Semi-Automatic Classification Model on Benthic Habitat Using Spot-7 Imagery in Penerusan Bay, Bali

Devica Natalia Br Ginting, Anang Dwi Purwanto

Abstract

Benthic habitats are one of the interesting marine resources and its existence must be preserved. Provision of up-to-date benthic habitat information requires a relatively large amount of time and money. The use of remote sensing technology is one of the best solution. This study aims to develop a semi-automatic processing model that is fast, accurate, and with broad spatial coverage. The satellite image data used is the SPOT-7 image acquired on April 11th, 2018. The method used is a supervised classification with a decision tree algorithm. The analysis was carried out using a script developed in the open-source R application. The results showed that the model used was able to accelerate the processing of benthic habitat extracted from the initial process to the classification. The model developed is able to classify habitat classes based on the training sample data provided so that it does not affect the user’s ability to determine the habitat class. The resulting model accuracy is 93.6%. The validation of the resulting classification showed an overall accuracy of 59% and a kappa accuracy of 0.46. It is necessary to carry out further research by increasing quality and quantity of training samples from each object of benthic habitats and developing scripts in order to produce better mapping accuracy.

Keywords

benthic habitat; semi-automatic; decision tree; SPOT-7; Penerusan Bay

Full Text:

PDF

References

Anggoro, A,. Siregar, V.P., & Agus, S.B. (2015, in Indonesian). Geomorphological Zone Mapping of Coral Reef Ecosystems Using the OBIA Method, Case Study on Pari Island. Jurnal Penginderaan Jauh, 12(1), 1-12.

Ardiansyah, M.A., & Rusdi, M. (2004, in Indonesian). Discrimination of HTI (Industrial Plantation Forest) Stands Using Object Oriented Classification Case Study PT. HTI Wira Karya Sakti, Jambi. PIT. Masyarakat Penginderaan Jauh Indonesia XIII, Jakarta 22-23 Desember 2004.

Ardiyanto, R., & Hartono. (2015, in Indonesian). PMapping Coral Reefs Using Object-Based Classification Methods on Multispectral Quickbird-2 Imagery on Kemujan Island, Karimunjawa Islands, Jepara, Central Java. Jurnal Bumi Indonesia, 4(1), 327-335.

Astrium Services. (2013). SPOT 6 & SPOT 7 Imagery User Guide. Astrium an Eads Company.

Azhar. A, Damar. A, Bengen. D.G., & Atmadipoera. A. S. (2018). Shallow water marine habitat mapping of Kaledupa Island using integrating tradisional ecological knowledge and multispectral image classification. IOP Conf. Series: Earth and Environmental Science 241(2019) 012038. doi:10.1088/1755-1315/241/1/012038

Badan Informasi Geospasial. (2011, in Indonesian). SNI 7716:2011 concerning Mapping of shallow marine bottom habitats.

Belgiu, M., & Dragut, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing 114, 24-31. DOI:10.1016/j.isprsjprs.2016.01.011.

Brock. C.J, Kuffner. I.B, Harley. R., & Wright. C. W. (2006) Northern Florida reef tract benthic metabolism scaled by remote sensing. Marine Ecology Progress Series 312, 123-139. DOI: 10.3354/meps312123

R. R Development Core Team. (2016) A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria.

Effrosynidis, D., Arampatzis, A., & Sylaios, G. (2018). Seagrass detection in the Mediterranean: A supervised learning approach. Ecol. Inf. 2018, 48, 158–170.

Foody, GM. (2002). Status of Land Cover Classification Accuracy Assesment. Remote Sensing of Environtment. 80:185–201.

Gapper, J.J., Askary, H.E., Linstead, E., & Piechota, T. (2018). Evaluation of Spatial Generalization Characteristics of a Robust Classifier as Applied to Coral Reef Habitats in Remote Islands of the Pacific Ocean. Remote Sens, 10(11), 1774. DOI:10.3390/rs10111774

Gapper, J.J., Askary, H.E., Linstead, E., & Piechota, T. (2019). Coral Reef Change Detection in Remote Pacific Islands Using Support Vector Machine Classifiers. Remote Sens. 2019, 11(13), 1525.

Ginting, D.N.B., & Arjasakusuma, S. (2021, in Indonesian). Seagrass Mapping Using Machine Learning With Planetscope Imagery in Nusa Lembongan. Jurnal Kelautan Tropis, 24(3), 323-332.

Hochberg, E. J., Atkinson, M. J., Apprill, A., and Andrefouet, S. (2004) Spectral reflectance of coral. Coral Reefs 2004, 23, 84–95.

Humaida, N., Sudarsono, B., & Prasetyo, Y. (2015, in Indonesian). Comparative Analysis of Settlement Density using Supervised Classification and Segmentation (Case Study of Bandung City). Jurnal Geodesi UNDIP, 4(4), 75-78.

Jaya, I.N.S. (2010, in Indonesian). Digital Image Analysis Remote Sensing Perspective for Natural Resources Management. Fakultas Kehutanan Institut Pertanian Bogor.

Meyer, C.A. (2008). Application of Remote Sensing Methods to Assess the Spatial Extent of the Seagrass Resource in St. Joseph Sound and Clearwater Harbor, Florida, U.S.A.” Graduate Theses and Dissertations. University of South Florida.

Phinn, S.R., Roelfsama, C.M., & Mumby, P.J. (2011). Multiscale, object-based image analysis for mapping geomorphic and ecological zones on coral reefs. IntJRemote Sens. 33, 6367-6388.

Purwanto, A., Setiawan, K., & Ginting, D. (2019, in Indonesian). Utilization of Remote Sensing Data for Shallow Marine Habitat Extraction at Pemuteran Beach, Bali, Indonesia. Jurnal Kelautan Tropis. Vol22. 165. 10.14710.

Rancangan Standar Nasional Indonesia (RSNI) Klasifikasi Habitat Dasar Perairan Laut SNI 7987:2014

Radiarta, I.N., & Erlania. (2015, in Indonesian). Mapping of Marine Fish Floating Cages in Pegametan Bay and Passing Bay, Buleleng Regency, Bali. Prosiding Forum Inovasi Teknologi Akuakultur 2015.

Selgrath, J.C., Roelfsema. C., Gergel. A.E., & Vincent. A. C.J. (2016). Mapping for coral reef conservation: comparing the value of participatory and remote sensing approaches. Ecosphere,7(5). https://doi.org/10.1002/ecs2.1325

Setiawan, K.T., Winarso, G., Ginting, D.N.B., Manessa, M.D.M., Surahman., Anggraini, N., Hartuti, M., Asriningrum, W., & Parwati, E. (2021, in Indonesian). Utilization Of Semi-Analytical Methods For Determining Batimetry Using High Resolution Satellite Images. Jurnal Penginderaan Jauh dan Pengolahan Data Citra Digital, 18(1), 1-13. http://dx.doi.org/10.30536/j.pjpdcd.2021.v17.a3409

Suyanto. (2011). Artificial Intelegent (Cetakan kedua). Informatika: Bandung.

Thorhaug, A., Richardson, A.D., & Berlyn, G.P. (2007). Spectral reflectance of the seagrasses: Thalassia testudinum, Halodule wrightii, Syringodium filiforme and five marine algae. International Journal of Remote Sensing, 28(7), 1487-1501.

Wicaksono, P., Aryaguna. P.A., & Lazuardi. W. (2019). Benthic Habitat Mapping Model and Cross Validation Using Machine-Learning Classification Algorithms. Remote Sens, 11(11). 1279. doi:10.3390/rs11111279

Wolff. S., Schulp. C.J.E., & Verburg. P.H. (2015). Mapping ecosystem services demand: A review of current research and future perspectives. Ecological Indicators, 55(August 2015), 159-171. DOI: 10.1016/j.ecolind.2015.03.016

Wouthuyzen, S., Herandarudewi, S.M.C., & Komatsu, T. (2015). Stock assessment of brown seaweeds (Phaeophyceae) along the Bitung-Bentena Coast, North Sulawesi Province, Indonesia for alginate product using satellite remote sensing. UPT LPKSDMO Pulau Pari, Coremap-LIPI. The 2nd International Symposium on LAPAN-IPB Satellite for Food Security and Environmental Monitoring 2015, LISAT-FSEM 2015.

DOI: http://dx.doi.org/10.15578/segara.v17i3.9771