• Energy Research

Changes in streamflow within catchments can have a significant impact on agricultural production, as soil moisture loss, as well as frequent drying and wetting, may have an effect on the nutrient availability of many soils. In order to predict future changes and explore the impact of different scenarios, machine learning techniques have been used recently in the hydrological sector for simulation streamflow. This paper compares the use of four different models, namely artificial neural networks (ANNs), support vector machine regression (SVR), wavelet-ANN, and wavelet-SVR as surrogate models for a geophysical hydrological model to simulate the long-term daily water level and water flow in the River Shannon hydrological system in Ireland. The performance of the models has been tested for multi-lag values and for forecasting both short- and long-term time scales. For simulating the water flow of the catchment hydrological system, the SVR-based surrogate model performs best overall. Regarding modeling the water level on the catchment scale, the hybrid model wavelet-ANN performs the best among all the constructed models. It is shown that the data-driven methods are useful for exploring hydrological changes in a large multi-station catchment, with low computational cost.

Unequivocal change in the climate system has put coastal regions around the world at increasing risk from climate-related hazards. Monitoring the coast is often difficult and expensive, resulting in sparse monitoring equipment lacking in sufficient temporal and spatial coverage. Thus, low-cost methods to monitor the coast at finer temporal and spatial resolution are imperative for climate resilience along the world’s coasts. Exploiting such low-cost methods for the development of early warning support could be invaluable to coastal settlements. This paper aims to provide the most up-to-date low-cost techniques developed and used in the last decade for monitoring coastal hazards and their forcing agents via systematic review of the peer-reviewed literature in three scientific databases: Scopus, Web of Science and ScienceDirect. A total of 60 papers retrieved from these databases through the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol were analysed in detail to yield different categories of low-cost sensors. These sensors span the entire domain for monitoring coastal hazards, as they focus on monitoring coastal zone characteristics (e.g., topography), forcing agents (e.g., water levels), and the hazards themselves (e.g., coastal flooding). It was found from the meta-analysis of the retrieved papers that terrestrial photogrammetry, followed by aerial photogrammetry, was the most widely used technique for monitoring different coastal hazards, mainly coastal erosion and shoreline change. Different monitoring techniques are available to monitor the same hazard/forcing agent, for instance, unmanned aerial vehicles (UAVs), time-lapse cameras, and wireless sensor networks (WSNs) for monitoring coastal morphological changes such as beach erosion, creating opportunities to not only select but also combine different techniques to meet specific monitoring objectives. The sensors considered in this paper are useful for monitoring the most pressing challenges in coastal zones due to the changing climate. Such a review could be extended to encompass more sensors and variables in the future due to the systematic approach of this review. This study is the first to systematically review a wide range of low-cost sensors available for the monitoring of coastal zones in the context of changing climate and is expected to benefit coastal researchers and managers to choose suitable low-cost sensors to meet their desired objectives for the regular monitoring of the coast to increase climate resilience.