3 research outputs found
Insights From 15 Years of New York City's Drinking Water Quality Complaints
No full textDuring 2010-2024, more than 20,000 drinking water complaints were
reported in New York City (NYC).Descriptive and spatiotemporal
analytical results on these calls were developed using open, public data
sets from NYC311, a municipal complaint line.Unique characteristics and
spatiotemporal patterns of potential causes were identified, with the
overall goal of advocating for the use of open-source data to foster
collaboration among researchers, states, water utilities, and
industry.Collaborative work will emphasize more sustainable management
and operation of drinking water systems
Harnessing the Power of Random Forest for Precise Short-Term Water Demand Forecasting in Italian Water Districts
No full textWater demand forecasting is essential for ensuring a reliable water supply in any water utility. It involves making accurate predictions for both short- and long-term water needs. Many traditional time series forecasting methods are presently used; however, recent machine learning techniques have grown in popularity for their robustness and accuracy. Random forest is an emerging machine learning algorithm which was used to forecast short-term water demand for ten district metered areas in Italy. Our predictions on test datasets using the trained model yielded correlations as high as 0.98. Important explanatory variables affecting model performance included consumption patterns represented by the seven-day water demand lag. In this paper, we present a reliable application of the random forest algorithm for short-term water demand forecasting
Battle of Water Demand Forecasting
No full textAspart of the Battle of Water Networks competition series, the Battle of Water Demand Forecasting (BWDF) was organized in the context of the 3rd Water Distribution Systems Analysis and Computing and Control in the Water Industry (WDSA-CCWI) joint conference held in Ferrara (Italy) in 2024. In line with the previous editions of the Battle of Water Networks—the main objective of which was to address a specific problem related to the design and operation of water distribution networks—the BWDF aims to compare the effectiveness of methods for the short-term forecast of urban water demand in a set of real district metered areas. During the conference, 31 teams across the world participated in the BWDF and presented their approaches. The results obtained demonstrate the importance of (1) considering integrated approaches for short-term water demand forecasting; and (2) evaluating their performance in relation to more than one metric, case study, and period
