Digital elevation model prediction in Sudan’s data scarce mining regions: A comparison of neural network and classical interpolation approaches

Abstract

This study evaluates the effectiveness of Artificial Neural Networks (ANN) for generating Digital Elevation Models (DEMs) in the complex terrain of Port Sudan’s mining region, comparing its performance to traditional interpolation techniques: Inverse Distance Weighting (IDW), Ordinary Kriging (OK), and Universal Kriging (UK). The region's diverse topography posed challenges for accurate interpolation, addressed through precise correction of GPS elevation data, accounting for ionospheric and tropospheric variations. An ANN model trained using the Levenberg-Marquardt algorithm in MATLAB with a feedforward architecture was benchmarked against methods implemented in ArcGIS Pro. Model performance was assessed through visual outputs (3D surfaces, contour maps, error distributions) and statistical metrics (MAE, RMSE, R²). ANN significantly outperformed the conventional methods, achieving the highest accuracy (R² = 0.9963, MAE = 1.3896 m, RMSE = 1.9829 m) and strong generalization capacity. OK ranked second with R² = 0.9915, capturing spatial autocorrelation effectively, while IDW, though fairly accurate (R² = 0.9773), struggled with abrupt elevation changes. UK yielded the poorest results, likely due to challenges encountered in specifying or fitting an appropriate trend model for the study area's complex topography, which led to observed instability. Findings underscore ANN’s superior adaptability and reliability for DEM interpolation in rugged terrains, highlighting its potential for broader geospatial applications. The study advocates for the integration of machine learning in geospatial modeling. Furthermore, it suggests that exploring hybrid ANN–geostatistical approaches in future research holds potential to further enhance DEM accuracy. These improvements could benefit sectors such as mining, environmental monitoring, and infrastructure planning.

Keywords

• DEM
• ANN
• OK
• IDW
• UK

References

1. Agatonovic-Kustrin, S., & Beresford, R. (2000). Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of Pharmaceutical and Biomedical Analysis, 22(5), 717–727. https://doi.org/10.1016/S0731-7085(99)00272-1
2. Alavi, S. H., Bahrami, A., Mashayekhi, M., & Zolfaghari, M. (2024). Optimizing interpolation methods and point distances for accurate earthquake hazard mapping. Buildings, 14(6), 1823. https://doi.org/10.3390/buildings14061823
3. Anwer, H. A. (2025). Identifying suitable dam locations in Al Dinder: Integrating GIS, remote sensing, and hydrological factors. International Journal of Engineering and Geosciences, 10(3), 290-302. https://doi.org/10.26833/ijeg.1579147
4. Bhattacharjee, S., Ghosh, S. K., Chen, J., Bhattacharjee, S., Ghosh, S. K., & Chen, J. (2019). Spatial interpolation. Semantic kriging for spatio-temporal prediction, 19-41. Springer. https://doi.org/10.1007/978-981-13-8664-0_2
5. Bilgehan, M. H., Mustafa, H., & Hakan, K. (2022). Estimation of UAV flight time and battery consumption for photogrammetric application using multiple machine learning algorithms. Engineering Research Express, 4(2), 025050. https://doi.org/10.1088/2631-8695/ac7a0b
6. Bishop, C. M., & Nasrabadi, N. M. (2006). Pattern recognition and machine learning. Springer.
7. ‏ Bostan, P. (2017). Basic kriging methods in geostatistics. Yuzuncu Yıl University Journal of Agricultural Sciences, 27(1), 10–20. https://doi.org/10.29133/yyutbd.305093
8. Chen, F. W., & Liu, C. W. (2012). Estimation of the spatial rainfall distribution using inverse distance weighting (IDW) in the middle of Taiwan. Paddy and Water Environment, 10, 209–222. https://doi.org/10.1007/s10333-012-0319-1

9. Dobesch, H., Dumolard, P., & Dyras, I. (2013). Spatial interpolation for climate data: the use of GIS in climatology and meteorology. John Wiley & Sons.
10. Gentile, M., Courbin, F., & Meylan, G. (2013). Interpolating point spread function anisotropy. Astronomy & Astrophysics, 549, A1. https://doi.org/10.1051/0004-6361/201219739
11. Gui, R., Qin, Y., Hu, Z., Dong, J., Sun, Q., Hu, J., Yuan, Y., & Mo, Z. (2024). Neural network-based fusion of InSAR and Optical digital elevation models with consideration of local terrain features. Remote Sensing, 16(19), 3567. https://doi.org/10.3390/rs16193567
12. Habib, M. (2021). Evaluation of DEM interpolation techniques for characterizing terrain roughness. Catena, 198, 105072. https://doi.org/10.1016/j.catena.2020.105072
13. Habib, M., Alzubi, Y., Malkawi, A., & Awwad, M. (2020). Impact of interpolation techniques on the accuracy of large-scale digital elevation model. Open Geosciences, 12(1), 190-202. https://doi.org/10.1515/geo-2020-0012
14. Hashemi, M., Peralta, R. C., & Yost, M. (2024). Balancing results from AI-based geostatistics versus fuzzy inference by game theory bargaining to improve a groundwater monitoring network. Machine Learning and Knowledge Extraction, 6(3), 1871–1893. https://doi.org/10.3390/make6030092
15. Huang, F., Liu, D., Tan, X., Wang, J., Chen, Y., & He, B. (2011). Explorations of the implementation of a parallel IDW interpolation algorithm in a Linux cluster-based parallel GIS. Computers & Geosciences, 37(4), 426–434. https://doi.org/10.1016/j.cageo.2010.05.024
16. Husrevoglu, M., & Gundogdu, I. B. (2025). Evaluating the performance of ANN and ANFIS models for spatial precipitation prediction in complex terrain: a case study in central Anatolia. Theoretical and Applied Climatology, 156(7), 395. https://doi.org/10.1007/s00704-025-05637-2
17. 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
18. Ingre, B., & Yadav, A. (2015). Performance analysis of NSL-KDD dataset using ANN. 2015 International Conference on Signal Processing and Communication Engineering Systems, 92–96, Guntur, India.
19. Jarvis, C. H., Stuart, N., & Cooper, W. (2003). Informetric and statistical diagnostics to provide artificially-intelligent support for spatial analysis: The example of interpolation. International Journal of Geographical Information Science, 17(6), 495–516. https://doi.org/10.1080/1365881031000114099
20. Kanevski, M., & Maignan, M. (2004). Analysis and modelling of spatial environmental data. EPFL press.‏
21. Kumi-Boateng, B., & Ziggah, Y. Y. (2016). Accuracy assessment of cartesian (X, Y, Z) to geodetic coordinates (φ, λ, h) transformation procedures in precise 3D coordinate transformation–A case study of Ghana geodetic reference network. Journal of Geosciences and Geomatics, 4(1), 1–7. https://doi.org/10.12691/jgg-4-1-1
22. Kuntz, M., & Helbich, M. (2014). Geostatistical mapping of real estate prices: An empirical comparison of kriging and cokriging. International Journal of Geographical Information Science, 28(9), 1904–1921. https://doi.org/10.1080/13658816.2014.906041
23. Li, J., & Heap, A. D. (2014). Spatial interpolation methods applied in the environmental sciences: A review. Environmental Modelling & Software, 53, 173-189. https://doi.org/10.1016/j.envsoft.2013.12.008
24. Ly, S., Charles, C., & Degré, A. (2013). Different methods for spatial interpolation of rainfall data for operational hydrology and hydrological modeling at watershed scale: A review. Biotechnologie, agronomie, société et environnement, 17(2).
25. Makineci, H. B., Karabörk, H., & Durdu, A. (2022). ANN estimation model for photogrammetry-based UAV flight planning optimisation. International Journal of Remote Sensing, 43(15-16), 5686-5708. https://doi.org/10.1080/01431161.2021.1945159
26. Mesa-Mingorance, J. L., & Ariza-López, F. J. (2020). Accuracy assessment of digital elevation models (DEMs): A critical review of practices of the past three decades. Remote Sensing, 12(16), 2630. https://doi.org/10.3390/rs12162630
27. Mesić Kiš, I. (2016). Comparison of ordinary and universal kriging interpolation techniques on a depth variable (a case of linear spatial trend), case study of the Šandrovac field. Rudarsko-geološko-naftni zbornik, 31(2), 41–58. https://doi.org/10.17794/rgn.2016.2.4
28. Mohamed, T. (2024). The prediction of flood monitoring for image satellite using artificial neural networks. Journal of Karary University for Engineering and Science, 3(3). https://doi.org/10.54388/jkues.v3i3.261
29. Narin, O. G., Abdikan, S., Gullu, M., Lindenbergh, R., Balik Sanli, F., & Yilmaz, I. (2024). Improving global digital elevation models using space-borne GEDI and ICESat-2 LiDAR altimetry data. International Journal of Digital Earth, 17(1), 2316113. https://doi.org/10.1080/17538947.2024.2316113
30. Ozelkan, E., Bagis, S., Ozelkan, E. C., Ustundag, B. B., Yucel, M., & Ormeci, C. (2015). Spatial interpolation of climatic variables using land surface temperature and modified inverse distance weighting. International Journal of Remote Sensing, 36(4), 1000–1025. https://doi.org/10.1080/01431161.2015.1007248
31. Respati, S., & Sulistyo, T. (2023). The effect of the number of inputs on the spatial interpolation of elevation data using IDW and ANNs. Geodesy and Cartography, 49(1), 60-65.‏ https://doi.org/10.3846/gac.2023.16591
32. Selmy, S. A., Kucher, D. E., & Yang, Y. (2025). Geospatial Data: Acquisition, applications, and challenges. Remote Sensing-methods and applications: Methods and applications; Intechopen.
33. Setianto, A., & Triandini, T. (2013). Comparison of kriging and inverse distance weighted (IDW) interpolation methods in lineament extraction and analysis. Journal of Applied Geology, 5(1), 21–29. https://doi.org/10.22146/jag.7204
34. Shahbeik, S., Afzal, P., Moarefvand, P., & Qumarsy, M. (2014). Comparison between ordinary kriging (OK) and inverse distance weighted (IDW) based on estimation error: Case study of Dardevey iron ore deposit, NE Iran. Arabian Journal of Geosciences, 7, 3693–3704. https://doi.org/10.1007/s12517-013-0978-2
35. Singh, P., & Verma, P. (2019). A comparative study of spatial interpolation technique (IDW and Kriging) for determining groundwater quality. GIS and Geostatistical Techniques for Groundwater Science, 43–56. Elsevier.
36. Spanò, A., Sammartano, G., Calcagno Tunin, F., Cerise, S., & Possi, G. (2018). GIS-based detection of terraced landscape heritage: comparative tests using regional DEMs and UAV data. Applied Geomatics, 10, 77-97. https://doi.org/10.1007/s12518-018-0205-7
37. Szypuła, B. J. (2016). Geomorphometric comparison of DEMs built by different interpolation methods. Landform Analysis, 32. https://doi.org/10.12657/landfana.032.004
38. Tan, Q., & Xu, X. (2014). Comparative analysis of spatial interpolation methods: An experimental study. Sensors & Transducers, 165(2), 155–161.
39. Zandi, S. (2013). GeoComputational methods for surface and field data interpolation. Auckland University of Technology.
40. Ziggah, Y. Y., Youjian, H., Yu, X., & Basommi, L. P. (2016). Capability of artificial neural network for forward conversion of geodetic coordinates (ϕ, λ, h) to Cartesian coordinates (X, Y, Z). Mathematical Geosciences, 48(6), 687–721. https://doi.org/10.1007/s11004-016-9638-x