Urban Flood Prediction With 1D-2D Data Fusion and Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data-driven urban flooding prediction models suffer from low computational efficiency, inadequate real-time performance, and poor fit with observational data, leading to suboptimal flooding prevention strategies.
Innovation Solution
A method involving constructing a water depth and flow generation model using conditional variational autoencoders, a flood depth compensation model for error correction, and a data fusion model to generate an urban flooding inundation map, followed by parameter updates using mixed data sets to improve prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data-driven models are used for urban flooding prediction, then computational efficiency is improved, but the fit with observational data deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the predicted flood depth from the data-driven model is compared with actual observational data, and the difference (error term) is used to correct and update the model parameters. This continuous feedback loop allows the model to progressively improve its accuracy while maintaining the computational efficiency of data-driven approaches.
Solution Approach 2:
The patent dynamically adjusts model parameters by incorporating error terms derived from observational data. The parameters are updated iteratively to minimize the difference between predicted and observed flood depths, thereby improving the model's fit with observational data while preserving the speed advantage of data-driven methods.
2Measurement precision
If traditional mechanistic models are used for urban flooding prediction, then the fit with observational data is improved, but computational efficiency deteriorates
Solution Approach 1:
The patent segments the flooding prediction system into two complementary components: a data-driven model that provides rapid computational results and a correction mechanism that incorporates observational data. This segmentation allows the system to leverage the speed of data-driven models while incorporating the accuracy of traditional mechanistic models through error correction.
Solution Approach 2:
The patent introduces an intermediary correction term that bridges the gap between data-driven predictions and observational data. This intermediary element allows the system to combine the computational efficiency of data-driven models with the accuracy of observation-based corrections, creating a hybrid approach that achieves both goals.
3Loss of time
If real-time prediction is implemented, then response time is improved, but prediction accuracy deteriorates
Solution Approach 1:
The patent performs preliminary actions by pre-processing observational data and pre-calculating correction terms that can be applied in real-time. This preparation allows the system to maintain high prediction accuracy during real-time operation without the computational burden of processing all historical data at prediction time.
Solution Approach 2:
The patent applies partial correction action by using only the necessary error terms and correction factors needed for real-time prediction, rather than incorporating all available historical data into the real-time calculation. This selective approach maintains speed while achieving sufficient accuracy for effective flood warning.
Data Source
AI summary
An urban flooding prevention method includes: inverting the global water depth and the flow rate of the rainwater system, generating the urban flooding inundation map and the binary flooded grid at the monitoring time, and performing a rationality check of the global water depth of the rainwater system, the urban flooding inundation map and the binary flooded grid, performing a fusion processing based on the hydraulic connection between the 1D node and the 2D ground to obtain a label, and generating a new data set according to the label and the forecast rainfall, mixing the historical data set and the new data set to obtain a mixed data set, and using the updated model to predict the urban flooding, according to the prediction results, determining the early warning level of urban flooding, so as to generate the drainage scheme, and regulating the corresponding drainage facilities according to the drainage scheme.