Predicting in-stream water quality constituents at the watershed scale using machine learning.

Predicting in-stream water quality is necessary to support the decision-making process of protecting healthy waterbodies and restoring impaired ones. Data-driven modeling is an efficient technique that can be used to support such efforts. Our objective was to determine if in-stream concentrations of contaminants, nutrients-total phosphorus (TP) and total nitrogen (TN) -total suspended solids (TSS), dissolved oxygen (DO), and fecal coliform bacteria (FC) can be predicted satisfactorily using machine learning (ML) algorithms based on publicly available datasets. To achieve this objective, we evaluated four modeling scenarios, differing in terms of the required inputs (i.e., publicly available datasets (e.g., land-use/land cover)), antecedent conditions, and additional in-stream water quality observations (e.g., pH and turbidity). We implemented five ML algorithms-Support Vector Machines, Random Forest (RF), eXtreme Gradient Boost (XGB), ensemble RF-XGB, and Artificial Neural Network (ANN) -and demonstrated our modeling framework in an inland stream-Bullfrog Creek, located near Tampa, Florida. The results showed that, while including additional water quality drivers improved overall model performance for all target constituents, TP, TN, DO, and TSS could still be predicted satisfactorily using only publicly available datasets (Nash-Sutcliffe efficiency [NSE] > 0.75 and percent bias [PBIAS] < 10%), whereas FC could not (NSE < 0.49 and PBIAS >25%). Additionally, antecedent conditions slightly improved predictions and reduced the predictive uncertainty, particularly when paired with other water quality observations (6.9% increase in NSE for FC, and 2.7% for TP, TN, DO, and TSS). Also, comparable model performances of all water quality constituents in wet and dry seasons suggest minimal season-dependence of the predictions (<4% difference in NSE and < 10% difference in PBIAS). Our developed modeling framework is generic and can serve as a complementary tool for monitoring and predicting in-stream water quality constituents.

Chemical-Free Recovery of Elemental Selenium from Selenate-Contaminated Water by a System Combining a Biological Reactor, a Bacterium-Nanoparticle Separator, and a Tangential Flow Filter.

Biological selenate (SeO42-) reduction to elemental selenium nanoparticles (SeNPs) has been intensively studied but little practiced because of the additional cost associated with separation of SeNPs from water. Recovery of the SeNPs as a valuable resource has been researched to make the approach more competitive. Separation of the intracellular SeNPs from the biomass usually requires the addition of chemicals. In this research, a novel approach that combined a biological reactor, a bacterium-SeNP separator, and a tangential flow ultrafiltration module (TFU) was investigated to biologically reduce selenate and separate the SeNPs, biomass, and water from each other. This approach efficiently removed and recovered selenium while eliminating the use of chemicals for separation. The three units in the approach worked in synergism to achieve the separation and recovery. The TFU module retained the biomass in the system, which increased the biomass retention time and allowed for more biomass decay through which intracellular SeNPs could be released and recovered. SeNP aggregates were separated from bacterial aggregates due to their different interactions with a tilted polyethylene sheet in the bacterium-SeNP separator. SeNP aggregates stayed on the polyethylene sheet while bacterial aggregates settled down to the bottom of the separator.