Virridy Home | Lume — Water Quality Sensing Water for Carbon

Performance & Research

Validated sensor performance, calibration data, and the peer-reviewed science behind continuous microbial water quality monitoring.

What is Tryptophan-Like Fluorescence?

Tryptophan-like fluorescence (TLF) is an optical water quality parameter centered on excitation/emission wavelengths of approximately 275/340 nm. It reflects concentrations of compounds with fluorescence characteristics similar to the amino acid tryptophan, which is associated with microbial activity and fecal contamination.

A positive relationship between TLF intensity and fecal indicator bacteria (FIB), particularly E. coli, has been demonstrated across groundwater, surface water, estuarine, and urban watershed contexts on multiple continents. This makes TLF a promising real-time proxy for microbial contamination risk—complementing or replacing traditional culture-based methods that require 24–48 hours for results.

Lume Innovations

The Virridy Lume addresses many of the limitations identified in the TLF literature by coupling optical TLF sensing with machine learning models that account for environmental confounders. Rather than relying on static TLF thresholds, the Lume's algorithm adapts to site-specific conditions.

60s

Instant Results

The Lume returns a TLF reading in 60 seconds, compared to 24–48 hours for traditional culture-based methods.

< 0.1 ppb

Detection Limit

The Lume's minimum detection limit for tryptophan dissolved in deionized water.

1 CFU

Regulatory Threshold Classification

The Lume's binary classification at the 1 CFU/100 mL drinking water regulatory threshold yields 91% overall accuracy (Cohen's kappa = 0.82).

>94%

Categorical Accuracy

Site-specific calibrated categorical classifications of microbial contamination risk.

75%+

Linear Accuracy

Out-of-the-box accuracy on a continuous scale across 0–1,000 CFU/100 mL.

7%

Log-Scale Error

Mean absolute percentage error in log-transformed concentration space vs. culture-based methods.

Key Innovations

Machine learning quantification: Unlike earlier TLF sensors that report relative fluorescent units, the Lume quantifies actual E. coli concentrations using gradient-boosted decision tree models that capture nonlinear patterns in noisy sensor data. The ML model was validated across freshwater and coastal environments, including saline settings where enterococci are the regulatory indicator.

Multi-parameter correction: Built-in turbidity and temperature sensors allow the algorithm to correct for environmental interference that confounds raw TLF readings.

Drinking water performance: Binary classification at regulatory thresholds (1 and 10 CFU/100 mL) achieves 91–92% overall accuracy with Cohen's kappa of 0.82–0.84, indicating strong agreement with laboratory classifications.

Ocean transferability: In initial ocean deployments, the Lume achieved over 76% categorical accuracy using just six training samples, demonstrating transferability across microbial indicators and water matrices.

Patented Technology

Adaptive contamination detection: The Lume uses machine learning to learn normal conditions and trigger contamination alerts based on learned patterns rather than fixed thresholds. (US Patent 11,506,606 B2 — Bedell, Fankhauser, Sharpe, Wilson & Thomas)

Automated system-state classification: Time-series data from water infrastructure sensors are analyzed to classify system states and support operational decisions without manual inspection or rule-based logic. (US Patent 11,507,861 B2 — Wilson, Coyle, Thomas & Croshere)

Performance and Calibration

Drinking Water

The Lume has been validated for drinking water monitoring across chlorinated and unchlorinated supplies. Binary classification at regulatory thresholds of 1 and 10 CFU/100 mL yields 91–92% overall accuracy with Cohen's kappa of 0.82–0.84, indicating strong agreement between sensor and laboratory classifications with minimal bias toward either class. The sensor also detects chlorine residual presence with 85% accuracy.

Confusion matrices for binary classification of water quality using sensor predictions versus laboratory-observed E. coli concentrations at two regulatory thresholds: (a) 1 CFU/100 mL and (b) 10 CFU/100 mL. Both thresholds yielded high overall accuracy (0.91 and 0.92), balanced accuracy (0.91 and 0.92), and Cohen's kappa (0.82 and 0.84).
Chlorinated supply monitoring: scatter of predicted vs observed E. coli and confusion matrix of chlorine residual
Left: scatter of predicted versus laboratory-observed E. coli on logarithmic axes, separated by pre- and post-chlorinated samples. Right: binary classification of chlorine residual presence (0 vs > 0 ppm) showing 85% overall accuracy, balanced accuracy of 85%, and Cohen's kappa of 0.70.

Natural Waters

The Lume algorithm has been developed and extensively validated against Colilert® E. coli in freshwater systems. The platform has also been successfully deployed in saline coastal environments, where regulatory compliance is based on enterococci. In these initial ocean deployments, Lume achieved over 76% categorical accuracy using just six training samples.

Boulder Creek test dataset: comparison of model-estimated and laboratory-measured E. coli concentrations. Over 75% of predictions fall within the analytical uncertainty bounds of the Colilert reference method, with 7% MAPE in log-transformed space.
Laboratory validation against Colilert: categorical classification into three management-relevant bins (<10, 10–100, >100 MPN/100 mL). Accuracy 0.91, balanced accuracy 0.85, Cohen's kappa 0.60.
Global dataset: temporally structured cross-validation. RMSE was 0.58 (training) and 0.59 log units (test), with MAPE of 22.49% (training) and 18.84% (test).
Seine River, Paris: binary classification of E. coli contamination (<900 vs >900 CFU/100 mL) on held-out test data (20% of samples). The model achieved 96.8% accuracy and 94% balanced accuracy using three TLF sensors deployed along the Seine.

Four-Panel Method Comparison

How does the Lume compare to both EPA-approved laboratory methods? We analyzed paired samples measured by Colilert (IDEXX), membrane filtration (MF), and the Lume sensor across regression, Bland-Altman agreement, and categorical classification frameworks. The fourth panel additionally refits the Lume regression directly against MF, isolating the contribution of reference-method choice from sensor performance.

Four-panel method comparison: MF vs Colilert, Lume vs Colilert, Lume vs MF (Colilert-trained), Lume vs MF (MF-trained)

Key Findings

R² = 0.881

Lume vs. Colilert

The Colilert-trained Lume achieves stronger agreement with Colilert (R² = 0.881, n = 209) than the two EPA-approved methods achieve with each other (R² = 0.572, n = 153).

R² = 0.872

Lume vs. MF (MF-trained)

When refit against MF as the training target, the Lume achieves equivalent quantitative performance (R² = 0.872, n = 303) — showing the sensor is method-agnostic.

κ = 0.88

Categorical Agreement

Against Colilert, the Lume achieves “almost perfect” agreement (κ = 0.88), versus only “fair” agreement between the two lab methods (κ = 0.40).

The headline result: Sensor-to-reference agreement is bounded by reference-method reproducibility, not by Lume hardware. When the Colilert-trained Lume is tested against MF (a reference it was never trained on), R² drops to 0.514 — almost exactly the disagreement between the two lab methods themselves. When the Lume is instead calibrated directly against MF, performance jumps back to R² ≈ 0.87. Whichever culture method you hand the Lume as truth, it fits that method as well as or better than the two EPA-approved methods fit each other.

Why TLF Matters

Microbial water quality is most frequently assessed using E. coli as a risk indicator. However, relying exclusively on culture-based E. coli measurement is limiting: it is slow, expensive, requires trained personnel, and captures only a single point in time. Risk assessments can be significantly improved by integrating TLF as a complementary, continuously monitored parameter.

Advantages Over Traditional Methods

No Reagents Required

TLF sensing is purely optical. No consumables, reagents, or lab infrastructure needed for each measurement.

Higher Precision

In Kenya groundwater studies, TLF sampling showed 14% average relative percent difference between duplicates, compared to ≥26% for culture-based methods.

Continuous Monitoring

Sensors can operate autonomously for months, capturing short-duration contamination events that weekly grab samples miss.

More Precautionary

Research in Malawi showed TLF indicates broader contamination risk than microbial culturing, making it a useful high-level screening tool.

Dramatically Lower Cost

For the cost of a single lab-processed grab sample, a TLF sensor can deliver thousands of in-situ microbial estimates over weeks to months of continuous deployment.

Cross-Environment Versatility

TLF has been validated across groundwater, freshwater rivers, chlorinated piped systems, and saline coastal environments on multiple continents, with studies spanning Kenya, Malawi, the US, and France.

Known Limitations

TLF cannot be used as a direct proxy for E. coli on an individual sample basis. The TLF signal can be influenced by dissolved organic carbon (DOC), humic-like fluorescence (HLF), turbidity, and temperature. Standardization of TLF thresholds associated with different risk levels remains an active area of research. Performance is best in groundwater, which typically has low DOC, consistent temperature, and negligible turbidity.

Virridy Publications

Knopp, W., Klaus, J., Wilson, D., Vlah, M.J., Ross, M.R.V., Thomas, E. (2026)
EarthArXiv preprint
Virridy / Lume V1.2
Demaree, Fankhauser, Cole, Ross, Thomas (2026)
ES&T Water
Virridy
Fankhauser, K., Macharia, D., Coyle, J., Kathuni, S., McNally, A., Slinski, K., Thomas, E. (2022)
Science of the Total Environment
Virridy
Bedell, E.; Sharpe, T.; Purvis, T.; Brown, J.; Thomas, E. (2020)
Sustainability, 12, 3768
Virridy
Thomas, E., Brown, J. (2021)
Environmental Science & Technology, 55(1)
Virridy

Virridy Patents

DMRV Fusion Networks
Thomas et al., US Patent-Pending (2023)
Family: Drinking Water Treatment, In-Stream Water Quality, Wildfire Impact, Water Quality Prediction & Variability Attribution
Alarm Threshold Microbial Fluorimeter and Methods
Bedell, E., Fankhauser, K., Sharpe, T., Wilson D., Thomas, E.
US Patent 11,506,606 B2 — Nov 22, 2022
Machine Learning Techniques for Improved Water Service Delivery
Wilson, D., Coyle, J., Thomas, E., Croshere, S.
US Patent 11,507,861 B2 — Nov 22, 2022
System and Methods for Operating a Microcomputer in Sleep-Mode and Awake-Mode
Fleming, M., Spiller, K., Thomas, E.
US Patent 10,564,701 — Feb 18, 2020
Distributed Low-Power Monitoring System
Thomas, E., Fleming, M.
US Patent 9,077,783 B2 — July 7, 2015

TLF Research Timeline

2015

Baker et al. demonstrate in-situ tryptophan-like fluorescence as a real-time indicator of faecal contamination in drinking water supplies. (Water Research)

2018

Sorensen et al. evaluate TLF as a measure of microbial contamination risk in Kenyan groundwater across 37 water points. (Sci. Total Environ.)

2018

Khamis et al. establish real-time detection of faecally contaminated drinking water with TLF, defining threshold values. (Sci. Total Environ.)

2020

Bedell, Sharpe, Purvis, Brown & Thomas demonstrate low-cost TLF sensor concepts for fecal exposure detection. (Sustainability) • Virridy

2020

Nowicki et al. conduct a nine-month monitoring program in Malawi, finding TLF is a more precautionary risk indicator. (Sci. Total Environ.)

2022

Bedell, Harmon, Fankhauser, Shivers & Thomas field-validate a continuous in-situ fluorescence sensor coupled with ML. 83% accuracy. (Water Research) • Virridy

2025

Multiple groups evaluate TLF for combined sewer overflow watersheds and estuarine systems. (Sci. Total Environ.; ACS ES&T Water)

2026

Knopp, Klaus, Wilson et al. advance continuous in-situ quantification with Lume V1.2 sensor design and multi-site validation. (EarthArXiv) • Virridy

2026

Demaree, Fankhauser, Cole, Ross & Thomas develop sensor-informed predictive models for TOC and nutrients on the Upper Yampa River. (ES&T Water) • Virridy

Key External TLF Research

Baker, A., Cumberland, S., Bradley, C., et al. (2015)
Water Research
Foundational TLF
Sorensen, J.P.R., et al. (2018)
Science of the Total Environment, 622–623, 1236–1244
Groundwater
Khamis, K., et al. (2018)
Science of the Total Environment
Threshold Definition
Nowicki, S., et al. (2020)
Science of the Total Environment, 750, 141284
Screening Tool
Science of the Total Environment (2025)
Science of the Total Environment
Urban Watershed