Rainfall-runoff simulation is vital for planning and controlling flood control events. Hydrology modeling using Hydrological Engineering Center—Hydrologic Modeling System (HEC-HMS) is accepted globally for event-based or continuous simulation of the rainfall-runoff operation. Similarly, machine learning is a fast-growing discipline that offers numerous alternatives suitable for hydrology research’s high demands and limitations. Conventional and process-based models such as HEC-HMS are typically created at specific spatiotemporal scales and do not easily fit the diversified and complex input parameters. Therefore, in this research, the effectiveness of Random Forest, a machine learning model, was compared with HEC-HMS for the rainfall-runoff process. Furthermore, we also performed a hydraulic simulation in Hydrological Engineering Center—Geospatial River Analysis System (HEC-RAS) using the input discharge obtained from the Random Forest model. The reliability of the Random Forest model and the HEC-HMS model was evaluated using different statistical indexes. The coefficient of determination (R²), standard deviation ratio (RSR), and normalized root mean square error (NRMSE) were 0.94, 0.23, and 0.17 for the training data and 0.72, 0.56, and 0.26 for the testing data, respectively, for the Random Forest model. Similarly, the R², RSR, and NRMSE were 0.99, 0.16, and 0.06 for the calibration period and 0.96, 0.35, and 0.10 for the validation period, respectively, for the HEC-HMS model. The Random Forest model slightly underestimated peak discharge values, whereas the HEC-HMS model slightly overestimated the peak discharge value. Statistical index values illustrated the good performance of the Random Forest and HEC-HMS models, which revealed the suitability of both models for hydrology analysis. In addition, the flood depth generated by HEC-RAS using the Random Forest predicted discharge underestimated the flood depth during the peak flooding event. This result proves that HEC-HMS could compensate Random Forest for the peak discharge and flood depth during extreme events. In conclusion, the integrated machine learning and physical-based model can provide more confidence in rainfall-runoff and flood depth prediction.

Land use and land cover (LULC) change is one of the primary contributors to hydrological change in urban watersheds and can potentially influence stream flow and flood volume. Understanding the impacts of LULC change on urban hydrological processes is critical to effective urban water management and minimizing flood risks. In this context, this study aims to determine the impacts of LULC change on hydrological response in a fast transitioning watershed for the predicted years of 2050 and 2080. This research employs the hybrid land use classification technique, Cellular Automata–Markov (CA–Markov) model to predict land use changes, utilizing land use data from 2001, 2013, and 2021. Additionally, it incorporates a calibrated, event-specific hydrologic model known as the Personal Computer Storm Water Management Model (PCSWMM) to assess alterations in hydrological responses for storm events of various magnitudes. The findings indicate a transition of the watershed into an urbanized landscape, replacing the previous dominance of agriculture and forested areas. The initial urban area, constituting 11.6% of the total area in 2021, expands to cover 34.1% and 44.2% of the total area by 2050 and 2080, respectively. Due to the LULC changes, there are increases in peak discharge of 5% and 6.8% and in runoff volume of 8% and 13.3% for the years 2050 and 2080 for a 100-year return period storm event. Yet, the extent of these changes intensifies notably during storm events with lower return periods. This heightened impact is directly attributed to the swift urbanization of the watershed. These results underscore the pressing necessity to regulate LULC change to preserve the hydrological equilibrium.

Floods are amongst the most destructive and costly natural disasters impacting communities around the globe. The severity and reoccurrence of flooding events have been more common in recent years as a result of the changing climate and urbanization. Best Management Practices (BMPs) are commonly used flood management techniques that aim to alleviate flooding and its impacts by capturing surface runoff and promoting infiltration. Recent studies have examined the effectiveness of BMPs in countering the effects of flooding; however, the performance of such strategies still needs to be analyzed for possible future climate change. In this context, this research employs climate model-driven datasets from the North American Regional Climate Change Assessment Program to evaluate the effects of climate change on urban hydrology within a study region by calculating historical and projected 6 h 100-year storm depths. Finally, the climate-induced design storms are simulated in the PCSWMM model, and the three BMP options (i.e., porous pavement, infiltration trench, and green roof) are evaluated to alleviate the impact of flooding events. This study quantifies the impact of changing climate on flood severity based on future climate models. The results indicate that peak discharge and peak volume are projected to increase by a range of 5% to 43% and 8% to 94%, respectively. In addition, the results demonstrated that green roofs, Permeable Pavement, and infiltration trenches help to reduce peak discharge by up to 7%, 14%, and 15% and reduce flood volume by up to 19%, 24%, and 29%, respectively, thereby presenting a promising solution to address the challenges posed by climate change-induced flooding events.

Drought is a complex environmental hazard to ecosystems and society. Decision-making on drought management options requires evaluating and predicting the extremity of future drought events. In this regard, quantifiable indices such as the standardized precipitation index (SPI), the standardized precipitation evapotranspiration index (SPEI), and the standardized streamflow index (SSI) have been commonly used to characterize meteorological and hydrological drought. In general, the estimation and prediction of the indices require an extensive range of precipitation (SPI and SPEI) and discharge (SSI) datasets in space and time domains. However, there is a challenge for long-term and spatially extensive data availability, leading to the insufficiency of data in estimating drought indices. In this regard, this study uses satellite precipitation data to estimate and predict the drought indices. SPI values were calculated from the precipitation data obtained from the Centre for Hydrometeorology and Remote Sensing (CHRS) data portal for a study water basin. This study employs a hydrological model for calculating discharge and drought in the overall basin. It uses random forest (RF) and support vector regression (SVR) as machine learning models for SSI prediction for time scales of 1- and 3-month periods, which are widely used for establishing interactions between predictors and predictands that are both linear and non-linear. This study aims to evaluate drought severity variation in the overall basin using the hydrological model and compare this result with the machine learning model’s results. The results from the prediction model, hydrological model, and the station data show better correlation. The coefficients of determination obtained for 1-month SSI are 0.842 and 0.696, and those for the 3-month SSI are 0.919 and 0.862 in the RF and SVR models, respectively. These results also revealed more precise predictions of machine learning models in the longer duration as compared to the shorter one, with the better prediction result being from the SVR model. The hydrological model-evaluated SSI has 0.885 and 0.826 coefficients of determination for the 1- and 3-month time durations, respectively. The results and discussion in this research will aid planners and decision-makers in managing hydrological droughts in basins.

The experiences from recent urban flooding events suggest that the conventional centralized detention systems based on detention size expansion with minimum costs need to accommodate the extreme flooding events exceeding their design capacity. This study investigated the resilience effects of decentralized detention systems to address extreme flooding events in urban areas. An integrated flood resilience measure that integrates the regional performance of sub-basins with a decentralized flood control system was proposed and applied to an urban watershed including five sub-basins. Hydrologic and hydraulic analysis to quantify the hydrologic responses and resilience of the watershed to flooding scenarios was performed using the Hydrological Modeling System and Geospatial River Analysis System of Hydrological Engineering Centre models. The results identified the best locations of distributed detention ponds and characterized the effects of the decentralization levels of the detention system on enhancing flood resilience to extreme events. Additionally, an increase in the resilience effects of the decentralized detention system was found in the cases of more extreme flooding events from the combined impacts of high-intensity rainfall and land cover change. The findings suggest insights into incorporating decentralization strategies into decision-making on detention systems to resiliently cope with extreme flooding events in urban watersheds.