The effect of the number of inputs on the spatial interpolation of elevation data using IDW and ANNs
Abstract
Spatial interpolation is a required method to generate a continuous surface such as Digital Elevation Model (DEM) because field investigation for most of the surface’s part is time-consuming with a high demand in both human resources and monetory cost. One of the most used deterministic interpolation models is Inverse Distance Weighting (IDW) model. The model takes several neighbors’ information, and the weights are constructed based on the distance between the interpolated point and the neighbors’ points. From the machine learning model, Artificial Neural Networks (ANNs) model has also been used for spatial interpolation. The input of ANNs model is also one of the parameters that need to be defined when building the model. This paper evaluated the effect of the number of inputs (neighbors) on the elevation interpolation accuracy. We applied IDW and ANNs to interpolate the elevation of Balikpapan City, Indonesia. The results show that the accuracy increases significantly when the number of inputs is between one and three. However, after three inputs, additional input would not change the accuracy significantly. ANNs performed better than IDW. For three or more inputs, the MAE of ANNs and IDW interpolations are below 1.1 and around 2 meters, respectively.
Keyword : artificial neural network, digital elevation model, elevation interpolation, interpolation, inverse distance weighting, spatial interpolation
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Bartier, P. M., & Keller, C. P. (1996). Multivariate interpolation to incorporate thematic surface data using inverse distance weighting (IDW). Computers & Geosciences, 22(7), 795–799. https://doi.org/10.1016/0098-3004(96)00021-0
Chymyrov, A. (2021). Comparison of different DEMs for hydrological studies in the mountainous areas. The Egyptian Journal of Remote Sensing and Space Science, 24(3), 587–594. https://doi.org/10.1016/j.ejrs.2021.08.001
Ikechukwu, M. N., Ebinne, E., Idorenyin, U., & Raphael, N. I. (2017). Accuracy assessment and comparative analysis of IDW, spline and kriging in spatial interpolation of landform (topography): An experimental study. Journal of Geographic Information System, 9(3), 354–371. https://doi.org/10.4236/jgis.2017.93022
Jumaah, H. J., Ameen, M. H., Kalantar, B., Rizeei, H. M., & Jumaah, S. J. (2019). Air quality index prediction using IDW geostatistical technique and OLS-based GIS technique in Kuala Lumpur, Malaysia. Geomatics, Natural Hazards and Risk, 10(1), 2185–2199. https://doi.org/10.1080/19475705.2019.1683084
Keskin, M., Dogru, A. O., Balcik, F. B., Goksel, C., Ulugtekin, N., & Sozen, S. (2015). Comparing spatial interpolation methods for mapping meteorological data in Turkey. In Energy systems and management (pp. 33–42). Springer. https://doi.org/10.1007/978-3-319-16024-5_3
Li, Z., Zhu, C., & Gold, C. (2004). Digital terrain modeling: Principles and methodology. CRC Press. https://doi.org/10.1201/9780203357132
Liu, F., He, X., & Zhou, L. (2009). Application of generalized regression neural network residual kriging for terrain surface interpolation. In Proceedings SPIE: International Symposium on Spatial Analysis, Spatial-Temporal Data Modeling, and Data Mining (Vol. 7492). https://doi.org/10.1117/12.837425
Merwin, D. A., Cromley, R. G., & Civco, D. L. (2002). Artificial neural networks as a method of spatial interpolation for digital elevation models. Cartography and Geographic Information Science, 29(2), 99–110. https://doi.org/10.1559/152304002782053323
Noori, M. J., Hassan, H. H., & Mustafa, Y. T. (2014). Spatial estimation of rainfall distribution and its classification in Duhok governorate using GIS. Journal of Water Resource and Protection, 6, 75–82. https://doi.org/10.4236/jwarp.2014.62012
Nusret, D., & Dug, S. (2012). Applying the inverse distance weighting and kriging methods of the spatial interpolation on the mapping the annual precipitation in Bosnia and Herzegovina. In 6th International Congress on Environmental Modelling and Software (pp. 1–8). https://scholarsarchive.byu.edu/iemssconference/2012/Stream-B/229
Peterson, E. E., & Pearse, A. R. (2017). IDW‐Plus: An Arc GIS toolset for calculating spatially explicit watershed attributes for survey sites. JAWRA Journal of the American Water Resources Association, 53(5), 1241–1249. https://doi.org/10.1111/1752-1688.12558
Rigol, J. P., Jarvis, C. H., & Stuart, N. (2001). Artificial neural networks as a tool for spatial interpolation. International Journal of Geographical Information Science, 15(4), 323–343. https://doi.org/10.1080/13658810110038951
Robinson, T., & Metternicht, G. (2006). Testing the performance of spatial interpolation techniques for mapping soil properties. Computers and Electronics in Agriculture, 50(2), 97–108. https://doi.org/10.1016/j.compag.2005.07.003
Sentinel Hub. (2021). EO Browser. https://www.sentinel-hub.com/
Shepard, D. (1968). A two-dimensional interpolation function for irregularly-spaced data. Proceedings of the 1968 23rd ACM National Conference (pp. 517–524). https://doi.org/10.1145/800186.810616
Shiode, N., & Shiode, S. (2011). Street‐level spatial interpolation using network‐based IDW and ordinary kriging. Transactions in GIS, 15(4), 457–477. https://doi.org/10.1111/j.1467-9671.2011.01278.x
Sivapragasam, C., Arun, V., & Giridhar, D. (2010). A simple approach for improving spatial interpolation of rainfall using ANN. Meteorology and Atmospheric Physics, 109(1), 1–7. https://doi.org/10.1007/s00703-010-0090-z
Tomczak, M. (1998). Spatial interpolation and its uncertainty using automated anisotropic inverse distance weighting (IDW)-cross-validation/jackknife approach. Journal of Geographic Information and Decision Analysis, 2(2), 18–30