Vol 19 No 4 (2025): BAREKENG: Journal of Mathematics and Its Application
Articles

PREDICTION OF SOIL PARTICLES USING A SPATIALLY ADAPTIVE GEOGRAPHICALLY WEIGHTED K-NEAREST NEIGHBORS ORDINARY LOGISTIC REGRESSION APPROACH

pdf
  • Henny Pramoedyo,
  • Wigbertus Ngabu,
  • Atiek Iriany,
  • Sativandi Riza
Henny Pramoedyo
Statistic Department, Faculty of Mathematics and Science, University of Brawijaya, Indonesia
Wigbertus Ngabu
Mathematics Education Study Program, Faculty of Teacher Training and Education, Universitas Riau, Indonesia
Bio
Atiek Iriany
Statistic Department, Faculty of Mathematics and Science, University of Brawijaya, Indonesia
Sativandi Riza
Soil Science Department, Faculty of Agriculture, University of Brawijaya, Indonesia
DOI: https://doi.org/10.30598/barekengvol19iss4pp2815-2830
Published September 1, 2025
Keywords
  • Geographically Weighted,
  • K-Nearest Neighbors,
  • Logistic Regression,
  • Spatial modeling,
  • Soil texture prediction
How to Cite
[1]
H. Pramoedyo, W. Ngabu, A. Iriany, and S. Riza, “PREDICTION OF SOIL PARTICLES USING A SPATIALLY ADAPTIVE GEOGRAPHICALLY WEIGHTED K-NEAREST NEIGHBORS ORDINARY LOGISTIC REGRESSION APPROACH”, BAREKENG: J. Math. & App., vol. 19, no. 4, pp. 2815-2830, Sep. 2025.

Copyright (c) 2025 Henny Pramoedyo, Wigbertus Ngabu, Atiek Iriany, Sativandi Riza

Creative Commons License

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

Abstract

Soil particle prediction is crucial in various fields, including agriculture, environmental management, and geotechnical applications. The spatial variation of soil texture significantly affects land fertility, erosion risk, and construction feasibility. However, conventional statistical methods and machine learning techniques often fail to capture the complex spatial heterogeneity in soil distribution. This study proposes the Geographically Weighted K Nearest Neighbors Ordinary Logistic Regression (GWKNNOLR) method to improve the accuracy of soil particle classification by integrating geographically weighted regression with an adaptive spatial weighting mechanism using the K Nearest Neighbors (KNN) algorithm. The objective of this research is to develop and evaluate a spatially adaptive classification model that more accurately predicts soil particle categories, namely sand, silt, and clay, by incorporating local spatial dependencies using GWKNNOLR in the Kalikonto watershed (DAS Kalikonto) in Batu. This study utilizes field measurement data combined with digital terrain modeling to analyze the relationship between local morphological variables and soil texture classification (sand, silt, and clay). The study area includes 50 observation points and 8 test variables. The model's performance is compared to the Ordinary Logistic Regression (OLR) method. The results indicate that GWKNNOLR achieves a classification accuracy of 88 percent, outperforming OLR, which only reaches 80 percent. Integrating KNN as a spatial weighting mechanism enhances adaptability to variations in sample distribution, leading to more accurate predictions. These findings emphasize the importance of considering spatial dependencies in soil texture modeling. The proposed method can support sustainable land resource management, erosion risk mitigation, and precision agriculture by providing more reliable soil classification. Future research may explore further optimization of spatial weighting mechanisms and the application of this method in different geographical regions.

pdf

Downloads

Download data is not yet available.

References

  1. D. Kim, B. H. Nam, and H. Youn, “EFFECT OF CLAY CONTENT ON THE SHEAR STRENGTH OF CLAY–SAND MIXTURE,” International Journal of Geo-Engineering, vol. 9, pp. 1–12, 2018.doi: https://doi.org/10.1186/s40703-018-0087-x
  2. E. J. Parent, S.-É. Parent, and L. E. Parent, “DETERMINING SOIL PARTICLE-SIZE DISTRIBUTION FROM INFRARED SPECTRA USING MACHINE LEARNING PREDICTIONS: METHODOLOGY AND MODELING,” PLoS One, vol. 16, no. 7, p. e0233242, 2021.doi: https://doi.org/10.1371/journal.pone.0233242
  3. J. M. Moreno-Maroto and J. Alonso-Azcarate, “EVALUATION OF THE USDA SOIL TEXTURE TRIANGLE THROUGH ATTERBERG LIMITS AND AN ALTERNATIVE CLASSIFICATION SYSTEM,” Appl Clay Sci, vol. 229, p. 106689, 2022.doi: https://doi.org/10.1016/j.clay.2022.106689
  4. M. Heidari, S. Zalaghaie, M. R. Nikudel, and A. Seif, “PREDICTION OF THE LOESS SOILS COLLAPSE SENSITIVITY CLASSES BY APPLICATION OF ORDINAL LOGISTIC REGRESSION, NORTHEASTERN IRAN,” Iranian Journal of Engineering Geology, vol. 16, no. 2, 2023.
  5. S. Zalaghaie, M. Heidari, M. R. Nikudel, S. H. Jalali, and A. Seif, “APPLICATION OF ORDINAL LOGISTIC AND GENE EXPRESSION PROGRAMMING METHODS TO PREDICT THE COLLAPSE SENSITIVITY CLASSES OF LOESS SOILS, A CASE STUDY: GOLESTAN PROVINCE, NORTHEASTERN IRAN,” Environ Monit Assess, vol. 195, no. 2, p. 305, 2023.doi: https://doi.org/10.1007/s10661-023-10915-5
  6. H. Pramoedyo, W. Ngabu, S. Riza, and A. Iriany, “SPATIAL ANALYSIS USING GEOGRAPHICALLY WEIGHTED ORDINARY LOGISTIC REGRESSION (GWOLR) METHOD FOR PREDICTION OF PARTICLE-SIZE FRACTION IN SOIL SURFACE,” in IOP Conference Series: Earth and Environmental Science, IOP Publishing, 2024, p. 012005.doi: https://doi.org/10.1088/1755-1315/1299/1/012005
  7. M. Kubara and K. Kopczewska, “AKAIKE INFORMATION CRITERION IN CHOOSING THE OPTIMAL K-NEAREST NEIGHBOURS OF THE SPATIAL WEIGHT MATRIX,” Spat Econ Anal, vol. 19, no. 1, pp. 73–91, 2024.doi: https://doi.org/10.1080/17421772.2023.2176539
  8. X. Peng, R. Chen, K. Yu, F. Ye, and W. Xue, “AN IMPROVED WEIGHTED K-NEAREST NEIGHBOR ALGORITHM FOR INDOOR LOCALIZATION,” Electronics (Basel), vol. 9, no. 12, p. 2117, 2020.doi: https://doi.org/10.3390/electronics9122117
  9. H. Pramoedyo, A. Iriany, W. Ngabu, and S. Riza, “SOIL PARTICLE PREDICTION USING SPATIAL ORDINARY LOGISTIC REGRESSION,” Advances in Decision Sciences, vol. 28, no. 1, pp. 66–92, 2024.doi: https://doi.org/10.47654/v28y2024i2p66-92
  10. X. Yang, Y. Yang, S. Xu, J. Han, Z. Chai, and G. Yang, “A NEW ALGORITHM FOR LARGE-SCALE GEOGRAPHICALLY WEIGHTED REGRESSION WITH K-NEAREST NEIGHBORS,” ISPRS Int J Geoinf, vol. 12, no. 7, p. 295, 2023.doi: https://doi.org/10.3390/ijgi12070295
  11. P. Jafary, D. Shojaei, A. Rajabifard, and T. Ngo, “AUTOMATING PROPERTY VALUATION AT THE MACRO SCALE OF SUBURBAN LEVEL: A MULTI-STEP METHOD BASED ON SPATIAL IMPUTATION TECHNIQUES, MACHINE LEARNING AND DEEP LEARNING,” Habitat Int, vol. 148, p. 103075, 2024.doi: https://doi.org/10.1016/j.habitatint.2024.103075
  12. W. Ngabu, R. Fitriani, H. Pramoedyo, and A. B. Astuti, “CLUSTER FAST DOUBLE BOOTSTRAP APPROACH WITH RANDOM EFFECT SPATIAL MODELING,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 17, no. 2, pp. 945–954, 2023.doi: https://doi.org/10.30598/barekengvol17iss2pp0945-0954
  13. F. M. Seaton, P. B. L. George, I. Lebron, D. L. Jones, S. Creer, and D. A. Robinson, “SOIL TEXTURAL HETEROGENEITY IMPACTS BACTERIAL BUT NOT FUNGAL DIVERSITY,” Soil Biol Biochem, vol. 144, p. 107766, 2020.doi: https://doi.org/10.1016/j.soilbio.2020.107766
  14. L. Xiong, G. Tang, X. Yang, and F. Li, “GEOMORPHOLOGY-ORIENTED DIGITAL TERRAIN ANALYSIS: PROGRESS AND PERSPECTIVES,” Journal of geographical sciences, vol. 31, pp. 456–476, 2021.doi: https://doi.org/10.1007/s11442-021-1853-9
  15. A. Iriany, W. Ngabu, D. Ariyanto, and H. Pramoedyo, “KRIGING PREDICTION AND SIMULATION MODEL: ANALYSIS OF SURFACE SOIL PARTICLE SIZE DISTRIBUTION.,” Mathematical Modelling of Engineering Problems, vol. 12, no. 4, 2025, doi: https://doi.org/10.18280/mmep.120408 .
  16. Z. Guo et al., “SOIL TEXTURE IS AN IMPORTANT FACTOR DETERMINING HOW MICROPLASTICS AFFECT SOIL HYDRAULIC CHARACTERISTICS,” Environ Int, vol. 165, p. 107293, 2022.doi: https://doi.org/10.1016/j.envint.2022.107293
  17. H. Pramoedyo, W. Ngabu, S. Riza, and L. Amaliana, “SINGLE BOOTSTRAP APPROACH WITH GEOGRAPHICALLY WEIGHT REGRESSION MODELING USING PARTICLE-SIZE FRACTION,” J Theor Appl Inf Technol, vol. 31, no. 10, 2023, [Online]. Available: www.jatit.org
  18. R. J. Tallarida, R. B. Murray, R. J. Tallarida, and R. B. Murray, “CHI-SQUARE TEST,” Manual of pharmacologic calculations: with computer programs, pp. 140–142, 1987.doi: https://doi.org/10.1007/978-1-4612-4974-0_43
  19. M. Alrumaidhi and H. A. Rakha, “FACTORS AFFECTING CRASH SEVERITY AMONG ELDERLY DRIVERS: A MULTILEVEL ORDINAL LOGISTIC REGRESSION APPROACH,” Sustainability, vol. 14, no. 18, p. 11543, 2022.doi: https://doi.org/10.3390/su141811543
  20. H. Khaulasari and F. Suhaeri, “MAPPING OF GENDER INEQUALITY IN INDONESIA BASED ON INFLUENCING FACTORS USING GEOGRAPHICALLY WEIGHTED ORDINAL LOGISTIC REGRESSION,” BAREKENG: Jurnal Ilmu Matematika Dan Terapan, vol. 18, no. 1, pp. 233–244, 2024.doi: https://doi.org/10.30598/barekengvol18iss1pp0233-0244
  21. J. Liang, G. Bi, and C. Zhan, “MULTINOMIAL AND ORDINAL LOGISTIC REGRESSION ANALYSES WITH MULTI-CATEGORICAL VARIABLES USING R,” Ann Transl Med, vol. 8, no. 16, p. 982, 2020.doi: https://doi.org/10.21037/atm-2020-57
  22. B. French and M. S. Shotwell, “REGRESSION MODELS FOR ORDINAL OUTCOMES,” JAMA, vol. 328, no. 8, pp. 772–773, 2022.doi: https://doi.org/10.1001/jama.2022.12104
  23. B. S. Tusa, S. A. Kebede, and A. B. Weldesenbet, “SPATIAL DISTRIBUTION AND DETERMINANT FACTORS OF ANEMIA AMONG ADULTS AGED 15–59 IN ETHIOPIA; USING MIXED-EFFECTS ORDINAL LOGISTIC REGRESSION MODEL,” BMC Nutr, vol. 7, pp. 1–12, 2021.doi: https://doi.org/10.1186/s40795-021-00424-4
  24. I. O. Asare and A. C. Mensah, “CRASH SEVERITY MODELLING USING ORDINAL LOGISTIC REGRESSION APPROACH,” Int J Inj Contr Saf Promot, vol. 27, no. 4, pp. 412–419, 2020.doi: https://doi.org/10.1080/17457300.2020.1790615
  25. W. Ngabu, H. Pramoedyo, A. Iriany, and R. Fitriani, “HYBRID MODELING OF DEEP NEURAL NETWORKS AND ORDINARY LOGISTIC REGRESSION FOR PREDICTING GROUNDWATER QUALITY,” Mathematical Modelling of Engineering Problems, vol. 12, no. 3, pp. 774–786, 2025, doi: https://doi.org/10.18280/mmep.120304.
  26. G. Tutz, “ORDINAL REGRESSION: A REVIEW AND A TAXONOMY OF MODELS,” Wiley Interdiscip Rev Comput Stat, vol. 14, no. 2, p. e1545, 2022.doi: https://doi.org/10.1002/wics.1545
  27. S. Jayawardena, J. Epps, and E. Ambikairajah, “ORDINAL LOGISTIC REGRESSION WITH PARTIAL PROPORTIONAL ODDS FOR DEPRESSION PREDICTION,” IEEE Trans Affect Comput, vol. 14, no. 1, pp. 563–577, 2020.doi: https://doi.org/10.1109/TAFFC.2020.3031300
  28. A. Iriany, W. Ngabu, and D. Ariyanto, “RAINFALL MODELING USING THE GEOGRAPHICALLY WEIGHTED POISSON REGRESSION METHOD,” BAREKENG: Jurnal Ilmu Matematika dan Terapan, vol. 18, no. 1, pp. 627–636, 2024.doi: https://doi.org/10.30598/barekengvol18iss1pp0627-0636
  29. A. Comber et al., “THE GWR ROUTE MAP: A GUIDE TO THE INFORMED APPLICATION OF GEOGRAPHICALLY WEIGHTED REGRESSION,” arXiv preprint arXiv:2004.06070, 2020.
  30. V. N. Mishra, V. Kumar, R. Prasad, and M. Punia, “GEOGRAPHICALLY WEIGHTED METHOD INTEGRATED WITH LOGISTIC REGRESSION FOR ANALYZING SPATIALLY VARYING ACCURACY MEASURES OF REMOTE SENSING IMAGE CLASSIFICATION,” Journal of the Indian Society of Remote Sensing, vol. 49, pp. 1189–1199, 2021.doi: https://doi.org/10.1007/s12524-020-01286-2
  31. S. Zhang, S. Ray, R. Lu, and Y. Zheng, “SPRIG: A LEARNED SPATIAL INDEX FOR RANGE AND KNN QUERIES,” in Proceedings of the 17th International Symposium on Spatial and Temporal Databases, 2021, pp. 96–105.doi: https://doi.org/10.1145/3469830.3470892
  32. S. Liu, R. De Lacerda, and J. Fiorina, “PERFORMANCE ANALYSIS OF ADAPTIVE K FOR WEIGHTED K-NEAREST NEIGHBOR BASED INDOOR POSITIONING,” in 2022 IEEE 95th Vehicular Technology Conference:(VTC2022-Spring), IEEE, 2022, pp. 1–5.doi: https://doi.org/10.1109/VTC2022-Spring54318.2022.9860699
  33. X. Chen and Y. Chen, “QUANTIFYING THE RELATIONSHIPS BETWEEN NETWORK DISTANCE AND STRAIGHT-LINE DISTANCE: APPLICATIONS IN SPATIAL BIAS CORRECTION,” Ann GIS, vol. 27, no. 4, pp. 351–369, 2021.doi: https://doi.org/10.1080/19475683.2021.1966503
  34. X. Yang, Y. Yang, S. Xu, J. Han, Z. Chai, and G. Yang, “A NEW ALGORITHM FOR LARGE-SCALE GEOGRAPHICALLY WEIGHTED REGRESSION WITH K-NEAREST NEIGHBORS,” ISPRS Int J Geoinf, vol. 12, no. 7, p. 295, 2023.doi: https://doi.org/10.3390/ijgi12070295
  35. M. K. Campbell, A. Donner, and K. M. Webster, “ARE ORDINAL MODELS USEFUL FOR CLASSIFICATION?,” Stat Med, vol. 10, no. 3, pp. 383–394, 1991.doi: https://doi.org/10.1002/sim.4780100310