Publication Frequency Adjustment
2025-07-08
Drought Forecast Using Traditional and Custom Models for Dhaka, Bangladesh
Authors
-
Aunik Hasan Mridul
Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh
-
Tanumoy Bose
Department of Electrical and Electronics Engineering, Ahsanullah University of Science and Technology, Dhaka 1208, Bangladesh
-
Swapneel Biswas
Department of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka 1208, Bangladesh
-
Nafi Ahmed
Department of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka 1208, Bangladesh
-
S. M. Hasan Kabir
Department of Computer Science and Engineering, Daffodil International University, Dhaka 1216, Bangladesh
-
Nebadeta Nath Tonney
Department of Computer Science and Engineering, American International, University-Bangladesh, Dhaka 1229, Bangladesh
-
Pooja Saha
Department of Geography and Environment, University of Dhaka, Dhaka 1000, Bangladesh
DOI:
https://doi.org/10.30564/re.v7i5.10103Abstract
Water scarcity and climate change are two of the biggest worldwide concerns. A complicated and sometimes underappreciated occurrence, drought has an impact on many facets of human existence. Early drought forecasts are therefore essential for water resource management and strategic planning. In order to improve the accuracy of drought prediction, this work presents a unique hybrid model that combines the Autoregressive Moving Average (ARMA), Holt-Winters (Exponential Smoothing) model, Autoregressive Integrated Moving Average (ARIMA), and Random Forest Regressor model. We do a thorough analysis of the Dhaka Division, Bangladesh, daily precipitation data from January 1981 to March 2025. In contrast to other research that only examined standalone machine learning algorithms or conventional statistical models, our study combines the two and offers a comparative performance analysis of hybrid models in the context of drought prediction using SPI. Furthermore, the study uses these models in the understudied setting of Dhaka, Bangladesh, a place where little previous research has been done on drought forecasting. When examined side by side, our hybrid model Holt-Winters with LSTM model outperforms the hybrid approach. For SPI daily predictions, significant statistical parameters like Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) are especially crucial. This noteworthy enhancement highlights how much more accurate the innovative model is in forecasting droughts in Bangladesh's Dhaka Division. Our findings highlight the hybrid model's vital importance in tackling the problems caused by drought in the larger framework of climate change and water resource management.
Keywords:
ARMA; ARIMA; Mean Absolute Error; LSTM; DroughtReferences
[1] Mishra, A.K., Singh, V.P., 2010. A review of drought concepts. Journal of Hydrology. 391(1–2), 202–216. DOI: https://doi.org/10.1016/j.jhydrol.2010.07.012
[2] Wilhite, D.A., 2005. Drought and Water Crises. CRC Press: Boca Raton, FL, USA. DOI: https://doi.org/10.1201/9781420028386
[3] Khan, Md.M.H., Muhammad, N.S., El-Shafie, A., 2020. Wavelet based hybrid ANN-ARIMA models for meteorological drought forecasting. Journal of Hydrology. 590, 125380. DOI: https://doi.org/10.1016/j.jhydrol.2020.125380
[4] Wu, H., Hubbard, K.G., Wilhite, D.A., 2004. An agricultural drought risk-assessment model for corn and soybeans. International Journal of Climatology. 24(6), 723–741. DOI: https://doi.org/10.1002/joc.1028
[5] Mishra, A.K., Desai, V.R., 2005. Drought forecasting using stochastic models. Stochastic Environmental Research and Risk Assessment. 19(5), 326–339. DOI: https://doi.org/10.1007/s00477-005-0238-4
[6] Guttman, N.B., 1998. Comparing the palmer drought index and the standardized precipitation index. Journal of the American Water Resources Association. 34(1), 113–121. DOI: https://doi.org/10.1111/j.1752-1688.1998.tb05964.x
[7] Zargar, A., Sadiq, R., Naser, B., et al., 2011. A review of drought indices. Environmental Reviews. 19, 333–349. DOI: https://doi.org/10.1139/a11-013
[8] Zhang, G.P., 2003. Time Series Forecasting Using a Hybrid ARIMA and Neural Network Model. Neurocomputing. 50, 159–175. DOI: https://doi.org/10.1016/s0925-2312(01)00702-0
[9] Nourani, V., Alami, M.T., Aminfar, M.H., 2009. A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation. Engineering Applications of Artificial Intelligence. 22(3), 466–472. DOI: https://doi.org/10.1016/j.engappai.2008.09.003
[10] Nourani, V., Hosseini Baghanam, A., Adamowski, J., et al., 2014. Applications of hybrid wavelet–Artificial Intelligence models in hydrology: A review. Journal of Hydrology. 514, 358–377. DOI: https://doi.org/10.1016/j.jhydrol.2014.03.057
[11] Wang, W., Ding, J., 2003. Wavelet Network Model and Its Application to the Prediction of Hydrology. 1(1), 67–71.
[12] Kriechbaumer, T., Angus, A., Parsons, D., et al., 2014. An improved wavelet–ARIMA approach for forecasting metal prices. Resources Policy. 39, 32–41. DOI: https://doi.org/10.1016/j.resourpol.2013.10.005
[13] Venkata Ramana, R., Krishna, B., Kumar, S.R., et al., 2013. Monthly Rainfall Prediction Using Wavelet Neural Network Analysis. Water Resources Management. 27(10), 3697–3711. DOI: https://doi.org/10.1007/s11269-013-0374-4
[14] Seo, Y., Choi, Y., Choi, J., 2017. River Stage Modeling by Combining Maximal Overlap Discrete Wavelet Transform, Support Vector Machines and Genetic Algorithm. Water. 9(7), 525. DOI: https://doi.org/10.3390/w9070525
[15] Quilty, J., Adamowski, J., Boucher, M., 2019. A Stochastic Data‐Driven Ensemble Forecasting Framework for Water Resources: A Case Study Using Ensemble Members Derived From a Database of Deterministic Wavelet‐Based Models. Water Resources Research. 55(1), 175–202. DOI: https://doi.org/10.1029/2018wr023205
[16] Kim, T.-W., Valdés, J.B., 2003. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrologic Engineering. 8(6), 319. DOI: https://doi.org/10.1061/(ASCE)1084-0699(2003)8:6(319)
[17] Partal, T., Kişi, Ö., 2007. Wavelet and neuro-fuzzy conjunction model for precipitation forecasting. Journal of Hydrology. 342(1–2), 199–212. DOI: https://doi.org/10.1016/j.jhydrol.2007.05.026
[18] Rathinasamy, M., et al., 2014. Wavelet‐based multiscale performance analysis: An approach to assess and improve hydrological models. Water Resources Research. 50(12), 9721–9737. DOI: https://doi.org/10.1002/2013wr014650
[19] Adamowski, J., Fung Chan, H., Prasher, S.O., et al., 2012. Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada. Water Resources Research. 48(1). DOI: https://doi.org/10.1029/2010wr009945
[20] Shabri, A., 2015. A Hybrid Model for Stream Flow Forecasting Using Wavelet and Least Squares Support Vector Machines. Jurnal Teknologi. 73(1), 101–111. DOI: https://doi.org/10.11113/jt.v73.3380
[21] Belayneh, A., Adamowski, J., Khalil, B., 2015. Short-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet transforms and machine learning methods. Sustainable Water Resources Management. 2(1), 87–101. DOI: https://doi.org/10.1007/s40899-015-0040-5
[22] Belayneh, A., Adamowski, J., 2012. Standard Precipitation Index Drought Forecasting Using Neural Networks, Wavelet Neural Networks, and Support Vector Regression. Applied Computational Intelligence and Soft Computing. 2012, 1–13. DOI: https://doi.org/10.1155/2012/794061
[23] Soh, Y.W., Koo, C.H., Huang, Y.F., et al., 2018. Application of artificial intelligence models for the prediction of standardized precipitation evapotranspiration index (SPEI) at Langat River Basin, Malaysia. Computers and Electronics in Agriculture. 144, 164–173. DOI: https://doi.org/10.1016/j.compag.2017.12.002
[24] Danandeh Mehr, A., Kahya, E., Özger, M., 2014. A gene–wavelet model for long lead time drought forecasting. Journal of Hydrology. 517, 691–699. DOI: https://doi.org/10.1016/j.jhydrol.2014.06.012
[25] Djerbouai, S., Souag-Gamane, D., 2016. Drought Forecasting Using Neural Networks, Wavelet Neural Networks, and Stochastic Models: Case of the Algerois Basin in North Algeria. Water Resources Management. 30(7), 2445–2464. DOI: https://doi.org/10.1007/s11269-016-1298-6
[26] Deo, R.C., Tiwari, M.K., Adamowski, J.F., et al., 2016. Forecasting effective drought index using a wavelet extreme learning machine (W-ELM) model. Stochastic Environmental Research and Risk Assessment. 31(5), 1211–1240. DOI: https://doi.org/10.1007/s00477-016-1265-z
[27] Hayes, M., Svoboda, M., Wall, N., et al., 2011. The Lincoln declaration on drought indices: universal meteorological drought index recommended. Bulletin of the American Meteorological Society. 92(4), 485–488. DOI: https://doi.org/10.1175/2010BAMS3103.1
[28] Koycegiz, C., Buyukyildiz, M., 2019. Calibration of SWAT and Two Data-Driven Models for a Data-Scarce Mountainous Headwater in Semi-Arid Konya Closed Basin. Water. 11(1), 147. DOI: https://doi.org/10.3390/w11010147
[29] Koycegiz, C., Buyukyildiz, M., 2022. Investigation of precipitation and extreme indices spatiotemporal variability in Seyhan Basin, Turkey. Water Supply. 22(12), 8603–8624. DOI: https://doi.org/10.2166/ws.2022.391
[30] Koycegiz, Cihangir, Buyukyildiz, Meral, 2022. Investigation of spatiotemporal variability of some precipitation indices in Seyhan Basin, Turkey: monotonic and sub-trend analysis. Natural Hazards. 116(2), 2211–2244. DOI: https://doi.org/10.1007/s11069-022-05761-6
[31] Mahmud, I., Bari, S.H., Rahman, M.T.U., 2016. Monthly rainfall forecast of Bangladesh using autoregressive integrated moving average method. Environmental Engineering Research. 22(2), 162–168. DOI: https://doi.org/10.4491/eer.2016.075
[32] Mallat, S.G., 1989. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 11(7), 674–693. DOI: https://doi.org/10.1109/34.192463
[33] Mckee, T.B., Doesken, N.J., Kleist, J., 1995. Drought monitoring with multiple time scales. 9, 233–236.
[34] Souther, S., Colombo, S., Lyndon, N.N., 2023. Integrating traditional ecological knowledge into US public land management: Knowledge gaps and research priorities. Frontiers in Ecology and Evolution. 11, 988126. DOI: https://doi.org/10.3389/fevo.2023.988126
[35] Gasmi, A., Rahoma, Y.T., Soliman, M.M., 2024. Time Series Forecasting Using Hybrid ARIMA-LSTM for Rainfall Prediction. Journal of Hydrology and Environment Research. 13(2), 101–111.
[36] Agudelo, M., Paredes, L., Gutierrez, R.G., 2025. Drought forecasting using a hybrid neural architecture for integrating time series and static data. Environmental Modelling & Software. 167, 105534.
[37] Zhang, J., Chen, W., Liu, Q., 2025. STAT-LSTM: A multivariate spatiotemporal feature aggregation model for SPEI-based drought prediction. Knowledge-Based Systems. 284, 111035.
[38] Zhang, P., Liu, X., Wang, J., 2022. A review of deep learning applications for drought forecasting. Water Resources Management. 36(3), 983–1001.
[39] Rezaiy, H., Shabri, A.B., 2023. Short-term drought forecasting using hybrid EEMD-ARIMA model based on SPI. Stochastic Environmental Research and Risk Assessment. 37, 453–469.
[40] Otkin, J.A., Hain, C.R., Svoboda, M., 2021. DroughtCast: A machine learning approach for forecasting drought categories. Journal of Applied Meteorology and Climatology. 60(8), 1173–1187.
[41] Dikshit, S., Li, H., Waters, D.M., 2021. Long-term drought forecasting using LSTM for NSW, Australia. Remote Sensing. 13(14), 2721–2738.
[42] Tang, K., Yuan, L., Zhang, T., 2025. Quantum-empowered drought forecasting using a Mamba Network for SPEI analysis. AI for Earth Science Journal. 2, 1–14.
[43] Hossaini-Moghari, M., Khosravi, A., 2021. Application of LSTM and RBF in short-term drought prediction based on SPI. Journal of Hydrology. 602, 126748.
[44] Brust, C., Abolafia-Rosenzweig, A., Mote, T.L., 2021. Flash Drought Forecasting: Progress and Challenges in the Deep Learning Era. Drought Research Quarterly. 8, 25–36.
[45] Rahman, M., Azim, M.A., 2022. Assessment of Meteorological Drought in Bangladesh Using SPI. Journal of Climate Research. 14(2), 67–78.
[46] Rabby, T., Adhikary, S.K., 2024. Uncertainty-based drought assessment in Bangladesh using SPI. Environmental Systems Research. 13(1), 11.
[47] Mondol, S., Hasan, M., Islam, M.S., 2021. Observed Trends of Meteorological Drought in Bangladesh using EDI and SPI. Theoretical and Applied Climatology. 143(3–4), 1233–1246.
[48] Islam, N., Ahmed, R.U., Jahan, M., 2021. Comparative Evaluation of SPI and EDI for Drought Monitoring in Bangladesh. Climate Dynamics and Sustainability. 6(2), 209–220.
[49] Paul, A., Kabir, R., Khatun, M.A., 2025. Enhanced drought forecasting using satellite and machine learning data for Bangladesh. Remote Sensing of Environment. 302, 112949.
[50] Hossain, T., Rahman, S.M., 2021. Evaluating agricultural drought using EDI over Bangladesh's northwestern belt. Agricultural Water Management. 250, 106827.
[51] Khatun, M., Khan, A.M., 2021. CMIP5-Based Drought Projections for Bangladesh Using SPI and EDI. Climatic Change Letters. 159(1), 83–95.
[52] Rahman, A., Baten, S.A., Nahar, T., 2020. An integrated drought risk mapping using TVDI and climatic indicators in NW Bangladesh. Natural Hazards. 104, 1201–1216.
[53] Alam, M.U., Jahan, S.S., Kawsar, F.M., 2020. Pre-Monsoon Water Scarcity in Agriculture: A Parametric SPI Approach in Bangladesh. Hydrology and Earth System Sciences Discussions. 25(5), 2401–2418.
[54] Ali, M.M., Mahmud, T., Barua, R.S., 2021. Volatility and Predictability of SPI-Based Droughts in Northwestern Bangladesh. Climate Risk Management. 34, 10037.
[55] NASA, 2018. ArcGIS Web Application. Nasa.gov. Available from: https://power.larc.nasa.gov/data-access-viewer/ (cited 17 March 2025)
Downloads
How to Cite
Mridul, A. H., Bose, T., Biswas, S., Ahmed, N., Kabir, S. M. H., Tonney, N. N., & Saha, P. (2025). Drought Forecast Using Traditional and Custom Models for Dhaka, Bangladesh. Research in Ecology, 7(5), 1–16. https://doi.org/10.30564/re.v7i5.10103
Issue
Article Type
Article
License
Copyright © 2025 Aunik Hasan Mridul, Tanumoy Bose, Swapneel Biswas, Nafi Ahmed, S. M. Hasan Kabir, Nebadeta Nath Tonney, Pooja Saha
This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.
