No abstract

No abstract

Urban flooding poses risks to the safety of drivers and pedestrians, and damages infrastructures and lifelines. It is important to accommodate cities and local agencies with enhanced rapid flood detection skills and tools to better understand how much flooding a region may experience at a certain period of time. This results in flood management orders being announced in a timely manner, allowing residents and drivers to preemptively avoid flooded areas. This research combines information received from ground observed data derived from road closure reports from the police department, with remotely sensed satellite imagery to develop and train machine-learning models for flood detection for the City of San Diego, CA, USA. For this purpose, flooding information are extracted from Sentinel 1 satellite imagery and fed into various supervised and unsupervised machine learning models, including Random Forest (RF), Support Vector Machine (SVM), and Maximum Likelihood Classifier (MLC), to detect flooded pixels in images and evaluate the performance of these ML models. Moreover, a new unsupervised machine learning framework is developed which works based on the change detection (CD) approach and combines the Otsu algorithm, fuzzy rules, and iso-clustering methods for urban flood detection. Results from the performance evaluation of RF, SVM, MLC and CD models show 0.53, 0.85, 0.75 and 0.81 precision measures, 0.9, 0.85, 0.85 and 0.9 for recall values, 0.67, 0.85, 0.79 and 0.85 for the F1-score, and 0.69, 0.87, 0.83 and 0.87 for the accuracy measure, respectively, for each model. In conclusion, the new unsupervised flood image classification and detection method offers better performance with the least required data and computational time for enhanced rapid flood mapping. This systematic approach will be potentially useful for other cities at risk of urban flooding, and hopefully for detecting nuisance floods, by using satellite images and reducing the flood risk of transportation design and urban infrastructure planning.

Coastal hazard vulnerability assessment has been centered around the multi-variate analysis of geo-physical and hydroclimate data. The representation of coupled socio-environmental factors has often been ignored in vulnerability assessment. This study develops an integrated socio-environmental Coastal Vulnerability Index (CVI), which simultaneously combines information from five vulnerability groups: biophysical, hydroclimate, socio-economic, ecological, and shoreline. Using the Multi-Criteria Decision Making (MCDM) approach, two CVI (CVI-50 and CVI-90) have been developed based on average and extreme conditions of the factors. Each CVI is then compared to a data-driven CVI, which is formed based on Probabilistic Principal Component Analysis (PPCA). Both MCDM and PPCA have been tied into geospatial analysis to assess the natural hazard vulnerability of six coastal counties in South Carolina. Despite traditional MCDM-based vulnerability assessments, where the final index is estimated based on subjective weighting methods or equal weights, this study employs an entropy weighting technique to reduce the individuals’ biases in weight assignment. Considering the multivariate nature of the coastal vulnerability, the validation results show both CVI-90 and PPCA preserve the vulnerability results from biophysical and socio-economic factors reasonably, while the CVI-50 methods underestimate the biophysical vulnerability of coastal hazards. Sensitivity analysis of CVIs shows that Charleston County is more sensitive to socio-economic factors, whereas in Horry County the physical factors contribute to a higher degree of vulnerability. Findings from this study suggest that the PPCA technique facilitates the high-dimensional vulnerability assessment, while the MCDM approach accounts more for decision-makers' opinions.

No abstract