When
rainwater harvesting is utilized as an alternative water resource
in buildings, a combination of municipal water and rainwater is typically
required to meet water demands. Altering source water chemistry can
disrupt pipe scale and biofilm and negatively impact water quality
at the distribution level. Still, it is unknown if similar reactions
occur within building plumbing following a transition in source water
quality. The goal of this study was to investigate changes in water
chemistry and microbiology at a green building following a transition
between municipal water and rainwater. We monitored water chemistry
(metals, alkalinity, and disinfectant byproducts) and microbiology
(total cell counts, plate counts, and opportunistic pathogen gene
markers) throughout two source water transitions. Several constituents
including alkalinity and disinfectant byproducts served as indicators
of municipal water remaining in the system since the rainwater source
does not contain these constituents. In the treated rainwater, microbial
proliferation and Legionella spp. gene copy numbers
were often three logs higher than those in municipal water. Because
of differences in source water chemistry, rainwater and municipal
water uniquely interacted with building plumbing and generated distinctively
different drinking water chemical and microbial quality profiles.
Understanding the end-use of water is essential to a plethora of critical research in premise plumbing. However, direct access to end-use data through physical sensors is prohibitively expensive for most researchers, building owners, operators, and practitioners. Therefore, machine learning models can alleviate these costs by predicting downstream end-use events (e.g., sink, shower, dishwasher, and washing machine) via an affordable subset of upstream sensors. Choosing which upstream sensors, as well as data preprocessing methods, are best for machine learning has historically been a manual process. This paper proposes a novel approach to systematically configure the machine platform automatically. The optima were determined through a Pareto analysis of the exhaustive combinations of upstream predictors and preprocessing methods. The model was trained and validated with real-world data obtained from a house that has been extensively monitored for over a year. Results from the analysis suggested that downstream events can be effectively predicted with minimum overfitting error for most categories, using as few as two to four upstream sensors. This study automatically implemented highly accurate machine learning models to predict downstream features within premise plumbing systems, significantly lowering the costs of researching residential plumbing best practices such as water conservation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.