Enhancing Spatial Interpolation: A Multi-Layer Inverse Distance Weighting Model for Complex Regression and Classification Tasks in Spatial Data Analysis

Authors: Yakin Hajlaoui, Richard Labib, Jean-Franc¸ois Plante, Michel Gamache

Abstract:

This study presents the Multi-Layer Inverse Distance Weighting Model (ML-IDW), inspired by the mathematical formulation of both multi-layer neural networks (ML-NNs) and Inverse Distance Weighting model (IDW). ML-IDW leverages ML-NNs’ processing capabilities, characterized by compositions of learnable non-linear functions applied to input features, and incorporates IDW’s ability to learn anisotropic spatial dependencies, presenting a promising solution for nonlinear spatial interpolation and learning from complex spatial data. We employ gradient descent and backpropagation to train ML-IDW. The performance of the proposed model is compared against conventional spatial interpolation models such as Kriging and standard IDW on regression and classification tasks using simulated spatial datasets of varying complexity. Our results highlight the efficacy of ML-IDW, particularly in handling complex spatial dataset, exhibiting lower mean square error in regression and higher F1 score in classification.

Keywords: Deep Learning, Multi-Layer Neural Networks, Gradient Descent, Spatial Interpolation, Inverse Distance Weighting.

References:

[1] J. Heaton, “Ian goodfellow, yoshua bengio, and aaron courville: Deep learning: The mit press, 2016, 800 pp, isbn: 0262035618,” Genetic programming and evolvable machines, vol. 19, no. 1, pp. 305–307, 2018.
[2] C. M. Bishop and N. M. Nasrabadi, Pattern recognition and machine learning. Springer, 2006, vol. 4, no. 4.
[3] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986.
[4] J. Kim, Y. Lee, M.-H. Lee, and S.-Y. Hong, “A comparative study of machine learning and spatial interpolation methods for predicting house prices,” Sustainability, vol. 14, no. 15, p. 9056, 2022.
[5] I. Chahrour and J.Wells, “Comparing machine learning and interpolation methods for loop-level calculations,” SciPost Physics, vol. 12, no. 6, p. 187, 2022.
[6] D. Radoˇcaj, M. Juriˇsi´c, R. ˇ Zupan, and O. Antoni´c, “Spatial prediction of heavy metal soil contents in continental Croatia comparing machine learning and spatial interpolation methods,” Geodetski list, vol. 74, no. 4, pp. 357–372, 2020.
[7] G. T. Nwaila, S. E. Zhang, J. E. Bourdeau, H. E. Frimmel, and Y. Ghorbani, “Spatial interpolation using machine learning: from patterns and regularities to block models,” Natural Resources Research, vol. 33, no. 1, pp. 129–161, 2024.
[8] J. K. Yamamoto, “Correcting the smoothing effect of ordinary kriging estimates,” Mathematical geology, vol. 37, pp. 69–94, 2005.
[9] X. Li, Y. Ao, S. Guo, and L. Zhu, “Combining regression kriging with machine learning mapping for spatial variable estimation,” IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 1, pp. 27–31, 2019.
[10] Z. Huang, H. Wang, and R. Zhang, “An improved kriging interpolation technique based on svm and its recovery experiment in oceanic missing data,” 2012.
[11] R. Karami and P. Afzal, “Estimation of elemental distributions by combining artificial neural network and inverse distance weighted (idw) based on lithogeochemical data in kahang porphry deposit, central iran,” Universal Journal of Geoscience, vol. 3, no. 2, pp. 59–65, 2015.
[12] T. Tunc¸ay, P. Alaboz, O. Dengiz, and O. Bas¸kan, “Application of regression kriging and machine learning methods to estimate soil moisture constants in a semi-arid terrestrial area,” Computers and Electronics in Agriculture, vol. 212, p. 108118, 2023.
[13] D. Cho, J. Im, and S. Jung, “A new statistical downscaling approach for short-term forecasting of summer air temperatures through a fusion of deep learning and spatial interpolation,” Quarterly Journal of the Royal Meteorological Society, vol. 150, no. 760, pp. 1222–1242, 2024.
[14] J. Tan, X. Xie, J. Zuo, X. Xing, B. Liu, Q. Xia, and Y. Zhang, “Coupling random forest and inverse distance weighting to generate climate surfaces of precipitation and temperature with multiple-covariates,” Journal of Hydrology, vol. 598, p. 126270, 2021.
[15] B. S. Murphy, “Pykrige: development of a kriging toolkit for python,” in AGU fall meeting abstracts, vol. 2014, 2014, pp. H51K–0753.
[16] R. Tolosana-Delgado, V. Pawlowsky-Glahn, and J. Egozcue, “Simplicial indicator kriging,” Journal of China University of Geosciences, vol. 19, no. 1, pp. 65–71, 2008.
[17] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
[18] D. Shepard, “A two-dimensional interpolation function for irregularly-spaced data,” in Proceedings of the 1968 23rd ACM national conference, 1968, pp. 517–524.
[19] N. S.-N. Lam, “Spatial interpolation methods: a review,” The American Cartographer, vol. 10, no. 2, pp. 129–150, 1983.
[20] O. Babak and C. V. Deutsch, “Statistical approach to inverse distance interpolation,” Stochastic Environmental Research and Risk Assessment, vol. 23, pp. 543–553, 2009.
[21] Z.-N. Liu, X.-Y. Yu, L.-F. Jia, Y.-S. Wang, Y.-C. Song, and H.-D. Meng, “The influence of distance weight on the inverse distance weighted method for ore-grade estimation,” Scientific Reports, vol. 11, no. 1, p. 2689, 2021.
[22] D. E. Rumelhart, R. Durbin, R. Golden, and Y. Chauvin, “Backpropagation: The basic theory,” in Backpropagation. Psychology Press, 2013, pp. 1–34.
[23] Q. Guan, P. C. Kyriakidis, and M. F. Goodchild, “A parallel computing approach to fast geostatistical areal interpolation,” International Journal of Geographical Information Science, vol. 25, no. 8, pp. 1241–1267, 2011.
[24] P. J. van Oosterom, H. Ploeger, A. Mansourian, S. Scheider, R. Lemmens, and B. Van Loenen, “Proceedings-the 26th agile international conference on geographic information science spatial data for design: Preface,” in 26th AGILE Conference on Geographic Information Science, AGILE 2023: Spatial data for design. Copernicus, 2023.
[25] F. Huang, S. Bu, J. Tao, and X. Tan, “Opencl implementation of a parallel universal kriging algorithm for massive spatial data interpolation on heterogeneous systems,” ISPRS international journal of geo-information, vol. 5, no. 6, p. 96, 2016.
[26] J.-P. C. Pierre Delfiner, Geostatistics: Modeling Spatial Uncertainty. WILEY, Mar. 2012. Online. Available: https://www.ebook.de/de/product/15356462/pierre_delfiner_jean_paul_chiles_geostatistics_modeling_spatial_uncertainty.html