Hybrid-based Bayesian algorithm and hydrologic indices for flash flood vulnerability assessment in coastal regions: machine learning, risk prediction, and environmental impact

Natural hazards and severe weather events are a matter of serious threat to humans, economic activities, and the environment. Flash floods are one of the extremely devastating natural events around the world. Consequently, the prediction and precise assessment of flash flood-prone areas are mandatory for any flood mitigation strategy. In this study, a new hybrid approach of machine learning (ML) algorithm and hydrologic indices opted to detect impacted and highly vulnerable areas. The obtained models were trained and validated using a total of 189 locations from Wadi Ghoweiba and surrounding area (case study). Various controlling factors including varied datasets such as stream transport index (STI), stream power index (SPI), lithological units, topographic wetness index (TWI), slope angle, stream density (SD), curvature, and slope aspect (SA) were utilized via hyper-parameter optimization setting to enhance the performance of the proposed model prediction. The hybrid machine learning (HML) model, developed by combining naïve Bayes (NïB) approach and hydrologic indices, was successfully implemented and utilized to investigate flash flood risk, sediment accumulation, and erosion predictions in the studied site. The synthesized new hybrid model demonstrated a model accuracy of 90.8% compared to 87.7% of NïB model, confirming the superior performance of the obtained model. Furthermore, the proposed model can be successfully employed in large-scale prediction applications.

Application of hydrological indices for erosion hazard mapping using Spatial Analyst tool

Hydrological indices provide excellent input to geographic information systems for the successful mapping of erosion-prone areas. In this research, a digital elevation model was processed and analyzed to obtain the necessary hydrological indices necessary for erosion modeling. The indices (such as sediment transport index, compound topography index, and stream power index) along with other themes (Like Slope gradient, curvature, distance to channels, and channel density) were overlaid using the "Weighted Sum" overlay tool in the geographic information system. The results showed that 33.14 km² of the test watershed (sub-basin of Abay, Ethiopia) falls in very high/severe erosion zone and needs immediate conservation measures. A total of 98.26 km², 153.40 km², and 263.17 km² fall in high-, moderate-, and low-erosion hazard zones, respectively. Therefore, the primary and secondary derivatives of the digital elevation model along with morphometric parameters coupled with a Spatial Analyst tool proves to be a powerful integrated approach in demarcating erosion vulnerable zones and could be applied at regional and continental scale for proper watershed management.

Ecohydrological Index, Native Fish, and Climate Trends and Relationships in the Kansas River Basin

This study quantified climatological and hydrological trends and relationships to presence and distribution of two native aquatic species in the Kansas River Basin over the past half-century. Trend analyses were applied to indicators of hydrologic alteration (IHAs) at 34 streamgages over a 50-year period (1962-2012). Results showed a significant negative trend in annual streamflow for 10 of 12 western streamgages (up to -7.65 mm/50 yr) and smaller negative trends for most other streamgages. Significant negative trends in western Basin streamflow were more widespread in summer (12 stations) than winter or spring (6 stations). The negative-trend magnitude and significance decreased from west to east for maximum-flow IHAs. Minimum- flow IHAs, however, significantly decreased at High Plains streamgages but significantly increased at Central Great Plains streamgages. Number of zero-flow days showed positive trends in the High Plains. Most streamgages showed negative trends in low- and high-flow pulse frequency and high-flow pulse duration, and positive trends in low-flow pulse duration. These results were consistent with increasing occurrence of drought. Shift in occurrence from present (1860-1950) to absent (2000-2012) was significantly related (p<0.10) to negative trends of 1-day maximum flows (both species) and indices associated with reduced spawning-season flows for Plains Minnow and shifting annual-flow timing and increased flow intermittency for Common Shiner. Both species were absent for all western Basin sites and had different responses to hydrological index trends at eastern Basin sites. These results demonstrate ecohydrological index changes impact distributions of native fish and suggest target factors for assessment or restoration activities.