ESTIMASI BIOMASSA VEGETASI KEBUN RAYA BOGOR MENGGUNAKAN KOMBINASI CITRA WORLDVIEW-2 DAN ALGORITMA PEMELAJARAN MESIN

##plugins.themes.academic_pro.article.main##

Didi Usmadi
Didit Okta Pribadi

Abstrak

Metode pengukuran yang efektif dan efisien sangat diperlukan dalam mengestimasi biomassa vegetasi suatu kawasan dengan kerapatan kanopi yang tinggi. Kombinasi citra WorldView-2 dan algoritma pemelajaran mesin dapat menjadi alternatif metode dalam mengestimasi biomassa vegetasi di Kebun Raya Bogor. Penelitian ini bertujuan untuk mengetahui variabel dari citra WorldView-2 yang dapat digunakan untuk mengestimasi biomassa vegetasi Kebun Raya Bogor, mengetahui algoritma pemelajaran mesin yang paling akurat dalam mengestimasi biomassa di lapangan, dan mengestimasi serta memetakan biomassa vegetasi Kebun Raya Bogor. Variabel yang berkorelasi signifikan dengan biomassa yaitu NIR-reflectance, Blue-Correlation, Green-Correlation, NIR-Mean dan NIR-Variance. Variabel NIR-Mean merupakan variabel yang terpenting dalam pendugaan biomassa vegetasi. Algoritma Random Forest merupakan model terbaik dalam mengestimasi biomassa vegetasi dengan nilai r, PBIAS, RMSE, MAE dan RSR masing-masing sebesar 0,83, -11,51%, 185,47 Mg/ha, 139,43 Mg/ha, dan 0,56. Estimasi biomassa vegetasi Kebun Raya Bogor antara 6,27–1.576,90 Mg/ha dengan rata-rata sebesar 183,96 Mg/ha dan total biomassa sebesar 13,23 Gg. Kombinasi antara citra WorldView-2 dan algoritma Random Forest memiliki akurasi lebih tinggi dibandingkan dengan algoritma Artificial Neural Network dan Support Vector Machine dalam memprediksi biomassa vegetasi Kebun Raya Bogor. Kebun Raya Bogor memiliki peran yang sangat penting dalam mitigasi perubahan iklim, terutama untuk Kota Bogor.

##plugins.themes.academic_pro.article.details##

Cara Mengutip
Usmadi D, Pribadi DO. 2021. ESTIMASI BIOMASSA VEGETASI KEBUN RAYA BOGOR MENGGUNAKAN KOMBINASI CITRA WORLDVIEW-2 DAN ALGORITMA PEMELAJARAN MESIN. Buletin Kebun Raya 24(1): 1-12. https://doi.org/10.14203/bkr.v23i1.632

Referensi

  1. Arifanti VB, Dharmawan IWS, Wicaksono D. 2014. Potensi cadangan karbon tegakan hutan sub montana di Taman Nasional Gunung Halimun Salak. Jurnal Penelitian Sosial dan Ekonomi Kehutanan 11 (1): 13–31.
  2. Bouckaert RR, Frank E, Hall M, Kirkby R, Reutemann PP, Seewald A, Scuse D. 2016. WEKA Manual for Version 3-9-1. University of Waikato, Hamilton, New Zealand.
  3. BSN. 2011. Pengukuran dan penghitungan cadangan karbon–Pengukuran lapangan untuk penaksiran cadangan karbon hutan (ground based forest carbon accounting). Badan Standardisasi Nasional.
  4. Cahyaningrum ST, Hartoko A, Suryanti. 2014. Biomassa karbon mangrove pada kawasan mangrove Pulau Kemujan Taman Nasional Karimunjawa. Diponegoro Journal of Maquares 3(3): 34?42.
  5. Calvão T, Palmeirim JM. 2004. Mapping Mediterranean scrub with satellite imagery: biomass estimation and spectral behavior. International Journal of Remote Sensing 25: 1–14.
  6. Chave J, Andalo C, Brown S, Cairns MA, Chambers JQ, Eamus D, Folster H, Fromard F, Higuchi N, Kira T, Lescure JP, Nelson BW, Ogawa H, Puig H, Rie´ra B, Yamakura T. 2005. Tree allometry and improved estimation of carbon stocks and balance in tropical forests. Oecologia 145: 87–99.
  7. Chen L, Wang Y, Ren C, Zhang B, Wang Z. 2019. Optimal combination of predictors and algorithms for forest above-ground biomass mapping from sentinel and srtm data. Remote Sensing 11. DOI: https://doi.org/10.3390/rs11040414.
  8. Chollet F, Allaire JJ. 2017. Deep learning with R. Manning Publications. USA.
  9. Eckert S. 2012. Improved forest biomass and carbon estimations using texture measures from WorldView-2 satellite data. Remote Sensing 4: 810–829. DOI: https://doi.org/110.3390/rs4040810.
  10. ESA. 2020. Sentinel 2 Toolbox. http://step.esa.int/main/toolboxes/sentinel-2-toolbox. (diakses 25 Januari 2020)
  11. Ginting TT, Prayogo C. 2018. Pendugaan cadangan karbon hutan jati (Tectona Grandis Linn. F) dengan berbagai persamaan alometrik pada berbagai kelas umur jati. Jurnal Tanah dan Sumberdaya Lahan 5(2): 1019?1026.
  12. Goetz SJ, Baccini A, Laporte N, Tracy J, Walker WS, Kellndorfer J, Houghton RA, Sun M. 2009. Mapping and monitoring carbon stocks with satellite observations: A comparison of methods. Carbon balance and management. 4 (2) : 1–7. DOI: https://doi.org/ 10.1186/1750-0680-4-2.
  13. Goodman RC, Phillips OL, Torres DC, Freitas L, Cortese ST, Monteagudo A, Baker TR. 2013. Amazon palm biomass and allometry. Forest Ecology and Management 310: 994–1004.
  14. Gupta HV, Sorooshian S, Yapo PO. 1999. Status of automatic calibration for hydrologic models: Comparison with multilevel expert calibration. Journal of Hydrologic Engineering 4: 135–143.
  15. Haralick RM, Shanmugam K, Denstien I. 1973. Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics 3 (6): 610–621.
  16. ICRAF-Database. 2020. Wood Density http://db.worldagroforestry.org//wd. (diakses 25 Januari 2020).
  17. IPCC. 2001. Climate change 2001: The Scientific Basis. Contribution of Working Group I to the Third Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge University Press, Cambridge.
  18. Karsenty A, Blanco C, Dufour T. 2003. Forest and climate change. Instruments related to the United Nations Framework Convention on Climate Change and their potential for sustainable forest management in Africa. Food and Agriculture Organization of The United Nations. Rome.
  19. Khudinyan M. 2019. The use of remotely sensed data for forest biomass monitoring a case of forest sites in North-Eastern Armenia. Master Thesis, Information Management School, Nova University of Lisbon.
  20. Li L, Zhou X, Chen L, Chen L, Zhang Y, Liu Y. 2020. Estimating urban vegetation biomass from Sentinel-2A image data. Forests 11(125). DOI: https://doi.org/10.3390/f11020125.
  21. Melo LCD, Sanquetta CR, Corte APD, Mognon F. 2015. Methodological alternatives in the estimate of biomass for young individuals of Bambusa spp. Bioscience Journal Uberlândia 31: 791–800.
  22. Moriasi DN, Arnold JG, Liew MWV, Bingner RL, Harmel RD, Veith TL. 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE 50(3): 885?900.
  23. Mutanga O, Adama E, Choa MA. 2012. High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. International Journal of Applied Earth Observation and Geoinformation 18: 399–406.
  24. Pandit S, Tsuyuki S, Dube T. 2018. Estimating above-ground biomass in sub-tropical buffer zone community forests, Nepal, using Sentinel 2 data. Remote Sensing 10 (4): 601. DOI: https://doi.org/10.3390/rs10040601.
  25. Rozak AH, Astutik S, Mutaqien Z, Widyatmoko D, Sulistyawati E. 2017. Hiperdominansi jenis dan biomassa pohon di Taman Nasional Gunung Gede Pangrango, Indonesia. Jurnal Ilmu Kehutanan 11: 85–96.
  26. Shobairi SOR, Usoltsev VA, Chasovskikh VP, Li M. 2018. Exploring forest aboveground biomass estimation using Landsat, forest inventory and analysis data base. Analysis 4 (15): 632–641.
  27. Singh J, Knapp HV, Demissie M. 2004. Hydrologic modeling of the Iroquois River watershed using HSPF and SWAT. ISWS CR 2004-08. Illinois State Water Survey.
  28. Updike T, Comp C. 2010. Radiometric use of WorldView-2 imagery. Technical N. Digital Globe Inc.
  29. Usmadi D, Hidayat S, Yuzammi, Asikin D. 2015. Potensi biomassa dan cadangan karbon Kebun Raya Balikpapan, Kalimantan Timur. Buletin Kebun Raya 18 (1): 1–14.
  30. Vafaei S, Soosani J, Adeli K, Fadaei H, Naghavi H, Pham TD, Bui DT. 2018. Improving accuracy estimation of forest aboveground biomass based on incorporation of ALOS-2 PALSAR-2 and Sentinel-2A imagery and machine learning: a case study of the hyrcanian forest area (Iran). Remote Sensing 10: 172–191. DOI: https://doi.org/10.3390/rs10020172.
  31. Vastaranta M, Yu X, Luoma V, Karjalainen M, Saarinen N, Wulder MA, White JC, Persson HJ, Hollaus M, Yrttimaa T, Holopainen M, Hyyppä J. 2018. Aboveground forest biomass derived using multiple dates of WorldView-2 stereo-imagery: quantifying the improvement in estimation accuracy. International Journal of Remote Sensing 39 (23): 8766-8783. DOI: https://doi.org/10.1080/01431161.2018.1492176.
  32. Vescovo L, Wohlfahrt G, Balzarolo M, Pilloni S, Sottocornola M, Rodeghiero M, Gianelle D.. 2012. New spectral vegetation indices based on the near-infrared shoulder wavelengths for remote detection of grassland phytomass. International Journal of Remote Sensing 10 (33). DOI: https://doi.org/10.1080/01431161.2011.607195.
  33. Wahyuni NI. 2012. Integrasi pengindraan jauh dalam penghitungan biomasa hutan. Info BPK Manado 2 (2):115–126.
  34. Widyatmoko D, Astutik S, Sulistyawati E, Rozak AH, Mutaqien Z. 2013. Stok karbon dan biomassa di Cagar Biosfer Cibodas, Indonesia. Konservasi biocarbon, lanskap dan kearifan lokal untuk masa depan: Integrasi pemikiran multidimensi untuk keberlanjutan. Kebun Raya Cibodas, Cibodas.