Land use change in the Peruvian Amazon through artificial intelligence algorithms
DOI:
https://doi.org/10.20873/jbb.uft.cemaf.v9n1.celisKeywords:
support vector machine, Boosting, Ucayali, Sentinel, PeruSat1Abstract
The research aims to analyze the best supervised satellite image classification model to determine the change in land use between the Support Vector Machine (SVM) and Boosting algorithms for the Peruvian Amazon. Nueva Requena district and different areas of the Amazon basin are currently facing an alarming change in forest cover and land use change, generating important changes in environmental processes. Sentinel-2A satellite images were used, with wavelengths in the visible spectral range and two robust algorithms: Support Vector Machine (SVM) and the Boosting algorithm or decision trees. Twenty-five supervised classifications were made with said algorithms and different inputs from satellite images. The best model of land use change resulted from the classification of the year 2016 with the Boosting algorithm and for the year 2018 it was made with the Support Vector Machine (SVM) algorithm, then through the map algebra the change of use of the Earth. This model presented the lowest classification error of 22.7%, the validation was performed with high-resolution PERUSAT-1 images for the year 2018 and Google Earth images for the year 2016, providing a Kappa index of 0.606 and the percentage correctly classified (PCC) 86.10% for the year 2016 and the Kappa index of 0.560 and the correctly classified percentage (PCC) of 82.30% for the year 2018 demonstrating the considerable and moderate concordance strength respectively.
References
Basterra I. Teledetección - imágenes satelitales - procesamiento digital de imágenes. Cátedra de fotointerpretación - Depar-tamento de Geociencias Facultad de Ingeniería de la Univer-sidad Nacional del Nordeste. Argentina. 2011.
Brondízio E. Agriculture intensification, economic identity, and shared invisibility in Amazonian peasantry: Caboclos and colonists in comparative perspective. Classical Antiquity v. 26, p. 181–214, 2009. https://doi.org/10.1007/978-1-4020-9283-1_9.
Defensoría del Pueblo. Adjuntía para la Prevención de Con-flictos Sociales y la Gobernabilidad. Lima, Perú. 109 p. 2019.
Geist HJ, Lambin EF. Proximate causes and underlying driv-ing forces of tropical deforestation. BioScience v. 52, n. 2, p. 143 – 150, 2002. https://doi.org/10.1641/0006-3568(2002)052[0143:pcaudf]2.0.co;2.
Haines-Young R. Land use and biodiversity relationships. Land Use Policy, v. 26, p. 178 – 286, 2009. https://doi.org/10.1016/j.landusepol.2009.08.009.
Instituto Nacional de Estadística e Informática del Perú (INEI). Shape político del distrito de Nueva Requena, provincia de Coronel Portillo, departamento de Ucayali. Lima-Perú, 2015.
Intergovernmental Panel on Climate Change (IPCC). The Physical Science Basis. Working Group I Contribution to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge, United Kingdom and New York, USA. 1585 p. 2013.
Decreto Ley 23416. Creación de distrito de Nueva Requena, Perú. 1982.
Mapbiomas Amazonía. Colección 2.0. RAISG, 2020. https://amazonia.mapbiomas.org/
Ministerio del Ambiente (MINAM). Decreto Supremo Minis-terial. N°007-2016-Minam. Lima Perú. 2016.
Ministerio del Ambiente MINAM). Mapa de pérdida de los bosques húmedos amazónicos del Perú 2000 - 2011 - Me-moria Descriptiva. Lima Perú. 120 p. 2014.
Olaya V. Sistemas de Información Geográfica. 852 p. 2014. https://www.icog.es/TyT/files/Libro_SIG.pdf
Olofsson P, Foody GM, Stehman SV, Woodcock CE. Mak-ing better use of accuracy data in land change studies: Esti-mating accuracy and area and quantifying uncertainty using stratified estimation. Remote Sensing of Environment, v. 129, p. 122–131, 2013. https://doi.org/10.1016/j.rse.2012.10.031.
Organización de las Naciones Unidas para la Alimentación y la Agricultura (FAO). State of the world’s forests 2016. El estado de los bosques del mundo 2016. Los bosques y la agricultura: desafíos y oportunidades en relación con el uso de la tierra. Roma, Italia, 2016. 119 p.
Peña J. Efectos ecológicos de los cambios de coberturas y usos del suelo en la Marina Baixa (ALICANTE). Año de publicación 2007. 558 p. Disertación (Doctorado en Biolo-gía) - Universidad de Alicante. España.
Perz SG. The changing social contexts of deforestation in the Brazilian Amazon. Social Science Quarterly, v. 83, n. 1, p. 35–52, 2002. https://doi.org/10.1111/1540-6237.00069.
Potapov P, Hansen MC, Laestadius L, Turubanova S, Yaro-shenko A, Thies C, Smith W, Zhuravleva I, Komarova A, Minnemeyer S, Esipova E. The last frontiers of wilderness: Tracking loss of intact forest landscapes from 2000 to 2013. Science Advances, v. 3, n. 1, p 1-14, 2017. https://doi.org/10.1126/sciadv.1600821
Rubin de Celis E. Modelos de clasificación para detección del cambio de uso de la tierra en la Amazonia peruana. Año de publicación: 2019. 153 p. Disertación (Doctorado em Inge-niería Forestal) - Universidad Federal do Paraná. Curitiba.
Schielein J y Börner J. Recent transformations of land-use and land-cover dynamics across different deforestation frontiers in the Brazilian Amazon. Land Use Policy v. 76, p. 81–94, 2018.
Servicio Nacional Forestal y de Fauna Silvestre (SERFOR). Ley Forestal y Fauna Silvestre N°20763 y sus reglamentos. Bosques productivos para la vida. Lima, Perú, p. 345, 2015.
Servicio Nacional Forestal y de Fauna Silvestre (SERFOR). Cobertura y deforestación en los Bosques Húmedos Ama-zónicos al 2017. Lima, Perú, p. 14, 2017.
Vijay V, Pimm Sl, Jenkins Cn, Smith Sj. The impacts of oil palm on recent deforestation and biodiversity loss. PLoS ONE 11(7): e0159668. Doi: 10.1371/journal.pone.0159668, 2016.
Zamora S, López T, Rodríguez J, Blanco M. Metodología de validación de los mapas de usos de la tierra de Nicaragua. Ministerio del Ambiente y los Recursos Naturales de MA-RENA. Nicaragua, p. 17, 2016
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 - Journal of Biotechnology and Biodiversity
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0 at http://creativecommons.org/licenses/by/4.0/) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Available at The Effect of Open Access, at http://opcit.eprints.org/oacitation-biblio.html).
