Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie
Ecosystems at coastal terrestrial–aquatic interfaces play a significant role in global biogeochemical cycles. In this study, we aimed to characterize coastal wetlands with particular focus on the co-variability between plant dynamics, topography, soil, and other environmental factors. We proposed a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/14/3285 |
| _version_ | 1797416170603675648 |
|---|---|
| author | Léa Enguehard Nicola Falco Myriam Schmutz Michelle E. Newcomer Joshua Ladau James B. Brown Laura Bourgeau-Chavez Haruko M. Wainwright |
| author_facet | Léa Enguehard Nicola Falco Myriam Schmutz Michelle E. Newcomer Joshua Ladau James B. Brown Laura Bourgeau-Chavez Haruko M. Wainwright |
| author_sort | Léa Enguehard |
| collection | DOAJ |
| description | Ecosystems at coastal terrestrial–aquatic interfaces play a significant role in global biogeochemical cycles. In this study, we aimed to characterize coastal wetlands with particular focus on the co-variability between plant dynamics, topography, soil, and other environmental factors. We proposed a functional zonation approach based on machine learning clustering to identify the spatial regions, i.e., zones that capture these co-varied properties. This approach was applied to publicly available datasets along Lake Erie, in the Great Lakes Region. We investigated the heterogeneity of coastal ecosystem structures as a function of along-shore distance and transverse distance, based on the spatial data layers, including topography, wetland vegetation cover, and the time series of Landsat’s enhanced vegetation index (EVI) between 1990 and 2020. Results showed that the topographic metrics (elevation and slope), soil texture, and plant productivity influence the spatial distribution of wetland land-covers (emergent and phragmites). These results highlight a natural organization along the transverse axis, where the elevation and the EVI increase further away from the coastline. In addition, the clustering analysis allowed us to identify regions with distinct environmental characteristics, as well as the ones that are more sensitive to interannual lake-level variations. |
| first_indexed | 2024-03-09T05:59:44Z |
| format | Article |
| id | doaj.art-ce53acf46d99468f96167ac11f124b5e |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:59:44Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ce53acf46d99468f96167ac11f124b5e2023-12-03T12:10:21ZengMDPI AGRemote Sensing2072-42922022-07-011414328510.3390/rs14143285Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake ErieLéa Enguehard0Nicola Falco1Myriam Schmutz2Michelle E. Newcomer3Joshua Ladau4James B. Brown5Laura Bourgeau-Chavez6Haruko M. Wainwright7Earth and Environmental Sciences Area, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USAEarth and Environmental Sciences Area, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USAEPOC UMR 5805, CNRS, Bordeaux INP, 1 Allée F. Daguin, 33607 Pessac, FranceEarth and Environmental Sciences Area, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USAComputational Biosciences Group, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USAComputational Biosciences Group, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USAMichigan Tech Research Institute, Michigan Technical University, Ann Arbor, MI 48105, USAEarth and Environmental Sciences Area, Lawrence Berkeley National Laboratory, 1 Cyclotron Road, Berkeley, CA 94720, USAEcosystems at coastal terrestrial–aquatic interfaces play a significant role in global biogeochemical cycles. In this study, we aimed to characterize coastal wetlands with particular focus on the co-variability between plant dynamics, topography, soil, and other environmental factors. We proposed a functional zonation approach based on machine learning clustering to identify the spatial regions, i.e., zones that capture these co-varied properties. This approach was applied to publicly available datasets along Lake Erie, in the Great Lakes Region. We investigated the heterogeneity of coastal ecosystem structures as a function of along-shore distance and transverse distance, based on the spatial data layers, including topography, wetland vegetation cover, and the time series of Landsat’s enhanced vegetation index (EVI) between 1990 and 2020. Results showed that the topographic metrics (elevation and slope), soil texture, and plant productivity influence the spatial distribution of wetland land-covers (emergent and phragmites). These results highlight a natural organization along the transverse axis, where the elevation and the EVI increase further away from the coastline. In addition, the clustering analysis allowed us to identify regions with distinct environmental characteristics, as well as the ones that are more sensitive to interannual lake-level variations.https://www.mdpi.com/2072-4292/14/14/3285coastal wetlandsplant productivityGreat Lakes Regionmachine learningfunctional zonationremote sensing |
| spellingShingle | Léa Enguehard Nicola Falco Myriam Schmutz Michelle E. Newcomer Joshua Ladau James B. Brown Laura Bourgeau-Chavez Haruko M. Wainwright Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie Remote Sensing coastal wetlands plant productivity Great Lakes Region machine learning functional zonation remote sensing |
| title | Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie |
| title_full | Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie |
| title_fullStr | Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie |
| title_full_unstemmed | Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie |
| title_short | Machine-Learning Functional Zonation Approach for Characterizing Terrestrial–Aquatic Interfaces: Application to Lake Erie |
| title_sort | machine learning functional zonation approach for characterizing terrestrial aquatic interfaces application to lake erie |
| topic | coastal wetlands plant productivity Great Lakes Region machine learning functional zonation remote sensing |
| url | https://www.mdpi.com/2072-4292/14/14/3285 |
| work_keys_str_mv | AT leaenguehard machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT nicolafalco machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT myriamschmutz machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT michelleenewcomer machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT joshualadau machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT jamesbbrown machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT laurabourgeauchavez machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie AT harukomwainwright machinelearningfunctionalzonationapproachforcharacterizingterrestrialaquaticinterfacesapplicationtolakeerie |