Maia Analytica Receives NSF SBIR grant to develop Wastewater AI and Training Tools
Maia Analytica announces an innovative project that aims to revolutionize wastewater treatment, backed by a Small Business Innovation Research (SBIR) grant. This ground-breaking initiative will develop a software platform capable of real-time monitoring and proactive management of wastewater facilities. Its primary goal is to enhance nutrient removal and recovery while significantly reducing costs.
This advanced technology promises a transformative impact on the wastewater industry. Operators will be able to predict and diagnose future process upsets, proactively mitigate underlying issues, and prevent pollutant releases without resorting to heavy use of costly and environmentally damaging chemicals. The resulting improvements in treatment effectiveness and cost efficiency will enhance the sustainability of wastewater treatment infrastructure and reduce the financial burdens associated with its operation.
Significant commercial benefits are expected post-deployment, with potential annual savings of up to $1.4M per large facility. This would result from improved compliance and a reduction in chemical costs, representing a market opportunity of more than $420M in the United States alone.
Beyond economic advantages, the project aims to deliver a significant improvement in regulatory compliance (up to 35%) and a reduction in chemical treatment costs (up to 35%). It will also provide much-needed support to a rapidly changing workforce, where 50% of operators are expected to retire over the next 5–10 years.
Moreover, Maia Analytica plans to introduce a game-based training program for training new operators, equipping them with the skills necessary to manage increasingly sophisticated facilities.
The software platform, which is a key part of this SBIR Phase II project, will utilize operational, biological, and meteorological data to provide vital process forecasts and insights into biological phosphorus removal. The integration of machine-learning forecast models will form the backbone of a decision-making system that diagnoses and mitigates upsets in the notoriously unstable biological phosphorus removal process.
In the project’s final phase, a full-scale wastewater facility’s data systems will be synchronized with the software platform to deliver real-time results. The efficacy of the solution will be thoroughly evaluated over a 12-month pilot testing period.
This project embodies the National Science Foundation’s statutory mission and has received support after a thorough evaluation based on the Foundation’s intellectual merit and broader impacts review criteria.
Contact firstname.lastname@example.org for more information.