Meet the Lume

Get in touch to learn more about the Lume!

Got Poop? Find out if you're drinking or swimming in contaminated water.

The Lume is the first single-unit fluorimetric sensor for continuous microbial contamination monitoring. Its integrated power and data transmission reduce deployment and maintenance costs while delivering higher sensitivity and accuracy than other sensors or traditional sampling methods.

Continuous, Real-Time Microbial Water Quality Monitoring

Public health and pollution-response decisions depend on timely, spatially resolved information. Traditional culture-based sampling typically delivers results 24–48 hours after collection and is often too sparse to capture short-lived or localized contamination events. As a result, many contamination pulses remain undetected, limiting the effectiveness of advisories, mitigation efforts, and operational responses. Lume addresses this gap by providing continuous data that reflect actual conditions as they change.

Lume directly measures tryptophan-like fluorescence and applies data-driven modeling to estimate microbial contamination risk in near real time. Each sensor operates autonomously and transmits data via cellular or satellite networks to a secure cloud platform, where results are available through dashboards and APIs. For the cost of a single grab sample, Lume can deliver thousands of in-situ microbial estimates, dramatically improving temporal coverage between laboratory measurements.


Proven Performance for Microbial Risk Assessment

Field and laboratory evaluations demonstrate that Lume provides reliable quantitative and categorical estimates of microbial contamination across environmentally relevant concentration ranges. Across multiple independently deployed sensors, model-estimated E. coli concentrations closely align with laboratory reference methods over approximately three orders of magnitude. Agreement is strongest at moderate-to-high concentrations that drive public health risk, with consistent performance observed across sensors, sites, and hydrologic conditions.

At very low concentrations, increased uncertainty reflects known limitations of both optical measurements and culture-based enumeration methods, reinforcing Lume’s role as a real-time screening and decision-support tool rather than a replacement for laboratory confirmation.

Out-of-the-box performance can achieve at least 75% accuracy on a continuous, linear scale across 0-1,000 CFU/100 mL compared to culture based methods, while site-specific calibrated categorical classifications can exceed 90% prediction accuracy. This level of performance minimizes the likelihood of missing meaningful contamination events while avoiding unnecessary alarms near advisory thresholds.


What Lume Enables

Continuous microbial data from Lume allow organizations to move from reactive to proactive water quality management. By capturing rapid changes that occur between laboratory samples, Lume supports earlier detection of contamination events, improved situational awareness during storms and infrastructure failures, and more confident decision-making.

Organizations use Lume to detect contamination as it occurs, support same-day recreational water advisories, continuously screen source and receiving waters between lab analyses, prioritize confirmatory sampling, and reduce uncertainty between sampling campaigns. These capabilities support more timely and transparent communication with stakeholders and the public.


Real-World Applications

Lume is deployed across a range of monitoring contexts, including drinking water source protection, wastewater discharge monitoring, and recreational water management. Typical applications include monitoring piped systems, private and community wells, filtration and disinfection processes, treated effluent and receiving waters, urban stormwater and combined sewer overflow systems, and agricultural return flows. In recreational settings such as rivers, beaches, parks, and marinas, Lume supports public-facing dashboards, automated alerts, and adaptive management of high-use areas.


Built on Science. Ready for Scale.

Lume builds on peer-reviewed research and multi-site field validation to address the limitations of traditional microbial monitoring approaches. By combining optical sensing with adaptive data modeling, Lume maintains performance under changing environmental conditions where static thresholds and infrequent sampling fall short.

Whether protecting drinking water sources or managing recreational waters, Lume provides the confidence to act faster, earlier, and with better information.

IMG_4258

The Virridy Lume is a sensitive, continuous, in-situ, remotely reporting tryptophan-like fluorescence sensor for semi-quantification of fecal contamination as E. coli.

Why a Lume Array Beats Grab Samples

An array provides the temporal and spatial coverage that single grab samples cannot. By measuring every few minutes, arrays capture short-duration events—storm pulses, combined sewer overflows, irrigation returns—that a weekly schedule typically misses. Placing sensors to bracket reaches, confluences, and outfalls adds spatial resolution, allowing teams to localize hotspots and rank likely sources. The result is higher decision accuracy for advisories and source identification because you’re combining many observations across time and space rather than relying on a single point measurement. Operationally, arrays reduce routine logistics and lab spend while freeing staff for targeted investigations, and they enable rapid outcome verification—quantifying the effect of BMPs, repairs, or green infrastructure in days to weeks instead of seasons.

For drinking water systems, the Lume can monitor drinking water safety in chlorinated, piped water supplies as well as distributed water systems such as household or community filters and storage tanks. 

Standard deployment:  10+ units, $200/month per site, minimum 12-month contracts. 

Monthly subscription includes: device lease, connectivity, secure data hosting, dashboard/API, fleet health monitoring, remote updates, onboarding and siting support.

Start an Array Today

Alex Johnson, Chief Strategy Officer
[email protected] • +1-503-504-9668

Play Video

Hardware and Analytics

  • TLF wavelengths detect E. coli. Additional wavelengths can be configured for Cl-A for algae detection and FDOM for organic matter.
  • Turbidity sensor allows NTU quantification as well as controls for effect on fluorescence.
  • Temperature sensor as data and correction.
  • GPS coordinates.
  • Outputs quantification of E. coli levels and not simply relative fluorescent units.
  • Does not require regular calibration and cleaning.
  • Designed for continuous in-situ use.
  • Retails for considerably lower cost than the competition. 
  • Remotely programmable sampling between 30 seconds and 24 hours. 
  • Up to one-year battery life between recharge (on hourly sampling and 24 hour reporting). 
  • Option for wired or solar powered. 
  • Single integrated hardware. No bulky external power supply or telemetry units. 
  • Machine learning analytics supporting microbial quantification. 
  • Protected online dashboard and API. 

Implementation Design

  • Array design: Joint siting plan to bracket sources and decision points.
  • Deployment: Mount, power, connect—data streams within minutes.
  • Operations: Alerts for exceedances/events; periodic siting optimization as patterns emerge.
  • Verification: Use continuous data streams to validate fixes and document performance.

Data Governance and Integration

  • Role-based dashboard access; export to existing data management platforms via API.
  • Audit trail on device health, uptime, and data quality checks.
  • Documentation package available for SOPs, siting rationales, and QA/QC procedures.

The Lume is a fully integrated, internet connected (cellular and satellite) sensor solution. The sensor head measures tryptophan-like fluorescence, turbidity and temperature. Sampling can be remotely programmed for between 30 seconds and 24 hours, and reporting between 5 minutes and several days. With 24-hour reporting, the battery will last up to a year on a single charge. The sensor head can be cleaned with a hand-twist removal of the cover. The battery can be charged with solar or wall power. The antenna can be internal to the Lume, an external whip (as pictured) or on a wire.

Performance and Calibration

Comparison of model-estimated and laboratory-measured E. coli concentrations for a river deployment. Predictions show strong agreement with Colilert measurements across the range of approximately 10–400~CFU/100 mL. Approximately 75% of predictions fall within the analytical uncertainty bounds of the Colilert reference method, indicating that most differences between predicted and observed values are consistent with expected assay variability.

Confusion matrix summarizing categorical classification performance of the Lume during bench-scale validation. Laboratory E. coli concentrations were grouped into three management-relevant bins (<10, 10–100, and >100 MPN per 100 mL). Correct classifications are concentrated along the diagonal, with misclassifications predominantly occurring between adjacent categories. Overall accuracy was 0.91, with balanced accuracy of 0.77 and Cohen’s kappa of 0.58.

Comparison of model-estimated and laboratory-measured E. coli concentrations across a global dataset using a temporally structured evaluation. The most recent 20% of observations were withheld as an independent holdout set, with earlier data used for model training and validation, to assess forward-in-time generalization. Predicted concentrations show strong agreement with laboratory measurements across more than four orders of magnitude, with comparable performance across training, validation, and held-out data. Mean absolute percentage error (MAPE) remained below approximately 21% across all splits. Agreement is strongest at moderate to high concentrations, with greater dispersion at low concentrations reflecting reduced fluorescence signal-to-noise ratios and the inherent uncertainty of culture-based enumeration methods.

Patents

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

Papers

Knopp, W., Klaus, J., Wilson, D., Vlah, M., Ross, M., Thomas, E., Advancing continuous in-situ quantification of microbial contamination in environmental waters using tryptophan-like fluorescence - Sensor design and validation, preprint, 2026.

Fankhauser, K., Macharia D., et al. Estimating groundwater use and demand in arid Kenya through assimilation of satellite data and in-situ sensors with machine learning toward drought early action," Science of the Total Environment, 2022.

Thomas, E., Wilson, D., Kathuni, S., Libey A., Chintalpati, P., Coyle, J. “A contribution to drought resilience in East Africa through groundwater pump management informed by ensemble machine learning, in-situ instrumentation and remote sensing”, Science of The Total Environment, 2021.

Thomas, E., Brown, J., “Using Feedback to Improve Accountability in Global Environmental Health and Engineering, Environmental Science and Technology, 2020.

Thomas, E., et al., The Drought Resilience Impact Platform (DRIP): Improving Water Security Through Actionable Water Management Insights, Frontiers in Climate, V2. A6. 2020.

Bedell, E.; Sharpe, T.; Purvis, T.; Brown, J.; Thomas, E. Demonstration of Tryptophan-Like Fluorescence Sensor Concepts for Fecal Exposure Detection in Drinking Water in Remote and Resource Constrained SettingsSustainability 2020, 12, 3768.

Evan Thomas, Elizabeth Jordan, Karl Linden, Beshah Mogesse, Tamene Hailu, Hussein Jirma, Patrick Thomson, Johanna Koehler, Greg Collins, Reducing drought emergencies in the Horn of Africa, Science of The Total Environment, Volume 727, 2020, 138772, ISSN 0048-9697,https://doi.org/10.1016/j.scitotenv.2020.138772.