Mostrar el registro sencillo del documento

dc.rights.licenseReconocimiento 4.0 Internacional
dc.contributor.advisorBohórquez Castañeda, Martha Patricia
dc.contributor.authorAlbarracín Barrera, Camilo Andrés
dc.coverage.temporal2019
dc.date.accessioned2024-02-12T21:56:13Z
dc.date.available2024-02-12T21:56:13Z
dc.date.issued2023-12-14
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/85690
dc.descriptionilustraciones a color, diagramas, mapas
dc.description.abstractEl monitoreo de cultivos de coca es esencial para la formulacio ́n de pol ́ıticas pu ́blicas de drogas a nivel global, especialmente con la expansio ́n hacia a pa ́ıses no tradicionales. Como el principal productor de coca ́ına del mundo, Colombia ejemplifica los desaf ́ıos inherentes al monitoreo de este cultivo. El modelo actual de monitoreo, establecido en colaboracio ́n con la Oficina de las Naciones Unidas contra la Droga y el Delito (UNODC), ofrece una estimacio ́n robusta pero sujeta a mejoras en t ́erminos de oportunidad y eficiencia, dado que depende de la interpretaci ́on visual de ima ́genes satelitales anuales. Este trabajo presenta una metodolog ́ıa innovadora que emplea XGBoost con datos multiespectrales y espacio-temporales, principalmente de ima ́genes Sentinel-2. El flujo de trabajo escalable utiliza Google Earth Engine (GEE) para acceder a las im ́agenes satelitales y extraer variables para la clasificacio ́n. Los modelos XGBoost se entrenan para diferenciar entre coca y no coca y se optimizan utilizando un m ́etodo de validaci ́on cruzada espacial. Al aplicarse en dos zonas de Putumayo, Colombia, esta metodolog ́ıa produce una puntuaci ́on Kappa de 0,7512 usando datos de Sentinel-2, superando la puntuaci ́on Kappa de 0,7090 alcanzada en trabajos anteriores. Este avance representa un paso significativo en la precisio ́n de la clasificacio ́n a gran escala de cultivos de coca. Un experimento complementario utilizando imagenes de Planet, de mayor resolucio ́n, en una de las zonas para 2021 produjo una precisi ́on menor pero una mejor delimitacio ́n geom ́etrica, verificada al evaluar la homogeneidad espectral entre pol ́ıgonos clasificados y pol ́ıgonos de referencia. Esta notable mejora en las metodolog ́ıas de clasificacio ́n de cultivos tiene el potencial de fortalecer las operaciones de las fuerzas del orden, perfeccionar las pol ́ıticas de drogas e influir en las relaciones internacionales.
dc.description.abstractCoca crop monitoring is essential for the formulation of public drug policies at the global level, especially with the expansion into non-traditional countries. As the world’s leading cocaine producer, Colombia exemplifies the challenges inherent in monitoring this crop. The current monitoring model, established in collaboration with the United Nations Office on Drugs and Crime (UNODC), offers a robust estimate but is subject to improvement in terms of timeliness and efficiency, as it relies on visual interpretation of annual satellite imagery. This paper presents an innovative methodology that employs XGBoost with multispectral and spatio-temporal data, mainly from Sentinel-2 imagery. The scalable workflow uses Google Earth Engine (GEE) to access satellite imagery and extract variables for classification. The XGBoost models are trained to differentiate between coca and non-coca and optimized using a spatial cross-validation method. When applied in two areas of Putumayo, Colombia, this methodology produced a Kappa score of 0,7512 using Sentinel-2 data, surpassing the Kappa score of 0,7090 achieved in previous work. This advance represents a significant step forward in the accuracy of large-scale coca field classification. A complementary experiment using higher resolution Planet imagery in one of the zones for 2021 produced a lower accuracy but better geometric delineation, verified by assessing spectral homogeneity between classified polygons and reference polygons. This marked improvement in crop classification methodologies has the potential to strengthen law enforcement operations, refine drug policies and influence international relations.
dc.format.extent[xiii], 58 páginas
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherUniversidad Nacional de Colombia
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject.ddc000 - Ciencias de la computación, información y obras generales::004 - Procesamiento de datos Ciencia de los computadores
dc.subject.ddc510 - Matemáticas::519 - Probabilidades y matemáticas aplicadas
dc.titleCoca crop classification and mapping using spectral, temporal and spatial features from satellite imagery for the Catatumbo region in Colombia - 2019
dc.typeTrabajo de grado - Maestría
dc.type.driverinfo:eu-repo/semantics/masterThesis
dc.type.versioninfo:eu-repo/semantics/acceptedVersion
dc.publisher.programBogotá - Ciencias - Maestría en Ciencias - Estadística
dc.coverage.countryColombia
dc.coverage.regionRegión del Catatumbo
dc.coverage.regionNorte de Santander
dc.description.degreelevelMaestría
dc.description.degreenameMagíster en Ciencias - Estadística
dc.description.researchareaEstadística Espacial
dc.identifier.instnameUniversidad Nacional de Colombia
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombia
dc.identifier.repourlhttps://repositorio.unal.edu.co/
dc.publisher.facultyFacultad de Ciencias
dc.publisher.placeBogotá, Colombia
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotá
dc.relation.references[Abdikan et al., 2023] Abdikan, S., Sekertekin, A., Narin, O. G., Delen, A., and Sanli, F. B. (2023). A comparative analysis of SLR, MLR, ANN, XGBoost and CNN for crop height estimation of sunflower using sentinel-1 and sentinel-2. Advances in Space Research, 71(7):3045–3059.
dc.relation.references[Aerts et al., 2015] Aerts, S., Haesbroeck, G., and Ruwet, C. (2015). Multivariate coefficients of variation: Comparison and influence functions. Journal of Multivariate Analysis, 142:183–198.
dc.relation.references[Arbia, 2014] Arbia, G. (2014). A Primer for Spatial Econometrics. Palgrave Macmillan UK.
dc.relation.references[Aybar et al., 2020] Aybar, C., Wu, Q., Bautista, L., Yali, R., and Barja, A. (2020). rgee: An r package for interacting with google earth engine. Journal of Open Source Software, 5(51):2272.
dc.relation.references[Bohorquez et al., 2017] Bohorquez, M., Giraldo, R., and Mateu, J. (2017). Multivariate functional random fields: prediction and optimal sampling. Stochastic Environmental Research and Risk Assessment, 31(1):53–70.
dc.relation.references[Bouhennache et al., 2018] Bouhennache, R., Bouden, T., Taleb-Ahmed, A., and Cheddad, A. (2018). A new spectral index for the extraction of built-up land features from landsat 8 satellite imagery. Geocarto International, 34(14):1531–1551.
dc.relation.references[Breiman, 2001] Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
dc.relation.references[Breiman et al., 1984] Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984). Classification And Regression Trees. Routledge.
dc.relation.references[Ceballos and Lopera, 2009] Ceballos, N. and Lopera, G. (2009). El caso coca nasa. Cuadernos de Investigaci ́on.
dc.relation.references[Ceccato et al., 2002] Ceccato, P., Gobron, N., Flasse, S., Pinty, B., and Tarantola, S. (2002). Designing a spectral index to estimate vegetation water content from remote sensing data: Part 1. Remote Sensing of Environment, 82(2-3):188–197.
dc.relation.references[Chen et al., 2004] Chen, D., Stow, D. A., and Gong, P. (2004). Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case. International Journal of Remote Sensing, 25(11):2177–2192.
dc.relation.references[Chen and Guestrin, 2016] Chen, T. and Guestrin, C. (2016). Xgboost: Scalable tree boosting system. CoRR, abs/1603.02754.
dc.relation.references[El Financiero, 2023] El Financiero (2023). Destruyen casi 18,000 plantas de coca en guatemala.
dc.relation.references[El Tiempo, 2023] El Tiempo (2023). La coca florece en m ́exico a la sombra de drogas sint ́eticas.
dc.relation.references[ESA, nda] ESA, E. S. A. (n.d.a). User guides - sentinel-2 msi - overview - sentinel online. https://sentinels.copernicus.eu/web/sentinel/user-guides/sentinel-2-msi/overview. Accessed: 2023-07-29
dc.relation.references[ESA, ndb] ESA, E. S. A. (n.d.b). User guides - sentinel-2 msi - resolutions - sentinel online. https://sentinels.copernicus.eu/web/sentinel/user-guides/sentinel-2-msi/resolutions. Accessed: 2023-07-29.
dc.relation.references[ESA, ndc] ESA, E. S. A. (n.d.c). User guides - sentinel-2 msi - revisit and coverage - sentinel online. https://sentinels.copernicus.eu/web/sentinel/user-guides/sentinel-2-msi/revisit-coverage. Accessed: 2023-07-29.
dc.relation.references[Farfán and Jaramillo, 2009] Farfán, F. and Jaramillo, A. (2009). Sombrío para el cultivo del café según la nubosidad de la región. Avances Técnicos.
dc.relation.references[Frampton et al., 2013] Frampton, W. J., Dash, J., Watmough, G., and Milton, E. J. (2013). Evaluating the capabilities of sentinel-2 for quantitative estimation of biophysical variables in vegetation. ISPRS Journal of Photogrammetry and Remote Sensing, 82:83–92.
dc.relation.references[Friedman et al., 2000] Friedman, J., Hastie, T., and Tibshirani, R. (2000). Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). The Annals of Statistics, 28(2).
dc.relation.references[Friedman, 2001] Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5).
dc.relation.references[Galindo and Fernández, 2010] Galindo, A. and Fernánndez, J. (2010). Plantas de coca en Colombia. discusión crítica sobre la taxonomía de las especies cultivadas del género erythroxylum p. browne (erythroxylaceae).
dc.relation.references[Gerber et al., 2018] Gerber, F., de Jong, R., Schaepman, M. E., Schaepman-Strub, G., and Furrer, R. (2018). Predicting missing values in spatio-temporal remote sensing data. IEEE Transactions on Geoscience and Remote Sensing, 56(5):2841–2853.
dc.relation.references[Haboudane, 2004] Haboudane, D. (2004). Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sensing of Environment, 90(3):337–352.
dc.relation.references[Huang et al., 2022] Huang, L., Liu, Y., Huang, W., Dong, Y., Ma, H., Wu, K., and Guo, A. (2022). Combining random forest and XGBoost methods in detecting early and mid-term winter wheat stripe rust using canopy level hyperspectral measurements. Agriculture, 12(1):74.
dc.relation.references[Huber et al., 2022] Huber, F., Yushchenko, A., Stratmann, B., and Steinhage, V. (2022). Extreme gradient boosting for yield estimation compared with deep learning approaches. Computers and Electronics in Agriculture, 202:107346.
dc.relation.references[Huete, 1988] Huete, A. (1988). A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 25(3):295–309.
dc.relation.references[InfoBAE, 2022] InfoBAE (2022). Autoridades localizan 25.000 arbustos de hoja de coca en el caribe hondureño
dc.relation.references[Jensen, 2006] Jensen, J. R. (2006). Remote Sensing of the Environment. Prentice Hall.
dc.relation.references[Jiang and Shekhar, 2017] Jiang, Z. and Shekhar, S. (2017). Spatial Big Data Science. Springer International Publishing.
dc.relation.references[Karpatne et al., 2016] Karpatne, A., Jiang, Z., Vatsavai, R. R., Shekhar, S., and Kumar, V. (2016). Monitoring land-cover changes: A machine-learning perspective. IEEE Geoscience and Remote Sensing Magazine, 4(2):8–21.
dc.relation.references[Louhaichi et al., 2001] Louhaichi, M., Borman, M. M., and Johnson, D. E. (2001). Spatially located platform and aerial photography for documentation of grazing impacts on wheat. Geocarto International, 16(1):65–70.
dc.relation.references[Machado et al., 2019] Machado, M. R., Karray, S., and de Sousa, I. T. (2019). LightGBM: an effective decision tree gradient boosting method to predict customer loyalty in the finance industry. In 2019 14th International Conference on Computer Science &amp Education (ICCSE). IEEE.
dc.relation.references[Matteucci and Morello, 2001] Matteucci, S. and Morello, J. (2001). Aspectos ecológicos del cultivo de coca. 1(8).
dc.relation.references[McFEETERS, 1996] 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.
dc.relation.references[Mishra and Mishra, 2012] Mishra, S. and Mishra, D. R. (2012). Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters. Remote Sensing of Environment, 117:394–406.
dc.relation.references[Mohanaiah et al., 2013] Mohanaiah, P., P.Sathyanarayana, and GuruKumar, L. (2013). Image texture feature extraction using glcm approach. International Journal of Scientific and Research Publications, 3(5).
dc.relation.references[Mutanga and Kumar, 2019] Mutanga, O. and Kumar, L. (2019). Google earth engine applications. Remote Sensing, 11(5):591.
dc.relation.references[Nazir et al., 2021] Nazir, A., Ullah, S., Saqib, Z. A., Abbas, A., Ali, A., Iqbal, M. S., Hussain, K., Shakir, M., Shah, M., and Butt, M. U. (2021). Estimation and forecasting of rice yield using phenology-based algorithm and linear regression model on sentinel-II satellite data. Agriculture, 11(10):1026.
dc.relation.references[Oliver and Webster, 1990] Oliver, M. A. and Webster, R. (1990). Kriging: a method of interpolation for geographical information systems. International journal of geographical information systems, 4(3):313–332.
dc.relation.references[Park et al., 2021] Park, J., Lee, Y., and Lee, J. (2021). Assessment of machine learning algorithms for land cover classification using remotely sensed data. Sensors and Materials, 33(11):3885.
dc.relation.references[Park et al., 2018] Park, S., Im, J., Park, S., Yoo, C., Han, H., and Rhee, J. (2018). Classification and mapping of paddy rice by combining landsat and SAR time series data. Remote Sensing, 10(3):447.
dc.relation.references[PBC, 2022] PBC, P. L. (2022). Combined imagery product specifications.
dc.relation.references[Piedelobo et al., 2019] Piedelobo, L., Herna ́ndez-Lo ́pez, D., Ballesteros, R., Chakhar, A., Pozo, S. D., Gonza ́lez-Aguilera, D., and Moreno, M. A. (2019). Scalable pixel-based crop classification combining sentinel-2 and landsat-8 data time series: Case study of the duero river basin. Agricultural Systems, 171:36–50.
dc.relation.references[Rouse et al., 1974] Rouse, J. W., Haas, R. H., Schell, J. A., Deering, D. W., et al. (1974). Monitoring vegetation systems in the great plains with erts. NASA Spec. Publ, 351(1):309.
dc.relation.references[Rustowicz, 2017] Rustowicz, R. M. (2017). Crop classification with multi-temporal satellite imagery.
dc.relation.references[Saini and Ghosh, 2021] Saini, R. and Ghosh, S. K. (2021). Crop classification in a heterogeneous agricultural environment using ensemble classifiers and single-date sentinel-2a imagery. Geocarto International, 36(19):2141–2159.
dc.relation.references[Serrano, 2014] Serrano, M. (2014). Cultivos il ́ıcitos de coca y bienestar en las regiones productoras: Un ana ́lisis desde el enfoque de capacidades.
dc.relation.references[Tatsumi et al., 2015] Tatsumi, K., Yamashiki, Y., Torres, M. A. C., and Taipe, C. L. R. (2015). Crop classification of upland fields using random forest of time-series landsat 7 ETM data. Computers and Electronics in Agriculture, 115:171–179.
dc.relation.references[Tobler, 1970] Tobler, W. R. (1970). A computer movie simulating urban growth in the detroit region. Economic Geography, 46:234.
dc.relation.references[UNODC, 2023] UNODC (2023). World drug report 2023.
dc.relation.references[UNODC and MINJUSTICIA, 2010] UNODC and MINJUSTICIA (2010). Caracter ́ısticas agroculturales de los cultivos de coca 2005-2010.
dc.relation.references[UNODC and MINJUSTICIA, 2012] UNODC and MINJUSTICIA (2012). Estructura econo ́mica de la unidades productores agropecuarias en zonas de influencia de cultivos de coca.
dc.relation.references[UNODC and MINJUSTICIA, 2019] UNODC and MINJUSTICIA (2019). Monitoreo de cultivos il ́ıcitos 2018.
dc.relation.references[UNODC and MINJUSTICIA, 2022] UNODC and MINJUSTICIA (2022). Monitoreo de cultivos il ́ıcitos 2021.
dc.relation.references[Valavi et al., 2018] Valavi, R., Elith, J., Lahoz-Monfort, J. J., and Guillera-Arroita, G. (2018). blockcv: An r package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models. Methods in Ecology and Evolution, 10(2):225–232.
dc.relation.references[Valen, 1974] Valen, L. V. (1974). Multivariate structural statistics in natural history. Journal of Theoretical Biology, 45(1):235–247.
dc.relation.references[Yu and Zhu, 2020] Yu, T. and Zhu, H. (2020). Hyper-parameter optimization: A review of algorithms and applications.
dc.relation.references[A ́ngel, 2012] A ́ngel, Y. (2012). Metodolog ́ıa para identificar cultivos de coca mediante ana ́lisis de para ́metros red edge y espectroscopia de im ́agenes.
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.subject.agrovocVigilancia de cultivos
dc.subject.agrovocCrop monitoring
dc.subject.lembAerofotografía en control de drogas y narcóticos
dc.subject.lembPhotography, aerial in drug and narcotic control
dc.subject.lembCultivos ilícitos - Mediciones
dc.subject.lembFotografía multiespectral - Métodos estadísticos
dc.subject.lembMultispectral photogrphy - Statistical methods
dc.subject.proposalclasificación de cultivos
dc.subject.proposalcoca
dc.subject.proposalXGBoost
dc.subject.proposaldatos multiespectrales
dc.subject.proposalespacio-temporal
dc.subject.proposalGoogle Earth Engine
dc.subject.proposalpolítica de drogas
dc.subject.proposalPlanet
dc.subject.proposalcrop classification
dc.subject.proposalmultispectral data
dc.subject.proposalspatial-temporal
dc.subject.proposaldrug policy
dc.title.translatedClasificación y mapeo de cultivos de coca utilizando características espectrales, temporales y espaciales a partir de imágenes satelitales para la región del Catatumbo en Colombia - 2019
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.contentImage
dc.type.contentText
dc.type.redcolhttp://purl.org/redcol/resource_type/TM
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2
dcterms.audience.professionaldevelopmentEstudiantes
dcterms.audience.professionaldevelopmentInvestigadores
dcterms.audience.professionaldevelopmentMaestros


Archivos en el documento

Thumbnail

Este documento aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del documento

Reconocimiento 4.0 InternacionalEsta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.Este documento ha sido depositado por parte de el(los) autor(es) bajo la siguiente constancia de depósito