Intelligent Hardware Optimization
At Viridis, we're committed to leveraging cutting-edge computational science, statistical modelling and machine learning tools to accelerate the development of our electro-oxidation technology, reduce R&D costs, enhance product performance, and generate measurable operational and economic benefits for our clients. Our Intelligent Hardware Optimization Strategy is designed to support rapid innovation while strengthening the scalability, intelligence, and cost-effectiveness of our water treatment solutions.
Here's exactly how we put the power of AI and advanced analytics to work:
We integrate Computational Fluid Dynamics modeling to optimize the internal flow of our electro-oxidation cells. This enables us to:
Improve mass transport of contaminants to the active surfaces.
​
Reduce energy consumption by minimizing flow resistance.
​
Identify and eliminate design inefficiencies before physical prototyping.​
By using CFD simulations, we can rapidly iterate cell designs to enhance performance and durability, reducing the trial-and-error cycles typically required in physical testing.
MASS TRANSPORT
Computational Fluid Dynamics
WATER CHEMISTRY
Data Analysis, Experimental Design and Statistical Modelling for Smart Testing
We use statistical models to streamline our experimental design process. This includes:
Identifying key variables impacting performance through statistical modeling data analytics.
Using Design of Experiments (DoE) to strategically plan and minimize the number of tests needed.
Extracting actionable insights from test results to guide further iterations..
This approach allows us to reduce R&D timelines, conserve laboratory resources, and build more robust systems with fewer experiments.
To explore novel electrode coatings and catalytic materials, we leverage quantum chemistry simulations enhanced by AI techniques. These simulations help us:​
Predict the electrochemical behavior of new materials at the atomic level.
​
Screen large databases of potential materials before synthesis.
​
Focus our lab efforts only on the most promising candidates.
This predictive capability accelerates the development of next-generation electrodes with higher selectivity, stability, and cost-efficiency.
ELECTRODE MATERIALS
Quantum Chemistry for Material Discovery
CONTROL SYSTEM
​Predictive Modeling for Operational Intelligence
We are developing machine learning predictive models and control systems to improve the real-time operation of our technology in the field. These models:​​
​Use sensor data (e.g., flow rate, voltage, contaminant levels) to predict performance trends.
​
Enable proactive maintenance and troubleshooting.
​
Continuously learn from operational data using neural networks to optimize system behavior.
This smart control approach reduces downtime, extends component life, and ensures consistent treatment performance while minimizing OPEX for clients.
Technical Advisors
Samira Siahrostami, PhD.
Prof. Siahrostami specializes in computational material design for advanced catalysis applications in electrolyzers, batteries, and fuel cells.
Her research employs quantum mechanical simulations to reveal reaction mechanisms at catalyst surfaces, providing crucial insights into kinetic and thermodynamic properties that determine electrochemical performance.
By bridging fundamental theory with practical applications, Prof. Siahrostami develops actionable strategies for designing more efficient, durable, and sustainable catalysts. Her multi-scale approach combines quantum mechanics and machine learning to identify optimal materials for real-world energy conversion technologies.
At Viridis, Prof. Siahrostami's pioneering work guides our development of novel materials that enhance electrolyzer performance. Her expertise helps identify promising catalyst candidates with superior efficiency, longevity, and cost-effectiveness for water treatment applications, playing an instrumental role in our mission to advance water purification technology.​
Ignacio Bermudez Corrales, PhD.
Dr. Corrales is a distinguished technical leader with a expertise in AI, Machine Learning, and Data Science, with a PhD from Politecnico di Torino.
Dr. Corrales brings expertise honed at industry giants including Palo Alto Networks, Splunk, and Symantec. His work includes developing Prisma Cloud Copilot, developing advanced machine learning systems, advancing cybersecurity analytics, and creating innovative patent-protected technologies for complex data environments, all underpinned by a robust foundation in telecommunications engineering.
​
Dr. Corrales joined Viridis driven by his belief in our mission to solve water treatment challenges critical for life on Earth. His expertise in developing sophisticated machine learning models and analyzing complex data streams uniquely positions him to guide our AI integration efforts. His innovative mindset and proven track record in delivering impactful solutions make him invaluable as we navigate the intersection of technology and environmental sustainability.​