Remote Sensing (RS)
Somayeh Aslani Katouli; Reza Shah-Hosseini; Hamid Bagheri
Abstract
Extended Abstract
Introduction
A flood is a widespread and dramatic natural disaster that affects the life, infrastructure, economy, and local ecosystems of the world. In this paper, a method for flood detection in urban (and suburban) environments using the intensity and coherence of SAR based on ...
Read More
Extended Abstract
Introduction
A flood is a widespread and dramatic natural disaster that affects the life, infrastructure, economy, and local ecosystems of the world. In this paper, a method for flood detection in urban (and suburban) environments using the intensity and coherence of SAR based on a convolutional neural network is introduced, and from the time series of SAR intensity and coherence to draw flood without obstruction (e.g. Flooded bare soils and short vegetation) are used. Non-cohesive areas blocked by floods (e.g., flooded vegetation) and cohesive areas with flood-blocked areas (e.g., frequently constructed flooded areas) are distinguished.
This method is flexible according to the time period of the data sequences (at least one pair of pre-event and event intensities and one pair of pre-event and in-event coherence are required). The increasing number of SAR missions in orbit that have a fixed viewing scenario with a short retry time increases the chances of seeing a flood event, while also having a good pre-event scene achieved by the same sensor. This makes this method desirable for operational emergency responses.
Materials & Methods
CNN algorithm is a multilayer perceptron that is designed to identify two-dimensional information of images and includes: input layer, convolution layer, sample layer, and output layer. The CNN algorithm has two main processes: collection and sampling.
The convolution process involves the use of a trainable Fx filter, deconvolution of the input image (the first step of image input, input after image convolution, is the feature of each layer called Feature Map), then by adding bx can be hand convolution of the CX layer Found. Sampling process: n pixels are collected from each neighborhood to form a pixel, then weighted with a scalar weight of Wx + 1 and a bx + 1 bias is added, then a map of The Narrow n times feature map properties are generated.
Three images of Sentinel-1A VV polarization, wide width interference (IW), and mode (SLC) data were used in this study. Intensity images were pre-processed with radiometric calibration, noise reduced with a spell-filter (window size 5.5 pixels), and converted from linear units to decibels. Coherent images were obtained with a pair of consecutive images with a window of 7.28 (range _ azimuth). Validation data set due to the lack of other data in two separate sections of ground data in the urban area of GonbadKavous that have been collected to identify homes damaged by floods and terrestrial reality data from gamma image thresholds for output validation were extracted.
Results & Discussion
In this section, the results of the study are qualitatively and quantitatively analyzed. Because the simultaneous display of SAR data over time in the form of RGB compounds is widely used in the qualitative interpretation of land cover and surface dynamics, RGB compounds are used to provide evidence of flood magnitude in terms of intensity and coherence. For both cases, the results of combining intensity and coherence and intensity alone and coherence alone are quantitatively analyzed. Overall accuracy (OA), kappa correlation coefficient, false-positive rate (FPR), precision (e.g., correctly predicted positive patterns out of the total predicted patterns in a positive class), recall (e.g., a fraction of properly classified positive patterns), and an F1 score (ie the harmonic mean between precision and recall). Flood reference and ground data are mentioned and reported based on the reference.
Conclusion
In this paper, a method for mapping floods in urban environments based on SAR intensity and interferometry coherence was introduced. A combination of intensity and coherence extracts flood information in different types of land cover and outlet. This method was tested on the KavousGonbad flood incident obtained by various SAR sensors and the flood maps were confirmed by the flood reference resulting from thresholding and ground harvesting and satisfactory results were shown in this case study. The findings of this experiment show that the shared use of SAR intensity and coherence provides more reliable information than the use of SAR intensity and coherence alone in urban areas with different landscapes. In particular, flood detection in less cohesive / non-cohesive areas (e.g., bare soils, vegetation, vegetated areas) relies heavily on multi-temporality, while multi-temporal coherence provides more comprehensive flood information in areas Create coherence (e.g., mostly built-up areas). However, some flood-specific situations, such as flooded parking lots and flooded dense building blocks, are still challenging in terms of intensity and coherence. Also, since the proposed method is sensor and scene independent, with very frequent and regular observations of SAR missions such as Sentinel-1 and RADARSAT (RCM), there are opportunities to map global floods on a global scale, especially in small countries. Provides income.
