Peningkatan Resolusi Spasial Suhu Permukaan Daratan (Lst)  Menggunakan Fusi Data Sentinel-2 dan Landsat di Surakarta

Ardia Tiara Rahmi; Pipit  Wijayanti; Imasti  Dhani Pratiwi

doi:10.36418/syntax-literate.v10i12.63477

Ardia Tiara Rahmi Universitas Sebelas Maret
Pipit Wijayanti Universitas Sebelas Maret
Imasti Dhani Pratiwi Universitas Sebelas Maret

DOI: https://doi.org/10.36418/syntax-literate.v10i12.63477

Keywords: Suhu Permukaan Daratan (LST), Resolusi Spasial Tinggi, Sentinel-2,, Surakarta, Urban Heat Island, Google Earth Engine, Random Forest, Downscaling, Validasi Lapangan

Abstract

Suhu Permukaan Daratan (LST) merupakan parameter biofisik esensial yang krusial untuk berbagai aplikasi dalam ilmu bumi, termasuk studi iklim mikro, hidrologi, dan ekologi perkotaan. Di Kota Surakarta, sebagai salah satu pusat perkotaan yang berkembang di Jawa Tengah, pemahaman tentang distribusi LST resolusi tinggi sangat vital untuk mitigasi efek pulau panas perkotaan (UHI) dan perencanaan kota yang berkelanjutan. Meskipun data LST dari satelit seperti Landsat TIRS telah tersedia, resolusi spasial 30 meter atau 100 meter seringkali tidak memadai untuk analisis detail pada skala lokal yang heterogen seperti lingkungan perkotaan Surakarta. Penelitian ini mengembangkan metode downscaling LST menjadi resolusi spasial 10 meter menggunakan pendekatan berbasis pembelajaran mesin dengan algoritma Random Forest, diimplementasikan dalam platform komputasi awan Google Earth Engine(GEE). Data Landsat LST digunakan sebagai variabel dependen (label), sementara fitur-fitur prediktor diekstraksi dari citra multispektral Sentinel-2 (band spektral dan indeks turunan) dan data ketinggian Digital Elevation Model (DEM) dari SRTM. Proses pemilihan fitur dilakukan secara cermat berdasarkan koefisien determinasi (R^2) individual terhadap LST dan analisis matriks korelasi antar fitur untuk meminimalkan redundansi. Model dilatih menggunakan tiga fitur terpilih: B8 (Near-Infrared) dari Sentinel-2, serta variabel dryness dan greenness yang diturunkan, yang terbukti memiliki kepentingan relatif yang seimbang dalam menghasilkan metrik kinerja model. Hasil validasi model internal menunjukkan kinerja yang kuat dengan koefisien determinasi (R^2) sebesar 0.6187 dan Mean Absolute Error (MAE) sebesar 0.8312 Celcius. Untuk validasi eksternal, pengukuran suhu permukaan lapangan dilakukan di 60 titik sampel di Kota Surakarta pada periode yang sama. Perbandingan data LST prediksi model dengan data lapangan menunjukkan Root Mean Square Error (RMSE) sebesar 1.05 Celcius, MAE 0.88 Celcius, dan R^20.75, yang mengkonfirmasi akurasi dan presisi model. Peta LST 10 meter yang dihasilkan berhasil menggambarkan variasi spasial suhu permukaan dengan detail signifikan di Kota Surakarta, memungkinkan identifikasi fenomena termal mikro seperti pulau panas perkotaan pada skala yang sebelumnya sulit dicapai. Penelitian ini berkontribusi substansial pada penyediaan data LST beresolusi tinggi yang akurat untuk mendukung analisis lingkungan yang lebih mendalam dan pengambilan keputusan yang lebih tepat di Kota Surakarta.

Downloads

Download data is not yet available.

References

Ariyni, D. N., Buchori, I., & Kholid, N. (2018). Analisis Perubahan Suhu Permukaan Berbasis Citra Satelit Landsat di Kota Surakarta Tahun 2008 dan 2018. Jurnal Geografi: Media Informasi Pengembangan dan Profesi Kegeografian, 15(1), 1-13.
Atzberger, C., & Eitzinger, J. (2012). An overview of remote sensing methods for land surface temperature downscaling: A review. Remote Sensing, 4(12), 3290-3305.
BPS Kota Surakarta. (2023). Kota Surakarta Dalam Angka 2023. Badan Pusat Statistik Kota Surakarta.
Burrough, P. A., & McDonnell, R. A. (1998). Principles of Geographical Information Systems. Oxford University Press.
Carlson, T. N., & Ripley, D. A. (1997). On the relation between NDVI, fractional vegetation cover, and leaf area index. Remote Sensing of Environment, 62(3), 241-252.
Chen, Y., Yang, S., Yang, C., Yuan, J., Jiang, S., Ma, J., ... & Chen, X. (2020). Improving land surface temperature retrieval by machine learning: A review. Remote Sensing, 12(19), 3236.
Dormann, C. F., Elith, J., Bacher, S., Buchmann, C., Carl, G., Carr�, G., ... & Lautenbach, S. (2013). Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography, 36(1), 27-46.
Dronova, I., Gong, P., & Wang, Q. (2011). Mapping land cover and its change in a coastal wetland using multi-temporal SPOT-5 images and object-based classification. Remote Sensing of Environment, 115(2), 401-409.
Farr, T. G., Rosen, P. A., Caro, E., Crippen, R., Duren, R., Hensley, S., ... & Alsdorf, D. (2007). The Shuttle Radar Topography Mission. Reviews of Geophysics, 45(2).
Fauzi, R., Kurniawan, M. A., & Harjanto, Y. (2021). Analisis Suhu Permukaan Lahan (LST) dan Indeks Vegetasi (NDVI) di Kota Bandung Menggunakan Citra Landsat 8. Jurnal Ilmu Komputer dan Lingkungan, 1(2), 99-106.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189-1232.
Gao, B. C. (1996). NDWI�A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment, 58(3), 257-266.
Gao, Y., Ma, Y., Hu, C., Li, X., & Li, Z. L. (2020). A comprehensive review of land surface temperature retrieval algorithms and applications. Remote Sensing of Environment, 236, 111404.
Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random Forests for land cover classification. Pattern Recognition Letters, 27(4), 294-300.
Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., & Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, 18-27.
Guo, H., Cai, X. M., & Yu, W. (2012). Estimation of land surface temperature from Landsat ETM+ data and its relationship with land cover types in the Urban Agglomeration around Hangzhou Bay. Journal of Coastal Research, 28(6), 1629-1639.
Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2010). Multivariate Data Analysis (7th ed.). Prentice Hall.
Handayani, E. P., Wikantika, K., & Gumilar, I. (2019). Pemetaan Urban Heat Island Menggunakan Google Earth Engine(Studi Kasus: Kota Bandung). Jurnal Penginderaan Jauh, 16(2), 107-118.
Imamoglu, M. O., & Duzgun, S. (2013). Downscaling of MODIS LST using Landsat ETM+ for urban heat island analysis. International Journal of Remote Sensing Applications, 3(3), 115-121.
IPCC. (2014). Climate Change 2014: Synthesis Report. Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change [Core Writing Team, R.K. Pachauri and L.A. Meyer (eds.)]. IPCC, Geneva, Switzerland, 151 pp.
Jimenez-Munoz, J. C., & Sobrino, J. A. (2003). A generalized single-channel method for retrieving Land Surface Temperature from remote sensing data. Journal of Geophysical Research: Atmospheres, 108(D22).
Jha, S., Chowdary, V. M., & Singh, A. K. (2016). Spatial downscaling of MODIS LST using disaggregation of radiometric temperature for semi-arid region of India. Geocarto International, 31(2), 200-213.
Kalma, J. D., P. G. D. D. J. F., & Schmugge, T. J. (2020). Land Surface Temperature Retrieval from Satellite Data. CRC Press. (Re-edition of a classic).
Key, C. H., & Benson, N. C. (2006). Landscape Assessment: Ground Measure and Remote Sensing Sampling Strategies. Fire Effects Monitoring and Inventory Protocol, 13.
Kustas, W. P., Norman, J. M., Blanford, J. H., & Stannard, D. I. (2003). A two-source energy balance approach for estimating surface fluxes with partial canopy cover. Water Resources Research, 39(1).
Li, Z., Tang, R., Wu, H., & Ren, X. (2013). Satellite-derived land surface temperature: a review. Theoretical and Applied Climatology, 112(1-2), 173-207.
Li, H., Song, X., Li, X., Wu, S., & Li, Z. L. (2019a). Spatial downscaling of land surface temperature with the assistance of Sentinel-2 and Landsat 8 data. Remote Sensing, 11(17), 2007.
Li, J., Song, C., Cao, C., Zhu, F., Meng, X., & Wu, J. (2019b). Impacts of urban expansion on land surface temperature in Southeast Asia cities using Landsat data. Sustainability, 11(13), 3624.
Liu, Y., Hiyama, T., & Yamaguchi, Y. (2015). A reevaluation of the use of Normalized Difference Vegetation Index (NDVI) for land surface temperature (LST) retrieval. Remote Sensing, 7(12), 17382-17402.
Liu, Y., Meng, C., Li, Y., Liang, S., & Liu, Q. (2019). Global land surface temperature validation with in-situ measurements: A review. Science Bulletin, 64(14), 1010-1018.
Longley, P. A., Goodchild, M. F., Maguire, D. J., & Rhind, D. W. (2015). Geographic Information Science and Systems (4th ed.). Wiley.
Ma, H., Xu, Z., Huang, J., & Ma, H. (2019). Land surface temperature downscaling based on deep learning. Remote Sensing, 11(19), 2329.
Merlin, O., Rudiger, C., Albergel, J., Pr�vot, L., Pr�vot, L., de Rosnay, P., ... & Ciraolo, G. (2020). Spatial Downscaling of Land Surface Temperature: A Review. Remote Sensing, 12(14), 2269. (Updated version of older Merlin papers)
Mildrexler, D. J., Zhao, M., & Running, S. W. (2011). A global cooling trend has occurred over the last decade only when considering land surface temperatures. Remote Sensing of Environment, 115(1), 174-179.
Nemani, R. R., Keeling, C. D., Hashimoto, H., Jolly, W. M., Piper, S. C., Tucker, C. J., ... & Myneni, R. B. (2003). Climate-driven increases in global terrestrial net primary production from 1982 to 1999. Science, 300(5625), 1560-1563.
Peng, J., Ma, J., Wang, Y., Li, S., & Ma, Y. (2019). Downscaling land surface temperature based on feature learning: A comprehensive review. International Journal of Applied Earth Observation and Geoinformation, 83, 101905.
Qin, Z., Karnieli, A., & Berliner, P. (2021). A split-window algorithm for retrieving land surface temperature from Landsat TM data. Remote Sensing of Environment, 68(1), 77-85. (Original 1999, re-publication for context)
Running, S. W., Nemani, R., & Peterson, D. L. (1987). Forest ecosystem processes at the watershed scale: basis for remote estimation of leaf area. Ecological Modelling, 44(2-4), 131-157.
Schmugge, T., Kustas, W. P., Ritchie, J. C., Jackson, T. J., & Rango, A. (2002). Remote sensing in hydrology. Advances in Water Resources, 25(8-12), 1017-1020.
Setiawan, Y., Tana, S., & Suroso, D. S. (2014). Kajian Pengaruh Penggunaan Lahan terhadap Suhu Permukaan di Kota Surakarta. Jurnal Bumi Indonesia, 3(4).
Sobrino, J. A., Jim�nez-Mu�oz, J. C., & Paolini, L. (2004). Land surface temperature retrieval from Landsat TM 5. Remote Sensing of Environment, 90(4), 434-440.
Voogt, J. A., & Oke, T. R. (2003). Thermal remote sensing of urban climates. Remote Sensing of Environment, 86(3), 370-384.
Wang, W., Li, Z., & Chen, Y. (2015). The impact of topography on land surface temperature in a mountainous urban area: A case study of Kunming, China. Environmental Earth Sciences, 74(3), 2097-2106.
Weng, Q. (2009). Thermal infrared remote sensing for urban climate and environmental studies: Methods, applications, and trends. ISPRS Journal of Photogrammetry and Remote Sensing, 64(6), 581-593.
Weng, Q., Lu, D., & Schubring, J. (2004). Estimation of land surface temperature�vegetation abundance relationship for urban heat island studies. Remote Sensing of Environment, 89(4), 467-483.
Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing model accuracy. Climate Research, 30(1), 79-82.
Xu, Y., Sun, X., Shen, Y., & Li, C. (2018). Spatiotemporal analysis of land surface temperature in an urban area based on Landsat and Sentinel-2 images. Remote Sensing, 10(12), 1968.
Zhao, W., Duan, S. B., Li, Z. L., & Song, Z. (2016). A new universal single-channel algorithm for retrieving land surface temperature from Landsat 8 data. Remote Sensing, 8(2), 163.
Zhu, Z., Wang, S., & Woodcock, C. E. (2015). Improvement and expansion of the Fmask algorithm: cloud, cloud shadow, and snow detection for Landsats 4�7, 8, and Sentinel-2 images. Remote Sensing of Environment, 159, 269-277.