NOAA-CESSRST Seminar Series
Understanding the Mechanics of Environmental Changes Using Autonomous Systems by Dr. Álvarez
Abstract
Dr. Laura Alvarez’s research efforts have followed two main cores, autonomous systems applied to earth sciences, and Computational Fluid Dynamics (CFD) modeling of river systems. In the autonomous systems field, she has been working on adapting algorithms of path planning for reconnaissance by applying machine learning in the development of autonomous robots, such as autonomous boats and Unmanned Aerial Systems (UAS) to deeply understand water-mediated environments, including bathymetry, flow features, object recognition, and material classifications. The use of autonomous systems significantly reduced the time of data collection and human power hours, compared to traditional methods, becoming an alternative for collecting and studying water bodies. One of the primary goals of this research is to achieve a deeper understanding of geomorphologic processes, where a-priori information is unavailable, using advanced algorithms adopted from geo-statistics, mathematics, geophysics, and information theory. She complements the robotics research with physically-based models as a tool to understand the fluid dynamics and macro-turbulence in relationship with sediment transport and bed evolution in large-scale scale river systems. She also develops state-of-the-art Computational Fluid Dynamics (CFD) models for the study of sediment transport and morphodynamic processes in fluvial systems. Her primary goal is to achieve a deeper understanding of fluid and sediment motion in river systems, and how these motions are represented at different spatial scales. In this seminar, Dr. Laura Alvarez will discuss her research.
Source: https://www.cessrst.org/news-and-events/event-detail/seminar-series-tbd-feb-11-2021
Merging Multi-Platform Sensors, Models and AI for Advanced Hydrologic Prediction by Dr. Moreno
Abstract
"Hyper-resolution, distributed hydrologic models coupled with high-resolution, distributed information from ground stations and remote sensing (from satellites, radars, or intelligent systems) have become an important tool for predicting the behavior of hydrosystems due to the comprehensive capabilities of their process-based representation, accurate results, and minimal calibration. The conceptual framework on which these models are built determines their broad applicability to a set of problems such as drought prediction, flood forecasting, water sustainability, and watershed responses under climate and land cover changes. Machine learning, as an emerging tool, complements observations and model outputs through big data synthesis, feature elicitation, pattern recognition, clustering, and the finding of dynamic data-based mathematical relationships.''
Source: https://www.cessrst.org/news-and-events/event-detail/seminar-series-tbd-feb-25-2021
Information and videos obtained from the NOAA-CESSRST official website.