Research Article
BibTex RIS Cite

Digital Elevation Modeling with Heuristic Regression Techniques

Year 2021, Issue: 24, 484 - 488, 15.04.2021
https://doi.org/10.31590/ejosat.916012

Abstract

In this study, elevation values of the Mert River Basin of Samsun were estimated by M5 model tree (M5-tree) and Multivariate Adaptive Regression Splines (MARS) using base map which contains horizontal and vertical location informations. Results were compared with univariate and multivariate linear regression methods (MLR). In the study, three different input scenarios were tried as: (i) elevation forecast with X coordinate information, (ii) elevation forecast with Y coordinate information, (iii) elevation forecast with X and Y coordinate information. Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and coefficient of determination (R2) were utilized as comparison criteria. According to modeling results: (1) M5-tree regression method provided the best results, (2) MARS method was more suitable than the univariate and multivariate linear regression methods, (3) Single variable linear regression method provided the worst estimate, (4) M5-tree regression method can be successfully used in elevation modeling.

References

  • Abolfathi, S., Yeganeh-Bakhtiary, A., Hamze-Ziabari, S. M., & Borzooei, S. (2016). Wave runup prediction using M5′ model tree algorithm. Ocean Engineering, 112, 76–81. https://doi.org/10.1016/j.oceaneng.2015.12.016
  • Adamowski, J., Chan, H. F., Prasher, S. O., & Sharda, V. N. (2012). Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. Journal of Hydroinformatics, 14(3), 731–744. https://doi.org/10.2166/hydro.2011.044
  • Akçın, H., Kutoğlu, H. Ş., & Terlemezoğlu, B. (2005). Deni̇z Di̇bi̇ Topoğrafyasının Yapay Si̇ni̇r Ağlarıyla Modellenmesi̇ (pp. 1–8). Ankara: TMMOB Harita ve Kadastro Mühendisleri Odası 10. Türkiye Harita Bilimsel ve Teknik Kurultayı.
  • Bhattacharya, B., & Solomatine, D. P. (2005). Neural networks and M5 model trees in modelling water level-discharge relationship. Neurocomputing, 63(SPEC. ISS.), 381–396. https://doi.org/10.1016/j.neucom.2004.04.016
  • De Andrés, J., Lorca, P., De Cos Juez, F. J., & Sánchez-Lasheras, F. (2011). Bankruptcy forecasting: A hybrid approach using fuzzy c-means clustering and multivariate adaptive regression splines (MARS). Expert Systems with Applications, 38(3), 1866–1875. https://doi.org/10.1016/j.eswa.2010.07.117
  • Demir, V., & Ülke, A. (2020). Yapay Sinir Ağları Yardımıyla Yükseklik Modellemesi (Samsun -Mert Irmağı Havzası Örneği ) Height Modeling with Artificial Neural Networks ( Samsun-Mert River Basin). Gazi Mühendislik Bilimleri Dergisi, 6(1), 54–61. https://doi.org/https://dx.doi.org/10.30855/gmbd.2020.01.05
  • Demir V, Bilge H, & Bektaş S. (2017) Yapay Sinir Ağları Yardımıyla Sayısal Yükseklik Modellemesi, IX. Ulusal Hidroloji Kongresi 04 – 06 Ekim 2017 Diyarbakır/Türkiye (Özet Bildiri)
  • Demir V, Çıtakoğlu H, Geyikli M. S., & Kuyucu H. (2017). Estimation of Digital Elevation Model by Artificial Intelligence Methods. 1 st International Symposium on Multidisciplinary Studies and Innovative Technologies, 257, November 2-4 Tokat/Türkiye (Özet Bildiri)
  • Dipova, N., & Cangir, B. (2010). Lagün kökenli kil-silt zeminde sikişabilirlik özelliklerinin regresyon ve yapay sinir aǧlari yöntemleri ile belirlenmesi. Teknik Dergi/Technical Journal of Turkish Chamber of Civil Engineers, 21(3), 5069–5086.
  • Elith, J., & Leathwick, J. (2007). Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines. Diversity and Distributions, 13(3), 265–275. https://doi.org/10.1111/j.1472-4642.2007.00340.x
  • Etemad-Shahidi, A., & Mahjoobi, J. (2009). Comparison between M5 tree model tree and neural networks for prediction of significant wave height in Lake Superior. Ocean Engineering, 36(15–16), 1175–1181. https://doi.org/10.1016/j.oceaneng.2009.08.008
  • Leathwick, J. R., Rowe, D., Richardson, J., Elith, J., & Hastie, T. (2005). Using multivariate adaptive regression splines to predict the distributions of New Zealand’s freshwater diadromous fish. Freshwater Biology, 50(12), 2034–2052. https://doi.org/10.1111/j.1365-2427.2005.01448.x
  • Lee, T.-S., Chiu, C.-C., Chou, Y.-C., & Lu, C.-J. (2006). Mining the customer credit using classification and regression tree and multivariate adaptive regression splines. Computational Statistics & Data Analysis, 50(4), 1113–1130. https://doi.org/10.1016/j.csda.2004.11.006
  • Mitchell, T. M. (1997). Machine learning. New York: The McGraw-Hill Companies.
  • P. Bera, S. O. Prasher, R. M. Patel, A. Madani, R. Lacroix, J. D. Gaynor, … S. H. Kim. (2006). Application of MARS in Simulating Pesticide Concentrations in Soil. Transactions of the ASABE, 49(1), 297–307. https://doi.org/10.13031/2013.20228
  • Pal, M., & Deswal, S. (2009). M5 model tree based modelling of reference evapotranspiration. Hydrological Processes, 23(10), 1437–1443. https://doi.org/10.1002/hyp.7266
  • Pourghasemi, H. R., & Rossi, M. (Eds.). (2019). Natural Hazards GIS-Based Spatial Modeling Using Data Mining Techniques (Vol. 48). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-319-73383-8
  • Put, R., Xu, Q. S., Massart, D. L., & Vander Heyden, Y. (2004). Multivariate adaptive regression splines (MARS) in chromatographic quantitative structure-retention relationship studies. Journal of Chromatography A, 1055(1–2), 11–19. https://doi.org/10.1016/j.chroma.2004.07.112
  • Quinlan, J. R. (1992). Learning With Continuous Classes. World Scientiic, 92, 343–348. https://doi.org/10.1.1.34.885
  • Sephton, P. (2001). Forecasting recessions: can we do better on MARS? Review, 83(2), 39–49.
  • Sharda, V. N., Patel, R. M., Prasher, S. O., Ojasvi, P. R., & Prakash, C. (2006). Modeling runoff from middle Himalayan watersheds employing artificial intelligence techniques. Agricultural Water Management, 83(3), 233–242. https://doi.org/10.1016/j.agwat.2006.01.003
  • Solomatine, D. P., & Xue, Y. (2004). M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China. Journal of Hydrologic Engineering, 9(6), 491–501. https://doi.org/10.1061/(ASCE)1084-0699(2004)9:6(491)
  • Zhang, W. G., & Goh, A. T. C. (2013). Multivariate adaptive regression splines for analysis of geotechnical engineering systems. Computers and Geotechnics, 48, 82–95. https://doi.org/10.1016/j.compgeo.2012.09.016
  • Zhang, W., & Goh, A. T. C. (2014). Multivariate adaptive regression splines and neural network models for prediction of pile drivability. Geoscience Frontiers, 7(1), 45–52. https://doi.org/10.1016/j.gsf.2014.10.003

Sezgisel Regresyon Teknikleri ile Sayısal Yükseklik Modellenmesi

Year 2021, Issue: 24, 484 - 488, 15.04.2021
https://doi.org/10.31590/ejosat.916012

Abstract

Bu çalışmada, Samsun Mert Irmağı Havzası’nda, hâlihazır haritalardan temin edilmiş yatay ve düşey koordinat bilgilerinin yer aldığı noktalardan yükseklik değerleri, M5 model ağacı (M5-tree) ve çok değişkenli uyarlamalı regresyon eğrileri (MARS) sezgisel regresyon yöntemleri kullanılarak tahmin edilmeye çalışılmıştır. Sonuçlar Tek ve Çok Değişkenli Regresyon (TDR-ÇDR) yöntemiyle karşılaştırılmıştır. Çalışmada 3 farklı giriş senaryosu incelenmiştir. Bunlar: X yönündeki koordinat bilgisiyle yükseklik tahmini (i); Y yönündeki koordinat bilgisiyle yükseklik tahmini (ii); X ve Y koordinat bilgisiyle yükseklik tahmini şeklindedir (iii). Karşılaştırma kriterleri olarak determinasyon katsayısı (R2), Ortalama Mutlak Hata (OMH) ve Karekök Ortalama Karesel Hata (KOKH) kullanılmıştır. Modelleme sonuçları incelendiğinde; (1) M5-tree regresyon yönteminin en iyi sonucu verdiği, (2) MARS yöntemi ÇDR ve TDR yöntemlerine göre daha iyi olduğu, (3) En kötü sonuç TDR yöntemi kullanılarak yapılan doğrusal regresyon modellemesinde tespit edilmiştir. (4) Özellikle, M5-tree sezgisel regresyon yönteminin yükseklik modellemesinde oldukça başarılı bir metot olduğu sonucuna ulaşılmıştır.

References

  • Abolfathi, S., Yeganeh-Bakhtiary, A., Hamze-Ziabari, S. M., & Borzooei, S. (2016). Wave runup prediction using M5′ model tree algorithm. Ocean Engineering, 112, 76–81. https://doi.org/10.1016/j.oceaneng.2015.12.016
  • Adamowski, J., Chan, H. F., Prasher, S. O., & Sharda, V. N. (2012). Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. Journal of Hydroinformatics, 14(3), 731–744. https://doi.org/10.2166/hydro.2011.044
  • Akçın, H., Kutoğlu, H. Ş., & Terlemezoğlu, B. (2005). Deni̇z Di̇bi̇ Topoğrafyasının Yapay Si̇ni̇r Ağlarıyla Modellenmesi̇ (pp. 1–8). Ankara: TMMOB Harita ve Kadastro Mühendisleri Odası 10. Türkiye Harita Bilimsel ve Teknik Kurultayı.
  • Bhattacharya, B., & Solomatine, D. P. (2005). Neural networks and M5 model trees in modelling water level-discharge relationship. Neurocomputing, 63(SPEC. ISS.), 381–396. https://doi.org/10.1016/j.neucom.2004.04.016
  • De Andrés, J., Lorca, P., De Cos Juez, F. J., & Sánchez-Lasheras, F. (2011). Bankruptcy forecasting: A hybrid approach using fuzzy c-means clustering and multivariate adaptive regression splines (MARS). Expert Systems with Applications, 38(3), 1866–1875. https://doi.org/10.1016/j.eswa.2010.07.117
  • Demir, V., & Ülke, A. (2020). Yapay Sinir Ağları Yardımıyla Yükseklik Modellemesi (Samsun -Mert Irmağı Havzası Örneği ) Height Modeling with Artificial Neural Networks ( Samsun-Mert River Basin). Gazi Mühendislik Bilimleri Dergisi, 6(1), 54–61. https://doi.org/https://dx.doi.org/10.30855/gmbd.2020.01.05
  • Demir V, Bilge H, & Bektaş S. (2017) Yapay Sinir Ağları Yardımıyla Sayısal Yükseklik Modellemesi, IX. Ulusal Hidroloji Kongresi 04 – 06 Ekim 2017 Diyarbakır/Türkiye (Özet Bildiri)
  • Demir V, Çıtakoğlu H, Geyikli M. S., & Kuyucu H. (2017). Estimation of Digital Elevation Model by Artificial Intelligence Methods. 1 st International Symposium on Multidisciplinary Studies and Innovative Technologies, 257, November 2-4 Tokat/Türkiye (Özet Bildiri)
  • Dipova, N., & Cangir, B. (2010). Lagün kökenli kil-silt zeminde sikişabilirlik özelliklerinin regresyon ve yapay sinir aǧlari yöntemleri ile belirlenmesi. Teknik Dergi/Technical Journal of Turkish Chamber of Civil Engineers, 21(3), 5069–5086.
  • Elith, J., & Leathwick, J. (2007). Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines. Diversity and Distributions, 13(3), 265–275. https://doi.org/10.1111/j.1472-4642.2007.00340.x
  • Etemad-Shahidi, A., & Mahjoobi, J. (2009). Comparison between M5 tree model tree and neural networks for prediction of significant wave height in Lake Superior. Ocean Engineering, 36(15–16), 1175–1181. https://doi.org/10.1016/j.oceaneng.2009.08.008
  • Leathwick, J. R., Rowe, D., Richardson, J., Elith, J., & Hastie, T. (2005). Using multivariate adaptive regression splines to predict the distributions of New Zealand’s freshwater diadromous fish. Freshwater Biology, 50(12), 2034–2052. https://doi.org/10.1111/j.1365-2427.2005.01448.x
  • Lee, T.-S., Chiu, C.-C., Chou, Y.-C., & Lu, C.-J. (2006). Mining the customer credit using classification and regression tree and multivariate adaptive regression splines. Computational Statistics & Data Analysis, 50(4), 1113–1130. https://doi.org/10.1016/j.csda.2004.11.006
  • Mitchell, T. M. (1997). Machine learning. New York: The McGraw-Hill Companies.
  • P. Bera, S. O. Prasher, R. M. Patel, A. Madani, R. Lacroix, J. D. Gaynor, … S. H. Kim. (2006). Application of MARS in Simulating Pesticide Concentrations in Soil. Transactions of the ASABE, 49(1), 297–307. https://doi.org/10.13031/2013.20228
  • Pal, M., & Deswal, S. (2009). M5 model tree based modelling of reference evapotranspiration. Hydrological Processes, 23(10), 1437–1443. https://doi.org/10.1002/hyp.7266
  • Pourghasemi, H. R., & Rossi, M. (Eds.). (2019). Natural Hazards GIS-Based Spatial Modeling Using Data Mining Techniques (Vol. 48). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-319-73383-8
  • Put, R., Xu, Q. S., Massart, D. L., & Vander Heyden, Y. (2004). Multivariate adaptive regression splines (MARS) in chromatographic quantitative structure-retention relationship studies. Journal of Chromatography A, 1055(1–2), 11–19. https://doi.org/10.1016/j.chroma.2004.07.112
  • Quinlan, J. R. (1992). Learning With Continuous Classes. World Scientiic, 92, 343–348. https://doi.org/10.1.1.34.885
  • Sephton, P. (2001). Forecasting recessions: can we do better on MARS? Review, 83(2), 39–49.
  • Sharda, V. N., Patel, R. M., Prasher, S. O., Ojasvi, P. R., & Prakash, C. (2006). Modeling runoff from middle Himalayan watersheds employing artificial intelligence techniques. Agricultural Water Management, 83(3), 233–242. https://doi.org/10.1016/j.agwat.2006.01.003
  • Solomatine, D. P., & Xue, Y. (2004). M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China. Journal of Hydrologic Engineering, 9(6), 491–501. https://doi.org/10.1061/(ASCE)1084-0699(2004)9:6(491)
  • Zhang, W. G., & Goh, A. T. C. (2013). Multivariate adaptive regression splines for analysis of geotechnical engineering systems. Computers and Geotechnics, 48, 82–95. https://doi.org/10.1016/j.compgeo.2012.09.016
  • Zhang, W., & Goh, A. T. C. (2014). Multivariate adaptive regression splines and neural network models for prediction of pile drivability. Geoscience Frontiers, 7(1), 45–52. https://doi.org/10.1016/j.gsf.2014.10.003
There are 24 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Vahdettin Demir 0000-0002-6590-5658

Esra Aslı Çubukçu 0000-0003-4159-205X

Publication Date April 15, 2021
Published in Issue Year 2021 Issue: 24

Cite

APA Demir, V., & Çubukçu, E. A. (2021). Sezgisel Regresyon Teknikleri ile Sayısal Yükseklik Modellenmesi. Avrupa Bilim Ve Teknoloji Dergisi(24), 484-488. https://doi.org/10.31590/ejosat.916012