not scale linearly with analyte concentration, making quantification difficult without extensive calibration.¹ By training a model on concentration-dependent spectral patterns rather than a fixed calibration curve, the research team reported a method that generalizes across a wide concentration range in real water matrices, rather than idealized laboratory solutions.¹

For water utilities, environmental monitoring agencies and instrument makers, the approach points toward field-deployable testing that could flag neonicotinoid contamination faster and at lower thresholds than standard laboratory methods such as mass spectrometry (MS), which require more time, sample preparation, and specialized equipment.¹ Current regulatory monitoring for neonicotinoids in drinking water is limited in the United States, and low-cost, rapid detection tools could support more routine surveillance as regulatory and public attention to the chemicals grows.¹

What is the American Chemical Society Fall 2026 Meeting and what is the theme of this conference?

The ACS Fall 2026 Meeting will bring together analytical chemists, spectroscopists, researchers, and industry professionals to talk about the latest trends and advancements in analytical science. This meeting will mark the 150th anniversary of the organization.³ To celebrate this milestone, ACS has developed a symposium featuring four Nobel Laureates and built the conference program around the theme “Chemists Making History.”³

For more information about the upcoming conference, you can visit the ACS website.

References

1. Cai, S. Quantitative Analysis of Neonicotinoids in Tap Water Using Concentration-dependent SERS and Machine Learning. Presented at the American Chemical Society Fall 2026 Meeting, Chicago, Illinois, August 24, 2026. Available at: https://acs.digitellinc.com/live/37/page/1374?search=spectroscopy&tags=475&page=59&window-jn2mj2
2. Buszewski, B.; Bukowska, M.; Ligor, M.; Staneczko-Baranowaska, I. A Holistic Study of Neonicotinoids Neuroactive Insecticides—Properties, Applications, Occurrence, and Analysis. Environ. Sci. Pollut. Res. Int. 2019, 26 (34), 34723–34740. DOI: 10.1007/s11356-019-06114-w
3. Wetzel, W. Why Spectroscopists Should Attend the ACS Fall 2026 Conference. Spectroscopy Online, 2026. https://www.spectroscopyonline.com/view/why-spectroscopists-should-attend-the-acs-fall-2026-conference (accessed July 14, 2026).