Conformal Prediction-Driven Adaptive Sampling for Digital Water Twins

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Homaei, Mohammadhossein, Tarif, Mehran, Rodriguez, Pablo Garcia, Caro, Andres, Avila, Mar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911420177711104
author Homaei, Mohammadhossein
Tarif, Mehran
Rodriguez, Pablo Garcia
Caro, Andres
Avila, Mar
author_facet Homaei, Mohammadhossein
Tarif, Mehran
Rodriguez, Pablo Garcia
Caro, Andres
Avila, Mar
contents Digital Twins (DTs) for Water Distribution Networks (WDNs) require accurate state estimation with limited sensors. Uniform sampling often wastes resources across nodes with different uncertainty. We propose an adaptive framework combining LSTM forecasting and Conformal Prediction (CP) to estimate node-wise uncertainty and focus sensing on the most uncertain points. Marginal CP is used for its low computational cost, suitable for real-time DTs. Experiments on Hanoi, Net3, and CTOWN show 33--34\% lower demand error than uniform sampling at 40\% coverage and maintain 89.4--90.2\% empirical coverage with only 5--10\% extra computation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05610
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conformal Prediction-Driven Adaptive Sampling for Digital Water Twins
Homaei, Mohammadhossein
Tarif, Mehran
Rodriguez, Pablo Garcia
Caro, Andres
Avila, Mar
Machine Learning
Artificial Intelligence
Optimization and Control
Digital Twins (DTs) for Water Distribution Networks (WDNs) require accurate state estimation with limited sensors. Uniform sampling often wastes resources across nodes with different uncertainty. We propose an adaptive framework combining LSTM forecasting and Conformal Prediction (CP) to estimate node-wise uncertainty and focus sensing on the most uncertain points. Marginal CP is used for its low computational cost, suitable for real-time DTs. Experiments on Hanoi, Net3, and CTOWN show 33--34\% lower demand error than uniform sampling at 40\% coverage and maintain 89.4--90.2\% empirical coverage with only 5--10\% extra computation.
title Conformal Prediction-Driven Adaptive Sampling for Digital Water Twins
topic Machine Learning
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2511.05610