Application of attached algae flow-ways for coupling biomass production with the utilization of dilute non-point source nutrients in the Upper Laguna Madre, TX

•Successful long-term outdoor operation of attached algae flow-way in Upper Laguna Madre, TX.•Persistent algal ash-free biomass production at 4 to 10 g/m2/day over two years.•TN and TP recovery at 300~500 mg/m2/day and 15~30 mg/m2/day, respectively.•Total solar irradiation was a key factor for biomass productivity of the flow-way.•Developed machine learning models with predictive capability (R2 = 0.67~0.75). The purpose of this study is to determine the potential for an attached algae flow-way system to efficiently produce algal biomass in estuarine surface waters by utilizing dilute non-point source nutrients from local urban, industrial, and agricultural discharges into the Upper Laguna Madre, Corpus Christi, Texas. The study was conducted over the course of two years to establish seasonal base-line biomass productivity and composition for bioproducts applications, and to identify key environmental factors and flow-way cohorts impacting biomass production. For the entire cultivation period, continuous ash-free biomass production at 4 to 10 g/m2/day (corresponding to nutrient recovery at 300 to 500 mg of nitrogen/m2/day and 15 to 30 mg of phosphorus/m2/day) was successfully achieved without system restart. Upon start-up, a latency period was observed which indicates roles for species succession from relatively low productivity, high ash content pioneer periphytic culture composed primarily of benthic diatoms from the source waters to higher productivity, reduced ash content, and more resilient culture mainly composed of filamentous chlorophyta, Ulva lactuca. Principal Component Analysis (PCA) was used to identify environmental factors driving biomass production, and machine learning (ML) models were constructed to assess the predictive capability of the data set for system performance using the local multi-season environmental variations. Environmental datasets were segregated for ML training, validation, and testing using three methods: regression tree, ensemble regression, and Gaussian process regression (GPR). The predicted ash-free biomass productivity using ML models resulted in root-squared-mean-errors (RSME) from 1.78 to 1.86 g/m2/day, and R2 values from 0.67 to 0.75 using different methods. The greatest contributor to net productivity was total solar irradiation, followed by air temperature, salinity, and pH. The results of the study should be useful as a decision-making tool to application of attached algae flow-ways for biomass production while