Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model building. The adoption of DL in hydrology has so far been gradual, but the field is now ripe for breakthroughs. This paper suggests that DL-based methods can open up a complementary avenue toward knowledge discovery in hydrologic sciences. In the new avenue, machine-learning algorithms present competing hypotheses that are consistent with data. Interrogative methods are then invoked to interpret DL models for scientists to further evaluate. However, hydrology presents many challenges for DL methods, such as data limitations, heterogeneity and co-evolution, and the general inexperience of the hydrologic field with DL. The roadmap toward DL-powered scientific advances will require the coordinated effort from a large community involving scientists and citizens. Integrating process-based models with DL models will help alleviate data limitations. The sharing of data and baseline models will improve the efficiency of the community as a whole. Open competitions could serve as the organizing events to greatly propel growth and nurture data science education in hydrology, which demands a grassroots collaboration. The area of hydrologic DL presents numerous research opportunities that could, in turn, stimulate advances in machine learning as well.

Heavy rainfall leads to severe flooding problems with catastrophic socio-economic impacts worldwide. Hydrologic forecasting models have been applied to provide alerts of extreme flood events and reduce damage, yet they are still subject to many uncertainties due to the complexity of hydrologic processes and errors in forecasted timing and intensity of the floods. This study demonstrates the efficacy of using eXtreme Gradient Boosting (XGBoost) as a state-of-the-art machine learning (ML) model to forecast gauge stage levels at a 5-min interval with various look-out time windows. A flood alert system (FAS) built upon the XGBoost models is evaluated by two historical flooding events for a flood-prone watershed in Houston, Texas. The predicted stage values from the FAS are compared with observed values with demonstrating good performance by statistical metrics (RMSE and KGE). This study further compares the performance from two scenarios with different input data settings of the FAS: (1) using the data from the gauges within the study area only and (2) including the data from additional gauges outside of the study area. The results suggest that models that use the gauge information within the study area only (Scenario 1) are sufficient and advantageous in terms of their accuracy in predicting the arrival times of the floods. One of the benefits of the FAS outlined in this study is that the XGBoost-based FAS can run in a continuous mode to automatically detect floods without requiring an external starting trigger to switch on as usually required by the conventional event-based FAS systems. This paper illustrates a data-driven FAS framework as a prototype that stakeholders can utilize solely based on their gauging information for local flood warning and mitigation practices.

The identification of flood hazards during emerging public safety crises such as hurricanes or flash floods is an invaluable tool for first responders and managers yet remains out of reach in any comprehensive sense when using traditional remote-sensing methods, due to cloud cover and other data-sourcing restrictions. While many remote-sensing techniques exist for floodwater identification and extraction, few studies demonstrate an up-to-day understanding with better techniques in isolating the spectral properties of floodwaters from collected data, which vary for each event. This study introduces a novel method for delineating near-real-time inundation flood extent and depth mapping for storm events, using an inexpensive unmanned aerial vehicle (UAV)-based multispectral remote-sensing platform, which was designed to be applicable for urban environments, under a wide range of atmospheric conditions. The methodology is demonstrated using an actual flooding-event—Hurricane Zeta during the 2020 Atlantic hurricane season. Referred to as the UAV and Floodwater Inundation and Depth Mapper (FIDM), the methodology consists of three major components, including aerial data collection, processing, and flood inundation (water surface extent) and depth mapping. The model results for inundation and depth were compared to a validation dataset and ground-truthing data, respectively. The results suggest that UAV-FIDM is able to predict inundation with a total error (sum of omission and commission errors) of 15.8% and produce flooding depth estimates that are accurate enough to be actionable to determine road closures for a real event.

This paper evaluates watershed-scale hydrologic performance of low-impact development (LID) features at two catchments in the Houston, Texas, region. White Oak Bayou is a traditional urban watershed that is frequently plagued with flooding. In contrast, The Woodlands is a master-planned suburban community designed to preserve its natural hydrology by implementing large-scale conservation features. The objectives of this study are threefold: (1) to propose a method to simulate small-scale infiltration-based LID features over a large area by using a distributed hydrologic model; (2) to quantify the cumulative hydrologic responses of watershedwide LID implementation; and (3) to compare the flood reduction potential between two distinct LID strategies (conservation LID and retrofit LID). Conservation (master-planned) LID integrates large-scale features (e.g., riparian buffers and swales) early in a watershed’s development, whereas retrofit LID implements site-scale features (e.g., green roofs and rain...