Geographically Weighted Random Forest Model for Addressing Spatial Heterogeneity of Monthly Rainfall with Small Sample Size

Rismania Hartanti Putri Yulianing Damayanti, Suci Astutik, Ani Budi Astuti

Abstract


Rainfall modeling often involves complex spatial patterns that vary across locations. Traditional spatial models such as Geographically Weighted Regression (GWR) assume linear relationships and may fall short in capturing nonlinear interactions among predictors and the small sample size is more challenging to fix the assumptions. To address this limitation, this study applies the Geographically Weighted Random Forest (GWRF) method is a hybrid approach that integrates Random Forest (RF), a non-parametric machine learning algorithm with geographically weighted modeling. GWRF is advantageous as it accommodates both spatial heterogeneity and nonlinear relationships, making it suitable for modeling monthly rainfall, which is inherently spatially varied and influenced by complex factors. This study aims to implement and evaluate the performance of the GWRF model in monthly rainfall prediction across East Java. The model is tested using various numbers of trees to determine the optimal structure, and its performance is assessed using Root Mean Square Error (RMSE), Akaike Information Criterion (AIC), and corrected AIC (AICc). Results indicate that the model tends to overestimate the Out-of-Bag (OOB) Error at all tree variations, with the smallest RMSE (85.68) achieved at 750 trees. Humidity emerges as the most influential variable in predicting monthly rainfall in the region, based on variable importance analysis

Keywords


Geographically; Heterogeneity Spatial; Rainfall; Random Forest

Full Text:

PDF

References


[1] A. Z.- Rutkowska and A. Michalik, “The Use of Spatial Data Infrastructure in Environmental Management:an Example from the Spatial Planning Practice in Poland,” Environmental Management, vol. 58, no. 4, pp. 619–635, Oct. 2016, doi: 10.1007/s00267-016-0732-0.

[2] A. S. Fotheringham, C. Brunsdon, and M. Charlton, “Geographically weighted regression,” The Sage handbook of spatial analysis, vol. 1, pp. 243–254, 2009.

[3] M. A. Suprayogi, B. Sartono, and K. A. Notodiputro, “GEOGRAPHICALLY WEIGHTED MACHINE LEARNING MODEL FOR ADDRESSING SPATIAL HETEROGENEITY OF PUBLIC HEALTH DEVELOPMENT INDEX IN JAVA ISLAND,” BAREKENG: J. Math. & App., vol. 18, no. 4, pp. 2577–2588, Oct. 2024, doi: 10.30598/barekengvol18iss4pp2577-2588.

[4] A. Sulekan and S. S. S. Jamaludin, “Review on Geographically Weighted Regression (GWR) approach in spatial analysis,” Malays J Fundam Appl Sci, vol. 16, no. 2, pp. 173–7, 2020.

[5] H. Hashimoto et al., “High‐resolution mapping of daily climate variables by aggregating multiple spatial data sets with the random forest algorithm over the conterminous United States,” Intl Journal of Climatology, vol. 39, no. 6, pp. 2964–2983, May 2019, doi: 10.1002/joc.5995.

[6] N. K. A. Appiah-Badu, Y. M. Missah, L. K. Amekudzi, N. Ussiph, T. Frimpong, and E. Ahene, “Rainfall Prediction Using Machine Learning Algorithms for the Various Ecological Zones of Ghana,” IEEE Access, vol. 10, pp. 5069–5082, 2022, doi: 10.1109/ACCESS.2021.3139312.

[7] N. Nurwatik, M. H. Ummah, A. B. Cahyono, M. R. Darminto, and J.-H. Hong, “A Comparison Study of Landslide Susceptibility Spatial Modeling Using Machine Learning,” IJGI, vol. 11, no. 12, p. 602, Dec. 2022, doi: 10.3390/ijgi11120602.

[8] H. Mahmoudzadeh, H. R. Matinfar, R. Taghizadeh-Mehrjardi, and R. Kerry, “Spatial prediction of soil organic carbon using machine learning techniques in western Iran,” Geoderma Regional, vol. 21, p. e00260, Jun. 2020, doi: 10.1016/j.geodrs.2020.e00260.

[9] R. Taghizadeh-Mehrjardi et al., “Multi-task convolutional neural networks outperformed random forest for mapping soil particle size fractions in central Iran,” Geoderma, vol. 376, p. 114552, Oct. 2020, doi: 10.1016/j.geoderma.2020.114552.

[10] A. Labade, B. Gupta, R. K. Gupta, and A. Kumar, “Machine Learning-Based Prototype Design for Rainfall Forecasting,” in Machine Intelligence and Data Science Applications, A. Ramdane-Cherif, T. P. Singh, R. Tomar, T. Choudhury, and J.-S. Um, Eds., in Algorithms for Intelligent Systems. , Singapore: Springer Nature Singapore, 2023, pp. 161–172. doi: 10.1007/978-981-99-1620-7_13.

[11] S. Georganos et al., “Geographical random forests: a spatial extension of the random forest algorithm to address spatial heterogeneity in remote sensing and population modelling,” Geocarto International, vol. 36, no. 2, pp. 121–136, Jan. 2021, doi: 10.1080/10106049.2019.1595177.

[12] S. Georganos and S. Kalogirou, “A Forest of Forests: A Spatially Weighted and Computationally Efficient Formulation of Geographical Random Forests,” IJGI, vol. 11, no. 9, p. 471, Aug. 2022, doi: 10.3390/ijgi11090471.

[13] S. Quiñones, A. Goyal, and Z. U. Ahmed, “Geographically weighted machine learning model for untangling spatial heterogeneity of type 2 diabetes mellitus (T2D) prevalence in the USA,” Sci Rep, vol. 11, no. 1, p. 6955, Mar. 2021, doi: 10.1038/s41598-021-85381-5.

[14] S. Wang, K. Gao, L. Zhang, B. Yu, and S. M. Easa, “Geographically weighted machine learning for modeling spatial heterogeneity in traffic crash frequency and determinants in US,” Accident Analysis & Prevention, vol. 199, p. 107528, May 2024, doi: 10.1016/j.aap.2024.107528.

[15] S. Astutik, A. Astuti, R. Damayanti, and A. Syalsabila, “A Hybrid Machine Learning and Kriging Approach for Rainfall Interpolation,” Int. J. Math. Comput. Sci., pp. 271–276, 2025, doi: 10.69793/ijmcs/01.2025/suci.

[16] Y. Andriyana et al., “Spatial Durbin Model with Expansion Using Casetti’s Approach: A Case Study for Rainfall Prediction in Java Island, Indonesia,” Mathematics, vol. 12, no. 15, p. 2304, Jul. 2024, doi: 10.3390/math12152304.

[17] P. Schober, C. Boer, and L. A. Schwarte, “Correlation Coefficients: Appropriate Use and Interpretation,” Anesthesia & Analgesia, vol. 126, no. 5, pp. 1763–1768, May 2018, doi: 10.1213/ANE.0000000000002864.

[18] L. Breiman, “Random forests,” Machine learning, vol. 45, pp. 5–32, 2001.

[19] A. Sekulić, M. Kilibarda, G. B. M. Heuvelink, M. Nikolić, and B. Bajat, “Random Forest Spatial Interpolation,” Remote Sensing, vol. 12, no. 10, p. 1687, May 2020, doi: 10.3390/rs12101687.

[20] C. Brunsdon, A. S. Fotheringham, and M. Charlton, “Spatial nonstationarity and autoregressive models,” Environment and Planning A, vol. 30, no. 6, pp. 957–973, 1998.

[21] M. M. Fischer and A. Getis, Eds., Handbook of Applied Spatial Analysis: Software Tools, Methods and Applications. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. doi: 10.1007/978-3-642-03647-7.

[22] A. Mittal and N. Paragios, “Motion-based background subtraction using adaptive kernel density estimation,” in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., Washington, DC, USA: IEEE, 2004, pp. 302–309. doi: 10.1109/CVPR.2004.1315179.

[23] G. Jia, A. Tabandeh, and P. Gardoni, “A density extrapolation approach to estimate failure probabilities,” Structural Safety, vol. 93, p. 102128, Nov. 2021, doi: 10.1016/j.strusafe.2021.102128.

[24] T. O. Hodson, “Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not,” Geosci. Model Dev., vol. 15, no. 14, pp. 5481–5487, Jul. 2022, doi: 10.5194/gmd-15-5481-2022.

[25] D. Althoff and L. N. Rodrigues, “Goodness-of-fit criteria for hydrological models: Model calibration and performance assessment,” Journal of Hydrology, vol. 600, p. 126674, Sep. 2021, doi: 10.1016/j.jhydrol.2021.126674.

[26] Y. Feng, C. Gao, X. Tong, S. Chen, Z. Lei, and J. Wang, “Spatial Patterns of Land Surface Temperature and Their Influencing Factors: A Case Study in Suzhou, China,” Remote Sensing, vol. 11, no. 2, p. 182, Jan. 2019, doi: 10.3390/rs11020182.

[27] E. Bevacqua, G. Zappa, F. Lehner, and J. Zscheischler, “Precipitation trends determine future occurrences of compound hot–dry events,” Nat. Clim. Chang., vol. 12, no. 4, pp. 350–355, Apr. 2022, doi: 10.1038/s41558-022-01309-5.

[28] T. M. Oshiro, P. S. Perez, and J. A. Baranauskas, “How Many Trees in a Random Forest?,” in Machine Learning and Data Mining in Pattern Recognition, vol. 7376, P. Perner, Ed., in Lecture Notes in Computer Science, vol. 7376. , Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 154–168. doi: 10.1007/978-3-642-31537-4_13.

[29] S. Janitza and R. Hornung, “On the overestimation of random forest’s out-of-bag error,” PLoS ONE, vol. 13, no. 8, p. e0201904, Aug. 2018, doi: 10.1371/journal.pone.0201904.

[30] S. N. Khan, D. Li, and M. Maimaitijiang, “A Geographically Weighted Random Forest Approach to Predict Corn Yield in the US Corn Belt,” Remote Sensing, vol. 14, no. 12, p. 2843, Jun. 2022, doi: 10.3390/rs14122843.

[31] Z. Su et al., “Modeling the Effects of Drivers on PM2.5 in the Yangtze River Delta with Geographically Weighted Random Forest,” Remote Sensing, vol. 15, no. 15, p. 3826, Jul. 2023, doi: 10.3390/rs15153826.

[32] Y. S. Dewi, S. Hastuti, and M. Fatekurohman, “Analysis of stunting in East Java, Indonesia using random forest and geographically weighted random forest regression,” Braz. J. Biom., vol. 42, no. 3, pp. 213–224, Aug. 2024, doi: 10.28951/bjb.v42i3.679.




DOI: https://doi.org/10.18860/cauchy.v10i1.32161

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Rismania Hartanti Putri Yulianing Damayanti, Suci Astutik, Ani Budi Astuti

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Editorial Office
Mathematics Department,
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
Faximile (+62) 341 558933
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.