Detecting flooded areas with machine learning techniques: case study of the Selška Sora river flash flood in September 2007

Abstract

Abstract. Floods seem to appear with increased frequency from one year to another. They create great damage to property and in some cases even result in lost lives. However, a quick and effective response by rescue services can greatly reduce the consequences. Machine learning techniques can reduce the time necessary for flood mapping. We test various machine learning methods to find the one with the highest classification accuracy. We also present the most important points for quick and effective machine learning procedures on remote sensing data. First, the data must be prepared correctly. We use satellite images, digital terrain models (DTMs), and the river network. The data in its primary form (e.g., bands of multispectral satellite images or DTMs) is insufficient. We also need certain derived attributes, such as the vegetation index or the slope derived from the DTM. Second, we must select suitable training samples and a suitable machine learning method. This approach to determining floods is presented in a case study of flash floods in the Selška Sora river valley. Machine learning techniques have proven successful in quickly determining flooded areas. The best results are produced by the J48 decision tree algorithm. The success of the ensemble machine learning methods is comparable to the J48 algorithm, while the JRip classification is not as good. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

An integrated fluvial and flash pluvial model using 2D high-resolution sub-grid and particle swarm optimization-based random forest approaches in GIS

“…Accuracy and precision of ML approaches were previously tested for flood probability by numerous researchers [25,26]. Decision tree (DT), artificial neural network, and logistic regression algorithms are some examples of ML models, and they are capable of modeling flooding probability and hazards [27]. Although some ML models can produce acceptable results, they still feature some special weak points that require improvement [28].…”

Applications of Open-Access Remotely Sensed Data for Flood Modelling and Mapping in Developing Regions

“…Analytical techniques for flood mapping using radar data include statistical active contouring, radiometric thresholding, histogram thresholding, pixel-based segmentation, fractal dimensioning of multi-temporal images, neural networks in a grid system, image segmentation and decision tree analysis [157,158]. Despite the advantages of radar RS, sensor noise and backscatter from vegetation and buildings have been identified as factors that hamper flood discrimination potential using radar data [157,159,160]. Furthermore, the temporal resolution, spatial accuracy and flood detection precision also affect the usability of radar images, especial for near-real-time flood forecasting in data-sparse regions [161,162].…”

“…advantages of radar RS, sensor noise and backscatter from vegetation and buildings have been identified as factors that hamper flood discrimination potential using radar data [157,159,160]. Furthermore, the temporal resolution, spatial accuracy and flood detection precision also affect the usability of radar images, especial for near-real-time flood forecasting in data-sparse regions [161,162].…”

A study on dynamic evaluation of urban integrated natural disaster risk based on vague set and information axiom

“…With the in-depth study of natural disaster risk, the development of risk assessment methods has experienced a process from qualitative to quantitative, from certainty to uncertainty and from stochastic uncertainty to fuzzy uncertainty (Yan and Zuo 2010;Lamovec et al 2012;Zhao et al 2012;Yoshimatsu and Abe 2006;Korkmaz, 2009;Liu and Xu 2007;Liu et al 2009;Genserik 2012;Wu et al 2008;Anselmo et al 1996;Zuo et al 2012;Chen et al 2011). However, these methods were used for some kind of disaster.…”