Hydrologic model performance evaluation depends on streamflow observations that are accurately positioned in the landscape. For distributed hydrologic models, this means that the streamflow observation need to be mapped to a location along the model streamflow network that represents the location of the observation station in a hydrologic system. However, the gridded representation of the modelled area causes a spatial mismatch between the hydrologic system and hydrologic model. In this study we aimed to develop a Machine learning-based method to improve matching between streamflow observations and streamflow simulations. The setup of this method was implemented in two steps: (1) a dataset was created consisting of streamflow characteristics of simulations and observations and (2) a Machine learning algorithm was trained with the created dataset. Three data sources were used for the creation of the dataset: (1) 595 streamflow observations were retrieved from the Global Runoff Database Centre (GRDC), (2) streamflow simulations were extracted from the European Flood Alert System (EFAS) and (3) we were provided with a manually created and checked dataset by European Centre for Medium Range Weather Forecasts linking each GRDC observation to the correct EFAS grid cell. To link 60% of the observations in the dataset with the correct grid cells, the observations required to be moved away from the cell corresponding to the geolocation of the observations. The method developed in this study anticipated this by creating a search window around the initial location of each observation. The streamflow simulations were extracted from the grid cells in the search window and compared with the streamflow observation. The algorithm aimed to select the streamflow simulation that best reflected the characteristics of the streamflow observation. The characteristics were described with streamflow signatures. Four Machine learning algorithms, a Logistic Regression, Random Forest, Support Vector Machine and K Nearest Neighbours algorithm, were trained with a Kfold Cross Validation procedure to match streamflow simulations with streamflow observations based on streamflow signatures. Their performance was compared with four benchmark algorithms: a Center Cell benchmark which places the observations on their initial location, and the Root Mean Squared Error, Kling-Gupta Efficiency and Nash-Sutcliffe Efficiency benchmarks that compare the streamflow observation with the streamflow simulations. We identified the Logistic Regression and Random Forest algorithms as the best performing algorithms. However, neither outperformed all benchmarks. Despite these results, we show the potential to automate matching between streamflow observations and streamflow simulations with a ML-based approach in this study.

The Tsleil-Wautuh Nation (TWN) reserve, Sleil-Waututh, located at the north shore of the Burrard Inlet in Vancouver (British Columbia, Canada) is strongly influenced by climate change. Sea level rise, coastal flooding and shoreline erosion are contributing to loss of land, damages to infrastructure, ecosystem changes and exposure of historic sites with cultural value. The TWN are a First Nation, a recognized group of aboriginal people in Canada, and have lived in harmony on the lands and waters of the Burrard Inlet since time out of mind. As TWN has a sacred obligation to be caretakers of the land, they retained Kerr Wood Leidal (KWL) to conduct a climate change hazard and vulnerability assessment and to design a ten year climate change adaptation action plan. The existing conditions in the area are investigated from a technical, environmental and sociological point of view, including a study of the community context of the TWN. Climate change exposes the project area to hazards such as sea level rise, acidification and water temperature changes among others. After conducting a hazard assessment, the following climate change induced hazards are evaluated: Coastal flooding, coastal erosion, intertidal area change, ocean acidification, harmful algae blooms and other ocean conditions (water temperature, e.g.). The impact of waves and rising sea levels are assessed through an Xbeach model. The impact of harmful algae blooms and other ocean conditions are evaluated though literature research. The potential of four different approaches, varying from traditional to building with nature-based solutions, to mitigate the identified hazards are discussed: a rip rap, a nourishment, a salt marsh and a clam garden. They are evaluated based on technical, environmental, economic and social feasibility. For each alternative a trade-off exists between protection against the identified hazards – mainly between the ability of each of the solutions to prevent or mitigate coastal flooding and erosion while preserving the local ecosystem and intertidal area. All alternatives help the TWN in their own way and although further research has to be done, this report provides an insight in four possible alternatives that could support the process of developing a satisfactory solution for the coastal hazards that cause problems for the TWN people and their reserve.