Implementing Random Forest Algorithm in GEE: Separation and Transferability on Built-Up Area in Central Java, Indonesia

Aninda W. Rudiastuti - National Research and Innovation Agency of Indonesia, Cibinong, 16911, Indonesia
Yustisi Lumban-Gaol - National Research and Innovation Agency of Indonesia, Cibinong, 16911, Indonesia
Florence E. S. Silalahi - National Research and Innovation Agency of Indonesia, Cibinong, 16911, Indonesia
Yosef Prihanto - National Research and Innovation Agency of Indonesia, Cibinong, 16911, Indonesia
Widodo S. Pranowo - Marine and Coastal Data Laboratory, Research & Development Center for Marine & Coastal Resources, North Jakarta, 14430, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.6.1.873

Abstract


Measuring the status of achievement of the SDGs is the task and concern of many countries in the world, including Indonesia. Indicators for achieving the SDGs enclose three main pillars, namely environmental, economic, and social. The updated land use/land cover information is needed for environmental pillars. One imperative land cover information is built-up land, which acts as a detector for expanding urban areas and measuring SDGs' target indicators. Indonesia's cultural diversity affects the distribution pattern of built-up land, especially settlements. This is a challenge in the up-to-date and rapid mapping of built-up land. This research aims to analyze the ability and transferability of the Random Forest model for built-up areas and settlements using Google Earth Engine (GEE) in Banyumas, Cilacap, and Tegal. Around 19 predictors from multi-sources satellites are integrated to identify four land cover classes. Discussion on predictor composition to improve model accuracy also carried on. The results showed that the algorithm separated four land cover classes, with the highest accuracy for separating water bodies and other classes (vegetation and open land), OA above 90%. Machine confusion regarding the separation between housing classes and other buildings was still found (F1 score 0.67 - 0.69). Applying the model to the other two areas resulted in a similar statistical trend to the trained model. However, the classification method developed in this paper can assist in the rapid description of land cover if up-to-date data from official sources are not available.

Keywords


Random forest; machine learning; Google Earth Engine (GEE); settlement; sentinel; Land Use/Land Cover (LULC).

Full Text:

PDF

References


Ministry of National Development Planning/ National Development Planning Agency, Metadata Indikator Tujuan Pembangunan Berkelanjutan (TPB)/ Sustainable Development Goals (SDGs) Indonesia - Pilar Pembangunan Lingkungan, 2nd ed. 2020.

G. Rousset, M. Despinoy, K. Schindler, and M. Mangeas, "Assessment of deep learning techniques for land use land cover classification in southern new Caledonia," Remote Sens., 2021, doi: 10.3390/rs13122257.

Kiswanto, S. Tsuyuki, Mardiany, and Sumaryono, "Completing yearly land cover maps for accurately describing annual changes of tropical landscapes," Glob. Ecol. Conserv., vol. 13, p. e00384, 2018, doi: 10.1016/j.gecco.2018.e00384.

H. Schubert, M. Rauchecker, A. C. Calvo, and B. Schütt, "Land use changes and their perception in the Hinterland of Barranquilla, Colombian Caribbean," Sustain., vol. 11, no. 23, pp. 1–21, 2019, doi: 10.3390/su11236729.

P. S. Roy et al., "Development of decadal (1985-1995-2005) land use and land cover database for India," Remote Sens., vol. 7, no. 3, pp. 2401–2430, 2015, doi: 10.3390/rs70302401.

E. B. Silva et al., "A Definition of Visual Interpretation Criterias to Mapping Land-Use and Land-Cover in the Brazilian Biomes," 2020 IEEE Lat. Am. GRSS ISPRS Remote Sens. Conf. LAGIRS 2020 - Proc., vol. XLII, no. March, pp. 173–176, 2020, doi: 10.1109/LAGIRS48042.2020.9165577.

G. Zhao and M. Yang, "Urban Population Distribution Mapping with Multisource Geospatial Data Based on Zonal Strategy," ISPRS Int. J. Geo-Information, vol. 9, no. 11, p. 654, 2020, doi: 10.3390/ijgi9110654.

D. H. Bui and L. Mucsi, "From land cover map to land use map: A combined pixel-based and object-based approach using multi-temporal landsat data, a random forest classifier, and decision rules," Remote Sens., vol. 13, no. 9, 2021, doi: 10.3390/rs13091700.

J. T. Nugroho,.Zylshal, N. M. Sari, and D. Kushardono, "A Comparison of Object-based and Pixel-based Approaches for Land Use/Land Cover Classification Using Lapan-A2 Microsatellite Data," Int. J. Remote Sens. Earth Sci., 2017, doi: 10.30536/j.ijreses.2017.v14.a2680.

A. Sekertekin, A. M. Marangoz, and H. Akcin, "Pixel-based classification analysis of land use land cover using Sentinel-2 and Landsat-8 data," in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 2017, doi: 10.5194/isprs-archives-XLII-4-W6-91-2017.

J. Ai, C. Zhang, L. Chen, and D. Li, "Mapping annual land use and land cover changes in the Yangtze Estuary Region using an object-based classification framework and landsat time series data," Sustain., vol. 12, no. 2, 2020, doi: 10.3390/su12020659.

N. Bashit, N. Sari Ristianti, Y. Eko Windarto, and D. Ulfiana, "The Mapping of Land Use Using Object-Based Image Analysis (OBIA) in Klaten Regency," E3S Web Conf., vol. 202, pp. 1–9, 2020, doi: 10.1051/e3sconf/202020206036.

H. Costa, G. M. Foody, and D. S. Boyd, "Supervised methods of image segmentation accuracy assessment in land cover mapping," Remote Sens. Environ., vol. 205, no. November 2017, pp. 338–351, 2018, doi: 10.1016/j.rse.2017.11.024.

P. Helber, B. Bischke, A. Dengel, and D. Borth, "Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 2019, doi: 10.1109/JSTARS.2019.2918242.

A. Vali, S. Comai, and M. Matteucci, "Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: A review," Remote Sensing. 2020, doi: 10.3390/RS12152495.

X. Liao, X. Huang, and W. Huang, "ML-LUM: A system for land use mapping by machine learning algorithms," J. Comput. Lang., vol. 54, no. February, 2019, doi: 10.1016/j.cola.2019.100908.

W. Mao, D. Lu, L. Hou, X. Liu, and W. Yue, "Comparison of machine-learning methods for urban land-use mapping in hangzhou city, china," Remote Sens., 2020, doi: 10.3390/rs12172817.

H. chien Shih, D. A. Stow, and Y. H. Tsai, "Guidance on and comparison of machine learning classifiers for Landsat-based land cover and land use mapping," Int. J. Remote Sens., 2019, doi: 10.1080/01431161.2018.1524179.

Y. H. Tsai, D. Stow, H. L. Chen, R. Lewison, L. An, and L. Shi, "Mapping vegetation and land use types in Fanjingshan National Nature Reserve using google earth engine," Remote Sens., 2018, doi: 10.3390/rs10060927.

I. Prasetyo, W. S. Pranowo, C. L. Tobing, A. Kurniawan, and T. Puliwarna, “Analisis Mangrove dari Citra Satelit sebagai Pertahanan Pantai dengan Menggunakan Pendekatan Cloud Computing,†J. Chart Datum, vol. 7, no. 1, pp. 47–62, 2021, doi: https://doi.org/10.37875/chartdatum.v7i1.189.

H. Shafizadeh-Moghadam, M. Khazaei, S. K. Alavipanah, and Q. Weng, "Google Earth Engine for large-scale land use and land cover mapping: an object-based classification approach using spectral, textural and topographical factors," GIScience Remote Sens., vol. 58, no. 6, pp. 914–928, 2021, doi: 10.1080/15481603.2021.1947623.

J. Camilo Fagua and R. Douglas Ramsey, "Geospatial modeling of land cover change in the Chocó-Darien global ecoregion of South America; One of most biodiverse and rainy areas in the world," PLoS One, 2019, doi: 10.1371/journal.pone.0211324.

P. Han, Q. Zhang, Y. Zhao, and F. Y. Li, "High-resolution remote sensing data can predict household poverty in pastoral areas, Inner Mongolia, China," Geogr. Sustain., vol. 2, no. 4, pp. 254–263, 2021, doi: 10.1016/j.geosus.2021.10.002.

B. Ghansah, C. Nyamekye, S. Owusu, and E. Agyapong, "Mapping flood-prone and Hazards Areas in rural landscape using Landsat images and random forest classification: A case study of Nasia watershed in Ghana," Cogent Eng., vol. 8, no. 1, 2021, doi: 10.1080/23311916.2021.1923384.

S. e. hyde. Soomro et al., "Mapping flood extend and its impact on land use/land cover and settlements variations: a case study of Layyah District, Punjab, Pakistan," Acta Geophys., 2021, doi: 10.1007/s11600-021-00677-4.

T. N. Widodo, H. Zubair, and R. Padjung, "Land use change study and the increased risk of floods disaster in Jeneberang watershed at Gowa Regency, South Sulawesi, Indonesia," IOP Conf. Ser. Earth Environ. Sci., vol. 824, no. 1, 2021, doi: 10.1088/1755-1315/824/1/012045.

A. Rudiastuti, N. M. Farda, and D. Ramdani, "Mapping built-up land and settlements: a comparison of machine learning algorithms in Google Earth engine," in Proc. SPIE 12082, Seventh Geoinformation Science Symposium 2021, 2021, vol. 1208206, no. December 2021, p. 47, doi: 10.1117/12.2619493.

H. Ji, X. Li, X. Wei, W. Liu, L. Zhang, and L. Wang, "Mapping 10-m Resolution Rural Settlements Using Multi-Source Remote Sensing Datasets with the Google Earth Engine Platform," 2020.

X. Zhang et al., "Development of a global 30-m impervious surface map using multi-source and multi-temporal remote sensing datasets with the Google Earth Engine platform," Earth Syst. Sci. Data Discuss., 2020, doi: 10.5194/essd-2019-200.

A. Al Kafy et al., "Remote sensing approach to simulate the land use/land cover and seasonal land surface temperature change using machine learning algorithms in a fastest-growing megacity of Bangladesh," Remote Sens. Appl. Soc. Environ., vol. 21, no. August 2020, p. 100463, 2021, doi: 10.1016/j.rsase.2020.100463.

Z. Sun et al., "A review of Earth Artificial Intelligence," Comput. Geosci., vol. 159, no. August 2021, p. 105034, 2022, doi: 10.1016/j.cageo.2022.105034.

P. E. Osgouei, S. Kaya, E. Sertel, and U. Alganci, "Separating built-up areas from bare land in mediterranean cities using Sentinel-2A imagery," Remote Sens., vol. 11, no. 3, 2019, doi: 10.3390/rs11030345.

A. Yong and X. Bin, "Information Extraction of Urban Expansion Based on Remote Sensing A case of Jinghui irrigation district in Shaanxi Province, China," Water Resour. Environ. Prot., no. 4, pp. 2683–2686, 2011.

T. Yugang, X. U. Yun, and Y. Xiaonan, “Perpendicular impervious index for remote sensing of multiple impervious surface extraction in cities,†Acta Geod. Cartogr. Sin., vol. 46, no. 4, p. 468, 2017.

M. Yuhe, Z. Mudan, Z. Peng, and W. Jian, "Comparison of Impervious Surface Extraction Index Based on Two Kinds of Satellite Sensors," Spacecr. Recover. Remote Sens., vol. 42, no. 2, pp. 139–151, 2021, doi: 10.3969/j.issn.1009-8518.2021.02.016.

Y. Zheng, L. Tang, and H. Wanga, "An improved approach for monitoring urban built-up areas by combining NPP-VIIRS night-time light, NDVI, NDWI, and NDBI," J. Clean. Prod., vol. 328, 2021, doi: 10.1016/j.jclepro.2021.129488.

I. N. Hidayati, R. Suharyadi, and P. Danoedoro, "Developing an Extraction Method of Urban Built-Up Area Based on Remote Sensing Imagery Transformation Index," Forum Geogr., vol. 32, no. 1, pp. 96–108, 2018, doi: 10.23917/forgeo.v32i1.5907.

F. Puturuhu, P. Danoedoro, J. Sartohadi, and D. Srihadmoko, "The Development of Interpretataion Method For Remote Sensing Imagery In Determining The Candidate of Landslide In Leitimur Paninsula, Ambon Island," J. Ilmu Lingkung., vol. 15, no. 1, p. 20, 2017, doi: 10.14710/jil.15.1.20-34.

Y. Zheng, L. Tang, and H. Wang, "An improved approach for monitoring urban built-up areas by combining NPP-VIIRS night-time light, NDVI, NDWI, and NDBI," J. Clean. Prod., vol. 328, p. 129488, 2021, doi: 10.1016/j.jclepro.2021.129488.

Q. Zhang, C. Schaaf, and K. C. Seto, "The Vegetation adjusted NTL Urban Index: A new approach to reduce saturation and increase variation in night-time luminosity," Remote Sens. Environ., vol. 129, pp. 32–41, 2013, doi: 10.1016/j.rse.2012.10.022.

L. Pasqualini and M. Parton, "Pseudo Random Number Generation: A Reinforcement Learning approach," Procedia Comput. Sci., vol. 170, no. 2019, pp. 1122–1127, 2020, doi: 10.1016/j.procs.2020.03.057.

S. Guha and H. Govil, "Land surface temperature and normalized difference vegetation index relationship: a seasonal study on a tropical city," SN Appl. Sci., vol. 2, no. 10, pp. 1–14, 2020, doi: 10.1007/s42452-020-03458-8.

P. Gong, X. Li, and W. Zhang, "40-Year ( 1978 – 2017 ) human settlement changes in China reflected by impervious surfaces from satellite remote sensing," Sci. Bull., vol. 64, no. 11, pp. 756–763, 2019, doi: 10.1016/j.scib.2019.04.024.