Changepoint Detection in Multivariate Climate Time Series: Performance Assessment of a Hybrid PELT and Isolation Forest Approach Against Baseline PELT
Main Article Content
Abstract
The research studied the performance of Hybrid Pruned Exact Linear Time and Isolation Forest (PELT + I Forest) against Baseline PELT in accurately detecting change points in Climate time series data using simulation. The research adopts a Monte Carlo simulation framework to design and evaluate a hybrid change-point detection technique that combines the Pruned Exact Linear Time (PELT) algorithm with machine learning anomaly detection method (I Forest). The hybrid approach (PELT+I Forest) is compared against baseline PELT using simulated multivariate climate datasets. Across small, moderate, and large sample sizes, the same directional patterns persist, temperature and humidity increase while rainfall decreases with more breaks. However, larger samples make the regime shifts more distinct and less noisy. This finding underscores that robust detection methods must perform well not only in large datasets but also in small samples, where noisy signals make breaks harder to capture. Enhanced detection algorithm like PELT+I Forest is therefore vital for early warning in short observational records or regional climate data with limited length. PELT+I Forest delivered consistent performance across moderate and large sample sizes, with marginal but steady improvements in balanced accuracy, making it more robust for longer or multivariate series.This study carried out a Performance Assessment on the developed, implemented and evaluated Hybrid change-point detection framework which integrates the Pruned Exact Linear Time (PELT) algorithm with machine learning anomaly detection method (Isolation Forest) for robust identification of structural breaks in multivariate climate time series against baseline PELT Algorithm. Relative to all other alternatives for Change Point Detection the hybrid PELT+I Forest approach balanced computational efficiency, interpretability, and robustness which retained PELT’s exact segmentation while using ML scorers to capture multivariate, nonlinear anomalies.
Article Details
References
Abdulkadir, Y., & Sani, A. (2021). Analysis of climate data using spatial techniques to estimate rainfall in the North West of Nigeria. FUDMA Journal of Sciences, 5(4), 174–181.
Ademuwagun, A. A., Suleiman, R. T., Olumuyiwa, S. A., Oyedeji, M. B., & Afolabi, R. T. (2024). Application of change point analysis to Nigerian rainfall data. The Journal of the Mathematical Association of Nigeria Ogun State (JOMANOGS): Mathematical Sciences and Education Series, 6(2), 94–108.
Arias, L. A., Oosterlee, C. W., & Cirillo, P. (2023). Analytic isolation and distance-based anomaly detection algorithm. Pattern Recognition, 141, 109607.
Bai, J., & Perron, P. (2003). Computation and analysis of multiple structural change models. Journal of Applied Econometrics, 18, 1–22.
Beaulieu, C., Chen, J., & Sarmiento, J. L. (2012). Change-point analysis as a tool to detect abrupt climate variations. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 370(1962), 1228–1249.
deYoung, B., Barange, M., Beaugrand, G., Harris, R., Perry, R. I., Scheffer, M., & Werner, F. (2008). Regime shifts in marine ecosystems: Detection, prediction and management. Trends in Ecology & Evolution, 23(7), 402–409.
Gomez, C., White, J. C., & Wulder, M. A. (2011). Characterizing the state and process of change in a dynamic forest environment using hierarchical spatio-temporal segmentation. Remote Sensing of Environment, 115, 1665–1679.
Hawkins, D. M. (2001). Fitting multiple change-point models to data. Computational Statistics & Data Analysis, 37(3), 323–341.
Haynes, K., Eckley, I. A., & Fearnhead, P. (2017). Computationally efficient changepoint detection for a range of penalties. Journal of Computational and Graphical Statistics, 26(1), 134–143.
Intergovernmental Panel on Climate Change. (2019). Special report on the ocean and cryosphere in a changing climate. Cambridge University Press.
Killick, R., & Eckley, I. A. (2014). Changepoint: An R package for changepoint analysis. Journal of Statistical Software, 58(3), 1–19.
Killick, R., Fearnhead, P., & Eckley, I. A. (2012). Optimal detection of changepoints with a linear computational cost. Journal of the American Statistical Association, 107(500), 1590–1598.
Kouakou Innocent N’dri, & Nadarajah, S. (2022). Statistical modeling of monthly maximum temperature in Senegal. Environmental Research Communications, 4, 075002.
Lenton, T. M. (2013). Environmental tipping points. Annual Review of Environment and Resources, 38, 1–29.
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining (pp. 413–422). IEEE.
Page, E. S. (1954). Continuous inspection schemes. Biometrika, 41(1–2), 100–115.
Parth, S., & Mohdzuned, S. (2020). A review on climate change impact analysis using statistical tools. In 25th International Conference on Hydraulics, Water Resources and River Engineering (Hydro 2020) (pp. 16–18). NIT Rourkela, India.
Reeves, J., Chen, J., Wang, X. L., Lund, R., & Lu, Q. Q. (2007). A review and comparison of changepoint detection techniques for climate data. Journal of Applied Meteorology and Climatology, 46(6), 900–915.
Scheffer, M., Bascompte, J., Brock, W. A., Brovkin, V., Carpenter, S. R., Dakos, V., et al. (2009). Early-warning signals for critical transitions. Nature, 461(7260), 53–59.
Truong, C., Oudre, L., & Vayatis, N. (2020). Selective review of offline change point detection methods. Signal Processing, 167, 107299.
Zwiers, F. W., & von Storch, H. (2004). On the role of statistics in climate research. International Journal of Climatology, 24(6), 665–680.