Detección automatizada de áreas quemadas en Costa Rica: un primer acercamiento
Barra lateral del artículo
Contenido principal del artículo
Resumen
En Costa Rica a pesar de diversos estudios sobre incendios forestales, la recolección de datos todavía es un trabajo arduo debido a las condiciones geográficas, hay zonas donde las condiciones de accesibilidad dificultan la recolección. Las imágenes satelitales son herramientas útiles en el estudio de diferentes zonas para detectar áreas quemadas y sus cicatrices. Sin embargo, el procesamiento por parte de los investigadores suele requerir tiempo debido a la cantidad de archivos que son necesarios para realizar el análisis. En este artículo proponemos un marco de trabajo basado en aprendizaje automático e índices espectrales para ayudar en la detección de áreas quemadas con un rendimiento computacional eficiente. Seleccionamos el Área de Conservación de Guanacaste como área de estudio para descargar imágenes de Sentinel-2, pudimos detectar zonas posiblemente afectadas por incendios forestales. A pesar de ser un primer acercamiento en la prevención de incendios forestales, nuestros resultados evidencian el potencial para desarrollar un futuro sistema de detección robusto.
Detalles del artículo
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
Los autores conservan los derechos de autor y ceden a la revista el derecho de la primera publicación y pueda editarlo, reproducirlo, distribuirlo, exhibirlo y comunicarlo en el país y en el extranjero mediante medios impresos y electrónicos. Asimismo, asumen el compromiso sobre cualquier litigio o reclamación relacionada con derechos de propiedad intelectual, exonerando de responsabilidad a la Editorial Tecnológica de Costa Rica. Además, se establece que los autores pueden realizar otros acuerdos contractuales independientes y adicionales para la distribución no exclusiva de la versión del artículo publicado en esta revista (p. ej., incluirlo en un repositorio institucional o publicarlo en un libro) siempre que indiquen claramente que el trabajo se publicó por primera vez en esta revista.
Citas
[1] C. Maffei and M. Menenti, “Predicting forest fires burned area and rate of spread from pre-fire multispectral satellite measurements,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 158, pp. 263–278, Dec. 2019, doi: https://doi.org/10.1016/j.isprsjprs.2019.10.013.
[2] S. T. Seydi, M. Hasanlou, and J. Chanussot, “Burnt-Net: Wildfire burned area mapping with single post-fire Sentinel-2 data and deep learning morphological neural network,” Ecological Indicators, vol. 140, p. 108999, Jul. 2022, doi: https://doi.org/10.1016/j.ecolind.2022.108999.
[3] X. Wang et al., “Estimation of Forest Fire Burned Area by Distinguishing Non-Photosynthetic and Photosynthetic Vegetation Using Triangular Space Method,” Remote Sensing, vol. 15, no. 12, p. 3115, Jun. 2023, doi: https://doi.org/10.3390/rs15123115.
[4] L. Jiao and Y. Bo, “Near real-time mapping of burned area by synergizing multiple satellites remote-sensing data,” GIScience & remote sensing/GIScience and remote sensing, vol. 59, no. 1, pp. 1956–1977, Nov. 2022, doi: https://doi.org/10.1080/15481603.2022.2143690.
[5] S. Lakhina, et al. “Increasing National Resilience through an Open Disaster Data Initiative - Federation of American Scientists,” Federation of American Scientists, Sep. 26, 2024. https://fas.org/publication/increasing-national-resilience-through-an-open-disaster-data-initiative/
[6] Shefali Juneja Lakhina and Anukool Lakhina, “Technology Entrepreneurship and Wildfire Risk Management,” Disaster risk reduction, pp. 277–295, Jan. 2022, doi: https://doi.org/10.1007/978-981-19-2053-0_15.
[7] N. Chucos, & E. Vega. “Vista de Evaluación de algoritmos de machine learning en la clasificación de imágenes satelitales multiespectrales, caso: Amazonia Peruana,” Doi.org, 2025. https://doi.org/10.37811/cl_rcm.v6i1.1843 (accessed Mar. 19, 2025)
[8] G. H. de Almeida Pereira, A. M. Fusioka, B. T. Nassu, and R. Minetto, “Active fire detection in Landsat-8 imagery: A large-scale dataset and a deep-learning study,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 178, pp. 171–186, Aug. 2021, doi: https://doi.org/10.1016/j.isprsjprs.2021.06.002.
[9] R. G. Negri, A. E. O. Luz, A. C. Frery, and W. Casaca, “Mapping Burned Areas with Multitemporal–Multispectral Data and Probabilistic Unsupervised Learning,” Remote Sensing, vol. 14, no. 21, p. 5413, Jan. 2022, doi: https://doi.org/10.3390/rs142154
[10] C. Campos-Vargas and D. Vargas-Sanabria, “Assessing the probability of wildfire occurrences in a neotropical dry forest,” Écoscience, vol. 28, no. 2, pp. 159–169, Apr. 2021, doi: https://doi.org/10.1080/11956860.2021.1916213.
[11] A. Quesada-Román and D. Vargas-Sanabria, “A geomorphometric model to determine topographic parameters controlling wildfires occurrence in tropical dry forests,” Journal of Arid Environments, vol. 198, p. 104674, Mar. 2022, doi: https://doi.org/10.1016/j.jaridenv.2021.104674.
[12] D. Vargas-Sanabria and C. Campos-Vargas, “Comparación multitemporal de áreas quemadas en un bosque seco tropical utilizando el índice de área quemada (IAQ),” Revista Forestal Mesoamericana Kurú, vol. 17, no. 41, pp. 29–36, Jul. 2020, doi: https://doi.org/10.18845/rfmk.v17i41.5280.
[13] A. da, Antonio, A. M. Ruiz-Armenteros, R. F. Henriques, and Santos, “Analysis of Spectral Separability for Detecting Burned Areas Using Landsat-8 OLI/TIRS Images under Different Biomes in Brazil and Portugal,” Forests, vol. 14, no. 4, pp. 663–663, Mar. 2023, doi: https://doi.org/10.3390/f14040663.
[14] B. I. Abrahim, Ammar Abd Jasim, M. R. Mahmood, H. R. Mahmood, H. A. Alalwan, and M. M. Mohammed, “Water Body Detection Using Sentinel-2 Imagery Through Particle Swarm Intelligence: A Novel Framework for Optimizing Spectral Multi-Band Index,” Eng—Advances in Engineering, vol. 6, no. 3, pp. 59–59, Mar. 2025, doi: https://doi.org/10.3390/eng6030059.
[15] A. G. Flores Rodríguez, J. G. Flores-Garnica, D. R. González-Eguiarte, A. Gallegos-Rodríguez, P. Zarazúa-Villaseñor, and S. Mena-Munguía, “Análisis comparativo de índices espectrales para ubicar y dimensionar niveles de severidad de incendios forestales,” Investigaciones Geográficas, no. 106, Nov. 2021, doi: https://doi.org/10.14350/rig.60396.
[16] L. Wasser et al., “Datacarpentry/Organization-Geospatial: Data Carpentry Introduction To Geospatial Concepts August 2018 Release,” OPAL (Open@LaTrobe) (La Trobe University), Aug. 2018, doi: https://doi.org/10.5281/zenodo.1404414.
[17] E. Alcaras, D. Costantino, F. Guastaferro, C. Parente, and M. Pepe, “Normalized Burn Ratio Plus (NBR+): A New Index for Sentinel-2 Imagery,” Remote Sensing, vol. 14, no. 7, p. 1727, Apr. 2022, doi: https://doi.org/10.3390/rs14071727.
[18] R. Guo, J. Yan, H. Zheng, and B. Wu, “Assessment of the Analytic Burned Area Index for Forest Fire Severity Detection Using Sentinel and Landsat Data,” Fire, vol. 7, no. 1, p. 19, Jan. 2024, doi: https://doi.org/10.3390/fire7010019.
[19] S. T. Seydi, M. Akhoondzadeh, M. Amani, and S. Mahdavi, “Wildfire Damage Assessment over Australia Using Sentinel-2 Imagery and MODIS Land Cover Product within the Google Earth Engine Cloud Platform,” Remote Sensing, vol. 13, no. 2, p. 220, Jan. 2021, doi: https://doi.org/10.3390/rs13020220.
[20] D. H. Janzen and W. Hallwachs, “Área de Conservación Guanacaste, northwestern Costa Rica: Converting a tropical national park to conservation via biodevelopment,” Biotropica, vol. 52, no. 6, pp. 1017–1029, Jan. 2020, doi: https://doi.org/10.1111/btp.12755.
[21] M. Ríos-Solano, A. M. Durán-Quesada, C. Birkel, H. G. Hidalgo, W. Cabos, and D. V. Sein, “Observed interannual variability and projected scenarios of drought in the Chorotega region, Costa Rica,” Atmósfera, vol. 38, Mar. 2024, doi: https://doi.org/10.20937/atm.53295.
[22] D.H., Janzen and W. Hallwachs, “Biodiversity conservation history and future in Costa Rica: the Case of Area de Conservación Guanacaste (ACG)”. In Costa Rican Ecosystems, Kappelle, M. Ed. Chicago: The University Of Chicago Press, 2016, pp. 290-342.
[23] ACG, “Temporada de incendios forestales 2023 Área de Conservación Guanacaste - Área de Conservación Guanacaste,” Área de Conservación Guanacaste, 2023. https://www.acguanacaste.ac.cr/noticias/noticias-programa-de-proteccion-e-incendios/5823-temporada-de-incendios-forestales-2023-area-de-conservacion-guanacaste (accessed Set. 06, 2025).
[24] M. De Ambiente, E. Sistema, N. De, and Á. De Conservación, “Informe anual Estadísticas SEMEC 2023 SINAC en Números.” Available: https://www.sinac.go.cr/ES/transprncia/Informe%20SEMEC/Informe%20SEMEC%202023.pdf
[25] D. Phiri, M. Simwanda, S. Salekin, V. R. Nyirenda, Y. Murayama, and M. Ranagalage, “Sentinel-2 Data for Land Cover/Use Mapping: A Review,” Remote Sensing, vol. 12, no. 14, p. 2291, Jul. 2020, doi: https://doi.org/10.3390/rs12142291.
[26] Rajagopalan Rengarajan, M. Choate, M. N. Hasan, and A. Denevan, “Co-registration accuracy between Landsat-8 and Sentinel-2 orthorectified products,” Remote Sensing of Environment, vol. 301, pp. 113947–113947, Dec. 2023, doi: https://doi.org/10.1016/j.rse.2023.113947.
[27] L. Yan and D. P. Roy, “Improving Landsat Multispectral Scanner (MSS) geolocation by least-squares-adjustment based time-series co-registration,” Remote Sensing of Environment, vol. 252, p. 112181, Jan. 2021, doi: https://doi.org/10.1016/j.rse.2020.112181.
[28] M. Vaqueiro, J. M. Fonseca, H. Oliveira, and A. Mora, “Multi-image Super-Resolution Algorithm Supported on Sentinel-2 Satellite Images Geolocation Error,” vol. 53, pp. 50–57, Jul. 2021, doi: https://doi.org/10.1109/yef-ece52297.2021.9505092.
[29] H. Farhadi, M. Mokhtarzade, H. Ebadi, and B. A. Beirami, “Rapid and automatic burned area detection using sentinel-2 time-series images in google earth engine cloud platform: a case study over the Andika and Behbahan Regions, Iran,” Environmental Monitoring and Assessment, vol. 194, no. 5, Apr. 2022, doi: https://doi.org/10.1007/s10661-022-10045-4.
[30] F. Ngadze, K. S. Mpakairi, B. Kavhu, H. Ndaimani, and M. S. Maremba, “Exploring the utility of Sentinel-2 MSI and Landsat 8 OLI in burned area mapping for a heterogenous savannah landscape,” PLOS ONE, vol. 15, no. 5, p. e0232962, May 2020, doi: https://doi.org/10.1371/journal.pone.0232962.
[31] E. Kurbanov et al., “Remote Sensing of Forest Burnt Area, Burn Severity, and Post-Fire Recovery: A Review,” Remote Sensing, vol. 14, no. 19, p. 4714, Sep. 2022, doi: https://doi.org/10.3390/rs14194714.
[32] K. Dvorakova, U. Heiden, K. Pepers, G. Staats, Gera van Os, and Bas van Wesemael, “Improving soil organic carbon predictions from a Sentinel–2 soil composite by assessing surface conditions and uncertainties,” vol. 429, pp. 116128–116128, Nov. 2022, doi: https://doi.org/10.1016/j.geoderma.2022.116128.
[33] G. E. Suárez-Fernández, J. Martínez-Sánchez, and P. Arias, “Assessment of vegetation indices for mapping burned areas using a deep learning method and a comprehensive forest fire dataset from Landsat collection,” Advances in Space Research, vol. 75, no. 2, pp. 1665–1685, Dec. 2024, doi: https://doi.org/10.1016/j.asr.2024.12.001
[34] Rabah Zennir and Boubaker Khallef, “Forest fire area detection using Sentinel-2 data: Case of the Beni Salah national forest ‒ Algeria,” Journal of Forest Science, vol. 69, no. 1, Jan. 2023, doi: https://doi.org/10.17221/50/2022-JFS.
[35] Shaparas Daliman, M. Jane, Pradnya Paramarta Raditya Rendra, Emi Sukiyah, Mohamad, and N. Sulaksana, “Dual Vegetation Index Analysis and Spatial Assessment in Kota Bharu, Kelantan using GIS and Remote Sensing,” BIO Web of Conferences, vol. 131, pp. 05009–05009, Jan. 2024, doi: https://doi.org/10.1051/bioconf/202413105009.
[36] T. J. Hawbaker et al., “The Landsat Burned Area algorithm and products for the conterminous United States,” Remote Sensing of Environment, vol. 244, p. 111801, Jul. 2020, doi: https://doi.org/10.1016/j.rse.2020.111801.
[37] Hasan Bilgehan Makineci, “Investigation of burned areas with multiplatform remote sensing data on the Rhodes 2023 forest fires,” Ain Shams Engineering Journal, pp. 102949–102949, Jul. 2024, doi: https://doi.org/10.1016/j.asej.2024.10294
[38] E. Rahimi, P. Dong, and C. Jung, “Global Pattern of Vegetation Homogeneity and Its Impact on Land Surface Temperature,” Land, vol. 14, no. 2, pp. 421–421, Feb. 2025, doi: https://doi.org/10.3390/land14020421.
[39] Polina Lemenkova and Olivier Debeir, “Computing Vegetation Indices from the Satellite Images Using GRASS GIS Scripts for Monitoring Mangrove Forests in the Coastal Landscapes of Niger Delta, Nigeria,” Journal of Marine Science and Engineering, vol. 11, no. 4, pp. 871–871, Apr. 2023, doi: https://doi.org/10.3390/jmse11040871
[40] M. P. Martín, I. Gómez, and E. Chuvieco, “Burnt Area Index (BAIM) for burned area discrimination at regional scale using MODIS data,” Forest Ecology and Management, vol. 234, p. S221, Nov. 2006, doi: https://doi.org/10.1016/j.foreco.2006.08.248.
[41] Y. Zheng, L. Tang, and H. Wang, “An improved approach for monitoring urban built-up areas by combining NPP-VIIRS nighttime light, NDVI, NDWI, and NDBI,” Journal of Cleaner Production, vol. 328, p. 129488, Dec. 2021, doi: https://doi.org/10.1016/j.jclepro.2021.129488.
[42] N. Zikiou, H. Rushmeier, M. I. Capel, Tarek Kandakji, N. Rios, and Mourad Lahdir, “Remote Sensing and Machine Learning for Accurate Fire Severity Mapping in Northern Algeria,” Remote Sensing, vol. 16, no. 9, pp. 1517–1517, Apr. 2024, doi: https://doi.org/10.3390/rs16091517.
[43] M. Saleh, “Evaluation of Jenks Natural Breaks Clustering Algorithm for Changepoint Identification in Streaming Sensor Data,” IEEE Sensors Letters, vol. 8, no. 10, pp. 1–4, Sep. 2024, doi: https://doi.org/10.1109/lsens.2024.3456292.
[44] M. Suyal and S. Sharma, “A Review on Analysis of K-Means Clustering Machine Learning Algorithm based on Unsupervised Learning,” Journal of Artificial Intelligence and Systems, vol. 6, no. 1, pp. 85–95, Jan. 2024, doi: https://doi.org/10.33969/ais.2024060106.
[45] P. Singh Thakur, et. al. “Analysis of time complexity of K-means and fuzzy C-means clustering algorithm,” Engineering Mathematics Letters, Jan. 2024, doi: https://doi.org/10.28919/eml/8402
[46] I. Herdiana, K. M. Alfin, Triyani, E. M. Nur, and Renny, “A More Precise Elbow Method for Optimum K-means Clustering,” arXiv (Cornell University), Feb. 2025, doi: https://doi.org/10.48550/arxiv.2502.008
[47] D. Chicco, A. Sichenze, and G. Jurman, “A simple guide to the use of Student’s t-test, Mann-Whitney U test, Chi-squared test, and Kruskal-Wallis test in biostatistics,” BioData Mining, vol. 18, no. 1, Aug. 2025, doi: https://doi.org/10.1186/s13040-025-00465-6
[48] S. K. Ahmed, “Research methodology simplified: How to choose the right sampling technique and determine the appropriate sample size for research,” Oral Oncology Reports, vol. 12, no. 100662, pp. 1–7, 2024, doi: https://doi.org/10.1016/j.oor.2024.100662.
[49] J. Lu, W. Song, X. Zuo, D. Zhu, and Q. Wei, “A Study of Apple Orchards Extraction in the Zhaotong Region Based on Sentinel Images and Improved Spectral Angle Features,” Applied Sciences, vol. 13, no. 20, p. 11194, Oct. 2023, doi: https://doi.org/10.3390/app132011194.
[50] I. El-Madafri, M. Peña, and N. Olmedo-Torre, “The Wildfire Dataset: Enhancing Deep Learning-Based Forest Fire Detection with a Diverse Evolving Open-Source Dataset Focused on Data Representativeness and a Novel Multi-Task Learning Approach,” Forests, vol. 14, no. 9, p. 1697, Sep. 2023, doi: https://doi.org/10.3390/f14091697.
[51] A. da P. Pacheco, J. A. da S. Junior, A. M. Ruiz-Armenteros, and R. F. F. Henriques, “Assessment of k-Nearest Neighbor and Random Forest Classifiers for Mapping Forest Fire Areas in Central Portugal Using Landsat-8, Sentinel-2, and Terra Imagery,” Remote Sensing, vol. 13, no. 7, p. 1345, Apr. 2021, doi: https://doi.org/10.3390/rs13071345.
[52] H. Xu et al., “Immediate assessment of forest fire using a novel vegetation index and machine learning based on multi-platform, high temporal resolution remote sensing images,” International Journal of Applied Earth Observation and Geoinformation, vol. 134, pp. 104210–104210, Oct. 2024, doi: https://doi.org/10.1016/j.jag.2024.104210.
[53] F. Chan, “Optimal Forecast Combination with Mean Absolute Error Loss,” CAMA Working Papers, Nov. 2023. https://ideas.repec.org/p/een/camaaa/2023-59.html
[54] A. Ahmad et al., “Naïve Bayes Classification of High-Resolution Aerial Imagery Optimization Modelling Analytic and Simulation (OptiMAS) Faculty of Information and Communication Technology,” IJACSA) International Journal of Advanced Computer Science and Applications, vol. 12, no. 11, 2021, Accessed: Nov. 06, 2025. [Online]. Available: https://thesai.org/Downloads/Volume12No11/Paper_20-Na%C3%AFve_Bayes_Classification_of_High_Resolution_Aerial_Imagery.pdf.
[55] F. Chollet, Deep Learning with Python. Shelter Island (New York, USA): Manning, Cop, 2018. Available: https://www.manning.com/books/deep-learning-with-python
[56] J. Cervantes, F. G. Lamont, L. R. Mazahua, and A. Lopez, “A comprehensive survey on support vector machine classification: Applications, challenges and trends,” Neurocomputing, vol. 408, no. 1, pp. 189–215, Sep. 2020, doi: https://doi.org/10.1016/j.neucom.2019.10.118.
[57] E. Izquierdo-Verdiguier and R. Zurita-Milla, “An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing,” International Journal of Applied Earth Observation and Geoinformation, vol. 88, p. 102051, Jun. 2020, doi: https://doi.org/10.1016/j.jag.2020.102051.
[58] K. Budholiya, S. K. Shrivastava, and V. Sharma, “An optimized XGBoost based diagnostic system for effective prediction of heart disease,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 7, Oct. 2020, doi: https://doi.org/10.1016/j.jksuci.2020.10.013.
[59] A. F. Militino, H. Goyena, U. Pérez-Goya, and M. D. Ugarte, “Logistic regression versus XGBoost for detecting burned areas using satellite images,” Environmental and ecological statistics, Jan. 2024, doi: https://doi.org/10.1007/s10651-023-00590-7.
[60] N. L. Fitriyani et al., “A Novel Approach Utilizing Bagging, Histogram Gradient Boosting, and Advanced Feature Selection for Predicting the Onset of Cardiovascular Diseases,” Mathematics, vol. 13, no. 13, pp. 2194–2194, Jul. 2025, doi: https://doi.org/10.3390/math13132194.
[61] A. Zhdanovskaya, D. Baidakova, and Dmitry Ustalov, “Data Labeling for Machine Learning Engineers: Project-Based Curriculum and Data-Centric Competitions,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 13, pp. 15886–15893, Jun. 2023, doi: https://doi.org/10.1609/aaai.v37i13.26886.
[62] T. Bleckmann, and G. Friege, “Concept maps for formative assessment: Creation and implementation of an automatic and intelligent evaluation method,” Knowledge Management & E-Learning: An International Journal, pp. 433–447, Sep. 2023, doi: https://doi.org/10.34105/j.kmel.2023.15.025.
[63] V. Sheth, U. Tripathi, and A. Sharma, “A Comparative Analysis of Machine Learning Algorithms for Classification Purpose,” Procedia Computer Science, vol. 215, pp. 422–431, 2022, doi: https://doi.org/10.1016/j.procs.2022.12.044.
[64] K. Adil, Fayçal Messaoudi, A. Ahmed, and M. Youness, “Machine Learning and Deep Learning based Students’ Grades Prediction,” Research Square (Research Square), Aug. 2023, doi: https://doi.org/10.21203/rs.3.rs-3192793/v1.
[65] C. Aliferis and G. Simon, “Overfitting, Underfitting and General Model Overconfidence and Under-Performance Pitfalls and Best Practices in Machine Learning and AI,” Computers in health care (New York), pp. 477–524, Jan. 2024, doi: https://doi.org/10.1007/978-3-031-39355-6_10.
[66] Y. Sharon and D. Yehuda. “How Does Perfect Fitting Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks,” Arxiv.org, 2021. https://arxiv.org/html/2405.17377v1#S5 (accessed Feb. 06, 2026).
[67] E. Jafarigol, T. Trafalis, and N. Mohammadi, “A Review of Machine Learning Techniques in Imbalanced Data and Future Trends,” arXiv.org, 2023. https://arxiv.org/abs/2310.07917 (accessed Nov. 06, 2025).
[68] J. H. Joloudari, A. Marefat, M. A. Nematollahi, S. S. Oyelere, and S. Hussain, “Effective Class-Imbalance Learning Based on SMOTE and Convolutional Neural Networks,” Applied Sciences, vol. 13, no. 6, p. 4006, Jan. 2023, doi: https://doi.org/10.3390/app13064006.
[69] M. A. Lones, “Avoiding common machine learning pitfalls,” Patterns, p. 101046, Aug. 2024, doi: https://doi.org/10.1016/j.patter.2024.101046.
[70] P. Ettehadi Osgouei, E. Sertel, and M. E. Kabadayı, “Integrated usage of historical geospatial data and modern satellite images reveal long-term land use/cover changes in Bursa/Turkey, 1858–2020,” Scientific Reports, vol. 12, no. 1, May 2022, doi: https://doi.org/10.1038/s41598-022-11396-1
[71] J. P. Ocón et al., “Global tropical dry forest extent and cover: A comparative study of bioclimatic definitions using two climatic data sets,” PL