Identification of wetland complexes using satellite images and Machine Learning, municipality of Piamonte, Cauca (Colombia)
Abstract
The main objective of this study is to identify and delimit the wetland complexes in the municipality of Piamonte, Cauca, Colombia, in the flat region of the Amazonian piedmont. For this purpose, Geographic Information Systems (GIS) tools and Machine Learning (ML) methods, both supervised and unsupervised, were employed, together with the use of cloud computing through Google Earth Engine (GEE) for massive processing of SAR Sentinel-1B (GRD) satellite images. The methodology included the use of the K-Means clustering algorithm for automatic classification of wetland areas and the Random Forest (RF) method for identification in the flat Piedmont area. Five wetland complexes were defined and delimited based on topographic characteristics, such as changes in slope, direction and flow accumulation: Caquetá River Complex, Nabueno - Guayuyaco River Complex, Inchiyaco River Complex, Tontoyaco - Quebradón - Trajayaco Creek Complex and Fragua - Congor - Tambor River Complex. The most extensive class of wetlands corresponds to marshes with high vegetation (NaPaCiVeAl), with an area of 25,929.39 ha, representing the largest proportion in all the complexes. It is followed by the class associated with low vegetation marshes (NaPaCiVeBa), which covers a total of 1,795.51 ha.
Downloads
References
Alcaldía Municipal de Piamonte Cauca. 2018. EOT Piamonte. http://www.piamonte-cauca.gov.co/planes/eot-piamonte
Amani, M., Salehi, B., Mahdavi, S., Granger, J. E., Brisco, B., & Hanson, A. 2017. Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada. Canadian Journal of Remote Sensing, 43(4), 360–373. https://doi.org/10.1080/07038992.2017.1346468
Banks, S., White, L., Behnamian, A., Chen, Z., Montpetit, B., Brisco, B., Pasher, J., y Duffe, J. 2019. Wetland Classification with Multi-Angle/Temporal SAR Using Random Forests. Remote Sensing, 11(6), 670. https://doi.org/10.3390/rs11060670
Breiman, L. 2001. Random forests. Machine learning, 45:5–32.
Catálogo de mapas - IDEAM. (s. f.). Sistema de Información Ambiental de Colombia SIAC. http://www.siac.gov.co/catalogo-de-mapas
Conrad, O., Bechtel, B., Bock, M., Dietrich, H., Fischer, E., Gerlitz, L., Wehberg, J., Wichmann, V., and Böhner, J. 2015. System for Automated Geoscientific Analyses (SAGA) v. 2.1.4, Geosci. Model Dev., 8, 1991-2007. https://doi.org/10.5194/gmd-8-1991-2015
CRC-WWF. 2003. Informe técnico final: Caracterización ambiental preliminar de los humedales de la cuenca río cauca en el departamento del cauca. Informe Técnico, page 113.
CRC-WWF. 2006. Caracterización ambiental preliminar de los humedales de la meseta de Popayán y Puracé en el departamento del cauca. Informe Técnico, page 187.
CRC. 2008. Caracterización del complejo de humedales de la meseta de Popayán, como insumo para la formulación del plan de manejo. Informe Técnico.
CRC. 2013. Plan de gestión ambiental regional. PGAR. Corporación Autónoma Regional del Cauca – CRC. Informe Técnico.
CRC. 2014. Plan de manejo de humedales del municipio de San Sebastián. Informe Técnico.
CRC. 2017. Plan de manejo reserva forestal protectora regional verdeyaco “el oxígeno”.
municipio de Santa Rosa. Informe Técnico.
CRC. 2019. Plan de manejo reserva forestal protectora regional Serranía la Vieja. municipio de Santa Rosa. Informe Técnico.
Cortés-Duque, J. y Estupiñán-Suarez, L. M. 2016. Las huellas del agua. Propuesta metodológica para identificar y comprender el límite de los humedales de Colombia. Instituto de Investigación de Recursos Biológicos Alexander von Humboldt. Fondo Adaptación, Bogotá D. C., Colombia.
Ecosystem, C. D. S. 2024. Copernicus Data Space Ecosystem - Europe’s eyes on Earth. Copernicus Data Space Ecosystem. https://dataspace.copernicus.eu/
Fifing, H. S. N. and Hermawan, A. 2019. Monitoring water surface changes of wetlands using fuzzy k-means algorithm with sentinel-1 sar data. PROCEEDING BOOK VOL. 2, page 331.
Gounaridis, D., Chorianopoulos, I., Symeonakis, E. y Koukoulas, S. 2019. A random forest-cellular automata modelling approach to explore future land use/cover change in attica (greece), under different socio-economic realities and scales. Science of The Total Environment, 646:320–335. https://doi.org/10.1016/j.scitotenv.2018.07.302
Gulácsi, A. y Kovács, F. 2020. Sentinel-1-imagery-based high-resolution water cover detection on wetlands, aided by google earth engine. Remote Sensing, 12(10):1614. https://doi.org/10.3390/rs12101614
Huijuan M.A., Xiaohong G.A.O. y Xiaotian, G.U. G. 2019. Random forest classification of landsat 8 imagery for the complex terrain area based on the combination of spectral, topographic and texture information. Journal of Geo-information Science, 21(3):359–371. https://doi.org/10.12082/dpxxkx.2019.180346
IGAC. s. f. Colombia en Mapas. Instituto Geográfico Agustín Codazzi. https://www.colombiaenmapas.gov.co/
INGEOMINAS. 2000. Geología de la Plancha 412– Río La Fragua, escala 1:100.000.
INGEOMINAS. 2000. Geología de la Plancha 430– Mocoa, escala 1:100.000.
INGEOMINAS. 2000. Geología de la Plancha 431– Puerto Nuevo, escala 1:100.000.
IDEAM, 2010. Leyenda Nacional de Coberturas de la Tierra. Metodología CORINE Land Cover adaptada para Colombia Escala 1:100.000. Instituto de Hidrología, Meteorología y Estudios Ambientales. Bogotá, D. C., 72p. https://www.purace-cauca.gov.co/MiMunicipio/DocumentosGestinRiesgoYDesastres/Estudios%20gesti%C3%B3n%20del%20riesgo%20Purac%C3%A9/Leyenda%20nacional%20coberturas%20tierra.pdf
Johnson, W. C., Werner, B., Guntenspergen, G. R., Voldseth, R. A., Millett, B., Naugle, D. E., Tulbure, M., Carroll, R. W. H., Tracy, J., and Olawsky, C. (2010). Prairie Wetland Complexes as Landscape Functional Units in a Changing Climate. BioScience, 60(2):128–140.
LaRocque, A., Phiri, C., Leblon, B., Pirotti, F., Connor, K., & Hanson, A. (2020). Wetland Mapping with Landsat 8 OLI, Sentinel-1, ALOS-1 PALSAR, and LiDAR Data in Southern New Brunswick, Canada. Remote Sensing, 12(13), 2095. https://doi.org/10.3390/rs12132095
Landuyt, L., Verhoest, N. E., y Van Coillie, F. M. 2020. Flood mapping in vegetated areas using an unsupervised clustering approach on sentinel-1 and-2 imagery. Remote Sensing, 12(21):3611. https://doi.org/10.3390/rs12213611
Lawrence, R. L., & Moran, C. J. (2015). The AmericaView classification methods accuracy comparison project: A rigorous approach for model selection. Remote Sensing Of Environment, 170, 115-120. https://doi.org/10.1016/j.rse.2015.09.008
Ley 388 de 1997. Por la cual se modifica la Ley 9 de 1989, y la Ley 2 de 1991 y se dictan otras disposiciones. 18 de julio de 1997. D.O. No. 43.091.
L’Heureux, A., Grolinger, K., Elyamany, H. F. y Capretz, M. A. M. 2017. Machine learning with big data: Challenges and approaches. IEEE Access, 5:7776–7797. https://doi.org/10.1109/ACCESS.2017.2696365
Martinis, S., Kuenzer, C., Wendleder, A., Huth, J., Twele, A., Roth, A., and Dech, S. (2015). Comparing four operational sar-based water and flood detection approaches. International Journal of Remote Sensing, 36(13):3519–3543.
Montgomery, J., Mahoney, C., Brisco, B., Boychuk, L., Cobbaert, D. y Hopkinson, C. 2021. Remote sensing of wetlands in the prairie pothole region of North America. Remote Sensing, 13(19):3878. https://doi.org/10.3390/rs13193878
Peng, K., Jiang, W., Deng, Y., Liu, Y., Wu, Z. y Chen, Z. 2020. Simulating wetland changes under different scenarios based on integrating the random forest and clue-s models: A case study of wuhan urban agglomeration. Ecological Indicators, 117:106671. https://doi.org/10.1016/j.ecolind.2020.106671
Piamonte en el departamento de Cauca - Municipio y alcaldía de Colombia. (s. f.). https://www.municipio.com.co/municipio-piamonte.html#
R: The R Project for Statistical Computing. s. f. http://www.r-project.org/
Salinas, J. B. G., Eggerth, M. K. P., Miller, M. E., Meza, R. R. B., Chacaltana, J. T. A., Acuña, J. R. y Barroso, G. F. 2020, 1 marzo. Wetland mapping with multitemporal sentinel radar remote sensing in the southeast region of Brazil. En 2020 IEEE Latin American GRSS ISPRS Remote Sensing Conference (LAGIRS). https://doi.org/10.1109/lagirs48042.2020.9165593
Secretaría Distrital de Ambiente Bogotá. s. f.. Humedales de Bogotá. Secretaría Distrital de Ambiente. https://www.ambientebogota.gov.co/humedales
SGC y UNAL. 2014. Mapa Geomorfológico plancha 412 – Río La Fragua, aplicado a la Zonificación de Amenaza por Movimientos en Masa, escala 1:100.000
SGC y UNAL. 2014. Mapa Geomorfológico plancha 430 - Mocoa, aplicado a la Zonificación de Amenaza por Movimientos en Masa, escala 1:100.000
SGC y UIS. 2015. Mapa Geomorfológico plancha 431 – Puerto Nuevo, aplicado a la Zonificación de Amenaza por Movimientos en Masa, escala 1:100.000
SINCHI. 2012. Zonificación ambiental y ordenamiento de la reserva forestal de la amazonia. 38–127.
Yilmaz, O. S. 2023. Automatic detection of water surfaces using k-means++ clustering algorithm with landsat-9 and sentinel-2 images on the google earth engine platform. Bilge International Journal of Science and Technology Research, 7(2):105111. https://doi.org/10.30516/bilgesci.1262550
Zevenbergen, L. W., Thorne C. R. 1987. Quantitative analysis of land surface topography. Earth Surface Processes and Landforms. 12: 12-56.
Zhang, J., Liu, X., Qin, Y., Fan, Y. y Cheng, S. 2024. Wetlands Mapping and Monitoring with Long-Term Time Series Satellite Data Based on Google Earth Engine, Random Forest, and Feature Optimization: A Case Study in Gansu Province, China. Land, 13(9), 1527. https://doi.org/10.3390/land13091527
Copyright (c) 2024 Universidad del Cauca
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
.png)
