This project will develop techniques for the use of process and data driven computational models, data science, machine learning (ML) and artificial intelligence (AI) to support planning, design, and implementation of natural and nature-based features (NNBFs) in water resources infrastructure.
The
Ecohydrology Team at the ERDC Environmental Laboratory is conducting research to incorporate engineered natural and nature-based features (NNBFs) into water resources infrastructure planning and management to deliver economic, environmental, and social benefits.
Data-driven ML/AI models are needed to better simulate the evolution of NNBFs with the context of their environment on decadal timescales under a variety of possible loading conditions.
To parameterize these models, data science and literature review will be conducted to categorize and synthesize existing information about the performance of NNBFs in past experiments and to support the development of hybrid process-based, ML/AI engineering models.
Program Description/Objective:
The R&D objectives are to support several needs within this broad topic area, namely:
(1) the completion of literature reviews describing the state of research and practice and (2) short reports outlining methods, tasks, and deliverables for specific subtopics, which include:
(a) The role of AI/ML in supporting natural and nature-based features (NNBF) research and designs; b) Modeling feedbacks between physical and natural/ecological systems; (c) Characterization of NNBFs performance and risk reduction benefits, and (d)Engineered design of NNBFs.
Each of these literature reviews and short reports should be less than 10 pages, include citations and background data, code, etc.