Remote estimation of aquatic light environments using machine learning: A new management tool for submerged aquatic vegetation

Loading...
Thumbnail Image
File version

Accepted Manuscript (AM)

Author(s)
Pearson, Ryan M
Collier, Catherine J
Brown, Christopher J
Rasheed, Michael A
Bourner, Jessica
Turschwell, Mischa P
Sievers, Michael
Connolly, Rod M
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
2021
Size
File type(s)
Location
Abstract

Submerged aquatic vegetation (SAV; e.g. seagrasses, macroalgae), forms key habitats in shallow coastal systems that provide a plethora of ecosystem services, including coastal protection, climate mitigation and supporting fisheries production. Light limitation is a critical factor influencing the growth and survival of SAV, thus it is important to understand how much light SAV needs, and receives, to effectively assess the risk that light limitation poses. Light monitoring is commonly used to inform environmental decision making to minimise loss of SAV habitat, but the temporal and spatial extent of monitoring is often limited by cost and logistical difficulties. An ability to remotely estimate light across different locations can therefore improve the conservation and management of SAV habitats. Here we combine an extensive monitoring program with publicly available data and machine learning to develop a model that estimates the light reaching submerged seagrasses in a shallow subtropical embayment in southern Queensland, Australia. Our model accurately predicts the intensity of photosynthetically active radiation (PAR) reaching the canopy of SAV from entirely remotely available data. The best performing model predicted light intensity with >99% at the management relevant daily, and 14-day rolling average time resolutions. This model enables monitoring of light available to SAV without an ongoing need for in-water instruments, minimising cost and risk to personnel, and improving assessment speed. The technique can be applied to SAV management plans in shallow waters throughout the world, where suitable remote public data is available.

Journal Title

Science of The Total Environment

Conference Title
Book Title
Edition
Volume

782

Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement

© 2021 Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (http://creativecommons.org/licenses/by-nc-nd/4.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, providing that the work is properly cited.

Item Access Status
Note
Access the data
Related item(s)
Subject

Biological oceanography

Environmental sciences

Marine and estuarine ecology (incl. marine ichthyology)

Ecological impacts of climate change and ecological adaptation

Environmental assessment and monitoring

Environmental management

Artificial intelligence

Persistent link to this record
Citation

Pearson, RM; Collier, CJ; Brown, CJ; Rasheed, MA; Bourner, J; Turschwell, MP; Sievers, M; Connolly, RM, Remote estimation of aquatic light environments using machine learning: A new management tool for submerged aquatic vegetation, Science of The Total Environment, 2021, pp. 146886

Collections