Remote Sensing and Machine Learning for Drought Assessment: The Role of Aerodynamic Drivers in Ceará, Brazil
DOI:
https://doi.org/10.11137/1982-3908_2026_49_72838Keywords:
Random Forest, Palmer Drought Severity IndexAbstract
This study aimed to create a spatiotemporal model of the Palmer Drought Severity Index in the state of Ceará, Brazil, using cloud computing and integrating a Random Forest machine learning model. Using the Google Earth Engine platform, the dataset selected for this work was TerraClimate, and the selected time interval was from 1994 to 2024. The model achieved a coefficient of determination (R²) of 0.72 and a Root Mean Squared Error of 1.27, demonstrating its ability to capture the non-linear dynamics of the region. The importance analysis of variables indicated 12-month accumulated precipitation as the main predictor (26.08%), followed by soil moisture (14.75%). Furthermore, wind speed (13.04%) stands out as a factor with greater influence than maximum temperature (8.19%), highlighting the relevance of the aerodynamic factor in the drought dynamics of the region. Spatially, the results estimate that approximately 8.7% of the state’s territory, particularly in the Inhamuns region and in the desertification nuclei of the municipality of Irauçuba, face extreme or severe drought vulnerability conditions. These findings suggest that data-driven models offer a robust and scalable alternative for assessing semi-arid areas with scarce data.
Downloads
References
Abatzoglou, J.T., Dobrowski, S.Z., Parks, S.A. & Hegewisch, K.C. 2018, ‘TerraClimate: a high-resolution global dataset of monthly climate and climatic water balance from 1958–2015’, Scientific Data, vol. 5, art. 170191, DOI: 10.1038/sdata.2017.191
Aldiansyah, S. & Saputra, R.A. 2022, ‘Comparison of machine learning algorithms for land use and land cover analysis using Google Earth Engine (case study: Wanggu watershed)’, International Journal of Remote Sensing and Earth Sciences, vol. 19, no. 2, pp. 197–210, DOI: 10.30536/ijreses.v19i2.13716
Almalki, R., Khaki, M., Saco, P.M. & Rodriguez, J.F. 2022, ‘Monitoring and mapping vegetation cover changes in arid and semi-arid areas using remote sensing technology: a review’, Remote Sensing, vol. 14, no. 20, art. 5143, DOI: 10.3390/rs14205143
Alvares, C.A., Stape, J.L., Sentelhas, P.C., Gonçalves, J.D.M. & Sparovek, G. 2013, ‘Köppen’s climate classification map for Brazil’, Meteorologische Zeitschrift, vol. 22, no. 6, pp. 711–728.
Amani, M., Ghorbanian, A., Ahmadi, S.A., Kakooei, M., Moghimi, A., Mirmazloumi, S.M. & Brisco, B. 2020, ‘Google Earth Engine cloud computing platform for remote sensing big data applications: a comprehensive review’, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 5326–5350, DOI: 10.1109/JSTARS.2020.3021052
Beguería, S., Vicente-Serrano, S.M. & Angulo-Martínez, M. 2010, ‘A multiscalar global drought dataset: the SPEIbase: a new gridded product for the analysis of drought variability and impacts’, Bulletin of the American Meteorological Society, vol. 91, no. 10, pp. 1351–1364.
Breiman, L. 2001, ‘Random forests’, Machine Learning, vol. 45, no. 1, pp. 5–32.
Carvalho, A.P.I., Amorim, R.R. & Nery, J.T. 2023, ‘Orography and its influence on the formation of the desertified nucleus in the Inhamuns region’, Mercator, vol. 22, art. e22005.
Costa, J.D.S.D., Ferreira, R.L.C., Silva, J.A.A.D., Silva, A.F.D. & Pessoa, M.M.D.L. 2022, ‘Growth dynamics of a seasonally dry tropical forest in the Brazilian semiarid region’, Ciência Florestal, vol. 32, no. 3, pp. 1594–1616, DOI: 10.5902/1980509868870
Duan, X., Aslam, R.W., Naqvi, S.A.A., Kucher, D.E., Afzal, Z., Raza, D., Muhammad, R.Z. & Said, Y. 2025, ‘Multi-index assessment and machine learning integration for drought monitoring in Yunnan, China, using Google Earth Engine’, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, DOI: 10.1109/JSTARS.2025.3580652
Gonçalves, S.T.N., Vasconcelos, J.F.D.C., Silveira, C.D.S., Costa, J.M.F.D. & Marcos, J.A.D. 2023, ‘Evaluation of drought indices in the hydrological monitoring of strategic reservoirs in Ceará, Brazil’, Revista Brasileira de Meteorologia, vol. 38, art. e38230018, DOI: 10.1590/0102-77863810018
Governo do Ceará, 2026. The State of Ceará, viewed 11 Feb. 2026, <https://cearatransparente.ce.gov.br/portal-da-transparencia/paginas/o-estado-do-ceara>.
Hird, J.N., DeLancey, E.R., McDermid, G.J. & Kariyeva, J. 2017, ‘Google Earth Engine, open-access satellite data, and machine learning in support of large-area probabilistic wetland mapping’, Remote Sensing, vol. 9, no. 12, art. 1315, DOI: 10.3390/rs9121315
Kyriou, A., Nikolakopoulos, K.G. & Koukouvelas, I.K. 2022, ‘Timely and low-cost remote sensing practices for the assessment of landslide activity in the service of hazard management’, Remote Sensing, vol. 14, no. 19, art. 4745, DOI: 10.3390/rs14194745
Landim, R.B.T.V., Silva, D.F.D. & Almeida, H.R.R.C. 2011, ‘Desertification in Irauçuba (CE): investigation of possible climatic and anthropogenic causes’, Revista Brasileira de Geografia Física, vol. 4, no. 1, pp. 1–21.
Maule, C.F., Thejll, P., Christensen, J.H., Svendsen, S.H. & Hannaford, J. 2013, ‘Improved confidence in regional climate model simulations of precipitation evaluated using drought statistics from the ENSEMBLES models’, Climate Dynamics, vol. 40, no. 1, pp. 155–173, DOI: 10.1007/s00382-012-1355-7
McVicar, T.R., Roderick, M.L., Donohue, R.J., Li, L.T., Van Niel, T.G., Thomas, A., Grieser, J., Jhajharia, D., Himri, Y., Mahowald, N.M., Mescherskaya, A.V., Kruger, A.C., Rehman, S. & Dinpashoh, Y. 2012, ‘Global review and synthesis of trends in observed terrestrial near-surface wind speeds: implications for evaporation’, Journal of Hydrology, vol. 416–417, pp. 182–205, DOI: 10.1016/j.jhydrol.2011.10.024
Melese, T., Assefa, G., Terefe, B., Belay, T., Bayable, G. & Senamew, A. 2025, ‘Machine learning-based drought prediction using Palmer Drought Severity Index and TerraClimate data in Ethiopia’, PLoS ONE, vol. 20, no. 6, art. e0326174, DOI: 10.1371/journal.pone.0326174.
Van Loon, A.F. & Van Lanen, H.A.J. 2012, ‘A process-based typology of hydrological drought’, Hydrology and Earth System Sciences, vol. 16, no. 7, pp. 1915–1946, DOI: 10.5194/hess-16-1915-2012
Mutanga, O. & Kumar, L. 2019, ‘Google Earth Engine applications’, Remote Sensing, vol. 11, no. 5, art. 591, DOI: 10.3390/rs11050591
Ni, Y., Qiu, B., Miao, X., Li, L., Chen, J., Tian, X., Zhao, S. & Guo, W. 2024, ‘Shift of soil moisture–temperature coupling exacerbated the 2022 compound hot–dry event in eastern China’, Environmental Research Letters, vol. 19, no. 1, art. 014059, DOI: 10.1088/1748-9326/ad178c
Palmer, W. C. 1965. Meteorological drought (Vol. 30). US Department of Commerce, Weather Bureau.
Pereira, J.M.R., Raimundo, C.D.C., Reis, J.D.S., Vasconcelos, J.F.D.C. & Martins, E.S.P.R. 2023, ‘Use of climate information in water allocation: a case study in a semiarid region’, Water, vol. 15, no. 13, art. 2460, DOI: 10.3390/w15132460
Roberts, D.R., Bahn, V., Ciuti, S., Boyce, M.S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J.J., Schröder, B., Thuiller, W., Warton, D.I., Wintle, B.A., Hartig, F. & Dormann, C.F. 2017, ‘Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure’, Ecography, vol. 40, no. 8, pp. 913–929, DOI: 10.1111/ecog.02881
Santos, K.A., Coltri, P.P., Greco, R., Oliveira Júnior, I.D. & São José, R.V. 2023, ‘Public policies in the Brazilian semiarid region: from combating drought to living with drought’, Geo UERJ, no. 42, art. e66666, DOI: 10.1007/s10113-022-01966-4
São José, R.V., Coltri, P.P., Greco, R., Souza, I.S. & Souza, A.P. 2022, ‘Drought hazard in the semiarid region of Bahia: vulnerabilities and climatic risks’, Revista Brasileira de Geografia Física, vol. 15, no. 4, pp. 1978–1993.
Savitha, C. & Talari, R. 2025, ‘Evaluating the performance of random forest, support vector machine, gradient tree boost, and CART for improved crop-type monitoring using greenest pixel composite in Google Earth Engine’, Environmental Monitoring and Assessment, vol. 197, no. 4, art. 388, DOI: 10.1007/s10661-025-13880-3
Silva, T., Pires, V., Cota, T., & Silva, Á. 2022, ‘Detection of drought events in setúbal district: Comparison between drought indices. Atmosphere, vol. 13, no. 1, 536, DOI: 10.3390/atmos13040536
Silva, T.M., 2022, ‘Geomorphology of the humid tropics—Brazil’s Southeast’. William Morris Davis – Revista de Geomorfologia, vol. 3, no. 1, pp. 1–28, DOI: 10.48025/ISSN2675-6900.v3n1.2022.146
Sparacino, J., Argibay, D.S. & Espindola, G. 2021, ‘Long-term (35 years) rainy and dry season characterization in semiarid northeastern Brazil’, Revista Brasileira de Meteorologia, vol. 36, no. 3, pp. 377–391, DOI: 10.1590/0102-77863630138
Velastegui-Montoya, A., Montalván-Burbano, N., Carrión-Mero, P., Rivera-Torres, H., Sadeck, L. & Adami, M. 2023, ‘Google Earth Engine: a global analysis and future trends’, Remote Sensing, vol. 15, no. 14, art. 3675, DOI: 10.3390/rs15143675
Wang, C., Li, Z., Chen, Y., Li, Y., Ouyang, L., Zhu, J., Sun, F., Song, S. & Li, H. 2024, ‘Changes in global heatwave risk and its drivers over one century’, Earth’s Future, vol. 12, no. 10, art. e2024EF004430, DOI: 10.1029/2024EF004430
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This journal is licensed under a Creative Commons — Attribution 4.0 International — CC BY 4.0, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
