In this study, we proposed a modified spherical variogram model aimed at improving the accuracy of spatial modeling in volume estimation. The model enhances the flexibility of the traditional spherical variogram structure by incorporating additional polynomial terms to better capture spatial variability in structured plantation datasets. Parameters such as nugget, sill, range, and the coefficients of the polynomial terms were estimated using the L-BFGS-B optimization algorithm under box constraints, ensuring numerical stability and physically meaningful values. The performance of the modified model was evaluated using real-world volume data from Tectona grandis Linn. f. (teak) trees planted in a multiclonal block in Brumas Camp, Tawau, Sabah, Malaysia. To assess model accuracy and generalizability, predicted volumes derived from the fitted variogram model were compared to measured values using three validation strategies: Full dataset fitting, Leave-One-Out Cross-Validation (LOOCV), and K-Fold Cross-Validation. The modified spherical variogram model demonstrated superior performance over the classical version in terms of weighted root mean squared error (RMSE) and coefficient of determination (R2). These findings highlighted the value of refining variogram structures to improve estimation precision in geostatistical applications, particularly when modeling spatially complex forest data.
Citation: Johannah Jamalul Kiram, Rossita Mohamad Yunus, Yani Japarudin, Mahadir Lapammu, Olivier Monteuuis, Doreen K. S. Goh. A modified spherical variogram model with constrained optimization for spatial volume estimation[J]. AIMS Mathematics, 2025, 10(12): 29664-29685. doi: 10.3934/math.20251304
In this study, we proposed a modified spherical variogram model aimed at improving the accuracy of spatial modeling in volume estimation. The model enhances the flexibility of the traditional spherical variogram structure by incorporating additional polynomial terms to better capture spatial variability in structured plantation datasets. Parameters such as nugget, sill, range, and the coefficients of the polynomial terms were estimated using the L-BFGS-B optimization algorithm under box constraints, ensuring numerical stability and physically meaningful values. The performance of the modified model was evaluated using real-world volume data from Tectona grandis Linn. f. (teak) trees planted in a multiclonal block in Brumas Camp, Tawau, Sabah, Malaysia. To assess model accuracy and generalizability, predicted volumes derived from the fitted variogram model were compared to measured values using three validation strategies: Full dataset fitting, Leave-One-Out Cross-Validation (LOOCV), and K-Fold Cross-Validation. The modified spherical variogram model demonstrated superior performance over the classical version in terms of weighted root mean squared error (RMSE) and coefficient of determination (R2). These findings highlighted the value of refining variogram structures to improve estimation precision in geostatistical applications, particularly when modeling spatially complex forest data.
| [1] | S. D. Iaco, M. Palma, D. Posa, Geostatistics and the role of variogram in time series analysis: A critical review, Statistical Methods for Spatial Planning and Monitoring, Milano, Springer, 2013, 47–75. https://doi.org/10.1007/978-88-470-2751-0_3 |
| [2] | M. A. Oliver, R. Webster, The variogram and modelling, Basic Steps in Geostatistics: The Variogram and Kriging, Cham, Springer International Publishing, 2015, 15–42. https://doi.org/10.1007/978-3-319-15865-5_3 |
| [3] |
Z. Arétouyap, P. N. Nouck, R. Nouayou, F. E. G. Kemgang, A. D. P. Toko, J. Asfahani, Lessening the adverse effect of the semivariogram model selection on an interpolative survey using kriging technique, SpringerPlus, 5 (2016), 549. https://doi.org/10.1186/s40064-016-2142-4 doi: 10.1186/s40064-016-2142-4
|
| [4] | M. Tomasetto, E. Arnone, L. M. Sangalli, Modeling anisotropy and non-stationarity through physics-informed spatial regression, Environmetrics, 35 (2024), e2889. |
| [5] | M. J. Pyrcz, C. V. Deutsch, Improved variogram models for more realistic estimation and simulation, Centre for Computational Geostatistics, University of Alberta, 2003. |
| [6] |
A. O. Finley, Comparing spatially‐varying coefficients models for analysis of ecological data with non‐stationary and anisotropic residual dependence, Methods Ecol. Evol., 2 (2011), 143–154. https://doi.org/10.1111/j.2041-210X.2010.00060.x doi: 10.1111/j.2041-210X.2010.00060.x
|
| [7] |
S. Reda, S. R. Nassif, Accurate spatial estimation and decomposition techniques for variability characterization, IEEE T. Semiconduct. M., 23 (2010), 345–357. https://doi.org/10.1109/TSM.2010.2051752 doi: 10.1109/TSM.2010.2051752
|
| [8] |
G. A. Qadir, Y. Sun, S. Kurtek, Estimation of spatial deformation for nonstationary processes via variogram alignment, Technometrics, 63 (2021), 548–561. https://doi.org/10.1080/00401706.2021.1883481 doi: 10.1080/00401706.2021.1883481
|
| [9] | O. Perrin, P. Monestiez, Modelling of non-stationary spatial structure using parametric radial basis deformations, Geostatistics for Environmental Applications, Dordrecht, Netherlands, Springer, 1999,175–186. https://doi.org/10.1007/978-94-015-9297-0_15 |
| [10] |
Y. Ling, Y. Shi, H. Hou, L. Pan, H. Chen, P. Liang, et al., Enhanced dung beetle optimizer for Kriging-assisted time-varying reliability analysis, AIMS Math., 9 (2024), 29296–29332. https://doi.org/10.3934/math.20241420 doi: 10.3934/math.20241420
|
| [11] |
L. Fang, Smooth digital terrain modeling in irregular domains using finite element thin plate splines and adaptive refinement, AIMS Math., 9 (2024), 30015–30042. https://doi.org/10.3934/math.20241450 doi: 10.3934/math.20241450
|
| [12] | I. Clark, Statistics or geostatistics? Sampling error or nugget effect, J. S. Afr. I. Min. Metall., 110 (2010), 307–312. |
| [13] | N. Cressie, Geostatistical analysis of spatial data, Spatial statistics and digital image analysis, National Academy Press Washington, DC, USA, 1991, 87–108. |
| [14] |
R. H. Byrd, P. Lu, J. Nocedal, C. Zhu, A limited memory algorithm for bound constrained optimization, SIAM J. Sci. Comput., 16 (1995), 1190–1208. https://doi.org/10.1137/0916069 doi: 10.1137/0916069
|
| [15] | J. Nocedal, S. J. Wright, Numerical optimization, Springer, 1999. |
| [16] |
O. Monteuuis, D. K. S. Goh, C. Garcia, D. Alloysius, J. Gidiman, R. Bacilieri, et al., Genetic variation of growth and tree quality traits among 42 diverse genetic origins of Tectona grandis planted under humid tropical conditions in Sabah, East Malaysia, Tree Genet. Genomes, 7 (2011), 1263–1275. https://doi.org/10.1007/s11295-011-0411-5 doi: 10.1007/s11295-011-0411-5
|
| [17] | D. K. S. Goh, Y. Japarudin, A. Alwi, M. Lapammu, A. Flori, O. Monteuuis, Growth differences and genetic parameter estimate of 15 teak (Tectona grandis Lf) genotypes of various ages clonally propagated by microcuttings and planted under humid tropical conditions, Silvae Genet., 62 (2013), 196–206. |
| [18] |
P. H. Hiemstra, E. J. Pebesma, C. J. W. Twenhöfel, G. B. M. Heuvelink, Real-time automatic interpolation of ambient gamma dose rates from the Dutch radioactivity monitoring network, Comput. Geosci., 35 (2009), 1711–1721. https://doi.org/10.1016/j.cageo.2008.10.011 doi: 10.1016/j.cageo.2008.10.011
|
Figures(7) / Tables(5)
Johannah Jamalul Kiram, Rossita Mohamad Yunus, Yani Japarudin, Mahadir Lapammu, Olivier Monteuuis, Doreen K. S. Goh. A modified spherical variogram model with constrained optimization for spatial volume estimation[J]. AIMS Mathematics, 2025, 10(12): 29664-29685. doi: 10.3934/math.20251304
DownLoad: