Machine learning on alluvial deposit Identification in dryland area
DOI:
https://doi.org/10.28998/contegeo.10i.24.18434Palavras-chave:
Dryland hydrology, Artificial intelligence, Decision tree, Machine learning, Remote sensingResumo
There is a growing global concern about water resources and an increasing interest in studies identifying groundwater. Alluvial aquifers exhibit varied forms and irregular distribution in the landscape, making their location challenging. This study applies machine learning (ML) techniques to detect alluvial deposits in the Riacho do Tigre watershed in the semi-arid region of northeastern Brazil. Fourteen input variables and one output variable were collected across approximately one and a half million points distributed along the main channels of the watershed. Using decision trees (DT), the model was trained and validated through k-fold cross-validation and bootstrap methods, achieving an accuracy of 0.916, indicating good performance in classifying alluvial areas.
Downloads
Referências
ALI, R. et al. Effectiveness of machine learning ensemble models in assessing groundwater potential in Lidder watershed, India. Acta Geophysica, v. 72, p. 2843-2856, 2023.
AL-JUAIDI, F. et al. Merged remotely sensed data for geomorphological investigations in deserts: examples from central Saudi Arabia. The Geographical Journal, v. 169, p. 117-130, 2003.
AMIT, R. et al. Soils as a tool for estimating ages of Quaternary fault scarps in a hyperarid environment: the southern Arava valley, the Dead Sea Rift, Israel. Catena, v. 28, p. 21-45, 1996.
ARDABILI, S. et al. Deep learning and machine learning in hydrological processes climate change and earth systems: a systematic review. Engineering for Sustainable Future, v. 101, p. 55-62, 2020.
BABIC, M. et al. Modeling and Classification of Alluvial Fans with DEMs and Machine Learning Methods: A Case Study of Slovenian Torrential Fans. Remote Sensing, v. 13, p. 1-18, 2021.
BRAGA, R. A. P. et al. Águas de Areia. 1. ed. Recife: Clã, 2016.
BÚRQUEZ, A. et al. Human-made small reservoirs alter dryland hydrological connectivity. Science of the Total Environment, v. 947 (10): 174673, 2024.
CAVALLI, M. et al. The effectiveness of airborne LiDAR data in the recognition of channel-bed morphology. Catena, v. 73, p. 249-260, 2008.
CAVALLI, M.; MARCHI, L. Characterisation of the surface morphology of an alpine alluvial fan using airborne LiDAR. Natural Hazards and Earth System Sciences, v. 8, p. 323-333, 2008.
CERVI, F.; TAZIOLI, A. Quantifying Streambed Dispersion in an Alluvial Fan Facing the Northern Italian Apennines: Implications for Groundwater Management of Vulnerable Aquifers. Hydrology, v. 8 (3):118, 2021.
CROUVI, O. et al. Quantitative mapping of arid alluvial fan surfaces using field spectrometer and hyperspectral remote sensing. Remote Sensing of Environment, v. 104, p. 103-117, 2006.
DÍAZ-ALCAIDE, S.; MARTÍNEZ-SANTOS, P. Review: Advances in groundwater potential mapping. Hydrogeology Journal, v. 27, p. 2307-2324, 2019.
EL BILALI, A et al. Comparing four machine learning model performances in forecasting the alluvial aquifer level in a semi-arid region. Journal of African Earth Sciences, v. 181:104244, 2021.
EFRON, B.; TIBSHIRANI, R. J. An introduction to the bootstrap. Chapman & Hall/CRC, 1993.
FARR, T. G.; CHADWICK, O. Geomorphic processes and remote sensing signatures of alluvial fans in the Kun Lun Mountains, China. Journal of Geophysical Research, v. 101, p. 23091-23100, 1996.
FRANKEL, K. L.; DOLAN, J. F. Characterizing arid region alluvial fan surface roughness with airborne laser swath mapping digital topographic data. Journal of Geophysical Research, v. 112, p. 1-14, 2007.
GABER, A. et al. Textural and Compositional Characterisation of Wadi Feiran Deposits, Sinai Peninsula, Egypt, Using Radarsat-1, PALSAR, SRTM and ETM+ Data. Remote Sensing, v. 2, p. 52-75, 2010.
GAFFOOR, Z. et al. A Comparison of Ensemble and Deep Learning Algorithms to Model Groundwater Levels in a Data-Scarce Aquifer of Southern Africa. Hydrology, v. 9, n. 7, 2022.
GILLESPIE, A. R. et al. Mapping Alluvial Fans in Death Valley, California using Multichannel Thermal Infrared Images. Geophysical Research Letters, v. 11, p. 1153-1156, 1984.
GOORABI, A. et al. Semi-automated method for the mapping of alluvial fans from DEM. Earth Science Informatics, v. 14, p. 1447-1466, 2021.
GHOLAMI, V. et al. Prediction of annual groundwater depletion: An investigation of natural and anthropogenic influences. Journal of Earth System Science, v. 132, 160, 2023.
HASTIE, T et al. The elements of statistical learning: data mining, inference, and prediction. 2nd ed. Springer, 2009.
HERTZ, G. et al. Estimating the age of desert alluvial surfaces with spaceborne radar data. Remote Sensing of Environment, v. 184, p. 288 – 301. 2016.
HOHENTHAL, J. et al. Laser scanning applications in fluvial studies. Progress in Physical Geography, v. 35, p. 782-809, 2011.
IACOBUCCI, G. Land-surface quantitative analysis for mapping and deciphering the construction processes of piedmont alluvial fans in the Anti-Lebanon Mountains. Geomorphology, v. 453, 109148, 2024.
JASECHKO, S. et al. Rapid groundwater decline and some cases of recovery in aquifers globally. Nature, v. 625, n. 7996, p. 715–721, 2024.
KAYHOMAYOON, Z. et al. How does a combination of numerical modeling, clustering, artificial intelligence, and evolutionary algorithms perform to predict regional groundwater levels? Computers and Electronics in Agriculture, v. 203, 107482, 2022.
LIMA, I. Inteligência Artificial. 1. ed. São Paulo: Grupo GEN, 2014.
LUIZ, T. B. P. Previsão de Dados de Água Subterrânea utilizando modelos baseados em Aprendizado de Máquina. Tese (Doutorado em Engenharia Civil) – Santa Maria: UFSM, 2022.
MARSLAND, S. Machine Learning: an algorithmic Perspective. Boca Raton: Taylor & Francis Group, LLC, 2015.
MARTÍNEZ-SANTOS, P.; RENARD, P. Mapping Groundwater Potential Through an Ensemble of Big Data Methods. Groundwater, v. 58, n. 4, p. 583–597, 2020.
MCLEOD, J. S. et al. Landscapes on the edge: River intermittency in a warming world. Geology, v. 52, n. 7, p. 512-516, 2024.
MITCHELL, T. M. Machine Learning. McGraw-Hill Science/Engineering/Math, 1997.
MUÑOZ-CARPENA, R. et al. Convergence of mechanistic modeling and artificial intelligence. Hydrologic science and engineering. Plos Water, v. 2, 59, 2023.
NGUYEN, P. T. et al. Improvement of credal decision trees using ensemble frameworks for groundwater potential modeling. Sustainability, v. 12, n. 7, 2622, 2020.
PIPAUD, I.; LEHMKUHL, F. Object-based delineation and classification of alluvial fans by application of mean-shift segmentation and support vector machines. Geomorphology, v. 293, p. 178-200, 2017.
QUINLAN, J. R. Induction of Decision Trees. Machine Learning, v. 1, n. 1, p. 81-106, 1986.
RABANAQUE, M. P. et al. Basin-wide hydromorphological analysis of ephemeral streams using machine learning algorithms. Earth Surface Processes and Landforms, v. 47, p. 1-17, 2021.
REGMI, N. R. et al. Mapping Quaternary alluvial fans in the southwestern United States based on multiparameter surface roughness of lidar topographic data. Journal of Geophysical Research, v. 119, p. 12-27, 2014.
RITCHIE, H.; EISMA, J. A.; PARKER, A. Sand dams as a potential solution to rural water security in drylands: Existing research and future opportunities. Frontiers in Water, v. 3, 31, 2021.
RUSSELL, S. J.; NORVIG, P. Inteligência Artificial: Uma Abordagem Moderna. Rio de Janeiro: Grupo GEN, 2022.
SEIFU, T. K. et al. Application of advanced machine learning algorithms and geospatial techniques for groundwater potential zone mapping in Gambela Plain, Ethiopia. Hydrology Research, v. 54, n. 10, p. 1246–1266, 2023.
SHAKYA, et al. Groundwater level prediction with machine learning for the Vidisha district, a semi-arid region of Central India. Groundwater for Sustainable Development, v. 19, 100825, 2022.
SILVA, A. F. P.; SOUZA, J. P. Análise da qualidade da água nos aquíferos aluviais da bacia Riacho do Tigre-PB: Uma abordagem hidrológica em ambientes fluviais semiáridos no Brasil. Revista de Geografia Norte Grande, n. 84, p. 323–336, 2023.
SILVA, A. F. P. L.; SOUZA, J. O. P. Caracterização Hidrossedimentológica dos trechos fluviais da bacia do Riacho do Tigre – PB. Caminhos de Geografia, v. 18, n. 63, p. 57–89, 2017.
SOUZA, J. O. P.; ALMEIDA, J. D. M. Processos fluviais em terras secas: uma revisão. Revista OKARA: Geografia em Debate, v. 9, p. 108–122, 2015.
SRIVASTAVA, D. K.; SHUKLA, A.; JEMNI, D. Prediction of Ground Water Level in Rajasthan State Using Machine Learning. Procedia Computer Science, v. 218, p. 1702-1711, 2023.
STALEY, D. M. et al. Surficial patterns of debris flow deposition on alluvial fans in Death Valley, CA using airborne laser swath mapping data. Geomorphology, v. 74, p. 152-163, 2005.
TAO, H. et al. Groundwater level prediction using machine learning models: A comprehensive review. Neurocomputing, v. 489, p. 271-308, 2022.
TAYER, T. C. et al. Identifying intermittent river sections with similar hydrology using remotely sensed metrics. Journal of Hydrology, v. 626, 130266, 2023.
UC-CASTILLO, J. L. et al. A systematic review and meta-analysis of groundwater level forecasting with machine learning techniques: Status and future directions. Environmental Modelling and Software, v. 168, 105788, 2023.
VADIATI, M. et al. Application of artificial intelligence models for prediction of groundwater level fluctuations: case study (Tehran-Karaj alluvial aquifer). Environmental Monitoring and Assessment, v. 194, 619, 2022.
ZARESEFAT, M.; DERAKHSHANI, R. Revolutionizing Groundwater Management with Hybrid AI Models: A Practical Review. Water, v. 15, 1750, 2023.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Este trabalho está licenciado sob uma licença Creative Commons Attribution-ShareAlike 4.0 International License. Os Autores dos trabalhos aceitos para publicação na revista CONTEXTO GEOGRÁFICO devem concordar com os termos a seguir: a) Autores mantém os direitos autorais e concedem à revista o direito de primeira publicação, com o trabalho licenciado sob a Creative Commons Atribuição-NãoComercial-SemDerivações 4.0 Internacional; b) Autores têm permissão e são estimulados a publicar e distribuir seu trabalho online;e c) Considerando que o acesso a revista é público, os artigos publicados são de uso gratuito, com atribuições próprias, em aplicações educacionais e não-comerciais.
