SDA-for-SDGs Keynote · University of Toronto · 2026

Measuring Global
Water Security.

Evan Thomas, PhD, PE, MPH, MBA
Professor, CU Boulder · Mortenson Center in Global Engineering & Resilience
CEO, Virridy Inc.
The Challenge

Water Quality Impairment at Scale

4B
People

drink microbially contaminated water

60%
of GDP

threatened by water insecurity

10%
of Emissions

half from water management, half from unmanaged human wastewater

50%
U.S. Rivers

fail Clean Water Act standards

Notes

Climate change is here — and the first thing most of us notice is what it's doing to our water. Dry places are becoming drier, with droughts driving crop failure, livestock death, and displacement. Wet places are becoming wetter, with flooding destroying communities and contaminating drinking water. Because of what we've done — through causing climate change and treating water as free — we can't count on water being where we need it, when we need it anymore.

Currently four billion people experience water stress. The United Nations projects that water insecurity will displace at least 700 million more people by 2030. By 2030 nearly five billion people will experience significant water stress because of climate change — and most of the time there is still plenty of water. The problem is we don't conserve and protect it so it's there when we need it most.

The Challenge · Global E. coli Data
10MObservations
180KSites
40Years
7Databases
Notes

Think of this map the way you think about the Earth at night seen from space — the bright spots show you where rich people live, not where people live. This water quality map is exactly the same. The dense clusters of measurement data show you where wealthy countries have invested in monitoring infrastructure. Over three billion people, nearly half the world's population, use firewood every day for cooking and staying warm. This is also where they live — and it's almost invisible on this map. These are the people facing the earliest and worst effects of climate change on their water, and they are almost entirely unmonitored.

Notes

This is how the global WASH sector has thought about clean water for fifty years. You raise money — from donors, governments, sometimes private capital. You buy hardware: water filters, hand pumps, cookstoves, solar systems, latrines. You hand it to families. You hope they use it. Outcome: better health. That's the conventional model — linear, one-shot, hope-based.

It is also why the global WASH sector has been struggling for twenty-five years. Hardware gets distributed; nobody knows if it works in practice; the next round of funding asks the same questions. The piece this picture is missing is what comes next.

Pillar 1 · From Visibility to Accountability
Notes

The big idea is to take the fast-growing world of climate finance — things like carbon credits — and turn it toward solving water problems. A carbon credit is a financial commodity worth about $20 today, representing a tonne of CO2 removed or not emitted. There's a multi-billion dollar market for carbon credits, and it's growing fast.

Carbon credits work because the atmosphere mixes — it really is legitimate to reduce emissions in one place to offset energy use in another. This hasn't been true for water. Save water in Colorado, it does nothing for Rwanda. But if you create a financial instrument that rewards water conservation in Colorado or water treatment in Rwanda, that credit becomes part of a liquid market. It can be bought and sold and create revenue that incentivizes the actions we all need to take. Monitoring closes the loop — you can only pay for outcomes you can measure.

The Lume in Action
Seine River · Paris
Pastoralist Boreholes · Kenya
Field Testing · Boulder Creek
In-Situ Monitoring · Bridge Deployment
Mortenson Center in Global Engineering — Overview

Global Mortality Among Children Under 5

Total deaths by cause, 1990–2021. Sources: IHME GBD 2021, UNICEF IGME 2024, WHO Global Health Estimates.

This chart shows the major causes of death in children under 5 from 1990 to 2021. The good news is that nearly every cause has declined substantially — lower respiratory infections dropped from over 10 million to under 3 million deaths. But notice malaria ticked back up recently, and the total is still nearly 5 million children per year. These are largely preventable deaths from causes we know how to address with existing technologies and interventions.

Extreme Poverty by Region

People living below $2.15/day (2017 PPP). Sub-Saharan Africa is the only region where absolute numbers are rising. Source: World Bank, 2024. By 2030, 9 in 10 people in extreme poverty will live in Sub-Saharan Africa.

This chart tells one of the most important stories in global health. East Asia, driven largely by China, saw an extraordinary decline in extreme poverty — from over a billion people to about 29 million. South Asia has also made remarkable progress. But Sub-Saharan Africa is the only region where the absolute number of people in extreme poverty is rising. By 2030, nine out of ten people living in extreme poverty will be in Sub-Saharan Africa. This is the geographic concentration that drives most of the disease burden we have been looking at.

Per Capita CO2 Emissions

High-income countries have the highest per capita emissions, while low-income countries with the greatest disease burden contribute the least.

Now look at who is causing climate change versus who is bearing the burden of disease. High-income countries have the highest per-capita CO2 emissions, while low-income countries with the greatest disease burden contribute the least. This is the equity dimension of climate and health — the populations least responsible for emissions are the most vulnerable to their health consequences, from heat stress to vector-borne disease expansion to food insecurity.

Death Rate from Diarrhoeal Diseases

Annual deaths per 100,000, all ages. Disease burden tracks fecal contamination — Sub-Saharan Africa and South Asia carry it. Source: IHME GBD via Our World in Data.

There is a direct relationship between wealth and health. The countries with the highest death rates from diarrhea — the DRC, Ethiopia, Kenya, Rwanda — are the same countries contributing the least to climate change and to the emissions that are making their water problems worse. It's basically the inverse of the CO2 emissions map. And climate change is making these problems worse. This is the regressive effect of capitalism — the people most harmed are the least responsible. Diarrhea caused by dirty drinking water kills over half a million children under five every year. These are preventable deaths.

Rwanda — Country Context

Key Indicators

  • Population: 14 million (2024)
  • GDP per capita: ~$800
  • Under-5 mortality: 38 per 1,000 live births
  • Over 80% rely on firewood as primary fuel
  • Most rural households drink untreated water

Study Location

Western Province, Rwanda — 96 sectors cluster-randomized, reaching 101,000 households with water filters and improved cookstoves.

Rwanda field Rwanda community
I have been working with Rwanda for 20 years with an incredibly talented and dedicated team of Rwandese and international professionals on water and climate projects. In Rwanda, there's too much water sometimes and the water is often dirty. Unsafe drinking water is still the number one cause of both illness and death among school-age children in Rwanda. Rwanda is a small, densely populated country with about 14 million people and a GDP per capita of roughly $800. Over 80% of the population relies on firewood for cooking, and most rural households drink untreated surface water. Under-5 mortality is 38 per 1,000 live births — dramatically better than 20 years ago but still 15 times higher than Norway. Our study was based in Western Province, where we cluster-randomized 96 sectors to reach 101,000 households.

Programme Implementation

Child with LifeStraw filter

LifeStraw Family 2.0 water filter in household

EcoZoom cookstove

EcoZoom Dura improved cookstove in use

Sensor monitoring

Electronic sensor monitoring deployment

Here you can see the three main components of the programme. On the left, the LifeStraw Family 2.0 water filter, which is a gravity-fed hollow fiber membrane filter that removes bacteria and parasites. In the middle, the EcoZoom Dura improved cookstove, designed to burn wood more efficiently and reduce smoke. And on the right, the electronic sensors we deployed to objectively monitor whether people were actually using these technologies. That third component turned out to be the most important contribution.
Community health worker training in Rwanda

Key Results — Tubeho Neza Trial

Health Outcomes (Children Under 5)

  • 29% reduction in 7-day prevalence of diarrhea
  • 25% reduction in acute respiratory infections
  • 97.5% reduction in fecal contamination of drinking water
  • 38% reduction in cryptosporidium seroconversion

Air Quality — A Cautionary Finding

  • Personal PM2.5 exposure remained unchanged despite improved cookstoves
  • Stove stacking: traditional fire use increased from 24% to 49% over study period

The Adherence Problem

  • Self-reported filter use: 67%
  • Sensor-detected filter use: 37%
  • Self-reported stove use: 84%
  • Sensor-detected stove use: 37%
  • Reported use declined: 75% → 68% → 65% across survey rounds

Economics

  • 5-year programme cost: ~$12 million
  • Estimated 5-year benefit: >$66 million
  • Fuelwood savings: 65,000 tons — enough to reverse regional deforestation

Sources: Kirby, Nagel et al. (2019) PLoS Medicine; Thomas et al. (2018) Lancet Planetary Health; Thomas (2019) The Conversation

Here are the headline results, and they tell a nuanced story. On the water side, we saw a 97.5% reduction in fecal contamination and a 29% reduction in childhood diarrhea. Those are strong results. But on the air quality side, personal PM2.5 exposure was unchanged despite the improved cookstoves, because of stove stacking. Households kept using their traditional fires alongside the new stoves. And the adherence data is perhaps the most important finding: self-reported filter use was 67%, but sensor-detected use was only 37%. People were telling us they were using the filter almost twice as much as they actually were. This gap fundamentally changed how I think about intervention evaluation.

Technology & Digital Monitoring

Water Filters

  • LifeStraw Family 2.0 household water filters
  • Significant microbiological effectiveness reducing E. coli contamination
  • Free distribution with carbon waiver for credit generation

Remote Sensing Innovation

  • Electronic sensors remotely transmitting usage data
  • Sensor-reported use was substantially lower than self-reported use
  • Demonstrated critical value of objective digital monitoring
  • Published in ACS Environmental Science & Technology

Carbon Credit Model

  • Pay-for-performance model funded by voluntary carbon credits
  • Health, livelihood, and environmental benefits substantially outweighed costs
  • Fuel savings and averted healthcare costs = largest economic gains
Sensor technology
The technology and monitoring story is really the engineering contribution of this project. The LifeStraw filters were highly effective at removing pathogens when used, which is the efficacy story. But the sensor data revealed a very different effectiveness story. We published these findings in ACS Environmental Science and Technology, and they demonstrated that self-reported data systematically overestimates use. The carbon credit model was also innovative because it created a pay-for-performance financing mechanism. Health and economic benefits substantially outweighed costs, with fuel savings and averted healthcare being the largest gains.
Liters Per Day · Observer Effect
Liters Per Day
Self-reported vs. sensor-measured water use
2 1 0
Survey
1.75 L
Known Sensor
0.85 L
Hidden Sensor
0.35 L
Water Pump · Functionality & Service Interval
Water Pump Functionality
& Service Interval
Sensor slide 1
Sensor slide 2
Sensor slide 3
Sensor slide 4
Amazi Rwanda portrait
DRIP Kenya portrait
Notes

In 2007, I started a company to get water treatment to families who relied on untreated water in Rwanda and Kenya. We were the first company to register with the United Nations to earn carbon credits for treating drinking water anywhere in the world. Some people boil their water; most people just drink dirty water. We earned carbon credits — and therefore revenue — by reducing demand for firewood used to boil water. That revenue paid for the water service on an ongoing basis and repaid investors.

These programs have so far reached over five million people with clean water, and mobilized private and public sector investments from venture capital, carbon credit buyers, NASA, and USAID of over $70 million, while generating over $100 million in returns for investors and as investment in communities. People are getting clean water in places where governments and donors aren't able to reach.

DRIP Kenya field photos

Forecasting Groundwater Demand from Space

69 IoT sensors + satellite data + 19-algorithm ML ensemble — Kenya ASALs. Science of the Total Environment 831 (2022) 154453.

Kenya ASAL study area showing 69 sensored NDMA boreholes and mean annual rainfall

Fig. 1 — 69 sensored NDMA boreholes (open circles) across 5 ASAL counties, 260,000 km². Mean annual CHIRPS rainfall shown.

69
IoT sensors
80%
peak accuracy
4-mo
forecast lead
2.5M
people tracked

Predicted probability of high demand (>75 L/p/d) — Jun–Sep 2021

4-panel map of predicted groundwater demand probability June-September 2021, Kenya ASALs

Fig. 3 — Red = high probability of demand exceeding 75 L/p/d; white/pale = low probability. Open circles = correct predictions; filled = incorrect. Overall accuracy 73–80%. Now adopted by FEWS NET & Kenya NDMA for drought early action.

This paper by Katie Fankhauser and colleagues, with Evan Thomas as corresponding author, answers a question that FEWS NET and the Kenya NDMA had been asking for years: where will rural groundwater demand exceed supply before a drought peaks? We deployed 69 IoT sensors — originally SweetSense, now Virridy hardware — across five arid counties in Kenya, covering 260,000 square kilometers. Over four years we accumulated 756 site-month observations of pump runtime and estimated per-capita water use. We then fused those observations with satellite rainfall, vegetation, and soil moisture data and trained an ensemble of 19 ML algorithms. The result is a gridded, 30-square-kilometer resolution forecast of groundwater use and demand at 1 to 4 month lead times. The map on the right shows June through September 2021 — the red areas are where the model predicted high demand. Open circles are correct predictions, filled circles are incorrect, and the overall accuracy ranges from 73 to 80 percent across those four months. During the 2021 drought the model identified 2.5 million people in high-demand areas. FEWS NET and NDMA now use these outputs for pre-positioning of emergency water trucking. The key insight is that a sparse sensor network — one sensor per 3,700 square kilometers — combined with satellite data and machine learning produces actionable early warning that no amount of manual field surveys could match.
DRIP · Drought Resilience Impact Platform · Kenya
57
Sites
42
Reporting
5
Counties
260K km²
Coverage
Site Status
Reporting
Inactive
Avg Daily Runtime by County — Past 30 Days
E. coli Monitoring — mWater Field Sampling
Loading…
Amazi Meza · School Safe Water Monitoring · Rwanda
432
Schools
410K
Students
8
Districts
347
WQ Samples
District
Burera
Rutsiro
Gisagara
Gakenke
Kamonyi
Nyagatare
Muhanga
Musanze
Students Served by District
E. coli Water Quality — 2023 Baseline (mWater)
Loading…
Sensor slide 9
Sensor slide 10
Sensor slide 11
Sensor slide 12
Boulder Creek · E. coli Storm Events · Spring 2026
5
Sensor Sites
3
Storm Events
1,986
Peak CFU/100mL
126
EPA Limit
Loading creek animation…
Discharge & Precipitation — Boulder Creek at Broadway
All BC Sensors — Continuous Fluorescence + E. coli Grabs
From Research to Product

The Lume Sensor
in the field.

Two decades of field research in low-income settings, now embedded in a commercial product. How continuous monitoring transforms the accountability loop into a sustainable business.

Virridy Inc.
CU Boulder Spin-out · 2022
thelume.ai · virridy.com
virridy.com
Our Solution

Global Water Security Solutions

Water sensor technology
💧

Lume Sensors

Three optical modes — TLF (E. coli), Chlorophyll-a (algae), FDOM (organics). 75%+ accuracy, >94% categorical. 1-year battery life.

Green energy carbon
🌱

Water for Carbon

Drinking water treatment, precision irrigation, and watershed restoration. Gold Standard, Verra & Regen certified. 29-49% diarrhea reduction.

Global network
🌍

Global Portfolio

10 active projects across 12 countries. IoT-verified impact — no self-reporting. 5.6x cost-benefit ratio across health, livelihood, and environment.

virridycarbon.com
Portfolio

High Integrity Water Projects Across Africa

thelume.ai
Technology

Meet the Lume

The first continuous, field-deployable E. coli proxy sensor — built on deep-UV fluorescence and on-device machine learning.

  • Deep-UV optical excitation at 280 nm targets tryptophan-like fluorescence — a direct proxy for fecal bacteria, not a surrogate of a surrogate
  • Three interchangeable modes: TLF (E. coli), Cl-A (algae/HABs), FDOM (dissolved organics) — same hardware, swapped optics
  • On-device ML anomaly detection learns site-specific baselines and flags contamination without fixed thresholds — US Patent 11,506,606 B2
  • 91–92% classification accuracy at regulatory thresholds; Cohen’s κ = 0.82–0.84 against Colilert reference method
  • No calibration required — optical design and ML together eliminate the drift-correction burden that has blocked continuous WQ sensing for decades

Bedell, Fankhauser, Sharpe, Wilson & Thomas — CU Boulder / Virridy

thelume.ai

Field Testing the Lume

Researchers deploying the Lume sensor in natural stream environments for real-time E. coli monitoring and validation studies.

thelume.ai
Virridy

Seine River, Paris

Virridy’s Lume sensors monitoring water quality for recreational swimming safety along the Seine River.

thelume.ai
Technology

Hardware & Analytics

Sensor Capabilities

  • TLF: E. coli & microbial contamination (280/350 nm)
  • Cl-A: algal biomass & bloom detection (470/680 nm)
  • FDOM: dissolved organics & nutrient loading (365/480 nm)
  • Integrated turbidity, temperature, GPS
  • No regular calibration or cleaning required

Operations

  • Sampling: 30 sec to 24 hours (remote config)
  • Battery: up to 1 year; solar or wall charging
  • Cellular & satellite connectivity
  • Single integrated unit — no external power or telemetry
  • ML quantification with protected dashboard & API

Economics

  • $200/month vs. competitors at $5K–$30K
  • 700+ data points/month/site
  • Hand-removable cover for tool-free field maintenance
  • Captures transient contamination events that weekly sampling misses
Lume v1.2 exploded technical view with labeled components
thelume.ai/research
Intelligence

Analytical Features

Lume sensor deployed in mountain stream

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

Machine learning code

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

Natural waterfall

Natural Waters Application

Gradient-boosted decision tree models achieving 75%+ accuracy across 0–1,000 CFU/100mL, >94% categorical accuracy with site calibration, and 7% MAPE (log-transformed).

thelume.ai/research
Performance

Drinking Water Classification

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.

Confusion matrices for binary classification of water quality using sensor predictions versus laboratory-observed E. coli concentrations at two regulatory thresholds.

thelume.ai/research
Performance

Chlorinated Supply Monitoring

The Lume detects chlorine residual presence in treated water supplies with 85% accuracy, distinguishing pre- and post-chlorinated samples.

Left: Predicted vs observed E. coli on log axes. Right: Binary classification of chlorine residual presence (accuracy 0.85, kappa 0.70).

thelume.ai/research
Performance

Natural Waters — Local Model

The Lume algorithm has been extensively validated against Colilert E. coli in freshwater systems. Over 75% of predictions fall within the analytical uncertainty bounds of the Colilert reference method, with 7% MAPE in log-transformed space.

Left: Boulder Creek test dataset. Right: Categorical classification into three management-relevant bins (<10, 10–100, >100 MPN/100 mL). Balanced accuracy 95%, Cohen's kappa 0.84.

thelume.ai/research
Performance

Natural Waters — Global Model

Temporally structured cross-validation across the global dataset. RMSE ranged from 0.55 (training) to 0.63 log units (test), with MAPE below 22% across both splits.

Left: Global dataset cross-validation. Right: Seine River, Paris — binary classification achieving 96.8% accuracy and 94% balanced accuracy using three TLF sensors.

thelume.ai
Development

Lume Development

⚙

Hardware Engineering

Internal and contracted expertise in IoT, signals, embedded systems, hardware design.

🧪

Analytical Science

Internal and contracted expertise in watershed AI/ML and front-end product development.

🏭

Manufacturing

Contract manufacturer established in China. 200 units produced, 60 sold as of March 2026.

🚚

Distribution

Internal through 2026; contracted thereafter.

📈

Sales & Applications

Extensive internal sales and research expertise.

🛡

Risk Management

Lume 1.1 traction will support positive margin on COGS in 2026 before further NRE investment.

thelume.ai
Market

Microbial Sensor Global Market

$5.57B

Global water quality sensor market in 2024, projected to reach $12.9B by 2033 (CAGR ~9%).

200K

Cl-A sensors sold in US in past 10 years. Annual market ~$100M. Microbial is the next frontier.

SensorDescriptionSetupEst. CostAccuracy
Virridy Lume Tryptophan sensor; ML model analysis Single, fully integrated IoT sensor $200/month/site 75%+ accuracy, >94% categorical
Proteus Sonde Multiparameter sonde Requires data logger, site-specific calibration $14K - $24K+ +/- 10 CFU/100mL
Chelsea UViLux Tryptophan, CDOM, BTEX, BOD Not specified ~$5,000 0.01 QSU sensitivity
YSI (Xylem) Chlorophyll only, no tryptophan Multiparameter sonde $4,985+ N/A for TLF
In Situ Inc. FDOM, CDOM, Cl-A, no tryptophan Multiparameter sonde + telemetry ~$10,000 N/A for TLF
virridycarbon.com
Business Model

Pricing Strategy

Competition sells for $5K - $30K one-time hardware cost. Virridy focuses on recurring revenue.

  • $557K Lume revenue YTD March 2026 (target exceeded); targeting $1M+ for full year
  • Target 50%+ margin on COGS
  • Convert from one-time sales to recurring subscriptions in 2026
  • Minimum 10+ units, 12-month contract
  • Includes: device lease, connectivity, cloud dashboard, API, fleet monitoring, firmware updates, onboarding support

Key Figures

$200
/month/unit
$1,200
COGS per unit

12-month minimum contract = 2x COGS

virridy.com

Rural Water Access, Kenya

Monitoring borehole water points in arid pastoral regions. IoT sensors verify functionality and usage for carbon credit verification.

virridy.com

Clean Water in Schools

LifeStraw water purifiers monitored by Virridy sensors in classrooms across Kenya — supporting access to safe drinking water and verified carbon credits.

NASA Reduced Gravity Aircraft — the Vomit Comet
Notes

My early career was as an Aerospace Engineer at NASA in Houston, where I designed drinking water systems for astronauts. This is what NASA calls the "Weightless Wonder" — but since I don't work there anymore, I can call it by its real name: the Vomit Comet. This is where we test technologies in reduced gravity before sending them to space.

Astronauts on the Space Station need the same things we do — shelter, food, air, and clean water. But water is incompressible, so it's really hard to pack it down and send it up on a rocket. It costs about $20,000 per liter of water sent to the Space Station. So instead, we recycle it. Every day, we collect the respiration, perspiration, and urination of every astronaut and recycle it back into drinking water. Today's coffee was also your buddy's coffee yesterday. Even with all that engineering, it still costs several thousand dollars for every drink of water on the Space Station. Back here on Earth, we use it like it's free — until it's not.

Notes

Meanwhile, in places like East Africa, another 40 million people are facing the risk of famine because of what was then the sixth consecutive season of drought. The people in these photos — the women walking miles to collect water, the children at the pumps — are living the direct consequences of a climate they did not create. This is the fieldwork. This is where the data has to come from. Every sensor we deploy here is one data point in a continent that has almost none.

Field Program Health Outcomes
92%
Increase in households with clean water
29%
Reduction in diarrhea
38%
Reduction in cryptosporidium exposure seroconversion
90
Averted childhood deaths per year anticipated
73%
Reduction in indoor air pollution among outdoor cooks
25%
Reduction in acute respiratory illness
7,500
Averted Disability-Adjusted Life Years (DALYs) annually
Notes

These programs have reached over five million people with clean water, and mobilized over $70 million in private and public investment — from venture capital, carbon credit buyers, NASA, and USAID — while generating over $100 million in returns. People are getting clean water in places where governments and donors can't reach. Investors take a risk, millions of people benefit, and companies see a modest return. That's the model.

These carbon credits are also a form of climate reparations. We caused climate change. People around the world are now feeling its effects. By taking money from carbon-emitting corporations to provide a basic water service, we are using capitalism to repair water supplies damaged by capitalism. The numbers on this slide are what that looks like in practice — not in theory.

SDA-for-SDGs Keynote · University of Toronto · 2026

Measuring Global
Water Security.

Evan Thomas, PhD, PE, MPH, MBA
Professor, CU Boulder · Mortenson Center in Global Engineering & Resilience
CEO, Virridy Inc.
The SDG Lens

Every SDG Needs Measurement

Different goals, different sensors, different data — same logic. Continuous, auditable measurement is the precondition for anyone being held accountable for outcomes on any SDG.

Where this talk lives
6Clean Water
& Sanitation
Water-quality sensors. Flow meters. Continuous utility telemetry.
3Good Health
& Well-being
Adherence sensors. Disease surveillance. Outcome tracking at the household.
13Climate
Action
Emissions sensing. Digital MRV. Climate-finance verification.
Same logic, different sensors
7Affordable
Energy
Cookstove use. Grid metering. Demand-side telemetry.
9Industry &
Innovation
IoT infrastructure. On-device ML. Open data platforms.
10Reduced
Inequalities
Equity-disaggregated data. Who gets measured, who does not.
15Life on
Land
Satellite remote sensing. Biodiversity monitoring. Land-cover tracking.
17Partnerships
for the Goals
Shared data platforms. Interoperable standards. Cross-sector data agreements.
The technology to measure now exists. The unsolved problem is the institutional design that decides who acts on the data — regulators, operators, financiers, donors. That’s the agenda — and it’s the one this week is built around.
For an audience opening an SDA-for-SDGs summer school, it is worth naming the goals explicitly. This talk lives primarily at the intersection of SDG 6, 3, and 13 — and surfaces trade-offs across 7, 9, 10, 15, and 17. The central insight is that carbon finance is what makes climate action actually pay for water access.
The Arc

We need more measurement. Then we need to ask who acts on it.

Data without incentives is just storage. The hard problem isn’t the sensor — it’s building the accountability structures that make someone responsible for what the sensor finds.

🌍
Still Mostly Unmeasured

4 billion people drink contaminated water. Sub-Saharan Africa has almost no monitoring data. The first step is simply knowing — and for most of the world, we still don’t.

🔬
The Tools Now Exist

Deep-UV fluorescence. On-device ML. No calibration. 91% accuracy at WHO thresholds. Continuous water quality records in Kenya and Rwanda where none existed before. The technology barrier is solved.

⚡
The Unsolved Problem

Regulatory mandates, performance contracts, carbon credits, donor accountability — these are the mechanisms that make someone responsible for acting on data. Without them, dashboards are just dashboards.

The sensors exist. The data is starting to flow. The open question is whether the policy, financing, and institutional structures exist to make acting on that data someone’s job.

Notes

I want to be precise about what I'm arguing. I'm not saying measurement solves the problem — data sitting in a dashboard does nothing. What I'm saying is that we need far more of it than we have, and then we need to be honest about the second question: who is actually incentivized to act on what it shows?

Right now, in most of the world, nobody is. There's no operator whose contract depends on the water quality reading. No regulator whose mandate covers the borehole in Turkana. No investor whose return is tied to whether the filter is being used. Carbon credits, performance-based contracts, regulatory mandates — these are the mechanisms that change that. The technology barrier is largely solved. The institutional and incentive barrier is not.

Thank You · SDA-for-SDGs Keynote · University of Toronto · 2026

Measuring Global
Water Security.

The gap between what we can now measure and what we choose to act on is a policy and business model problem — not a technology one.

Evan Thomas, PhD, PE, MPH, MBA
Professor · CU Boulder
Mortenson Center in Global Engineering & Resilience
evan.thomas@colorado.edu
CEO, Virridy Inc. · thelume.ai
Live Dashboards
thelume.ai — Boulder Creek
thelume.ai/boulder/stormevent
DRIP Kenya & Amazi Meza Rwanda
This Presentation
uoft-sda-sdg-keynote.pages.dev
← → navigate · O overview · F fullscreen · N notes view