Early Detection and Prediction of Harmful Algal Blooms Using Low Cost, Networked IOT Sensors and Machine Learning

EPA Contract Number: 68HERC20C0027
Title: Early Detection and Prediction of Harmful Algal Blooms Using Low Cost, Networked IOT Sensors and Machine Learning
Investigators: Lee, Christopher
Small Business: AquaRealTime, Inc.
EPA Contact: Richards, April
Phase: I
Project Period: March 1, 2020 through August 31, 2020
Project Amount: $100,000
RFA: Small Business Innovation Research (SBIR) - Phase I (2020) RFA Text |  Recipients Lists
Research Category: Small Business Innovation Research (SBIR) , SBIR - Clean and Safe Water


Harmful algal blooms (HABs) occur when the population of cyanobacteria in fresh or salt water explodes. HABs cause $14B in damages every year world-wide, because cyanobacteria release toxins into the water that threaten humans, livestock and native aquatic life. The only way to mitigate the damage from HABs is to detect them early and treat them with algicides as soon as possible. The problem is that cyanobacteria multiply extremely quickly, making human mediated monitoring unreliable and expense.

After extensive market research, we propose a solution to this problem known as AlgaeTracker™. This automated internet of things enabled sensor buoy is unlike anything else on the market. It is small {16 inches in diameter), light {10 lbs in weight) and contains a suite of advanced fluorescence sensors that allow it to detect and even predict a HAB before it happens, making preventative treatments possible for the first time. AlgaeTracker™ is connected to the internet via the cellular mobile phone network and continually reports the status of the body of water it is situated upon It then alerts users of impending HABs via cell phone messages or email. We already have LOls for $276K of annual recurring revenue and $60K in buoys purchases and predict recurring revenue of $20 million in 5 years.

The true innovation with AlgaeTracker™ however, is the cost; we aim to sell the buoy for only $400 which is close to the cost to produce the device. We then propose a subscription-based business model where customers benefit from access to a hardware warranty, and increasingly sophisticated analytics as our machine learning approach takes data from all of our buoys and constructs more accurate models that allow for better and faster predictions of HABs. We can also reprogram AlgaeTracker's™ onboard software over the cellular network, leveraging what we learn from our analytics. Contrast this with competitor devices that cost $30,000 and weigh 180lbs and have no downstream analytics or programmability.

A prototype AlgaeTracker™ has been built and is undergoing testing now. The purpose of this grant is to build a beta production model of AlgaeTracker™. We first propose to create algorithms to program an onboard microcontroller to make the sensors more accurate and sensitive. This is followed by lab and field trials and finally we'll undertake a redesign of the device to reduce the cost to produce it from $2000 to $400 and to make it more mass manufacturable.

Progress and Final Reports:

  • Final Report
  • SBIR Phase II:

    Early detection and prediction of harmful algal blooms using low cost, networked IOT sensors and machine learning