Citation :

M. Nivedhitha, S. Meganathan, A. Sumathi, R. Rajakumar, "Seasonal Rainfall Prediction Using," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 6, pp. 401-420, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I6P127

Abstract

Analysis of rainfall and weather variability in Chennai is carried out using twenty years of historical data (2003-2023) collected from the India Meteorological Department. The study examines the rainfall response to key meteorological factors such as temperature, wind speed, visibility, and dew point related to the Northeast Monsoon during the season from October to early January. Accordingly, the data was statistically processed and divided into seasonal segments that defined the NEM season. At the same time, PRCP values were grouped into seven categories from no rain to extreme heavy rainfall to account for the dynamic changes in rainfall intensity over time. Likewise, quantile-based grouping was used for other weather variables to divide them into low, medium, and high exposure categories for easier comparison. In response to the limitations of conventional ARIMA models that neglect the seasonal effects of monsoons and the nonlinear relationships between weather variables, this paper proposes the Extreme-Sensitive Hybrid Residual Forecasting (ES-HRF) method. This approach combines SARIMAX with Fourier components for handling seasonal series and exogenous weather series for handling temporal series, and further refines residuals with nonlinear learning from Gradient Boosting and Random Forest Regression. Extreme rainfall events are defined using quantile-based thresholds, and their performance is assessed using categorical verification scores. The proposed hybrid framework shows better prediction accuracy and robust extreme event detection performance than the individual statistical and machine learning models. The results emphasize the efficacy of the proposed method in improving the reliability of rainfall prediction and facilitating disaster preparedness, flood control, and weather-smart urban planning in monsoon-dominated areas.

Keywords

Climate trend analysis, Northeast monsoon, Quantile classification, Rainfall pattern analysis, SARIMAX, ES-HRF, Statistical approach.

References

[1] Climate Data, Data and Graphs for Weather and Climate in Chennai, 2021. [Online]. Available: https://en.climate-data.org/asia/india/tamil-nadu/chennai-1003222/ 

[2] India Meteorological Department Ministry of Earth Sciences Government of India, Rainfall Information Meteorological Sub-divisions, 2026. [Online]. Available: https://mausam.imd.gov.in/responsive/rainfallinformation_msd.php

[3] Government of India Earth System Science Organisation Ministry of Earth Sciences India Meteorological Department, Report on Northeast Monsoon, 2024. [Online]. Available: https://mausam.imd.gov.in/chennai/mcdata/ne_monsoon_2024.pdf

[4] Government of India Earth System Science Organisation Ministry of Earth Sciences India Meteorological Department, Report on Northeast Monsoon, 2023. [Online]. Available: https://mausam.imd.gov.in/chennai/mcdata/ne_monsoon_2023.pdf

[5] SANDRP, South Asia Network on Dams, Rivers and People, SANDRP, 2025. [Online]. Available: https://sandrp.in/2025/10/01/sw-monsoon-2025-district-wise-rainfall-in-india/  

[6] Amita Kumari et al., “Recent Decades have Witnessed a Strong East-West Gradient of Monsoon Precipitation Changes Over Northern India,” Atmospheric Research, vol. 318, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Shulin Deng et al., “Rainfall Seasonality Changes and Underlying Climatic Causes in Global Land Monsoon Regions,” Atmospheric Research, vol. 326, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Shawna McKinley et al., “Mapping the Impact of Extreme Weather on Global Events and Mass Gatherings: Trends and Adaptive Strategies,” International Journal of Disaster Risk Reduction, vol. 127, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link] 

[9] Rinu Fathima et al., “A Strong Influence of the Precession and Northern High Latitude Climate on the Monsoon Seasonality and Productivity in the Andaman Sea,” Global and Planetary Change, vol. 254, 2025.
[CrossRef] [Google Scholar] [Publisher Link] 

[10] Nur Asyiqin Isa et al., “Impact of Ground-Level Cool Conditions During Monsoon Seasons: Occurrences of Isolated Breakdown Pulse Trains Discharges and their Relationship with Ground Flashes Events in Tropical Thunderstorms,” Electric Power Systems Research, vol. 251, 2026.
[CrossRef] [Google Scholar] [Publisher Link] 

[11]  Ahmed M. Elshewey et al., “A Novel WD-SARIMAX Model for Temperature Forecasting using Daily Delhi Climate Dataset,” Sustainability, vol. 15, no. 1, pp. 1-15, 2022.
[CrossRef] [Google Scholar] [Publisher Link] 

[12] Rudi Setyo Prihatin, and Eri Zuliarso, “Rainfall Prediction using the SARIMAX and LSTM Methods in Semarang City,” Jurnal Inovtek Polbeng - Informatics Series, vol. 10, no. 3, pp. 1391-1401, 2025.
[CrossRef] [Google Scholar] [Publisher Link] 

[13] Md. Mehedi Hassan et al., “Machine Learning-based Rainfall Prediction: Unveiling Insights and Forecasting for Improved Preparedness,” IEEE Access, vol. 11, pp. 132196-132222, 2023.
[CrossRef] [Google Scholar] [Publisher Link] 

[14] Zhuoya Liu et al., “A Novel Linear Rainfall Forecast Model based on GNSS Observations and CAPE,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-9, 2024.
[CrossRef] [Google Scholar] [Publisher Link] 

[15] A.M. Chacón-Maldonado et al., “Improving Monsoon Forecasting based on Feature Selection and Explainable Artificial Intelligence,” Applied Soft Computing, vol. 185, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link] 

[16] Nagendra Prasad et al., “Late Holocene Vegetation History and Monsoonal Climate Change from the Core Monsoon Zone of India,” CATENA, vol. 246, 2024.
[CrossRef] [Google Scholar] [Publisher Link] 

[17] Saloni Sharma et al., “Observational Evidence of Changing Cloud Macro-Physical Properties Under Warming Climate Over the Indian Summer Monsoon Region,” Science of the Total Environment, vol. 947, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Kandula V. Subrahmanyam, M.V. Ramana, and Prakash Chauhan, “Long-Term Changes in Rainfall Epochs and Intensity Patterns of Indian Summer Monsoon in Changing Climate,” Atmospheric Research, vol. 295, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] P. Umamaheswari, and V. Ramaswamy, “An Integrated Framework for Rainfall Prediction and Analysis using a Stacked Heterogeneous Ensemble Model (SHEM),” Expert Systems with Applications, vol. 256, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Umamaheswari P, and V. Ramaswamy, “Optimized Preprocessing using time Variant Particle Swarm Optimization (TVPSO) and Deep Learning on Rainfall Data,” Journal of Scientific and Industrial Research, vol. 81, pp. 1317-1325, 2022.
[CrossRef] [Google Scholar]

[21] D. Ruhiat et al., “Ten Daily Rainfall Forecasting using SSA Algorithms and Seasonal Arima Model to Determine the Beginning of the Rainy Season,” IOP Conference Series: Earth and Environmental Science, vol. 1314, no. 1, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Amierul Aiman Hafidz Bin Muzaffar, R Kanesaraj Ramasamy, and Venushini Rajendran, “A Lightweight IoT-Enabled Agricultural Monitoring System with Arima-based Rainfall Forecasting for Precision Irrigation,” SSRN, pp. 1-42, 2025.
[Google Scholar] [Publisher Link]

[23] Huey Yin Tee, and Rosnalini Mansor, “Forecasting Rainfall Volume in Selangor with a Combined ARIMA Model,” Journal of Computational Innovation and Analytics (JCIA), vol. 3, no. 1, pp. 83-103, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Wenchuan Wang et al., “A Comparison of BPNN, GMDH, and ARIMA for Monthly Rainfall Forecasting based on Wavelet Packet Decomposition,” Water, vol. 13, no. 20, pp. 1-24, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Paramasivan Arumugam, and R. Saranya, “Outlier Detection and Missing Value in Seasonal ARIMA Model using Rainfall Data,” Materials Today: Proceedings, vol. 5, no. 1, pp. 1791-1799, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Francis Ayiah-Mensah et al., “Advancements in Seasonal Rainfall Forecasting: A Seasonal Auto-Regressive Integrated Moving Average Model with Outlier Adjustments for Ghana's Western Region,” Scientific African, vol. 28, pp. 1-21, 2025.
        [CrossRef] [Google Scholar] [Publisher Link]