Enhancing flood susceptibility modeling using multi-temporal SAR images, CHIRPS data, and hybrid machine learning algorithms

Mostafa Riazi; Khabat Khosravi; Kaka Shahedi; Sajjad Ahmad; Changhyun Jun; Sayed M Bateni; Nerantzis Kazakis

doi:10.1016/j.scitotenv.2023.162066

Enhancing flood susceptibility modeling using multi-temporal SAR images, CHIRPS data, and hybrid machine learning algorithms

Sci Total Environ. 2023 May 1:871:162066. doi: 10.1016/j.scitotenv.2023.162066. Epub 2023 Feb 10.

Authors

Mostafa Riazi¹, Khabat Khosravi², Kaka Shahedi³, Sajjad Ahmad⁴, Changhyun Jun⁵, Sayed M Bateni⁶, Nerantzis Kazakis⁷

Affiliations

¹ Department of Civil Engineering, Islamic Azad University of Khomeinishahr, Khomeinishahr, Iran.
² Department of Earth and Environment, Florida International University, Miami, USA.
³ Department of Watershed Management, Sari Agricultural Science and Natural Resources University, Sari, Iran.
⁴ Department of Civil and Environmental Engineering and Construction, University of Nevada, Las Vegas, USA.
⁵ Department of Civil and Environmental Engineering, College of Engineering, Chung-Ang University, Seoul, Republic of Korea. Electronic address: cjun@cau.ac.kr.
⁶ Department of Civil and Environmental Engineering and Water Resources Research Center, University of Hawaii at Manoa, Honolulu, HI, USA.
⁷ Department of Geology, Lab. of Engineering Geology & Hydrogeology, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece. Electronic address: kazakis@geo.auth.gr.

PMID: 36773901
DOI: 10.1016/j.scitotenv.2023.162066

Abstract

Flood susceptibility maps are useful tool for planners and emergency management professionals in the early warning and mitigation stages of floods. In this study, Sentinel-1 dB radar images, which provide Synthetic-Aperture Radar (SAR) data were used to delineate flooded and non-flooded locations. 12 input parameters, including elevation, lithology, drainage density, rainfall, Normalized Difference Vegetation Index (NDVI), curvature, ground slope, Stream Power Index (SPI), Topographic Wetness Index (TWI), soil, Land Use Land Cover (LULC), and distance from the river, were selected for model development. The importance of each input parameter on flood occurrences was assessed via the Mutual Information (MI) technique. Several machine learning models, including Radial Basis Function (RBF), and three hybrid models of Bagging (BA-RBF), Random Committee (RC-RBF), and Random Subspace (RSS-RBF), were developed to delineate flood susceptibility areas at Goorganrood watershed, Iran. The performance of each model was evaluated using several error indicators, including correlation coefficient (r), Nash Sutcliffe Efficiency (NSE), Mean Absolute Error (MSE), Root Mean Square Error (RMSE), and the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC). The results showed that the hybrid techniques enhanced the modeling performance of the standalone model, and generally, all hybrid models are more accurate than the standalone model. Although all developed models have performed well, RC-RBF outperforms all of them (AUC = 0.997), followed by BA-RBF (AUC = 0.996), RSS-RBF (AUC = 0.992), and RBF (AUC = 0.975). Generally, about 12 % of the study area has high and very high susceptibility to future flood occurrences.

Keywords: BA-RBF; CHIRPS data; Flood susceptibility mapping; Gorganrood watershed; Machine learning; Sentinel-1 SAR.