Machine Learning, Urban Water Resources Management and Operating Policy

Evangelos Rozos

doi:10.3390/resources8040173

Abstract

Meticulously analyzing all contemporaneous conditions and available options before taking operations decisions regarding the management of the urban water resources is a necessary step owing to water scarcity. More often than not, this analysis is challenging because of the uncertainty regarding inflows to the system. The most common approach to account for this uncertainty is to combine the Bayesian decision theory with the dynamic programming optimization method. However, dynamic programming is plagued by the curse of dimensionality, that is, the complexity of the method is proportional to the number of discretized possible system states raised to the power of the number of reservoirs. Furthermore, classical statistics does not consistently represent the stochastic structure of the inflows (see persistence). To avoid these problems, this study will employ an appropriate stochastic model to produce synthetic time-series with long-term persistence, optimize the system employing a network flow programming modelling, and use the optimization results for training a feedforward neural network (FFN). This trained FFN alone can serve as a decision support tool that describes not only reservoir releases but also how to operate the entire water supply system. This methodology is applied in a simplified representation of the Athens water supply system, and the results suggest that the FFN is capable of successfully operating the system according to a predefined operating policy.

Highlights

Water resource management is a notoriously difficult problem, mainly because of the uncertainty regarding inflows to the system, thereby making inevitable the probabilistic approach [1], which sets a framework of policy decisions related to the acceptable risk of failure [2].To support the implementation of policy decisions, both classical and data-driven methodologies have been employed.Machine learning has been emerging as a very efficient multi-functional tool in all scientific fields.Besides the information technology sector, machine learning is finding its way into drug discovery, agriculture, and even the legal industry [3]
UWOT [18,29] was employed to route the water demand according to the ratios of the FFNsbudget that correspond to operating
The network flow programming was applied with synthetic data of a significant length to reliably capture the risk of each operating policy and provide a long training period for the feedforward neural network (FFN)

Summary

Introduction

Water resource management is a notoriously difficult problem, mainly because of the uncertainty regarding inflows to the system, thereby making inevitable the probabilistic approach [1], which sets a framework of policy decisions related to the acceptable risk of failure [2]. Besides the information technology sector, machine learning is finding its way into drug discovery, agriculture, and even the legal industry [3]. It has been almost three decades since artificial intelligence (AI) applications (genetic algorithms, fuzzy logic, neural networks, etc.) appeared in hydrology. Raman and Chandramouli [5] employed a feedforward neural network (FFN) to formulate an operating rule for a single reservoir for irrigation

Methods

Results

Discussion

Conclusion