Application of deep learning methods for more efficient water demand forecasting

画像: 効率的な水需要予測のためのディープラーニング手法(英語)

Water systems around the world are under tremendous stress to meet the growing water demand due to population growth, rapid urbanization, climate change, etc. Optimal water allocation and water distribution system control are essential for managing this water demand. Water demand predictions aid in these operations leading to sustainable management of water supply systems. These predictions help in system maintenance, expansion, and in planning daily network operations. They can also help in managing water network leaks.

In recent years, such predictions have also found wide application in near-optimal control operations of water networks. Water demand prediction is an active field, where different methods and techniques have been applied including conventional statistical methods and machine learning methods. Due to advancements in the field of sensing and IoT, an increasing amount of data is becoming available for water distribution systems, including water demand data. Therefore, we are seeing greater use of deep learning methods to develop models for water demand forecasting in recent years as deep learning methods can deal with seasonality as well as random patterns in the data, and provide accurate results compared to traditional methods.

In a study presented at EGU General Assembly 2021,[1] we looked at commonly used deep learning methods for the development of a short-term water demand forecast model for a real-world water system. This will help the water system operators and urban planners in choosing the right method to utilize for their work. The algorithms studied in this work were: (i) Multi-Layer Perceptron (MLP) (ii) Gated Recurrent Unit (GRU) (iii) Long Short-Term Memory (LSTM) (iv) Convolutional Neural Networks (CNN) and (v) the hybrid algorithm CNN-LSTM.


This article is a sponsored article by