Improving sub-pixel imperviousness change prediction by ensembling heterogeneous non-linear regression models

• Autorzy: Drzewiecki W.

Identyfikatory

DOI

10.1515/geocart-2016-0016

• Języki publikacji: EN

Abstrakty

EN

In this work nine non-linear regression models were compared for sub-pixel impervious surface area mapping from Landsat images. The comparison was done in three study areas both for accuracy of imperviousness coverage evaluation in individual points in time and accuracy of imperviousness change assessment. The performance of individual machine learning algorithms (Cubist, Random Forest, stochastic gradient boosting of regression trees, k-nearest neighbors regression, random k-nearest neighbors regression, Multivariate Adaptive Regression Splines, averaged neural networks, and support vector machines with polynomial and radial kernels) was also compared with the performance of heterogeneous model ensembles constructed from the best models trained using particular techniques. The results proved that in case of sub-pixel evaluation the most accurate prediction of change may not necessarily be based on the most accurate individual assessments. When single methods are considered, based on obtained results Cubist algorithm may be advised for Landsat based mapping of imperviousness for single dates. However, Random Forest may be endorsed when the most reliable evaluation of imperviousness change is the primary goal. It gave lower accuracies for individual assessments, but better prediction of change due to more correlated errors of individual predictions. Heterogeneous model ensembles performed for individual time points assessments at least as well as the best individual models. In case of imperviousness change assessment the ensembles always outperformed single model approaches. It means that it is possible to improve the accuracy of sub-pixel imperviousness change assessment using ensembles of heterogeneous non-linear regression models.

Słowa kluczowe

EN

machine learning; model ensembles; sub-pixel classification; landsat

PL

zmiany klimatyczne; modelowanie hydrologiczne; las

• Wydawca: Komitet Geodezji PAN
• Czasopismo: Geodesy and Cartography
• Rocznik: 2016
• Tom: Vol. 65, no. 2
• Strony: 193--218
• Opis fizyczny: Bibliogr. 75 poz., rys., tab.

Twórcy

autor

Drzewiecki W.

• AGH University, Faculty of Mining Surveying and Environmental Engineering, Department of Geoinformation, Photogrammetry and Remote Sensing of Environment, al. Mickiewicza 30, 30-059 Kraków, Poland

Bibliografia

• [1] Arnold, C.L. Jr. and Gibbons, C.J. (1996). Impervious surface coverage: the emergence of a key environmental indicator. Journal of the American Planning Association, 62, 243–258.
• [2] Bauer, M.E., Heiner, N.J., Doyle, J.K. and Yuan, F. (2004). Impervious surface mapping and change monitoring using Landsat remote sensing. ASPRS Annual Conference Proc., unpaginated CD-ROM.
• [3] Bernat, K. and Drzewiecki W. (2014). Two-stage subpixel impervious surface coverage estimation: comparing classification and regression trees and artificial neural networks. In: Proc. SPIE Vol. 9244, 92441l, Image and Signal Processing for Remote Sensing. DOI: 10.1117/12.2067308.
• [4] Boser, B., Guyon, I. and Vapnik, V.A. (1992). Training Algorithm for Optimal Margin Classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 144–152.
• [5] Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
• [6] Breiman, L, Friedman, J.H., Olshen, R.A. and Stone, C.J. (1984). Classification and Regression Trees. CRC Press.
• [7] Caldwell, P.V., Sun, G., McNulty, S.G., Cohen, E.C. and Moore Myers, J.A. (2012). Impacts of impervious cover, water withdrawals, and climate change on river flows in the conterminous US, Hydrol. Earth Syst. Sci., 16, 2839–2857. DOI: 10.5194/hess-16-2839-2012.
• [8] Carreiras, J.M.B., Melo, J.B. and Vasconcelos, M.J. (2013). Estimating the Above-Ground Biomass in Miombo Savanna Woodlands (Mozambique, East Africa) Using L-Band Synthetic Aperture Radar Data. Remote Sens., 5, 1524-1548. DOI: 10.3390/rs5041524.
• [9] Chormański, J., Van de Voorde, T., De Roeck, T., Batelaan, O. and Canters, F. (2008). Improving distributed runoff prediction in urbanized catchments with remote sensing based estimates of impervious surface cover. Sensors, 8, 910–932.
• [10] Coelho, G.P. and Von Zuben, F.J. (2006). The influence of the pool of candidates on the performance of selection and combination techniques in ensembles. In: Proceedings of the International Joint Conference on Neural Networks, 10588–10595.
• [11] Dams, J., Dujardin, J., Reggers, R., Bashir, I., Canters, F. and Batelaan, O. (2013). Mapping impervious surface change from remote sensing for hydrological modeling. Journal of Hydrology, 485, 84–95. DOI: 10.1016/j.jhydrol.2012.09.045.
• [12] Deng, C. and Wu, C. (2012). BCI: A biophysical composition index for remote sensing of urban environments. Remote Sensing of Environment, 127, 247–259.
• [13] Deng, C. and Wu, C. (2013). The use of single-date MODIS imagery for estimating large-scale urban impervious surface fraction with spectral mixture analysis and machine learning techniques. ISPRS Journal of Photogrammetry and Remote Sensing, 86, 100–110. DOI: 10.1016/j.isprsjprs.2013.09.010.
• [14] Drzewiecki, W. (2016). Comparison of Selected Machine Learning Algorithms for Sub-Pixel Imperviousness Change Assessment. In: 2016 Baltic Geodetic Congress (Geomatics), 67–72. DOI: 10.1109/BGC.Geomatics.2016.21.
• [15] Dunn, O. J. (1961). Multiple comparisons among means. Journal of the American Statistical Association, 56, 293, 52–64.
• [16] Engler, R., Waser L.T., Zimmermann, N.E., Schaub, M., Berdos, S., Ginzler, C. and Psomas, A. (2013). Combining ensemble modeling and remote sensing for mapping individual tree species at high spatial resolution. Forest Ecology and Management, 310, 64–73. DOI: 10.1016/j.foreco.2013.07.059.
• [17] Esch, T., Conrad, C., Schorcht, G., Thiel, M. Wehrmann, T. and Dech, S. (2008). Model-based estimation of impervious surface by application of support vector machines. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XXXVII, Part B8, 41–44.
• [18] Eugster, M., Hothorn, T. and Leisch, F. (2008). Exploratory and Inferential Analysis of Benchmark Experiments. Ludwigs-Maximilians-Universität München, Department of Statistics, Tech. Rep, 30.
• [19] Fillipi, A.M., Güneralp, İ. and Randal, J. (2014). Hyperspectral remote sensing of aboveground biomass on a river meander bend using multivariate adaptive regression splines and stochastic gradient boosting. Remote Sensing Letters, 5, 5, 432–441. DOI: 10.1080/2150704X.2014.915070.
• [20] Freeman, E.A., Moisen, G.G., Coulston, J.W. and Wilson, B.T. (2016). Random forest and stochastic gradient boosting for predicting tree canopy cover: comparing tuning processes and model performance. Can. J. For. Res., 46, 323–339. DOI: 10.1139/cjfr-2014-0562.
• [21] Friedman, J. (1991). Multivariate Adaptive Regression Splines. The Annals of Statistics, 19(1), 1–141.
• [22] Friedman, J. (2002). Stochastic Gradient Boosting. Computational Statistics and Data Analysis, 38(4), 367–378.
• [23] Galeana-Pizaña, J.M., Núñez Hernández, J.M. and Romero, N.C. (2016). Remote Sensing-Based Biomass Estimation. In: M. Marghany (ed.), Environmental Applications of Remote Sensing, InTech, DOI: 10.5772/61813. Available online at: http://www.intechopen.com/books/environmental-applications-of-remote-sensing/remote-sensing-based-biomass-estimation.
• [24] García-Pedrajas, N., Hervás-Martínez, C. and Ortiz-Boyer, D. (2005). Cooperative coevolution of artificial neural network ensembles for pattern classification. IEEE Trans. Evolut. Comput., 9, 3, 271–302.
• [25] Gómez-Chova, L., Muñoz-Marí, J., Amorós-López, J., Izquierdo-Verdiguier, E. and Camps-Valls, G. (2013). Advances in synergy of AATSR-MERIS sensors for cloud detection. In: IEEE Int. Geos. Rem. Sensing Symposium (IGARSS) 2013, Jul 2013, pp. 4391–4394.
• [26] Güneralp, İ, Filippi, A.M. and Randall, J. (2014). Estimation of floodplain aboveground biomass using multispectral remote sensing and nonparametric modeling. International Journal of Applied Earth Observation and Geoinformation, 33, 119–126. DOI: 10.1016/j.jag.2014.05.004.
• [27] Hastie, T., Tibshirani, R. and Friedman, J. (2009). The Elements of Statistical Learning: Data Minig, Inference, and Prediction. Springer.
• [28] Heinermann, J. and Kramer, O. (2015). On heterogeneous machine learning ensembles for wind power prediction. In: Computational Sustainability: Papers from the 2015 AAAI Workshop, pp. 54–59.
• [29] Heremans, S. and Van Orshoven, J. (2015). Machine learning methods for sub-pixel land-cover classification in the spatially heterogeneous region of Flanders (Belgium): a multi-criteria comparison. International Journal of Remote Sensing, 36, 11, 2934–2962. DOI: 10.1080/01431161.2015.1054047.
• [30] Homer, C., Dewitz, J., Fry, J., Coan M., Hossain, N., Larson, C., Herold, N., McKerrow, A., Van Driel, J.N. and Wickham, J. (2007). Completion of the 2001 National Land Cover Database for the Conterminous United States. Photogrammetric Engineering and Remote Sensing, 73, 337–341.
• [31] Hothorn, T., Leisch F., Zeileis A. and Hornik K., (2005): The design and analysis of benchmark experiments. Journal of Computational and Graphical Statistics, 14, 3, 675–699.
• [32] Hussain, M., Chen, D., Cheng, A., Wei, H. and Stanley, D. (2013). Change detection from remotely sensed images: From pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, 80, 91–106. DOI: 10.1016/j.isprsjprs.2013.03.006.
• [33] Kew, W. and Mitchel, J.B.O. (2015). Greedy and linear ensembles of machine learning methods outperform single approaches for QPSR regression problems. Molecular Informatics, 34, 634–647.
• [34] Kircher, J. (2001). Data Analysis Toolkit #5: Uncertainty Analysis and Error Propagation. University of California Berkeley Seismological Laboratory. Available online at: http://seismo.berkeley.edu/~kirchner/eps_120/Toolkits/Toolkit_05.pdf.
• [35] Kuhn, M. (2008). Building Predictive Models in R Using the caret Package. Journal of Statistical Software, 28, 5, 1–26.
• [36] Kuhn, M. and Johnson K. (2013). Applied Predictive Modeling. Springer.
• [37] Lewiński, S. (2006). Rozpoznanie form pokrycia i użytkowania ziemi na zdjęciu satelitarnym Landsat ETM+ metodą klasyfikacji obiektowej. Roczniki Geomatyki, 4, 3, 139–150.
• [38] Li, L., Lu, D. and Kuang, W. (2016). Examining urban impervious surface distribution and its dynamic change in Hangzhou metropolis. Remote Sensing, 8, 3, 265. DOI: 10.3390/rs8030265.
• [39] Li, S., Harner, E.J. and Adjeroh, D.A. (2011): Random KNN feature selection – a fast and stable alternative to Random Forests. BMC Bioinformatics, 12:450.
• [40] Liu, W. and Wu E.Y. (2005): Comparison of non-linear mixture models: sub-pixel classification. Remote Sensing of Environment, 94, 145–154.
• [41] Lu, D., Li, G., Kuang, W. and Moran, E. (2014). Methods to extract impervious surface areas from satellite images. International Journal of Digital Earth, 7, 2, 93–112. DOI: 10.1080/17538947.2013.866173.
• [42] Lu, D., Li, G., Kuang, W. and Moran, E. (2014). Current situation and needs of change detection techiques. International journal of Image and Data Fusion, 5, 1, 13–38. DOI: 10.1080/19479832.2013.868372.
• [43] Mendes-Moreira, J., Soares, C., Jorge, A.M. and de Sousa, J.F. (2012). Ensamble approaches for regression: A survey. ACM Comp. Surv, 45, 1, Article 10.
• [44] Mohapatra, R.P. and Wu, C. (2010). High resolution impervious surface estimation: An integration of Ikonos and Landsat-7 ETM+ imagery. Photogrammetric Engineering and Remote Sensing, 76, 12, 1329–1341.
• [45] Morgan, M.G. and Henrion, M. (1990). Uncertainty: a guide to dealing with uncertainty in quantitative risk and policy analysis. Cambridge University Press.
• [46] Mountrakis, G., Watts R., Luo, L. and Wang, J. (2009). Developing collaborative classifiers using an expert-based model. Photogrammetric Engineering and Remote Sensing, 75, 7, 831–843.
• [47] Nawar, S., Buddenbaum, H., Hill, J. and Kozak, J. (2014). Modeling and Mapping of Soil Salinity with Reflectance Spectroscopy and Landsat Data Using Two Quantitative Methods (PLSR and MARS). Remote Sens., 6, 10813–10834. DOI: 10.3390/rs61110813.
• [48] Nawar, S., Buddenbaum, H. and Hill, J. (2015). Digital Mapping of Soil Properties Using Multivariate Statistical Analysis and ASTER Data in an Arid Region. Remote Sens., 7, 1181–1205. DOI: 10.3390/rs70201181.
• [49] Nielsen, N.H., Joergensen, A. and Larsen, A. (2011). Use of spectral analysis in urban drainage modelling. In: International Conference on Urban Drainage, 11–16 September 2011, Porto Alegre, Brazil. Available online at: https://web.sbe.hw.ac.uk/staffprofiles/bdgsa/temp/12th%20ICUD/PDF/PAP005251.pdf.
• [50] Partalas, I., Tsoumakas G., Hatzikos E.V. and Vlahavas I. (2008). Greeedy regression ensemble selection: Theory and application to water quality prediction. Information Sciences, 178, 3867–3879.
• [51] Perrone, M.P. and Cooper L.N. (1993). When networks disagree: Ensemble methods for hybrid neural networks. In: R. Mammone (ed.), Neural Networks for Speech and Image Processing. Chapman-Hall.
• [52] Qi, H. and Huang, M. (2007). Research on SVM ensemble and its application to remote sensing classification. In: Proceedings of the International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007), DOI: 10.2991/iske.2007.102.
• [53] Qian, Y., Zhou, W., Yan, J., Li, W. and Han, L. (2015). Comparing Machine Learning Classifiers for Object-Based Land Cover Classification Using Very High Resolution Imagery. Remote Sensing, 7, 153–168. DOI: 10.3390/rs70100153.
• [54] Quinlan, R. (1993). Combining instance–based and model–based learning. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 236–243.
• [55] Ridd, M.K. (1995). Exploring a V-I-S (vegetation-impervious surface-soil) model for urban ecosystem analysis through remote sensing: Comparative anatomy for cities. Int. J. Remote Sens., 16, 2165–2185.
• [56] Ripley, B. (1996). Pattern Recognition and Neural Networks. Cambridge University Press.
• [57] Rooney, N., Patterson, D., Anand, S. and Tsymbal, A. (2004). Dynamic integration of regression models. In: Proceedings of the International Workshop on Multiple Classifier Systems. Lecture Notes in Computer Science, vol. 3181. Springer, pp. 164–173.
• [58] Shahtahmassebi, A.R., Song, J., Zheng, Q., Blackburn, G.A., Wang, K., Huang, L.Y., Pan, Y., Moore, N., Shahtahmassebi, G., Haghighi, R.S. and Deng, J.S. (2016). Remote sensing of impervious surface growth: A framework for quantifying urban expansion and re-densification mechanisms. International Journal of Applied Earth Observation and Geoinformation, 46, 94–112. DOI: 10.1016/j.jag.2015.11.007.
• [59] Shao, Y. and Lunetta, R.S. (2011). Sub-pixel mapping of tree canopy, impervious surfaces, and cropland in the Laurentian Great Lakes Basin using MODIS time-series data. IEEE Journal of Selected Topics in Applied Earth Observation and Remote Sensing, 4, 2, 336–347. DOI: 10.1109/JSTARS.2010.2062173.
• [60] Smola, A.J. and Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14, 199–222.
• [61] Sun, H., Qie, G., Wang, G., Tan, Y., Li, J., Peng, Y., Ma, Z. and Luo, C. (2015). Increasing the accuracy of mapping urban forest carbon density by combining spatial modeling and spectral unmixing analysis, Remote Sensing, 7, 15114–15139. DOI: 10.3390/rs71115114.
• [62] Tewkesbury, A.P., Comber, A.J., Tate, N.J., Lamb, A. and Fisher, P.F. (2015). A critical synthesis of remotely sensed optical image change detection techniques. Remote Sensing of Environment, 160, 1–14. DOI: 10.1016/j.rse.2015.01.006.
• [63] Tokarczyk, P., Leitao, J.P., Rieckermann, J., Schindler, K. and Blumensaat, F. (2015). High-quality observation of surface imperviousness for urban runoff modelling using UAV imagery. Hydrol. Earth Syst. Sci., 19, 4215–4228.
• [64] Tsutsumida, N., Comber, A., Barret, K., Saizen, I. and Rustiadi, E. (2016). Sub-pixel classification of MODIS EVI for annual mappings of impervious surface areas. Remote Sensing, 8, 143. DOI: 10.3390/rs8020143.
• [65] Turner, II B.L. and Meyer, W.B. (1994). Global Land Use and Land Cover Change: An Overview. In: Meyer W.B. and Turner II B.L. (eds.), Changes in Land Use and Land Cover: A Global Perspective. Cambridge University Press, pp. 3–10.
• [66] Vapnik, V. (2010). The Nature of Statistical Learning Theory. Springer.
• [67] Vapnik, V., and Chervonenkis, A. (1971): On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appl., 16, 264–280.
• [68] Walton, J.T. (2008). Subpixel urban land cover estimation: comparing Cubist, Random Forest and Support Vector Regression. Photogrammetric Engineering and Remote Sensing, 75, 10, 1213–1222.
• [69] Weng, Q. (2012). Remote sensing of impervious surface in the urban areas: Requirements, methods and trends. Remote Sensing of Environment, 117, 34–49.
• [70] Wężyk, P., Hawryło P., Szostak, M., Pierzchalski, M. and de Kok, R. (2016). Using geobia and data fusion approach for land use and land cover mapping. Quaestiones Geographicae, 35, 1, 93–104.
• [71] Wichard, J., Merkwirth, C. and Ogorzałek, M. (2003). Building ensembles with heterogeneous models. In: Course of the International School on Neural Nets, IIASS, 22–28 Sep. 2002, Salerno, Italy. Available online at: http://www.j-wichard.de/publications/salerno_lncs_2003.pdf.
• [72] Xi, C., Jiancheng L., Zhanfeng, S., Changming, Z., Xin, Z. and Liegang, X. (2011). Estimation of impervious surface based on integrated analysis of classification and regression by using SVM. In: Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International, pp. 2809–2812.
• [73] Xu, H. (2006). Modification of normalized difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27, 14, 3025–2033.
• [74] Yang, L., Xian, G., Klaver, J. M. and Deal, B. (2003). Urban land-cover change detection through sub-pixel imperviousness mapping using remotely sensed data. Photogrammetric Engineering and Remote Sensing, 69, 9, 1003–1010.
• [75] Zhang, J. (2010). Multi-source remote sensing data fusion: status and trends. International Journal of Image and Data Fusion, 1, 1, 5–24.