Flood Hazard Risk Mapping Using a Pseudo Supervised Random Forest

Abstract

Devastating floods occur regularly around the world. Recently, machine learning models have been used for flood susceptibility mapping. However, even when these algorithms are provided with adequate ground truth training samples, they can fail to predict flood extends reliably. On the other hand, the height above nearest drainage (HAND) model can produce flood prediction maps with limited accuracy. The objective of this research is to produce an accurate and dynamic flood modeling technique to produce flood maps as a function of water level by combining the HAND model and machine learning. In this paper, the HAND model was utilized to generate a preliminary flood map; then, the predictions of the HAND model were used to produce pseudo training samples for a R.F. model. To improve the R.F. training stage, five of the most effective flood mapping conditioning factors are used, namely, Altitude, Slope, Aspect, Distance from River and Land use/cover map. In this approach, the R.F. model is trained to dynamically estimate the flood extent with the pseudo training points acquired from the HAND model. However, due to the limited accuracy of the HAND model, a random sample consensus (RANSAC) method was used to detect outliers. The accuracy of the proposed model for flood extent prediction, was tested on different flood events in the city of Fredericton, NB, Canada in 2014, 2016, 2018, 2019. Furthermore, to ensure that the proposed model can produce accurate flood maps in other areas as well, it was also tested on the 2019 flood in Gatineau, QC, Canada. Accuracy assessment metrics, such as overall accuracy, Cohen’s kappa coefficient, Matthews correlation coefficient, true positive rate (TPR), true negative rate (TNR), false positive rate (FPR) and false negative rate (FNR), were used to compare the predicted flood extent of the study areas, to the extent estimated by the HAND model and the extent imaged by Sentinel-2 and Landsat satellites. The results confirm that the proposed model can improve the flood extent prediction of the HAND model without using any ground truth training data.

InundatEd-v1.0: a height above nearest drainage (HAND)-based flood risk modeling system using a discrete global grid system

“…At regional scale, Burn (1997) has discussed the catchment procedure essential to undertake the flood frequency analysis. Faulkner et al (2016) devised the procedure to estimate the design flood levels using the available station data. Regional hydrological frequency analysis at ungauged sites is also studied by few researchers (Desai and Ouarda, 2021).…”

“…To this end, annual maximum discharge values (m 3 s −1 ) were extracted within R (R Core Team, 2019) at hydrometric stations maintained by Environment Canada within the Grand River and Ottawa River watersheds (HY-DAT) (Hutchinson, 2016). Only stations with a period of record >= 10 years of annual maximum discharge (England et al, 2018;Faulkner et al, 2016) were maintained (n = 32 and n = 54, respectively, for the Grand River watershed and the Ottawa River watershed). The minimum, median, and maximum periods of record for the Grand River watershed were 12, 50, and 86 years, respectively.…”

“…Hailegeorgis and Alfredsen (2017) discussed a regionalization procedure which ensures the homogeneity of the station-level data over any region. However, due to the limited availability of the discharge data, we avoided such subsampling and carried out the index flood method at the entire watershed scale (Faulkner et al, 2016). This, however, has impacted the upper quantiles of the flood estimation when comparing to the station-level data (Sect.…”

Deep Neural Network Utilizing Remote Sensing Datasets for Flood Hazard Susceptibility Mapping in Brisbane, Australia

“…Excessive urbanization and climate change are more often blamed as the main reasons for such hazards [1,2]. The massive human, economic, and infrastructure losses resulting from flood occurrences necessitate flood management, prediction, and early warning systems [3,4]. At a global scale, in the period 1995-2015, it was reported that 109 million people were influenced by flood hazards, with annual direct costs of 75 billion dollars [5]; only between 2011-2012, indirect damages and losses were reported as 95 billion dollars [6].…”

Inundation Assessment of the 2019 Typhoon Hagibis in Japan Using Multi-Temporal Sentinel-1 Intensity Images

“…Besides traditional methods, machine learning and statistical models have been used to investigate the probability of being flooded [35][36][37][38]. Different topographical, hydrological, and geological condition factors were applied to the existing machine learning models; then, the best conditioning factors and the models with the best results were adopted to generate flood susceptibility maps [35,36]. Moya et al [37] introduced a supervised machine learning classifier to learn from a past event to identify flooded areas during Typhoon Habibis.…”