Synthetic Streamflow Data Generation for Flood Forecasting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Interruptions in streamflow data from streamgages during flooding events limit the accuracy and availability of hydrological data, impacting flood forecasting and decision-making processes.

Innovation Solution

A method using artificial intelligence and machine learning to generate synthetic streamflow data by classifying and correlating data from multiple streamflow sources, creating a predictive model trained on historical data to produce real-time or near real-time synthetic data when measured data is unavailable.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If streamflow data is collected from multiple sources to improve accuracy, then data availability improves, but system complexity increases

Engineering Contradiction:

Improvestreamflow data availabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments streamflow data collection into multiple independent source streams, each monitored separately. When one source fails, others continue providing data, improving reliability without requiring a completely redundant system. The segmentation allows the system to handle partial failures gracefully.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The streamflow monitoring system is designed to accept and process data from multiple types of sources (streamgages, satellites, sensors) through a unified interface. This multi-functionality allows the system to adapt to different data sources without requiring separate processing systems, managing complexity while improving data availability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If real-time streamflow monitoring is maintained during flooding events, then decision-making accuracy improves, but vulnerability to data interruption increases

Engineering Contradiction:

Improveflood forecasting accuracyVSAvoiddata interruption risk

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system implements beforehand cushioning by pre-establishing multiple data collection pathways and backup sources before flooding events occur. When primary streamgages are damaged during floods, pre-configured alternative sources (satellites, other sensors) immediately provide data, cushioning against the harmful effect of data interruption and maintaining forecasting accuracy.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

3Duration of action of stationary object

If synthetic streamflow data is generated using AI models, then data continuity is improved, but model training requirements increase complexity

Engineering Contradiction:

Improvedata continuityVSAvoidmodel training complexity

Core Design Contradiction:

Duration of action of stationary objectVSDevice complexity

Solution Approach 1:

The AI models are trained in advance using historical streamflow data from multiple sources before they are needed for synthesis. This preliminary training action creates pre-trained models that can generate synthetic data immediately when real data is unavailable, ensuring data continuity without requiring complex real-time training operations.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11238356B2Method of predicting streamflow data

Publication Date: 2022.02.01 UNIVERSITY OF ALASKA FAIRBANKS

AI summary

A system and method for generating synthetic streamflow data for a malfunctioning streamgage is provided. The method uses both classification and regression techniques to accurately predict streamflow data for the malfunctioning streamgage based on measured streamflow data from other streamgages and based on correlations between the streamgages. The system and method may also provide a method of improved flood forecasting, by updating flood forecasts using synthetic streamflow data when measured streamflow data from one or more streamgages are unavailable. The system may generate flood forecast information and/or flood warning messages.