Muhammad Naveed Khaliq

Traditionally streamflow forecasting is accomplished using process-based hydrological models. These models could range from simple lumped type to more detailed distributed models. Lumped type models are easy to setup while distributed models require considerable skill and experience for setup. Due to the growing availability of large amounts of spatial and temporal data from various sources, such as remote sensing and re-analyses, and recent advances in the computational power, machine learning models are gaining momentum for solving applied engineering problems, triggering conceptual shifts perhaps led by rapid progress in data science and availability of ready-to-be-deployed software tools. These models have the ability to extract complex dynamical nonlinearities without explicitly defining the involved physical processes and their governing mathematical formulations, as is followed in the case of hydrological models. It is believed that new trends and conceptual shifts are essential for generating new knowledge, challenging or validating prevailing assumptions, and enhancing operational applications, which may include several water management-related functions, hydropower generation operations, and flood risk management across a range of temporal and spatial scales.In this study, two deep learning variants of machine learning models, i.e., (1) the attention-based encoder-decoder bidirectional long short-term memory (AB-ED-BiLSTM) network and (2) the attention-based encoder-decoder bidirectional gated recurrent units (AB-ED-BiGRU) network, were tested on multiple watersheds selected from the Ottawa River Basin, Canada. After developing and successfully evaluating watershed-specific models, regional versions of both models were developed and tested based on the leave-one-watershed-out strategy to emulate an ungauged scenario. Both models were driven mainly by soil moisture states of watersheds and meteorological data in order to evaluate their usefulness for streamflow forecasting at ungauged locations. Although not as ideal as one would desire, these models demonstrated reasonable skill in forecasting streamflow with one to seven days lead time when assessed in terms of coefficient of determination, Nash-Sutcliff Efficiency, and Kling-Gupta Efficiency performance metrics. However, considerable discrepancies were noticed in simulating peak flow values for certain watersheds. Overall results of the study suggest that soil moisture driven machine learning models can potentially be used to develop streamflow forecasting tools for ungauged locations, with AB-ED-BiGRU being computationally an inexpensive option compared to the AB-ED-BiLSTM model. Additional investigations will be required to improve their performance further, e.g., by employing multiple soil moisture products, available through remote sensing and re-analyses sources, and ensemble modelling techniques. Based on continuous scientific progress, emerging machine learning frameworks and architectures, and better understanding of the origins and limitations of existing models, improved hydrological forecasting at ungagged locations can be made possible. In essence, this study contributes towards enhancing our understanding of the role of soil moisture in developing machine learning based streamflow modelling and forecasting tools to support operational applications at ungauged locations, which are often neglected when developing real-time streamflow forecasting systems.

Canada has a long history of recurrent flooding, which has resulted in significant damage and large government disaster assistance disbursements. The most expensive flood in Canada was the 2013 Alberta flood, which resulted in total estimated losses of over five billion dollars, according to the Canadian disaster database. There is an increasing body of literature, suggesting that future climate change will alter precipitation and streamflow characteristics, snowpack, and snowmelt timing and magnitude. Extreme inflows that exceed dam discharge and storage capacity can lead to dam breach, posing significant risks to lives and properties on the downstream. Dams constructed decades ago are specifically vulnerable to unprecedented flood events. Therefore, in addition to other actions, an important step for enhancing and assessing climate-resilience of dams is to develop climate change informed approaches for estimating design floods and associated guidelines. For the development of design flood estimation guidelines, a variety of literature was explored, including journal articles, national and international guidelines, technical reports, and documents pertaining to regional climate change and catastrophic events. In addition, outcomes from a number of targeted dam vulnerability assessment case studies, involving development of physics-informed non-stationary flood frequency relationships and flood envelop curves, were also considered. Through a systematic review of traditional design practices, careful examination of regional climate change vulnerabilities, and outcomes of targeted dam vulnerability assessment case studies, it was realized that a variety of approaches will be required to ensure future climate-resilience of dams of all sizes, ranging from low-risk small dams to high-risk large dams. Therefore, traditional design flood estimation methodologies need to be innovated, following new design philosophies, advances in climate change science, and improved understandings of regional flood generating mechanisms. This presentation will discuss the steps taken to develop design flood estimation guidelines and the outcomes of various research activities, including the development of physics-informed non-stationary flood frequency analyses and creation of regional flood envelop curves to support design of critical water infrastructure.

Instantaneous peak flows (IPFs) are often required to derive design values for sizing various hydraulic structures, such as culverts, bridges, and small dams/levees, in addition to informing several water resources management-related activities. Compared to mean daily flows (MDFs), which represent averaged flows over a period of 24 h, information on IPFs is often missing or unavailable in instrumental records. In this study, conventional methods for estimating IPFs from MDFs are evaluated and new methods based on the nonlinear regression framework and machine learning architectures are proposed and evaluated using streamflow records from all Canadian hydrometric stations with natural and regulated flow regimes. Based on a robust model selection criterion, it was found that multiple methods are suitable for estimating IPFs from MDFs, which precludes the idea of a single universal method. The performance of machine learning-based methods was also found reasonable compared to conventional and regression-based methods. To build on the strengths of individual methods, the fusion modeling concept from the machine learning area was invoked to synthesize outputs of multiple methods. The study findings are expected to be useful to the climate change adaptation community, which currently heavily relies on MDFs simulated by hydrologic models.

This study investigates the capability of sequence-to-sequence machine learning (ML) architectures in an effort to develop streamflow forecasting tools for Canadian watersheds. Such tools are useful to inform local and region-specific water management and flood forecasting related activities. Two powerful deep-learning variants of the Recurrent Neural Network were investigated, namely the standard and attention-based encoder-decoder long short-term memory (LSTM) models. Both models were forced with past hydro-meteorological states and daily meteorological data with a look-back time window of several days. These models were tested for 10 different watersheds from the Ottawa River watershed, located within the Great Lakes Saint-Lawrence region of Canada, an economic powerhouse of the country. The results of training and testing phases suggest that both models are able to simulate overall hydrograph patterns well when compared to observational records. Between the two models, the attention model significantly outperforms the standard model in all watersheds, suggesting the importance and usefulness of the attention mechanism in ML architectures, not well explored for hydrological applications. The mean performance accuracy of the attention model on unseen data, when assessed in terms of mean Nash–Sutcliffe Efficiency and Kling-Gupta Efficiency is, respectively, found to be 0.985 and 0.954 for these watersheds. Streamflow forecasts with lead times of up to 5 days with the attention model demonstrate overall skillful performance with well above the benchmark accuracy of 70%. The results of the study suggest that the encoder–decoder LSTM, with attention mechanism, is a powerful modelling choice for developing streamflow forecasting systems for Canadian watersheds.