Skip to main content

Research Repository

Advanced Search

Ocean colour remote sensing for wetland mapping and chlorophyll concentration monitoring with spontaneous fluorescence and stimulated emission

People Involved

Project Description

The environmental status of marine waters plays an important role in monitoring the water extending from the shoreline to deep oceanic waters. Current reporting is based on expensive ship-based surveys that have very limited spatio-temporal coverage. Satellite based ocean colour remote sensing has the potential to significantly enhance monitoring capabilities.
Existing algorithms for chlorophyll concentration break down in turbid coastal waters subject to sediment resuspension or high concentrations of coloured dissolved organics in freshwater run-off. This project will tackle this problem by addressing two critical bottlenecks. Firstly, we will use advanced machine learning techniques to automatically identify optical water types and establish Chl algorithm performance using existing in situ datasets. Secondly, we will map wetland and link it to water quality.
In this project, we will use existing state-of-the-art machine learning approaches to categorise optical signals from ocean colour imagery, for monitoring/inspection of coastal regions.

Project Acronym Ocean Colour Sensing
Status Project Complete
Funder(s) Royal Society of Edinburgh
Value £12,000.00
Project Dates May 1, 2020 - Oct 31, 2023

You might also like

MOSAiC: Floe-scale observation and quantification of Arctic sea ice breakup and floe size during the autumn-to-summer transition Jan 1, 2021 - Apr 30, 2022
The seasonal cycle of sea ice freeze-up, deformation, breakup and melt is an important feedback that affects the decline of Arctic sea ice. Thinner, smaller summer ice floes in the expanding marginal ice zone (MIZ) could lead to the formation of wint... Read More about MOSAiC: Floe-scale observation and quantification of Arctic sea ice breakup and floe size during the autumn-to-summer transition.

Data For Net Zero Jun 1, 2022 - May 31, 2025
The Data for Net Zero (D4NZ) initiative will deliver shared analytics platforms and data science projects. The science will provide fact-based understanding and awareness on thematic challenges, set by industry, to uncover insights and visions to hel... Read More about Data For Net Zero.

AI and Hyperspectral Imaging based Non-Destructive inspection for Advancing Peat Use Efficiency in Whisky Production: A Feasibility Study Oct 1, 2023 - Mar 31, 2024
This project aims to explore the feasibility of non-destructive inspection for peat using hyperspectral imagery and machine learning techniques. The primary objectives are to determine the quality of peat, measure the level of phenol released during... Read More about AI and Hyperspectral Imaging based Non-Destructive inspection for Advancing Peat Use Efficiency in Whisky Production: A Feasibility Study.