Stochastic gradient boosting for urban change detection using multi-temporal LANDSAT-5TM in Yogyakarta, Indonesia
PDF

Keywords

Digital number
Histogram matching
Image classification

Abstract

Despite available remote sensing data, technical challenges in developing countries have hindered local urban authorities from updating periodic land cover maps. Therefore, this study proposed a practical approach for regions with insufficient ground truth data. The study implemented a machine learning algorithm using single date medium spatial resolution data to build a classifier for separating Urban and Non-Urban zones. Then, the classifier was employed on multiple dates in 1999, 2005, and 2011 to corroborate its robustness. Results showed the stochastic gradient boosting (SGB) algorithm succeeded in building a robust classifier using the digital number value of LANDSAT-5TM 2005 with an overall accuracy of 0.76 and an area under curve receiver operator characteristic (AUC-ROC) value of 0.83. Moreover, the classifier predicted that urban areas in Yogyakarta, Indonesia, reached 24,099 (hectares) ha; 26,598 ha; and 22,650 ha in 1999, 2005, and 2011, respectively. The classifier's performance in predicting multiple datasets combined with histogram matching of medium spatial resolution data showed satisfactory results comparable to reference data from Statistics Indonesia, indicating sufficient accuracy for areal-integrated multi-temporal urbanization monitoring.

https://doi.org/10.29037/ajstd.961
PDF

References

Afaq Y, Manocha A. 2021. Analysis on change detection techniques for remote sensing applications: A review. Ecological Informatics. 63:101310. doi:10.1016/j.ecoinf.2021.101310.

Alam M. 2020. Data normalization in machine learning. Towards Data Science. https://towardsdatascience.com/data-normalization-in-machine-learning-395fdec69d02.

Alawamy JS, Balasundram SK, Mohd. Hanif AH, Boon Sung CT. 2020. Detecting and Analyzing Land Use and Land Cover Changes in the Region of Al-Jabal Al-Akhdar, Libya Using Time-Series Landsat Data from 1985 to 2017. Sustainability. 12(11):4490. doi:10.3390/su12114490.

Brownlee J. 2014. Classification Accuracy is Not Enough: More Performance Measures You Can Use. Machine Learning Mastery. https://machinelearningmastery.com/classification-accuracy-is-not-enough-more-performance-measures-you-can-use/.

Brownlee J. 2020. Nested Cross-Validation for Machine Learning with Python. Machine Learning Mastery. https://machinelearningmastery.com/nested-cross-validation-for-machine-learning-with-python.

Chen Y. 2018. Improved relative radiometric normalization method of remote sensing images for change detection. Journal of Applied Remote Sensing. 12(04):1. doi:10.1117/1.JRS.12.045018.

Cochrane C. 2018. Time Series Nested Cross-Validation. Towards Data Science. https://towardsdatascience.com/time-series-nested-cross-validation-76adba623eb9.

DeFries RS, Chan JC-W. 2000. Multiple Criteria for Evaluating Machine Learning Algorithms for Land Cover Classification from Satellite Data. Remote Sensing of Environment. 74(3):503–515. doi:https://doi.org/10.1016/S0034-4257(00)00142-5.

Dubé J, Legros D. 2014. Spatial Autocorrelation. In: Spatial Econometrics Using Microdata. Hoboken, NJ, USA: John Wiley & Sons, Inc. p. 59–91. [accessed 2022 Dec 21]. https://onlinelibrary.wiley.com/doi/10.1002/9781119008651.ch3.

Friedman JH. 2002. Stochastic gradient boosting. Computational Statistics & Data Analysis. 38(4):367–378. doi:10.1016/S0167-9473(01)00065-2.

Geneletti D, La Rosa D, Spyra M, Cortinovis C. 2017. A review of approaches and challenges for sustainable planning in urban peripheries. Landscape and Urban Planning. 165:231–243. doi:10.1016/j.landurbplan.2017.01.013.

Gutierrez DD. 2015. Machine learning and data science: an introduction to statistical learning methods with R. First edition. Basking Ridge, NJ: Technics Publications.

Hansen C. 2019. Nested Cross-Validation Python Code. Machine Learning From Scratch. https://mlfromscratch.com/nested-cross-validation-python-code/#/.

Heydari SS, Mountrakis G. 2018. Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 Landsat sites. Remote Sensing of Environment. 204:648–658. doi:10.1016/j.rse.2017.09.035.

Hongsheng Zhang, Hui Lin, Yu Li. 2015. Impacts of Feature Normalization on Optical and SAR Data Fusion for Land Use/Land Cover Classification. IEEE Geoscience and Remote Sensing Letters. 12(5):1061–1065. doi:10.1109/LGRS.2014.2377722.

Hu W, Xie N, Hu R, Ling H, Chen Q, Yan S, Maybank S. 2014. Bin Ratio-Based Histogram Distances and Their Application to Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 36(12):2338–2352. doi:10.1109/TPAMI.2014.2327975.

Huriati N. 2008. Urban Fringe Area Development in Yogyakarta City 1992-2006 [PhD Thesis]. Universitas Indonesia. http://lib.ui.ac.id/file?file=digital/122959-S34156-Noni Huriati.pdf.

Jones JW, Starbuck MJ, Jenkerson CB. 2013. Landsat surface reflectance quality assurance extraction (version 1.7). Reston, VA Report No.: 11-C7. http://pubs.er.usgs.gov/publication/tm11C7.

Lawrence R. 2004. Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis. Remote Sensing of Environment. 90(3):331–336. doi:10.1016/j.rse.2004.01.007.

li W, Liu Z. 2011. A method of SVM with Normalization in Intrusion Detection. Procedia Environmental Sciences. 11:256–262. doi:10.1016/j.proenv.2011.12.040.

Lillesand TM, Kiefer RW, Chipman JW. 2015. Remote sensing and image interpretation. Seventh edition. Hoboken, N.J: John Wiley & Sons, Inc.

Lin L, Yue W, Mao Y. 2014. Multi-class image classification based on fast stochastic gradient boosting. Informatica. 38(3).

Mishra S, Shrivastava P, Maulana Azad National Institute of Technology Bhopal, Dhurvey P, Maulana Azad National Institute of Technology, Bhopal, India. 2017. Change Detection Techniques in Remote Sensing: A Review. International Journal of Wireless and Mobile Communication for Industrial Systems. 4(1):1–8. doi:10.21742/ijwmcis.2017.4.1.01.

Najamudin I. 2017. Flight Safety Case Study?: Adi Sucipto Airport Jogjakarta-Indonesia. International Refereed Journal of Engineering and Science (IRJES). 6(8):29. doi:10.183x/C6811932.

Richards JA. 2013. Remote sensing digital image analysis: an introduction. Fifth edition. Berlin: Springer.

Roy DP, Kovalskyy V, Zhang HK, Vermote EF, Yan L, Kumar SS, Egorov A. 2016. Characterization of Landsat-7 to Landsat-8 reflective wavelength and normalized difference vegetation index continuity. Remote Sensing of Environment. 185:57–70. doi:10.1016/j.rse.2015.12.024.

Saah D, Tenneson K, Matin M, Uddin K, Cutter P, Poortinga A, Nguyen QH, Patterson M, Johnson G, Markert K, et al. 2019. Land Cover Mapping in Data Scarce Environments: Challenges and Opportunities. Frontiers in Environmental Science. 7:150. doi:10.3389/fenvs.2019.00150.

Saito T, Rehmsmeier M. 2015. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. Brock G, editor. PLOS ONE. 10(3):e0118432. doi:10.1371/journal.pone.0118432.

Salazar JJ, Garland L, Ochoa J, Pyrcz MJ. 2022. Fair train-test split in machine learning: Mitigating spatial autocorrelation for improved prediction accuracy. Journal of Petroleum Science and Engineering. 209:109885. doi:10.1016/j.petrol.2021.109885.

Sandler AM, Rashford BS. 2018. Misclassification error in satellite imagery data: Implications for empirical land-use models. Land Use Policy. 75:530–537. doi:10.1016/j.landusepol.2018.04.008.

Schneider A, Mertes CM, Tatem AJ, Tan B, Sulla-Menashe D, Graves SJ, Patel NN, Horton JA, Gaughan AE, Rollo JT, et al. 2015. A new urban landscape in East–Southeast Asia, 2000–2010. Environmental Research Letters. 10(3):034002. doi:10.1088/1748-9326/10/3/034002.

Selang MA, Iskandar DA, Widodo R. 2018. Tingkat Perkembangan Urbanisasi Spasial Di Pinggiran KPY (Kawasan Perkotaan Yogyakarta) Tahun 2012-2016. In: Seminar Nasional Kota Layak Huni "Urbanisasi dan pengembangan Perkotaan. p. 32–40. https://trijurnal.trisakti.ac.id/index.php/lslivas/article/view/2741/2367.

Seo DK, Eo YD. 2019. Local-Based Iterative Histogram Matching for Relative Radiometric Normalization. Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography. 37(5):323–330. doi:10.7848/KSGPC.2019.37.5.323.

Smith A, Jones B, Anderson C. 2000. Example title of a journal article. ASEAN J Sci Technol Dev. 12(3):1–10. doi:10.29037/ajstd.123.

Universitas Islam Indonesia. 2017. Tata Ruang Kampus UII: “The Colours of Nature.” Universitas Islam Indonesia. https://www.uii.ac.id/lingkungan-keberlanjutan/.

Vorovencii I, Muntean MD. 2014. Relative radiometric normalization methods: overview and an application to Landsat images. Journal of Geodesy and Cadastre, RevCAD. 17(January):193–200.

Widyatmoko MR. 2007. Proses Urbanisasi Perdesaan di Daerah Istimewa Yogyakarta dan Urbanisasi di Indonesia yang Melatarbelakanginya [PhD Thesis]. University of Gadjah Mada. http://etd.repository.ugm.ac.id/home/detail_pencarian/36384.

Yang W, Xu L, Chen X, Zheng F, Liu Y. 2015. Chi-Squared Distance Metric Learning for Histogram Data. Mathematical Problems in Engineering. 2015:1–12. doi:10.1155/2015/352849.

Zanter K. 2017. Landsat Collection 1 Level 1 Product Definition. Department of the Interior, US Geological Survey. https://www.usgs.gov/media/files/landsat-collection-1-level-1-product-definition.

Zou Q, Xie S, Lin Z, Wu M, Ju Y. 2016. Finding the Best Classification Threshold in Imbalanced Classification. Big Data Research. 5:2–8. doi:10.1016/j.bdr.2015.12.001.

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright (c) 2022 The Author(s)

Downloads

Download data is not yet available.