Distributed Acoustic Sensing for Urban Flood Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Urban flooding is challenging to forecast due to data scarcity and technical challenges in sensing networks, particularly in urban areas, where high installation and maintenance costs, and limitations in remote sensing technologies like satellite imaging hinder timely identification of flood mechanisms and prevention strategies.
Innovation Solution
A data-driven street flood warning system employing distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) technologies combined with machine learning (ML) models to predict rain intensity and flood levels, using vibrational data from fiber optic cables and historical data to provide real-time flood warnings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If satellite imaging is used for flood monitoring, then coverage area is improved, but measurement precision and response time deteriorate due to cloud cover, complex street geometry, and long revisit time intervals
Solution Approach 1:
The patent replaces satellite imaging (remote optical sensing) with distributed acoustic sensing through fiber optic cables embedded in the urban environment. This substitution uses acoustic vibrations detected by fiber optics to monitor flooding, eliminating the limitations of cloud cover and long revisit times while maintaining continuous monitoring capability at street level.
Solution Approach 2:
The patent introduces fiber optic cables as intermediary sensing elements distributed throughout the urban infrastructure. These cables act as mediators between the flood event and the monitoring system, providing direct contact measurement of water presence and acoustic signatures of flooding, thereby improving precision without sacrificing coverage area.
2Measurement precision
If extensive sensing networks are installed for flood monitoring, then measurement precision is improved, but device complexity and maintenance cost increase
Solution Approach 1:
The patent leverages existing telecommunications fiber optic infrastructure for flood monitoring, making the sensing system multi-functional. The same fiber optic cables used for communication also serve as acoustic sensors for flood detection, eliminating the need for separate dedicated sensing networks and reducing overall system complexity while maintaining high measurement precision.
Solution Approach 2:
The distributed acoustic sensing system utilizes the existing fiber optic network that is already deployed throughout the urban environment for other purposes. This self-service approach allows flood monitoring to be achieved using infrastructure that is already in place, reducing the complexity and cost of deploying a new dedicated sensing network.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively predicts street flood status along telecommunications fiber optic cable routes, enabling proactive flood mitigation measures by providing accurate rain intensity and flood level predictions, reducing the need for external sensors and enabling timely alerts for decision-makers and the public.
Implementation Method 1
a distributed acoustic sensing (DAS) system includes an optical sensor fiber that serves as a sensing element distributed along a target route
Implementation Method 2
The DFOS/DAS system can detect and measure dynamic strain changes that occur along the length of the optical sensor fiber by detecting optical phase shifts of backscattered light
Data Source
AI summary
A data-driven street flood warning system that employs distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) and machine learning (ML) technologies and techniques to provide a prediction of street flood status along a telecommunications fiber optic cable route using the DFOS/DAS data and ML models. Operationally, a DFOS/DAS interrogator collects and transmits vibrational data resulting from rain events while an online web server provides a user interface for end-users. Two machine learning models are built respectively for rain intensity prediction and flood level prediction. The machine learning models serve as predictive models for rain intensity and flood levels based on data provided to them, which includes rain intensity, rain duration, and historical data on flood levels.