Land Reclamation in the Mississippi River Delta
Driven by the need to expand urban/industrial complexes, and/or mitigate anticipated environmental impacts (e.g., tropical storms), many coastal countries have long implemented large-scale land reclamation initiatives. Some areas, like coastal Louisiana, USA, have relied heavily on restoration activ...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/5/878 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850051773196140544 |
|---|---|
| author | Glenn M. Suir Christina Saltus Jeffrey M. Corbino |
| author_facet | Glenn M. Suir Christina Saltus Jeffrey M. Corbino |
| author_sort | Glenn M. Suir |
| collection | DOAJ |
| description | Driven by the need to expand urban/industrial complexes, and/or mitigate anticipated environmental impacts (e.g., tropical storms), many coastal countries have long implemented large-scale land reclamation initiatives. Some areas, like coastal Louisiana, USA, have relied heavily on restoration activities (i.e., beneficial use of dredged material) to counter extensive long-term wetland loss. Despite these prolonged engagements, the quantifiable benefits of these activities have lacked comprehensive documentation. Therefore, this study leveraged remote sensing data and advanced machine learning techniques to enhance the classification and evaluation of restoration efficacy within the wetlands adjacent to the Mississippi River’s Southwest Pass (SWP). By utilizing air- and space-borne imagery, land and water data were extracted and used to compare land cover changes during two distinct restoration periods (1978 to 2008 and 2008 to 2020) to historical trends. The classification methods employed achieved an overall accuracy of 85% with a Cohen’s kappa value of 0.82, demonstrating substantial agreement beyond random chance. To further assess the success of the SWP reclamation efforts in a global context, broad-based land cover data were generated using biennial air- and space-borne imagery. Results show that restoration activities along SWP have resulted in a significant recovery of degraded wetlands, accounting for approximately a 30 km<sup>2</sup> increase in land area, ranking among the most successful land reclamation projects in the world. The findings from this study highlight beneficial use of dredged material as a critical component in large-scale, recurring restoration activities aimed at mitigating degradation in coastal landscapes. The integration of remote sensing and machine learning methodologies provides a robust framework for monitoring and evaluating restoration projects, offering valuable insights into the optimization of ecosystem services. Overall, the research advocates for a holistic approach to coastal restoration, emphasizing the need for continuous innovation and adaptation in restoration practices to address the dynamic challenges faced by coastal ecosystems globally. |
| format | Article |
| id | doaj-art-35e66da7903249a2b32bf66daeea09d5 |
| institution | DOAJ |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-35e66da7903249a2b32bf66daeea09d52025-08-20T02:53:02ZengMDPI AGRemote Sensing2072-42922025-03-0117587810.3390/rs17050878Land Reclamation in the Mississippi River DeltaGlenn M. Suir0Christina Saltus1Jeffrey M. Corbino2U.S. Army Corps of Engineers, ERDC, Wetlands and Environmental Technologies Research Facility, Lafayette, LA 70504, USAU.S. Army Corps of Engineers, ERDC, Geospatial Data Analysis Facility, Vicksburg, MS 39180, USAU.S. Army Corps of Engineers, MVN, New Orleans, LA 70118, USADriven by the need to expand urban/industrial complexes, and/or mitigate anticipated environmental impacts (e.g., tropical storms), many coastal countries have long implemented large-scale land reclamation initiatives. Some areas, like coastal Louisiana, USA, have relied heavily on restoration activities (i.e., beneficial use of dredged material) to counter extensive long-term wetland loss. Despite these prolonged engagements, the quantifiable benefits of these activities have lacked comprehensive documentation. Therefore, this study leveraged remote sensing data and advanced machine learning techniques to enhance the classification and evaluation of restoration efficacy within the wetlands adjacent to the Mississippi River’s Southwest Pass (SWP). By utilizing air- and space-borne imagery, land and water data were extracted and used to compare land cover changes during two distinct restoration periods (1978 to 2008 and 2008 to 2020) to historical trends. The classification methods employed achieved an overall accuracy of 85% with a Cohen’s kappa value of 0.82, demonstrating substantial agreement beyond random chance. To further assess the success of the SWP reclamation efforts in a global context, broad-based land cover data were generated using biennial air- and space-borne imagery. Results show that restoration activities along SWP have resulted in a significant recovery of degraded wetlands, accounting for approximately a 30 km<sup>2</sup> increase in land area, ranking among the most successful land reclamation projects in the world. The findings from this study highlight beneficial use of dredged material as a critical component in large-scale, recurring restoration activities aimed at mitigating degradation in coastal landscapes. The integration of remote sensing and machine learning methodologies provides a robust framework for monitoring and evaluating restoration projects, offering valuable insights into the optimization of ecosystem services. Overall, the research advocates for a holistic approach to coastal restoration, emphasizing the need for continuous innovation and adaptation in restoration practices to address the dynamic challenges faced by coastal ecosystems globally.https://www.mdpi.com/2072-4292/17/5/878machine learningremote sensingland reclamationmulti-temporal trend analysiswetland restorationwetland classification |
| spellingShingle | Glenn M. Suir Christina Saltus Jeffrey M. Corbino Land Reclamation in the Mississippi River Delta Remote Sensing machine learning remote sensing land reclamation multi-temporal trend analysis wetland restoration wetland classification |
| title | Land Reclamation in the Mississippi River Delta |
| title_full | Land Reclamation in the Mississippi River Delta |
| title_fullStr | Land Reclamation in the Mississippi River Delta |
| title_full_unstemmed | Land Reclamation in the Mississippi River Delta |
| title_short | Land Reclamation in the Mississippi River Delta |
| title_sort | land reclamation in the mississippi river delta |
| topic | machine learning remote sensing land reclamation multi-temporal trend analysis wetland restoration wetland classification |
| url | https://www.mdpi.com/2072-4292/17/5/878 |
| work_keys_str_mv | AT glennmsuir landreclamationinthemississippiriverdelta AT christinasaltus landreclamationinthemississippiriverdelta AT jeffreymcorbino landreclamationinthemississippiriverdelta |