EXTREME GRADIENT BOOSTING -DRIVEN HYDROLOGICAL FORECASTING STREAMFLOWUNDER CMIP6 SCENARİOS
Keywords:
XGBoost, Streamflow forecasting, SHAP analysis, CMIP6, SSP ScenariosAbstract
Accurate streamflow forecasting is essential for sustainable water resource planning under increasing climate variability. This study investigates the performance of the Extreme Gradient Boosting (XGBoost) algorithm for monthly streamflow prediction in the Ceyhan River Basin, utilizing climate projections from General Circulation Models (GCMs) participating in CMIP6. The model was tested across four Shared Socioeconomic Pathways (SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5), using historical discharge data and climate predictors such as mean sea level pressure (mslp) and specific humidity (shum) as inputs. Evaluation metrics included RMSE, MAE, and the Nash–Sutcliffe Efficiency (NSE). The results show that the XGBoost model dynamically adapts to seasonal patterns and selects the best-performing configuration each month. Under high-emission scenarios, particularly SSP5-8.5, streamflow variability significantly increased. SHAP (SHapley Additive exPlanations) analysis enhanced model interpretability, identifying shum and mslp as key predictive features. These findings highlight the potential of XGBoost as a robust and explainable decision-support tool for climate-informed hydrological modeling.
References
1. Klemeš, V. (1986). Operational testing of hydrological simulation models. Hydrological Sciences Journal, 31(1), 13–24.
2. Seneviratne, S. I., et al. (2012). Changes in climate extremes and their impacts on the natural physical environment. IPCC Special Report on Extremes.
3. Guven, A., & Şebcioğlu, Ş. (2019). Climate change impact on hydropower: A review. Journal of Hydrology Research and Development, vol. 35, no. 2, pp. 123-135.
4. Nagabhyru, K. C. (2022). Bridging Traditional ETL Pipelines with AI Enhanced Data Workflows: Foundations of Intelligent Automation in Data Engineering. Available at SSRN 5505199.
5. O’Neill, B. C., et al., “The Scenario Model Intercomparison Project (ScenarioMIP) for CMIP6,” Geoscientific Model Development, vol. 9, pp. 3461–3482, 2016.
6. Eyring, V., et al., “Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization,” Geoscientific Model Development, vol. 9, pp. 1937–1958, 2016.
7. Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A. K., Hochreiter, S., & Nearing, G. S. (2019). Towards learning universal, regional, and local hydrological behaviors via machine learning. Hydrology and Earth System Sciences, 23(12), 5089–5110.
8. Kolla, S. K. (2024). Clinical Knowledge Intelligence through Deep Learning and Natural Language Understanding in Healthcare Platforms. International Journal of Advanced Engineering Science and Information Technology (IJAESIT), 7(3), 14088.
9. Chen, T., and Guestrin, C., “XGBoost: A scalable tree boosting system,” Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, pp. 785–794, 2016.
10. Feng, D., Wang, Y., Hao, Z., & Hao, F. (2020). Deep learning and traditional machine learning models for groundwater level prediction: A comparative study. Journal of Hydrology, 582, 124541.
11. Feng, D., Xu, Z., & Duan, Z. (2021). Application of machine learning techniques in hydrological modeling under CMIP6 scenarios: A review. Environmental Research Letters, 16(12), 124001.
12. DSI (State Hydraulic Works). (2014). Hydrological Data of Turkish River Basins. General Directorate of State Hydraulic Works, Ankara, Turkey.
13. Reddy Segireddy, A. (2024). Federated Cloud Approaches for Multi-Regional Payment Messaging Systems. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 15(2), 442-450.
14. DSI (State Hydraulic Works). (2015). Menzelet Dam Streamflow Records. General Directorate of State Hydraulic Works, Ankara, Turkey.
15. Canadian Climate Data and Scenarios (CCDS), Government of Canada. Available at: https://climate-scenarios.canada.ca/?page=pred-cmip6#cmip6-predictors
16. Meinshausen, M., et al. (2020). The SSP greenhouse gas concentrations and their extensions to 2500. Geoscientific Model Development.
17. Eyring, V., Bony, S., Meehl, G. A., Senior, C. A., Stevens, B., Stouffer, R. J., & Taylor, K. E. (2016). Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization. *Geoscientific Model Development*, 9(5), 1937–1958.
18. Reddy, V. A. R. (2024). Generative Intelligence for Healthcare Claims Processing and Personalized Benefits Management. International Journal of Advanced Engineering Science and Information Technology (IJAESIT), 7(3), 14099.
19. Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. *Journal of Machine Learning Research*, 13, 281–305.
20. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In *Proceedings of the 31st International Conference on Neural Information Processing Systems* (pp. 4768–4777).
21. Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models: Part I—A discussion of principles. *Journal of Hydrology*, 10(3), 282–290.
22. Hussain, A. Ansari, M. Danish, M and Azamathulla, H.M. (2025). Experimental and Machine Learning Approaches for Discharge Estimation in Arched Labyrinth Weirs, European Advanced Journal for Emerging Technologies (EAJET)-p-ISSN 3050-9734.
23. Gottimukkala, V. R. R. (2021). Digital Signal Processing Challenges in Financial Messaging Systems: Case Studies in High-Volume SWIFT Flows.
24. U Hansamali, RK Makumbura, U Rathnayake, HM Azamathulla, N Muttil
25. (2025).Leaky Dams as Nature-Based Solutions in Flood Management Part I: Introduction and Comparative Efficacy with Conventional Flood Control Infrastructure, Hydrology 12 (4), 95
26. U Hansamali, RK Makumbura, U Rathnayake, HM Azamathulla, N Muttil
27. Garapati, R. S. (2022). Web-Centric Cloud Framework for Real-Time Monitoring and Risk Prediction in Clinical Trials Using Machine Learning. Current Research in Public Health, 2, 1346.
28. Leaky Dams as Nature-Based Solutions in Flood Management Part II: Mechanisms, Effectiveness, Environmental Impacts, Technical Challenges, and Emerging Trends. Hydrology (2306-5338) 12 (4).
29. B Chaplot (2021). Prediction of rainfall time series using soft computing techniques
30. Environmental Monitoring and Assessment 193 (11), 721
Additional Files
Published
Data Availability Statement
None
