Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Machine learning (ML) models are increasingly deployed in urban water systems to optimize operations, enhance efficiency, and curb resource consumption amid growing sustainability demands. Yet, their transferability across plants is hampered by scenario differences-variations in environmental factors, protocols, and data distributions-that erode performance and necessitate energy-intensive retraining. While existing strategies focus on minimizing these differences via domain adaptation or fine-tuning, none exploit them as inherent prior knowledge for improved generalization. Here we show an environmental information adaptive transfer network (EIATN) framework that can leverage scenario differences to enable effective generalization across distinct prediction tasks within the same water plant. By evaluating EIATN across four scenario categories and 16 diverse ML architectures-yielding 64 models in total-we demonstrate its feasibility, with bidirectional long short-term memory emerging as the top performer, achieving a mean absolute percentage error of just 3.8 % while requiring only 32.8 % of the typical data volume. In a case study of Shenzhen's urban water system, it reduced carbon emissions by 40.8 % compared to fine-tuning and 66.8 % relative to direct modeling from scratch. EIATN unlocks the reuse of vast existing ML models in water systems, yielding substantial energy savings and fostering equitable, low-carbon intelligent management.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12320164PMC
http://dx.doi.org/10.1016/j.ese.2025.100604DOI Listing

Publication Analysis

Top Keywords

scenario differences
8
water plant
8
machine learning
8
learning models
8
urban water
8
water systems
8
water
5
leveraging scenario
4
differences cross-task
4
cross-task generalization
4

Similar Publications

A Quantitative Risk Assessment for Determining the Efficacy of Wearing Makeup in Reducing the Transmission of COVID-19 between Genders in the USA.

J Healthc Sci Humanit

January 2024

Formerly Associate Professor of Epidemiology and Risk Analysis, Department of Pathobiology/Department of Graduate Public Health, College of Veterinary Medicine, Tuskegee University, Phone: (334) 524-1988, Email:

The COVID-19 pandemic is a highly infectious disease of paramount public health importance. COVID-19 is mainly transmitted via human-to-human contact. This could be through self-inoculation resulting from failure to observe proper hand hygiene and infection control practices.

View Article and Find Full Text PDF

Background: It is unclear whether the current North Atlantic Treaty Organization (NATO) trauma system will be effective in the setting of Large-Scale Combat Operations (LSCO). We sought to model the efficacy of the NATO trauma system in the setting of LSCO. We also intended to model novel scenarios that could better adapt the current system to LSCO.

View Article and Find Full Text PDF

Significance: The spatial and temporal distribution of fluorophore fractions in biological and environmental systems contains valuable information about the interactions and dynamics of these systems. To access this information, fluorophore fractions are commonly determined by means of their fluorescence emission spectrum (ES) or lifetime (LT). Combining both dimensions in temporal-spectral multiplexed data enables more accurate fraction determination while requiring advanced and fast analysis methods to handle the increased data complexity and size.

View Article and Find Full Text PDF

Stewardship opportunities in peripartum infections: a review of quality improvement initiatives and future directions.

Antimicrob Steward Healthc Epidemiol

September 2025

Department of Obstetrics and Gynecology, Division of Maternal/Fetal Medicine, Prisma Health Upstate, Greenville, SC, USA.

Antimicrobial resistance is an urgent public health threat, and despite significant consumption of antimicrobials in pregnancy, there remain opportunities for improvement of their use in the obstetric population. Improvement in antimicrobial utilization can be streamlined by assessing baseline characteristics, utilization of diagnostic testing, awareness of peripartum protocols, and recognition of penicillin allergies. In a single healthcare system including 8 obstetric hospitals, an administrative review identified 199 different regimens used among 8,528 patients based on American College of Obstetrician and Gynecologists (ACOG) guidelines.

View Article and Find Full Text PDF

Avalanche transceiver search times during avalanche companion rescue - A prospective randomized single-blinded cross-over simulation study.

Resusc Plus

November 2025

Department of Anaesthesiology and Intensive Care Medicine, Innsbruck Medical University Hospital, Medical University of Innsbruck, Anichstrasse 35, 6020 Innsbruck, Austria.

Background: The aim of this study was to analyse the influence of voice navigation in a new generation of transceivers on the time and success rate of transceiver search in a simulated avalanche rescue scenario.

Methods: Fifty participants performed two randomized test runs, using two different transmitters with and without voice navigation. Primary outcome was success rate, total transceiver search and total location time, secondary outcome parameters comprised predefined time intervals (coarse search time, fine search time, probing time) and deviations from the recommended standard search procedure.

View Article and Find Full Text PDF