Using Convolutional Neural Networks to Build a Lightweight Flood Height Prediction Model with Grad-Cam for the Selection of Key Grid Cells in Radar Echo Maps
Open Access
Abstract
Recent climate change has brought extremely heavy rains and widescale flooding to many areas around the globe. However, previous flood prediction methods usually require a lot of computation to obtain the prediction results and impose a heavy burden on the unit cost of the prediction. This paper proposes the use of a deep learning model (DLM) to overcome these problems. We alleviated the high computational overhead of this approach by developing a novel framework for the construction of lightweight DLMs. The proposed scheme involves training a convolutional neural network (CNN) by using a radar echo map in conjunction with historical flood records at target sites and using Grad-Cam to extract key grid cells from these maps (representing regions with the greatest impact on flooding) for use as inputs in another DLM. Finally, we used real radar echo maps of five locations and the flood heights record to verify the validity of the method proposed in this paper. The experimental results show that our proposed lightweight model can achieve similar or even better prediction accuracy at all locations with only about 5~15% of the operation time and about 30~35% of the memory space of the CNN.Keywords
Funding Information
- Ministry of Science and Technology, Taiwan (107-2119-M-224-003-MY3, 110-2121-M-224-001)
This publication has 35 references indexed in Scilit:
- Support vector regression with modified firefly algorithm for stock price forecastingApplied Intelligence, 2018
- Deep feature learning and selection for activity recognition2018
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression2017
- Combining emerging patterns with random forest for complex activity recognition in smart homesApplied Intelligence, 2017
- Urban pluvial flood prediction: a case study evaluating radar rainfall nowcasts and numerical weather prediction models as model inputsWater Science & Technology, 2016
- K-nearest neighbor-based weighted twin support vector regressionApplied Intelligence, 2014
- Quantitative precipitation forecast using radar echo extrapolationAtmospheric Research, 2009
- The use of radar in hydrological modeling in the Czech Republic – case studies of flash floodsNatural Hazards and Earth System Sciences, 2006
- A tutorial on support vector regressionStatistics and Computing, 2004
- Interfacing an enhanced radar echo tracking algorithm with a rainfall-runoff model for real-time flood forecastingPhysics and Chemistry of the Earth, Part B: Hydrology, Oceans and Atmosphere, 2000