An Artificial Intelligence Model for Predicting Flooding and Drought in Bali Local Government Area of Taraba State, Nigeria
Article Sidebar
Main Article Content
Abstract
The ability to predict climate-induced phenomena like drought and flooding are critical for effective resource management and mitigation planning. This study investigates the application of advanced predictive models to forecast drought and flood indices using comprehensive meteorological datasets from Meteomatics' global weather monitoring platform. The dataset, spanning 14 years (2010–2024) for Bali, Taraba State, Nigeria, comprises over 5,000 data points and 33 climate variables. Data preprocessing included temporal sorting, duplicate removal, and missing value imputation through interpolation and forward-fill methods. Correlation analyses highlighted significant relationships among key features, such as temperature, humidity, wind speed, and solar energy, which play pivotal roles in drought and flooding dynamics. For predictive modeling, six approaches—ARIMA, SARIMA, Prophet, XGBoost, Random Forest, and LSTM—were evaluated across five targets: Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI), daily water balance, 30-day water balance, and SPEI-30d. The models underwent rigorous optimization through feature selection and hyperparameter tuning. Results revealed that machine learning models, particularly Random Forest and XGBoost, outperformed traditional statistical methods and neural networks in most scenarios, with XGBoost achieving an impressive R² of 0.843 for SPEI predictions. Prophet proved most effective for daily water balance predictions, while Random Forest excelled in 30-day water balance and SPEI-30d forecasting. This study underscores the critical importance of model optimization in enhancing predictive accuracy and demonstrates the potential of machine learning models for addressing complex hydrological forecasting challenges. The findings provide a robust framework for drought and flood prediction, contributing to improved water resource management and disaster preparedness strategies.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
IJCERT Policy:
The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.
By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.
References
C. Li, X. Ren, and G. Zhao, "Machine-learning-based imputation method for filling missing values in ground meteorological observation data," Algorithms, vol. 16, no. 9, p. 422, 2023, doi: 10.3390/a16090422.
K. E. Trenberth, "Changes in precipitation with climate change," Climate Res., vol. 47, pp. 123–138, 2011. [Online]. Available: https://www.int-res.com/articles/cr_oa/c047p123.pdf
R. G. Allen, L. S. Pereira, D. Raes, and M. Smith, Crop evapotranspiration – Guidelines for computing crop water requirements. Rome: FAO, 1998, FAO Irrigation and Drainage Paper 56.
M. H. Ibrahim et al., "Comparative assessment of evapotranspiration methods in tropical agroecological systems," J. Water Resour. Plan. Manag., vol. 147, no. 2, p. 04021008, 2021.
S. Irmak et al., "Performance of evapotranspiration equations under different climatic conditions," Agric. Water Manag., vol. 152, pp. 1–12, 2015.
J. Kim et al., "Evaluation of Priestley-Taylor and other simplified PET methods in diverse climates," Environ. Model. Assess., vol. 26, no. 3, pp. 45–62, 2021.
L. S. Pereira et al., "The Hargreaves and other temperature-based PET methods revisited," Water, vol. 12, no. 5, p. 1319, 2020.
C. Shoko and S. Nayna, "Application of the Makkink PET method for regional irrigation planning in humid areas," Water Resour. Res., vol. 58, no. 7, p. e2021WR030456, 2022.
R. Hadria, T. Benabdelouhab, H. Lionboui, and A. Salhi, "Comparative assessment of different reference evapotranspiration models towards a fit calibration for arid and semi-arid areas," J. Arid Environ., vol. 184, p. 104318, 2021, doi: 10.1016/j.jaridenv.2020.104318.
M. Vremec and R. A. Collenteur, "Technical note: Improved handling of potential evapotranspiration in hydrological studies with PyEt," Geosci. Model Dev., submitted. [Online]. Available: https://pyet.readthedocs.io
S. M. Vicente-Serrano, S. Beguería, and J. I. López-Moreno, "A multi-scalar drought index sensitive to global warming: The standardized precipitation evapotranspiration index," J. Climate, vol. 23, no. 7, pp. 1696–1718, 2010.
S. Beguería, S. M. Vicente-Serrano, and M. Angulo-Martínez, "A multiscalar global drought dataset: The SPEIbase," Bull. Amer. Meteorol. Soc., vol. 91, no. 10, pp. 1351–1354, 2010.
PyET Documentation, 2020. [Online]. Available: https://pyet.readthedocs.io
P. C. D. Milly, K. A. Dunne, and A. V. Vecchia, "Global patterns of groundwater depletion," Nature, vol. 438, no. 7065, pp. 12–14, 2005, doi: 10.1038/nature04388.
H. U. Mahmood, J. N. Jerome, and J. Jane, "Agricultural management strategy on food security in Taraba State," J. Biol. Agric. Healthcare, vol. 4, no. 8, pp. 29–31, 2014. [Online]. Available: https://typeset.io/pdf/agricultural-management-strategy-on-food-security-in-taraba-262x7d9u1v.pdf
S. Kang, L. Zhang, and X. Zeng, "Crop production in China’s arid and semi-arid regions," Agric. Water Manag., vol. 97, no. 9, pp. 1180–1191, 2010, doi: 10.1016/j.agwat.2010.02.005.
S. P. Harrison and I. C. Prentice, "Climate and the evolution of terrestrial ecosystems," Nature, vol. 467, no. 7315, pp. 1069–1073, 2010, doi: 10.1038/nature09422.
Y. Cao, S. Wang, and Q. Zhang, "Impacts of precipitation on soil moisture and vegetation growth in the Loess Plateau, China," Hydrol. Earth Syst. Sci., vol. 19, no. 11, pp. 4407–4420, 2015, doi: 10.5194/hess-19-4407-2015.
C. U. Igbokwe and P. I. Okonkwo, "Household food security response to climate change extreme events in Taraba State, Nigeria," J. Econ. Sustain. Dev., vol. 8, no. 22, pp. 23–32, 2017. [Online]. Available: https://typeset.io/pdf/household-food-security-response-to-climate-change-extreme-2pgmwnygyp.pdf
T. Ribera and J. Garcia, "The impact of irrigation and drought on the economy: Evidence from the United States," Water Resour. Res., vol. 45, no. 3, p. W03418, 2009, doi: 10.1029/2008WR006812.
D. W. Schindler, "The cumulative effects of climate warming and other human stresses on freshwater ecosystems in Canada," Freshwater Biol., vol. 46, no. 6, pp. 1–15, 2001, doi: 10.1111/j.1365-2427.2001.00772.x.
NASA, "Standardized Precipitation Index (SPI)," 2023. [Online]. Available: https://gmao.gsfc.nasa.gov/research/subseasonal/atlas/SPI-html/SPI-description.html
SPEI.CSIC, "About SPEI," 2023. [Online]. Available: https://spei.csic.es/home.html
N. I. Obot and A. E. Akpan, "Identification of influential weather parameters and seasonal patterns for drought prediction using artificial intelligence models," Sci. Rep., vol. 13, Art. no. 51111, 2023, doi: 10.1038/s41598-023-51111-2.
G. Wee et al., "A flood impact-based forecasting system by fuzzy inference techniques," J. Hydrol., vol. 625, p. 130117, 2023, doi: 10.1016/j.jhydrol.2023.130117.