Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach
There is currently a scarcity of paired in-situ aquatic optical and biogeophysical data for productive inland waters, which critically hinders our capacity to develop and validate robust retrieval models for Earth Observation applications. This study aims to address this limitation through the devel...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-03-01
|
Series: | Frontiers in Environmental Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2021.587660/full |
id |
doaj-c3d07ef80a59409c9df5a0cacc5ec617 |
---|---|
record_format |
Article |
spelling |
doaj-c3d07ef80a59409c9df5a0cacc5ec6172021-03-10T04:31:15ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2021-03-01910.3389/fenvs.2021.587660587660Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning ApproachJeremy Kravitz0Jeremy Kravitz1Mark Matthews2Lisl Lain3Sarah Fawcett4Stewart Bernard5Department of Oceanography, University of Cape Town, Cape Town, South AfricaBiospheric Science Branch, NASA Ames Research Center, Mountain View, CA, United StatesCyanoLakes (Pty) Ltd, Cape Town, South AfricaDepartment of Oceanography, University of Cape Town, Cape Town, South AfricaDepartment of Oceanography, University of Cape Town, Cape Town, South AfricaEarth Systems Earth Observation Division, CSIR, Cape Town, South AfricaThere is currently a scarcity of paired in-situ aquatic optical and biogeophysical data for productive inland waters, which critically hinders our capacity to develop and validate robust retrieval models for Earth Observation applications. This study aims to address this limitation through the development of a novel synthetic dataset of top-of-atmosphere and bottom-of-atmosphere reflectances, which is the first to encompass the immense natural optical variability present in inland waters. Novel aspects of the synthetic dataset include: 1) physics-based, two-layered, size- and type-specific phytoplankton inherent optical properties (IOPs) for mixed eukaryotic/cyanobacteria assemblages; 2) calculations of mixed assemblage chlorophyll-a (chl-a) fluorescence; 3) modeled phycocyanin concentration derived from assemblage-based phycocyanin absorption; 4) and paired sensor-specific top-of-atmosphere reflectances, including optically extreme cases and the contribution of green vegetation adjacency. The synthetic bottom-of-atmosphere reflectance spectra were compiled into 13 distinct optical water types similar to those discovered using in-situ data. Inspection showed similar relationships of concentrations and IOPs to those of natural waters. This dataset was used to calculate typical surviving water-leaving signal at top-of-atmosphere, and used to train and test four state-of-the-art machine learning architectures for multi-parameter retrieval and cross-sensor capability. Initial results provide reliable estimates of water quality parameters and IOPs over a highly dynamic range of water types, at various spectral and spatial sensor resolutions. The results of this work represent a significant leap forward in our capacity for routine, global monitoring of inland water quality.https://www.frontiersin.org/articles/10.3389/fenvs.2021.587660/fulleutrophicationEarth observationwater qualityinland watersmachine learningradiative transfer modeling |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jeremy Kravitz Jeremy Kravitz Mark Matthews Lisl Lain Sarah Fawcett Stewart Bernard |
spellingShingle |
Jeremy Kravitz Jeremy Kravitz Mark Matthews Lisl Lain Sarah Fawcett Stewart Bernard Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach Frontiers in Environmental Science eutrophication Earth observation water quality inland waters machine learning radiative transfer modeling |
author_facet |
Jeremy Kravitz Jeremy Kravitz Mark Matthews Lisl Lain Sarah Fawcett Stewart Bernard |
author_sort |
Jeremy Kravitz |
title |
Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach |
title_short |
Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach |
title_full |
Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach |
title_fullStr |
Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach |
title_full_unstemmed |
Potential for High Fidelity Global Mapping of Common Inland Water Quality Products at High Spatial and Temporal Resolutions Based on a Synthetic Data and Machine Learning Approach |
title_sort |
potential for high fidelity global mapping of common inland water quality products at high spatial and temporal resolutions based on a synthetic data and machine learning approach |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Environmental Science |
issn |
2296-665X |
publishDate |
2021-03-01 |
description |
There is currently a scarcity of paired in-situ aquatic optical and biogeophysical data for productive inland waters, which critically hinders our capacity to develop and validate robust retrieval models for Earth Observation applications. This study aims to address this limitation through the development of a novel synthetic dataset of top-of-atmosphere and bottom-of-atmosphere reflectances, which is the first to encompass the immense natural optical variability present in inland waters. Novel aspects of the synthetic dataset include: 1) physics-based, two-layered, size- and type-specific phytoplankton inherent optical properties (IOPs) for mixed eukaryotic/cyanobacteria assemblages; 2) calculations of mixed assemblage chlorophyll-a (chl-a) fluorescence; 3) modeled phycocyanin concentration derived from assemblage-based phycocyanin absorption; 4) and paired sensor-specific top-of-atmosphere reflectances, including optically extreme cases and the contribution of green vegetation adjacency. The synthetic bottom-of-atmosphere reflectance spectra were compiled into 13 distinct optical water types similar to those discovered using in-situ data. Inspection showed similar relationships of concentrations and IOPs to those of natural waters. This dataset was used to calculate typical surviving water-leaving signal at top-of-atmosphere, and used to train and test four state-of-the-art machine learning architectures for multi-parameter retrieval and cross-sensor capability. Initial results provide reliable estimates of water quality parameters and IOPs over a highly dynamic range of water types, at various spectral and spatial sensor resolutions. The results of this work represent a significant leap forward in our capacity for routine, global monitoring of inland water quality. |
topic |
eutrophication Earth observation water quality inland waters machine learning radiative transfer modeling |
url |
https://www.frontiersin.org/articles/10.3389/fenvs.2021.587660/full |
work_keys_str_mv |
AT jeremykravitz potentialforhighfidelityglobalmappingofcommoninlandwaterqualityproductsathighspatialandtemporalresolutionsbasedonasyntheticdataandmachinelearningapproach AT jeremykravitz potentialforhighfidelityglobalmappingofcommoninlandwaterqualityproductsathighspatialandtemporalresolutionsbasedonasyntheticdataandmachinelearningapproach AT markmatthews potentialforhighfidelityglobalmappingofcommoninlandwaterqualityproductsathighspatialandtemporalresolutionsbasedonasyntheticdataandmachinelearningapproach AT lisllain potentialforhighfidelityglobalmappingofcommoninlandwaterqualityproductsathighspatialandtemporalresolutionsbasedonasyntheticdataandmachinelearningapproach AT sarahfawcett potentialforhighfidelityglobalmappingofcommoninlandwaterqualityproductsathighspatialandtemporalresolutionsbasedonasyntheticdataandmachinelearningapproach AT stewartbernard potentialforhighfidelityglobalmappingofcommoninlandwaterqualityproductsathighspatialandtemporalresolutionsbasedonasyntheticdataandmachinelearningapproach |
_version_ |
1724227081311617024 |