DESLIZAMIENTO DE TIERRA, CAMBIO CLIMÁTICO E INTELIGENCIA ARTIFICIAL EXPLICABLE EN ZONAS ANDINO-AMAZÓNICAS VULNERABLES, MEDIANTE MODELADO ESPACIO-TEMPORAL
DOI:
https://doi.org/10.56519/ty981a39Palabras clave:
cambio climático, deslizamientos, inteligencia artificial, riesgos, variabilidadResumen
En las regiones vulnerables de los Andes y la Amazonía, las carreteras y asentamientos humanos están amenazados por deslizamientos de tierra, debido a la combinación de relieve escarpado, lluvias extremas y deforestación desenfrenada. El estudio buscó construir un modelo para predecir la susceptibilidad y el riesgo de deslizamientos bajo el marco del cambio climático, utilizando una combinación de técnicas en estadística geoespacial e inteligencia artificial explicable. El estudio propuesto enmarcó la integración de variables climáticas, topográficas, ambientales, geológicas e hidrográficas, antropogénicas y sociales en una matriz de análisis espacial para el uso de técnicas de aprendizaje automático interpretables y espaciales. Basándose en los resultados, se espera que el riesgo crezca continuamente desde el estado actual hasta el escenario severo de 2070, caracterizado por un aumento en el riesgo mediano y una mayor dispersión geográfica de áreas de riesgo alto y muy alto. Los factores más importantes, según el estudio, son el uso del suelo, las precipitaciones extremas y las precipitaciones acumuladas. Aunque se atribuyó un alto grado de precisión en la predicción en general al uso de Random Forest, aún sería necesario realizar una optimización adicional para mejorar el nivel de rendimiento del modelo, en particular la validación de eventos extremos y el equilibrio de clases. Los resultados parecen confirmar la hipótesis del estudio, es decir, que la combinación de esas herramientas permite generar un mapeo interpretable y útil, apropiado para su uso en marcos de planificación de riesgos y adaptación al cambio climático.
Descargas
Referencias
Lima, P., Steger, S., Glade, T., & Murillo-García, F. G. (2022). Literature review and bibliometric analysis on data-driven assessment of landslide susceptibility. Journal of Mountain Science, 19, 1670–1698. https://doi.org/10.1007/s11629-021-7254-9
Ospina-Gutiérrez, J. P., & Aristizábal, E. (2021). Application of artificial intelligence and machine learning techniques for landslide susceptibility assessment. Revista Mexicana de Ciencias Geológicas, 38(1), 43–54. https://doi.org/10.22201/cgeo.20072902e.2021.1.1605
Pugliese Viloria, A. de J., Folini, A., Carrion, D., & Brovelli, M. A. (2024). Hazard susceptibility mapping with machine and deep learning: A literature review. Remote Sensing, 16(18), 3374. https://doi.org/10.3390/rs16183374
Cargua, F., Espin, J., Valencia, N., Simbaña, J., Araujo, A., Ocampos, R., & Cornejo, M. (2024). Análisis de susceptibilidad a deslizamientos empleando el proceso de jerarquía analítica en una carretera amazónica del Ecuador. La Granja, 39(1), 117–138. https://doi.org/10.17163/lgr.n39.2024.07
Ali, S. A., Parvin, F., Vojteková, J., Costache, R., Linh, N. T. T., Pham, Q. B., et al. (2021). GIS-based landslide susceptibility modeling: A comparison between fuzzy multi-criteria and machine learning algorithms. Geoscience Frontiers, 12, 857–876. https://doi.org/10.1016/j.gsf.2020.09.004
Calderón-Guevara, J. A., Sánchez-Silva, M., Nitescu, C., & Villarraga, M. R. (2022). Comparative review of data-driven landslide susceptibility models: Case study in the Eastern Andes mountain range of Colombia. Natural Hazards, 113, 1105–1132. https://doi.org/10.1007/s11069-022-05339-2
Bravo-López, D., Fernández Del Castillo, T., Sellers, C., & Delgado-García, J. (2023). Analysis of conditioning factors in Cuenca, Ecuador, for landslide susceptibility maps generation employing machine learning methods. Land, 12(6), 1135. https://doi.org/10.3390/land12061135
Bravo-López, D., Fernández, T., Sellers, C., & Delgado-García, J. (2025). Combination of conditioning factors for generation of landslide susceptibility maps by extreme gradient boosting in Cuenca, Ecuador. Algorithms, 18(5), 258. https://doi.org/10.3390/a18050258
Puente-Sotomayor, F., Mustafa, A., & Teller, J. (2021). Landslide susceptibility mapping of urban areas: Logistic regression and sensitivity analysis applied to Quito, Ecuador. Geoenvironmental Disasters, 8, Article 9. https://doi.org/10.1186/s40677-021-00184-0
Dahal, A., & Lombardo, L. (2023). Explainable artificial intelligence in geoscience: A glimpse into the future of landslide susceptibility modeling. Computers & Geosciences, 176, 105364. https://doi.org/10.1016/j.cageo.2023.105364
Pradhan, B., Dikshit, A., Lee, C. W., & Kim, Y. T. (2023). An explainable AI model for landslide susceptibility modeling. Applied Soft Computing, 142, 110324. https://doi.org/10.1016/j.asoc.2023.110324
Le, H. V., Eu, S., Choi, J., Eu, S., Yeon, H., & Lee, S. (2024). Quantitative evaluation of uncertainty and interpretability in machine learning-based landslide susceptibility mapping through feature selection and explainable AI. Frontiers in Environmental Science, 12, 1424988. https://doi.org/10.3389/fenvs.2024.1424988
Lin, Q., Steger, S., Pittore, M., Zhang, J., Wang, L., Jiang, T., & Wang, Y. (2022). Evaluation of potential changes in landslide susceptibility and landslide occurrence frequency in China under climate change. Science of the Total Environment, 850, 158049. https://doi.org/10.1016/j.scitotenv.2022.158049
Guo, Z., Ferrer, J. V., Hürlimann, M., Medina, V., Puig-Polo, C., Yin, K., & Huang, D. (2023). Shallow landslide susceptibility assessment under future climate and land cover changes: A case study from Southwest China. Geoscience Frontiers, 14, 101542. https://doi.org/10.1016/j.gsf.2023.101542
Chaithong, T. (2024). Assessing the impact of climate change on landslide recurrence intervals in Nakhon Si Thammarat Province, Thailand, using CMIP6 climate models. Progress in Disaster Science, 22, 100330. https://doi.org/10.1016/j.pdisas.2024.100330
Tetteh, D., Abbey, S. J., Booth, C., & Nukah, P. (2025). Current understanding and uncertainties associated with climate change and the impact on slope stability: A systematic literature review. Natural Hazards Research. Advance online publication. https://doi.org/10.1016/j.nhres.2025.01.011
Capobianco, V., Choi, C. E., Crosta, G. B., et al. (2025). Effective landslide risk management in the era of climate change, demographic change, and evolving societal priorities. Landslides, 22, 2915–2933. https://doi.org/10.1007/s10346-024-02418-2
Ghosh, P., Bera, S., Talukdar, S., Priyadarshi, S., & Melo, R. (2026). Dynamics of population exposure to landslides under climate change scenarios. International Journal of Disaster Risk Reduction, 135, 106041. https://doi.org/10.1016/j.ijdrr.2026.106041
Samodra, G., Ngadisih, & Nugroho, F. S. (2024). Benchmarking data handling strategies for landslide susceptibility modeling using random forest workflows. Artificial Intelligence in Geosciences, 5, 100093. https://doi.org/10.1016/j.aiig.2024.100093
Liu, L.-L., Duan, C., Gao, J.-H., Xiao, H., Zhu, W.-Q., & Yang, C. (2026). Landslide susceptibility assessment using machine learning with a novel SHAP-based sampling strategy. Geoscience Frontiers, 17(2), 102188. https://doi.org/10.1016/j.gsf.2025.102188
Chutia, D., Deka, R. K., Kumar, R., Kumar, P., Chauhan, A., Singh, P. S., Nishant, N., Biswakarma, P., Sarma, K. K., & Aggarwal, S. P. (2026). Exploring the feasibility and challenges of AI-based rainfall-induced landslides prediction. Natural Hazards, 122(5), 180. https://doi.org/10.1007/s11069-025-07965-y
Macías, J., Quiñonez-Macías, M., Toulkeridis, T., & Pastor, J. L. (2024). Characterization and geophysical evaluation of the recent 2023 Alausí landslide in the northern Andes of Ecuador. Landslides, 21, 529–540. https://doi.org/10.1007/s10346-023-02185-6
Medina, V., Hürlimann, M., Guo, X., Lloret, A., & Vaunat, J. (2021). Fast physically-based model for rainfall-induced landslide susceptibility assessment at regional scale. CATENA, 201, 105213. https://doi.org/10.1016/j.catena.2021.105213
Ma, J., Shao, X., Xu, C., He, Y., & Zhang, P. (2021). MAT.TRIGRS (V1.0): A new open-source tool for predicting spatiotemporal distribution of rainfall-induced landslides. Natural Hazards Research, 1(3–4), 161–170. https://doi.org/10.1016/j.nhres.2021.11.001
Wang, C., Qin, Z., Xiao, T., Xiang, L., Peng, R., Mi, M., & Liu, X. (2026). Slope geological hazard risk assessment using Bayesian-optimized random forest: A case study of Linxiang City, China. Applied Sciences, 16(3), 1309. https://doi.org/10.3390/app16031309
Yi, Z., Liu, H., Tian, Z., Guo, Y., Liu, H., Zhang, J., Wu, Z., Su, Y., Luo, H., & Chen, H. (2026). Assessment of eco-geological vulnerability using multiple machine learning models: A case study of the Three Gorges Reservoir Area, China. Sustainability, 18(4), 1758. https://doi.org/10.3390/su18041758
Feng, J., Wu, G., Zhang, X., Jiang, Z., Zhang, Y., Chen, F., & Zhang, S. (2026). Current status and prospects of vegetation restoration on landslides. Land Degradation & Development, 37(4), 1193-1207. https://doi.org/10.1002/ldr.70189
Vega, J. A., Sepúlveda-Murillo, F. H., & Parra, L. (2023). Landslide modeling in a tropical mountain basin using machine learning algorithms and Shapley additive explanations. Air, Soil and Water Research, 16, 11786221231195824. https://doi.org/10.1177/11786221231195824
Chen, Y., Yuan, H., Chen, J., Pan, R., Deng, L., Huang, L., Zhang, M., & Yang, Q. (2026). Landslide early warning model based on multi-source monitoring data and unsupervised machine learning. Engineering Applications of Artificial Intelligence, 164, 113156. https://doi.org/10.1016/j.engappai.2025.113156
Nguyen, H.-H.-D., Nguyen, T.-N., Song, C.-H., & Kim, Y.-T. (2026). Probabilistic modeling of rainfall-induced landslide hazard using nonstationary generalized extreme value distribution with nonlinear characteristics. Advances in Space Research, S0273117726004837. https://doi.org/10.1016/j.asr.2026.04.019
Aman, M. A., & Chu, H.-J. (2026). Quantifying ecosystem resilience and recovery after landslides: Earth observation-based mapping of post-disturbance vegetation recovery using Newton’s law of cooling. Natural Hazards, 122(7), 314. https://doi.org/10.1007/s11069-025-07962-1
Amenta, L., & De Martino, P. (2026). Learning how to live with risk—The role of co-design for managing city–port thresholds in Castellammare di Stabia, Naples, Italy. Sustainability, 18(7), 3242. https://doi.org/10.3390/su18073242
Bertin, M., & Vincenti, E. (2026). Preventive repositioning of the settled city. En P. K. Kresl (Ed.), Mid-sized cities and regions in global competition (pp. 114-144). Edward Elgar Publishing. https://doi.org/10.4337/9781035372478.00011
Dreyer, J. T., Robinson, T. R., Katurji, M., Leith, K., & Williams, J. (2026). Increasing landslide susceptibility and intensity under climate change for Aotearoa New Zealand. Scientific Reports, 16, 11683. https://doi.org/10.1038/s41598-026-46684-7
Gargiulo, C., & Guida, C. (2026). Climate-proofing cities: A focus on vulnerability indices. International Planning Studies, 1-19. https://doi.org/10.1080/13563475.2026.2620774
Görür, N., & Yildiz, A. (2026). Neotectonics and earthquake preparedness in Türkiye: Embedding geological foresight in urban planning. Journal of Risk Research, 29(1), 14-22. https://doi.org/10.1080/13669877.2025.2611949
Gugg, G. (2026). From escape route to infrastructural trap: Anthropological insights on vulnerability along Italy’s SS 268 of Vesuvius. Journal of Modern Italian Studies, 1-28. https://doi.org/10.1080/1354571X.2025.2609246
John, A., Michalak, J. L., Svancara, L. K., Randels, C., & Lawler, J. J. (2026). Identifying climate‐change refugia for species management and conservation in the Pacific Northwest. Conservation Science and Practice, 8(1), e70174. https://doi.org/10.1111/csp2.70174
Lam, K. S. P., Lam, C., Chan, E. Y. M., & Lui, B. L. S. (2026). Landslides in Hong Kong: Historical insights, contributory factors and lessons learnt. Bulletin of Engineering Geology and the Environment, 85(5), 298. https://doi.org/10.1007/s10064-026-04983-3
Mondragón-Rodríguez, A., & Quesada-Román, A. (2026). Integrating geomorphological and socio-spatial factors for landslide risk zonation in Atenas, Costa Rica. Discover Hazards, 2(1), 8. https://doi.org/10.1007/s44475-026-00012-9
Morelli, T. L., Mozelewski, T., Cavalieri, C. N., Caven, A. J., Dreiss, L. M., Hovel, R. A., Hua, M., Jennings, M. K., John, A., Kehm, G., Keppel, G., Krawchuk, M. A., Langdon, S. F., Lawler, J. J., Lyon, L. M., Meigs, G. W., Mora‐Gonzalez, M., Nadeau, C. P., Słowińska, S., … Stralberg, D. (2026). Conserving climate‐change refugia: Insights from research and practice. Conservation Science and Practice, 8(1), e70160. https://doi.org/10.1111/csp2.70160
Pei, J., Dai, C., & Cui, T. (2026). A directed weighted network approach for hazard chain risk assessment including heavy rainfall induced geological disasters and flooding. Scientific Reports, 16(1), 2866. https://doi.org/10.1038/s41598-025-32694-4
Pilatasig, L., et al. (2025). Casual-Nuevo Alausí landslide (Ecuador, March 2023): A case study on the influence of the anthropogenic factors. GeoHazards, 6(2), 28. https://doi.org/10.3390/geohazards6020028
Scapellato, G., Licciardello, G., Blanco, G. L. M., Campione, F., Carbone, M. L., Castorina, S., Londino, A. M., Riggio, M., Sapienza, G., Scrofana, G., Tomarchio, S., Scalia, S., & Neri, M. (2026). Digital governance and geohazard mitigation in post-earthquake reconstruction: The 2018 Etna case study. GeoHazards, 7(1), 16. https://doi.org/10.3390/geohazards7010016
