Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing
Satellite remote sensing enables the mapping of large-scale spatiotemporal variations of Water Quality (WQ) parameters, including Total Suspended Solids (TSS) and Dissolved Organic Carbon (DOC). Ground-based bio-optical measurements are used to quantify and evaluate the relationship between the remo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954125002857 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849233609177694208 |
|---|---|
| author | S.L. Kesav Unnithan Nagur Cherukuru Timothy Ingleton Eric Lehmann Matt Paget Yiqing Guo Nathan Drayson Gemma Kerrisk |
| author_facet | S.L. Kesav Unnithan Nagur Cherukuru Timothy Ingleton Eric Lehmann Matt Paget Yiqing Guo Nathan Drayson Gemma Kerrisk |
| author_sort | S.L. Kesav Unnithan |
| collection | DOAJ |
| description | Satellite remote sensing enables the mapping of large-scale spatiotemporal variations of Water Quality (WQ) parameters, including Total Suspended Solids (TSS) and Dissolved Organic Carbon (DOC). Ground-based bio-optical measurements are used to quantify and evaluate the relationship between the remote sensing reflectance (Rrs) and the in-situ WQ parameters. However, the non-linear relationship is strongly influenced by optically complex coastal regions. We focus on quantifying the non-linear Rrs – WQ relationship using a dense Deep Learning (DL) model trained on an augmented spectral library dataset covering estuarine and off-shore regions along New South Wales coastline, Australia. The spectral library consists of WQ parameters and Inherent Optical Properties (IOP) of water samples, including absorption and backscattering coefficients that drive a radiative transfer model to derive resultant Rrs. We incorporate uncertainty into the WQ−IOP measurements and simulate an augmented spectral library for training a DL model for aquatic Remote Sensing (DL-RS) applications. The model error analysis revealed a) an inherent Mean Absolute Error (MAE) of 7 % for TSS and 22 % for DOC, b) a predictive MAE of 75 % (TSS) and 31 % (DOC) in temperate waters, and c) an in-situ optical closure predictive MAE of 18 % and a Mean Percentage Error of ±5 % upon comparing forward modelled Rrs outputs from DL-RS-derived IOP and WQ parameters with atmospherically corrected Landsat-8 imagery (2013−2022). The DL-RS model demonstrated improved performance and added computational efficiency over existing inversion models. The model thus provides valuable insights into the dynamics of WQ parameters in optically complex waters influenced by diverse land cover catchments. |
| format | Article |
| id | doaj-art-9f9c1e48b0754bd7843865587a0e5ecb |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-9f9c1e48b0754bd7843865587a0e5ecb2025-08-20T05:05:30ZengElsevierEcological Informatics1574-95412025-12-019010327610.1016/j.ecoinf.2025.103276Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensingS.L. Kesav Unnithan0Nagur Cherukuru1Timothy Ingleton2Eric Lehmann3Matt Paget4Yiqing Guo5Nathan Drayson6Gemma Kerrisk7Commonwealth Scientific and Industrial Research Organisation, Environment, Canberra 2601, Australia; Corresponding author.Commonwealth Scientific and Industrial Research Organisation, Environment, Canberra 2601, AustraliaNew South Wales Department of Climate Change, Energy, the Environment and Water, Sydney 2141, AustraliaCommonwealth Scientific and Industrial Research Organisation, Data61, Canberra 2601, AustraliaCommonwealth Scientific and Industrial Research Organisation, Environment, Canberra 2601, AustraliaCommonwealth Scientific and Industrial Research Organisation, Data61, Canberra 2601, AustraliaCommonwealth Scientific and Industrial Research Organisation, Environment, Canberra 2601, AustraliaCommonwealth Scientific and Industrial Research Organisation, Environment, Canberra 2601, AustraliaSatellite remote sensing enables the mapping of large-scale spatiotemporal variations of Water Quality (WQ) parameters, including Total Suspended Solids (TSS) and Dissolved Organic Carbon (DOC). Ground-based bio-optical measurements are used to quantify and evaluate the relationship between the remote sensing reflectance (Rrs) and the in-situ WQ parameters. However, the non-linear relationship is strongly influenced by optically complex coastal regions. We focus on quantifying the non-linear Rrs – WQ relationship using a dense Deep Learning (DL) model trained on an augmented spectral library dataset covering estuarine and off-shore regions along New South Wales coastline, Australia. The spectral library consists of WQ parameters and Inherent Optical Properties (IOP) of water samples, including absorption and backscattering coefficients that drive a radiative transfer model to derive resultant Rrs. We incorporate uncertainty into the WQ−IOP measurements and simulate an augmented spectral library for training a DL model for aquatic Remote Sensing (DL-RS) applications. The model error analysis revealed a) an inherent Mean Absolute Error (MAE) of 7 % for TSS and 22 % for DOC, b) a predictive MAE of 75 % (TSS) and 31 % (DOC) in temperate waters, and c) an in-situ optical closure predictive MAE of 18 % and a Mean Percentage Error of ±5 % upon comparing forward modelled Rrs outputs from DL-RS-derived IOP and WQ parameters with atmospherically corrected Landsat-8 imagery (2013−2022). The DL-RS model demonstrated improved performance and added computational efficiency over existing inversion models. The model thus provides valuable insights into the dynamics of WQ parameters in optically complex waters influenced by diverse land cover catchments.http://www.sciencedirect.com/science/article/pii/S1574954125002857Large-scale water quality mappingHigh-resolution optical remote sensingDeep learning |
| spellingShingle | S.L. Kesav Unnithan Nagur Cherukuru Timothy Ingleton Eric Lehmann Matt Paget Yiqing Guo Nathan Drayson Gemma Kerrisk Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing Ecological Informatics Large-scale water quality mapping High-resolution optical remote sensing Deep learning |
| title | Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing |
| title_full | Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing |
| title_fullStr | Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing |
| title_full_unstemmed | Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing |
| title_short | Mapping total suspended solids (TSS) and dissolved organic carbon (DOC) in complex coastal waters using deep learning enhanced remote sensing |
| title_sort | mapping total suspended solids tss and dissolved organic carbon doc in complex coastal waters using deep learning enhanced remote sensing |
| topic | Large-scale water quality mapping High-resolution optical remote sensing Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S1574954125002857 |
| work_keys_str_mv | AT slkesavunnithan mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT nagurcherukuru mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT timothyingleton mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT ericlehmann mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT mattpaget mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT yiqingguo mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT nathandrayson mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing AT gemmakerrisk mappingtotalsuspendedsolidstssanddissolvedorganiccarbondocincomplexcoastalwatersusingdeeplearningenhancedremotesensing |