Core Technologies
An algal strain library tuned to the water and environment of each region, paired with a high-precision cultivation control platform built on IoT sensing and AI inference — the proprietary base that ABC runs on.
Request technical documentationThree pillars of the technology base
Algal strain library
A library of microalgal strains optimised for the water quality, salinity, temperature and light of each region, built in-house. Genomic analysis supported by bioinformatics lets us assess CO₂ fixation capacity, nutrient uptake efficiency and cultivation stability from several angles, and propose the optimal strain or blend ratio. For the general mechanisms of CO₂ fixation and nutrient recovery, see the references below[1][2].
- ✓ Integrated with regional water-quality databases
- ✓ Genetic stability assessment of strains
- ✓ Custom blend design
IoT sensing
Real-time measurement of more than ten parameters (our implementation) including pH, dissolved oxygen, turbidity, temperature and light intensity. Edge computing handles on-site processing while a unified cloud dashboard manages data across multiple sites. The sensing foundation for microalgal cultivation follows Havlik et al.[3]
- ✓ Real-time multivariate sensing
- ✓ Low-latency control through edge processing
- ✓ Unified cloud dashboard
AI cultivation control
Reinforcement learning and time-series forecasting models optimise cultivation parameters automatically from sensor data, using our own algorithms. Adaptive control against weather, seasonal and load variation aims to hold algal density and quality steady through the year. AI control approaches for photobioreactors are reported in Fernández et al.[4] among others.
- ✓ Autonomous parameter optimisation via reinforcement learning
- ✓ Anticipatory control from time-series forecasts
- ✓ Anomaly detection and alerting
The moat built by a three-layer architecture
Selection × Library × Physical AI
Three proprietary layers systematize Algal Bloom Capture into a single MOAT
Non-GMO Genomic Selection
Non-GMO selective breeding avoids regulatory risk and social-acceptance hurdles. WGS, RNA-seq and QTL analysis rapidly screen growth rate, salt tolerance, lipid/protein content and flocculation.
Strain Library × Env. Matching
A strain library mapped across salinity, temperature, pH and influent composition. The optimal strain is supplied as "Strain as a Service" from customer water-quality data.
Physical AI for Bloom Control
A control model trained on time-series data (pH/OD/fluorescence/nutrients/flow) predicts the bloom–collapse cycle and controls proactively — implemented as Bloomo edge inference.
The evidence behind it
The three pillars of Core Technologies rest on the academic literature of microalgal cultivation, sensing and control, on top of which we have built our own library, algorithms and implementation. The individual performance figures (simultaneous measurement of more than ten parameters, stable cultivation through the year) are our own implementation and our own demonstrated values, and vary with the deployment environment.
References
- Mohsenpour S.F., et al. Integrating micro-algae into wastewater treatment: A review. Science of the Total Environment, 2021, 752, 142168. DOI →
- Chisti Y. Biodiesel from microalgae beats bioethanol. Trends in Biotechnology, 2008, 26(3), 126–131. DOI →
- Havlik I., Lindner P., Scheper T., Reardon K.F. On-line monitoring of large cultivations of microalgae and cyanobacteria. Trends in Biotechnology, 2013, 31(7), 406–414. DOI →
- Fernández F.G.A., et al. Conventional and emerging strategies for the microalgae biomass production from wastewater and industrial flue gases. Bioresource Technology, 2021, 321, 124475. DOI →
Technical detail and joint research
We can share specifications and research data for Core Technologies. You are equally welcome to approach us about joint research or a demonstration deployment.