Artificial intelligence and remote sensing as wetland guardians: prediction and early warning for preventive environmental management
DOI:
https://doi.org/10.30972/arq.279552Keywords:
wetlands, artificial intelligence, satellite imagery, remote sensing, preventive environmental managementAbstract
Wetlands are strategic ecosystems for water regulation, carbon capture and biodiversity support. In Argentina they cover approximately 21% of the national territory and face accelerating degradation due to anthropogenic and climatic pressures. This article presents a critical review of the convergence of artificial intelligence (AI) and satellite remote sensing as an early prediction tool for wetland status and dynamics, with particular attention to its potential contribution to preventive environmental management. Machine learning algorithms reviewed in the literature —Random Forest, convolutional neural networks and XGBoost— applied to Sentinel-1, Sentinel-2 and Landsat imagery are discussed alongside NDWI and NDVI spectral indices, and a preliminary methodological framework for continuous monitoring, change prediction and early warning activation is proposed for the Argentine Litoral region. The literature reviewed reports that these systems can achieve accuracies above 90% in detecting hydrological variations; however, this work does not include an original empirical validation, and its contribution should be understood as a bibliographic synthesis and a methodological proposal still to be developed and tested in the field.
References
Andros, C. S., Conery, I. W., Alvarado, T. R., DeVore, K. R., Calaway, T. D., Rovai, A. S., Ikeda, J., Collins, A. M., & Masue-Slowey, Y. (2026). Swamp-AI: a deep learning model for monitoring wetlands change across the globe. Scientific Reports, 16, Article 8830. https://doi.org/10.1038/s41598-026-39257-1
Boguszewski, A., Grabowski, T., Krzywda, M., Walczak, J., & Kowalski, M. (2022). A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification using limited training samples. International Journal of Applied Earth Observation and Geoinformation, 114, Article 103051. https://doi.org/10.1016/j.jag.2022.103051
Bonafilia, D., Tellman, B., Anderson, T., & Issenberg, E. (2020). Sen1Floods11: A georeferenced dataset to train and test deep learning flood algorithms for Sentinel-1. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1-8.
CONAE – Comisión Nacional de Actividades Espaciales. (2020). Imágenes satelitales elaboradas por la CONAE aportan información sobre áreas afectadas por las inundaciones en el Litoral Argentino. Ministerio de Ciencia, Tecnología e Innovación, Argentina. https://www.argentina.gob.ar/ciencia/conae
CONICET – Consejo Nacional de Investigaciones Científicas y Técnicas. (2023). Nuevo estudio publicado en Science vincula el aumento de las inundaciones en la llanura argentina con los cambios en el uso de la tierra. https://www.conicet.gov.ar
Convención de Ramsar. (2023). Global Wetland Outlook: Special Edition 2021. Ramsar Convention on Wetlands. https://www.ramsar.org
Gobierno de Argentina – Ministerio de Ambiente y Desarrollo Sustentable. (2022). ¿Qué son los humedales y por qué es importante conservarlos? https://www.argentina.gob.ar/ambiente/contenidos/humedales
Instituto Geográfico Nacional (IGN). (2024). Datos desde el espacio, información desde la nube: teledetección satelital y procesamiento remoto para la generación de información geoespacial. https://www.ign.gob.ar
Jocea, A. F., Porumb, L., Necula, L., & Raducanu, D. (2025). Sentinel-2 land cover classification: State-of-the-art methods and the reality of operational deployment—A systematic review. Sustainability, 17(22), Article 10324. https://doi.org/10.3390/su172210324
Mahdianpari, M., Salehi, B., Mohammadimanesh, F., Brisco, B., Homayouni, S., Gill, E., DeLancey, E. R., & Karami, O. (2019). Google Earth Engine, open-access satellite data, and machine learning in support of large-area probabilistic wetland mapping. Remote Sensing, 9(12), 1315. https://doi.org/10.3390/rs9121315
McFeeters, S. K. (1996). The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7), 1425-1432. https://doi.org/10.1080/01431169608948714
Nearing, G., Cohen, D., Dube, V., Gauch, M., Gilon, O., Harrigan, S., Hassidim, A., Klotz, D., Kratzert, F., Metzger, A., Nevo, S., Pappenberger, F., Prudhomme, C., Shalev, G., Shenzis, S., Tekalign, T. Y., Weitzner, D., & Matias, Y. (2024). Global prediction of extreme floods in ungauged watersheds. Nature, 627(8004), 559-563. https://doi.org/10.1038/s41586-024-07145-1
Nigar, A., Li, Y., Jat Baloch, M. Y., & Almutairi, M. H. (2024). Comparison of machine and deep learning algorithms using Google Earth Engine and Python for land classifications. Frontiers in Environmental Science, 12, Article 1378443. https://doi.org/10.3389/fenvs.2024.1378443
Salas, E. A. L., Subburayalu Kumaran, S., Bennett, R., Willis, L. P., & Mitchell, K. (2024). Machine learning-based classification of small-sized wetlands using Sentinel-2 images. AIMS Geosciences, 10(1), 62-79. https://doi.org/10.3934/geosci.2024005
Shahabi, H., Shirzadi, A., Ghaderi, K., Omidvar, E., Al-Ansari, N., Clague, J. J., Geertsema, M., Khosravi, K., Amini, A., Bahrami, S., Rahmati, O., Habibi, K., Mohammadi, A., Nguyen, H., Melesse, A. M., Bin Ahmad, B., & Ahmad, A. (2020). Flood detection and susceptibility mapping using Sentinel-1 remote sensing data and a machine learning approach: Hybrid intelligence of bagging ensemble based on K-Nearest Neighbor classifier. Remote Sensing, 12(2), 266. https://doi.org/10.3390/rs12020266
UN-SPIDER Knowledge Portal. (2022). Aplicación de datos del mes: aprendizaje automático para la detección de inundaciones. Oficina de las Naciones Unidas para Asuntos del Espacio Exterior. https://www.un-spider.org
Zerrouk, M., Ait El Kadi, K., Sebari, I., & Fellahi, S. (2025). Machine and deep learning for wetland mapping and bird-habitat monitoring: A systematic review of remote-sensing applications (2015–April 2025). Remote Sensing, 17(21), Article 3605. https://doi.org/10.3390/rs17213605
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Los autores ceden a Arquitecno los derechos de publicación de sus trabajos, toda vez que hayan sido admitidos como parte de alguno de sus números. Ellos, no obstante, retienen los derechos de propiedad intelectual y responsabilidad ética así como la posibilidad de dar difusión propia por los medios que consideren.
52.jpg){kind=logo}
