การจำแนกพันธุ์ไม้ป่าชายเลนเขตร้อน โดยใช้ข้อมูลพริสม่าไฮเปอร์สเปกตรัล กรณีศึกษาบริเวณแหลมตะลุมพุก ประเทศไทย
Tropical Mangrove Species Classification Using PRISMA Hyperspectral Data: A Case Study in Talumpuk Cape, Thailand
Keywords:
ข้อมูลพริสม่าไฮเปอร์สเปกตรัล , การรับรู้จากระยะไกล , การจำแนก , ป่าชายเลน , องค์ประกอบชนิด, PRISMA hyperspectral data , remote sensing , classification, mangrove, species compositionAbstract
ป่าชายเลนที่ใกล้สูญพันธุ์ภายใต้บัญชีแดงระบบนิเวศขององค์การระหว่างประเทศเพื่อการอนุรักษ์ธรรมชาติ (IUCN Red List of Ecosystems) เป็นหนึ่งในปัญหาร้ายแรงที่สุดของระบบนิเวศชายฝั่งของโลก ความกังวลนี้จำเป็นต้องมีการติดตาม ระบบนิเวศป่าชายเลนและความหลากหลายทางสายพันธุ์ภาพถ่ายดาวเทียมระบบไฮเปอร์สเปกตรัลที่มีความยาวคลื่นหลาย ร้อยช่วงคลื่นสามารถนำมาใช้จำแนกพันธุ์ไม้ป่าชายเลนได้ดาวเทียม PRISMA ถูกพัฒนาและส่งขึ้นโคจรซึ่งเป็นดาวเทียม สังเกตการณ์โลกดวงใหม่ภายใต้โครงการสาธิตเทคโนโลยีขององค์กรอวกาศอิตาลี (Italian Space Agency) ที่ปัจจุบันยังไม่มีการนำข้อมูลภาพถ่ายดาวเทียมดังกล่าวมาใช้จำแนกพันธุ์ไม้ป่าชายเลนในพื้นที่แหลมตะลุมพุกมาก่อน งานวิจัยนี้จึงเป็นการทดสอบประสิทธิภาพข้อมูลพริสม่าไฮเปอร์สเปกตรัลเพื่อจำแนกป่าชายเลนบริเวณแหลมตะลุมพุก อำเภอปากพนัง จังหวัดนครศรีธรรมราชเป็นครั้งแรก ในการจำแนกใช้การคัดเลือกช่วงคลื่นด้วย genetic algorithm (GA) และ sequential maximum angle convex cone (SMACC) ร่วมกับตัวจำแนกแบบ spectral angle mapper (SAM) เพื่อเลือกความถูกต้องมากที่สุด ทั้งนี้ ผลการจำแนกจากการคัดเลือกช่วงคลื่นทั้งสองแบบและการใช้แถบสเปกตรัมทั้งหมดของ PRISMA จะถูกนำมาเปรียบเทียบกัน โดยใช้ค่าความถูกต้องโดยรวม (Overall accuracy) และใช้ค่าสถิติการทดสอบ dependent sample t-test ผลการศึกษาพบว่า การคัดเลือกช่วงคลื่นด้วย GA สามารถปรับปรุงค่าความถูกต้องในการจำแนกเพิ่มขึ้นจากร้อยละ 80.72 เป็นร้อยละ 81.93 เมื่อเทียบกับการใช้แถบสเปกตรัมทั้งหมด ผลลัพธ์นี้จึงพิสูจน์ถึงประสิทธิภาพของการประยุกต์ใช้ข้อมูลภาพถ่ายดาวเทียม PRISMA ในการจำแนกพันธุ์ไม้ป่าชายเลนได้อย่างชัดเจน Endangered mangroves under the IUCN Red List of Ecosystems are one of the most severe issues of the world's coastal ecosystems. This concern required the necessary monitoring for mangrove ecosystems and their diversity. Hyperspectral satellite imagery is associated with hundreds of wavelengths can be used to categorize mangrove species. Therefore, this is an excellent opportunity for a new earth observation hyperspectral satellite, PRISMA, delivered by the Italian Space Agency. Currently, PRISMA information has not been previously used for mangrove species classificationin Talumpuk cape. This experiment launched the first-time examination of applying PRISMA hyperspectral on mangroves species categorization in Talumpuk cape, Pak Phanang District, Nakhon Si Thammarat Province. In the classification, two spectral band selectors, genetic algorithm (GA) and sequential maximum angle convex cone (SMACC), were associated with the spectral angle mapper (SAM) classifier to determine the most satisfactory hyperspectral band set. Classifications from those two selectors and entire bands were compared using overall accuracy and dependentsample t-test. The result revealed that the GA band selection could improve the classification accuracy from 80.72% to 81.93% compared to the entire band combination. This outcome undoubtedly proves the performance of PRISMA imagery's application on mangrove species classification.References
Adame, M. F., Connolly, R. M., Turschwell, M. P., Lovelock, C. E., Fatoyinbo, T., Lagomasino, D., Goldberg, L. A., Holdorf, J., Friess, D. A., & Sasmito, S. D. (2021). Future carbon emissions from global mangrove forest loss. Global change biology, 27(12), 2856-2866.
Anderson, J. R. (1976). A land use and land cover classification system for use with remote sensor data. (Vol. 964). US Government Printing Office.
Arfan, A., Toriman, M., Maru, R., & Sukri Nyompa, U. (2015). Reflectance characteristic of mangrove species using spectroradiometer HR-1024 in Suppa Coast, Pinrang, South Sulawesi, Indonesia. Asian Journal of Applied Sciences, 3(5).
Bai, J., Meng, Y., Gou, R., Lyu, J., Dai, Z., Diao, X., Zhang, H., Luo, Y., Zhu, X., & Lin, G. (2021). Mangrove diversity enhances plant biomass production and carbon storage in Hainan island, China. Functional Ecology, 35(3), 774-786.
Bandyopadhyay, S., & Pal, S. K. (2001). Pixel classification using variable string genetic algorithms with chromosome differentiation. IEEE Transactions on Geoscience and Remote Sensing, 39(2), 303-308.
Basyuni, M., Nainggolan, S., Qurrahman, T., Hasibuan, P., Sumaiyah, S., Sumardi, S., Siregar, E., & Nuryawan, A. (2019). Effect of Salt and Fresh Water Concentration on Polyisoprenoid Content in Bruguiera cylindrica Seedlings. Open access Macedonian journal of medical sciences, 7(22), 3803-3806.
Chakraborty, S. K. (2019). Bioinvasion and Environmental Perturbation: Synergistic Impact on Coastal–Mangrove Ecosystems of West Bengal, India. In Impacts of Invasive Species on Coastal Environments. (pp. 171-245). Cham: Springer.
Cochard, R. (2017). Coastal water pollution and its potential mitigation by vegetated wetlands: An overview of issues in Southeast Asia. Redefining Diversity & Dynamics of Natural Resources Management in Asia, Volume 1, 189-230.
Collins, D., Nguyen, V., Ta, T., Mao, L., Ishii, Y., Kitagawa, H., Nakashima, R., Vo, T., & Tamura, T. (2021). Sedimentary evolution of a delta-margin mangrove in Can Gio, northeastern Mekong River delta, Vietnam. Marine Geology, 433, 106417.
Constance, A., Haverkamp, P. J., Bunbury, N., & Schaepman-Strub, G. (2021). Extent change of protected mangrove forest and its relation to wave power exposure on Aldabra Atoll. Global Ecology and Conservation, 27, e01564.
Da Silva, M. F., Cruz, M. V., Vidal Júnior, J. D. D., Zucchi, M. I., Mori, G. M., & De Souza, A. P. (2021). Geographical and environmental contributions to genomic divergence in mangrove forests. Biological Journal of the Linnean Society, 132(3), 573-589.
Fauzi, N.F.M., Min, T.H. & Hashim, A.M. (2020). Assessment of Mangrove Replanting Site at Kg Tanjung Kepah, Lekir, Perak. In IOP Conference Series: Earth and Environmental Science, 549, 012054.
Friis, G., & Burt, J. A. (2020). Evolution of mangrove research in an extreme environment: Historical trends and future opportunities in Arabia. Ocean & Coastal Management, 195, 105288.
Gerald, B. (2018). A brief review of independent, dependent and one sample t-test. International Journal of Applied Mathematics and Theoretical Physics, 4(2), 50-54.
Ghosh, M. K., Kumar, L., & Roy, C. (2016). Mapping long-term changes in mangrove species composition and distribution in the Sundarbans. Forests, 7(12), 305.
Gruninger, J.H., Ratkowski, A.J., & Hoke, M.L. (2004). The sequential maximum angle convex cone (SMACC) endmember model. In Algorithms and technologies for multispectral, hyperspectral, and ultraspectral imagery X. (pp. 1-14). International Society for Optics and Photonics.
Halder, N.K., Merchant, A., Misbahuzzaman, K., Wagner, S., & Mukul, S.A. (2021a). Why some trees are more vulnerable during catastrophic cyclone events in the Sundarbans mangrove forest of Bangladesh? Forest Ecology and Management, 490, 119117.
Halder, S., Samanta, K., Das, S., & Pathak, D. (2021b). Monitoring the inter-decade spatial–temporal dynamics of the Sundarban mangrove forest of India from 1990 to 2019. Regional Studies in Marine Science, 44, 101718.
He, Z., Shi, Q., Liu, K., Cao, J., Zhan, W., & Cao, B. (2020). Object-oriented mangrove species classification using hyperspectral data and 3-D siamese residual network. IEEE Geoscience and Remote Sensing Letters, 17(12), 2150-2154.
Hickey, S., Radford, B., Callow, J., Phinn, S., Duarte, C. M., & Lovelock, C. (2021). ENSO feedback drives variations in dieback at a marginal mangrove site. Scientific reports, 11(1), 1-9.
Intarat, K. (2018). Remote sensing technique for mangrove studies: Tropical mangrove species classification with convolutional neural network and tropical mangrove tree biomass modelling with terrestrial laser scanner [Thesis, Chulalongkorn]. Chulalongkorn University.
Intarat, K., & Vaiphasa, C. (2020). Modeling Mangrove Above-Ground Biomass Using Terrestrial Laser Scanning Techniques: A Case Study of the Avicennia marina Species in the Bang Pu District, Thailand. International Journal of Geoinformatics, 16(2), 53-62.
Jannoud, I., Jaradat, Y., Masoud, M. Z., Manasrah, A., & Alia, M. (2022). The Role of Genetic Algorithm Selection Operators in Extending WSN Stability Period: A Comparative Study. Electronics, 11(1), 28.
Jing, X., Leigh, L., Helder, D., Pinto, C. T., & Aaron, D. (2019). Lifetime absolute calibration of the EO-1 Hyperion sensor and its validation. IEEE Transactions on Geoscience and Remote Sensing, 57(11), 9466-9475.
Khamprakop, S. (1975). Ministerial Regulation No. 732 (B.E. 2518). Retrieved March 12, 2022, from http://old.forest.go.th/nakhonsithammarat_12/dmdocuments/S1008.pdf. (in Thai)
Koedsin, W., & Vaiphasa, C. (2013). Discrimination of tropical mangroves at the species level with EO-1 Hyperion data. Remote Sensing, 5(7), 3562-3582.
Kumar, T., Mandal, A., Dutta, D., Nagaraja, R., & Dadhwal, V. K. (2019). Discrimination and classification of mangrove forests using EO-1 Hyperion data: A case study of Indian Sundarbans. Geocarto International, 34(4), 415-442.
L3HARRIS. (2021). ENVI 5.6. 1025 W. NASA Boulevard Melbourne, FL 32919. Licence No. E21-0076
Loizzo, R., Daraio, M., Guarini, R., Longo, F., Lorusso, R., Dini, L., & Lopinto, E. (2019). Prisma Mission Status and Perspective. International Geoscience and Remote Sensing Symposium IGARSS, 4503-4506.
Loizzo, R., Guarini, R., Longo, F., Scopa, T., Formaro, R., Facchinetti, C., & Varacalli, G. (2018). Prisma: The Italian hyperspectral mission. International Geoscience and Remote Sensing Symposium IGARSS 175-178.
Mahmood, H., Ahmed, M., Islam, T., Uddin, M. Z., Ahmed, Z. U., & Saha, C. (2021). Paradigm shift in the management of the Sundarbans mangrove forest of Bangladesh: Issues and challenges. Trees, Forests and People, 5, 100094.
Manjunath, K., Kumar, T., Kundu, N., & Panigrahy, S. (2013). Discrimination of mangrove species and mudflat classes using in situ hyperspectral data: a case study of Indian Sundarbans. GIScience & remote sensing, 50(4), 400-417.
McLeod, E., & Salm, R. V. (2006). Managing mangroves for resilience to climate change (Vol.64). Gland, Switzerland: World Conservation Union (IUCN).
Mitchell, M. (1998). An Introduction to Genetic Algorithms. USA: The MIT Press, Cambridge, Massachusetts.
MOAC. (1965). Ministerial Regulation No. 63 (B.E. 2508). Retrieved March 12, 2022, from http://old.forest.go.th/nakhonsithammarat_12/dmdocuments/S1003_63_2508.pdf. (in Thai)
Murugan, S., & Anandhi, D. U. (2016). An overview of crustacean diversity in mangrove ecosystem. In: Chakravarthy A., Arthropod Diversity and Conservation in the Tropics and Sub-tropics. (pp. 81-99). Singapore: Springer.
Panapitukkul, N., Duarte, C., Thampanya, U., Kheowvongsri, P., Srichai, N., Geertz-Hansen, O., Terrados, J., & Boromthanarath, S. (1998). Mangrove colonization: mangrove progression over the growing Pak Phanang (SE Thailand) mud flat. Estuarine, Coastal and Shelf Science, 47(1), 51-61.
Prasad, K.A., & Gnanappazham, L. (2014). Discrimination of mangrove species of Rhizophoraceae using laboratory spectral signatures. In2014 IEEE Geoscience and Remote Sensing Symposium. (pp. 2906-2909). IEEE.
Salghuna, N., & Pillutla, R. (2017). Mapping Mangrove Species Using Hyperspectral Data: A Case Study of Pichavaram Mangrove Ecosystem, Tamil Nadu. Earth Systems and Environment, 1(2), 1-12.
Shen, X., Zhang, Z., Zhai, C., & Li, R. (2022). A Meta-Analysis of the Overall Accuracy of Extent and Species of the Coastal Mangroves. Beijing Da Xue Xue Bao, 58(1), 135-146.
Sievers, M., Chowdhury, M. R., Adame, M. F., Bhadury, P., Bhargava, R., Buelow, C., Friess, D. A., Ghosh, A., Hayes, M. A., & McClure, E. C. (2020). Indian Sundarbans mangrove forest considered endangered under Red List of Ecosystems, but there is cause for optimism. Biological Conservation, 251, 108751.
Singh, M., Griaud, C., & Collins, C. M. (2021). An evaluation of the effectiveness of protected areas in Thailand. Ecological Indicators, 125, 107536.
Teeratanatorn, W. (2000). Mangroves of Pak Phanang Bay. Bangkok: Royal Forest Department. (in Thai)
Thompson, D. R., Mandrake, L., Gilmore, M. S., & Castano, R. (2010). Superpixel endmember detection. IEEE Transactions on Geoscience and Remote Sensing, 48(11), 4023-4033.
Thuy, T. D., Tuan, V. Q., & Nam, P. K. (2021). Does the devolution of forest management help conserve mangrove in the Mekong Delta of Viet Nam? Land Use Policy, 106, 105440.
Ullah, S., Groen, T. A., Schlerf, M., Skidmore, A. K., Nieuwenhuis, W., & Vaiphasa, C. (2012). Using a genetic algorithm as an optimal band selector in the mid and thermal infrared (2.5–14 µm) to discriminate vegetation species. Sensors, 12(7), 8755-8769.
Vaiphasa, C. (2006). Remote sensing techniques for mangrove mapping. Wageningen University and Research.
Vaiphasa, C., De Boer, W., Skidmore, A., Panitchart, S., Vaiphasa, T., Bamrongrugsa, N., & Santitamnont, P. (2007a). Impact of solid shrimp pond waste materials on mangrove growth and mortality: a case study from Pak Phanang, Thailand. Hydrobiologia,591(1), 47-57.
Vaiphasa, C., Ongsomwang, S., Vaiphasa, T., & Skidmore, A. K. (2005). Tropical mangrove species discrimination using hyperspectral data: A laboratory study. Estuarine Coastal and Shelf Science, 65(1-2), 371-379.
Vaiphasa, C., Skidmore, A. K., & de Boer, W. F. (2006). A post-classifier for mangrove mapping using ecological data. Isprs Journal of Photogrammetry and Remote Sensing, 61(1), 1-10.
Vaiphasa, C., Skidmore, A.K., de Boer, W.F., & Vaiphasa, T. (2007b) A hyperspectral band selector for plant species discrimination. Isprs Journal of Photogrammetry and Remote Sensing,62(3), 225-235.
Vangi, E., D’Amico, G., Francini, S., Giannetti, F., Lasserre, B., Marchetti, M., & Chirici, G. (2021). The new hyperspectral satellite PRISMA: Imagery for forest types discrimination. Sensors, 21(4), 1182.
Wan, L., Lin, Y., Zhang, H., Wang, F., Liu, M., & Lin, H. (2020). GF-5 Hyperspectral Data for Species Mapping of Mangrove in Mai Po, Hong Kong. Remote Sensing, 12(4), 656.
Wan, L., Zhang, H., Wang, T., Li, G., & Lin, H. (2018). Mangrove species discrimination from very high resolution imagery using gaussian markov random field model. Wetlands, 38(5), 861-874.
Wang, Y., Chao, B., Dong, P., Zhang, D., Yu, W., Hu, W., Ma, Z., Chen, G., Liu, Z., & Chen, B. (2021). Simulating spatial change of mangrove habitat under the impact of coastal land use: Coupling MaxEnt and DynaCLUE models. Science of The Total Environment, 788, 147914.
Wilkerson, S. (2008). Application of the Paired t-test. XULAneXUS, 5(1), 7.
Wirsansky, E. (2020). Hands-on genetic algorithms with Python: applying genetic algorithms to solve real-world deep learning and artificial intelligence problems. Packt Publishing Ltd.
Wong, F. K., & Fung, T. (2014). Combining EO-1 Hyperion and Envisat ASAR data for mangrove species classification in Mai Po Ramsar Site, Hong Kong. International Journal of Remote Sensing, 35(23), 7828-7856.
Xia, J., Yokoya, N., & Pham, T. D. (2020). Probabilistic mangrove species mapping with multiple-source remotesensing datasets using label distribution learning in Xuan Thuy National Park, Vietnam. Remote Sensing, 12(22), 3834.
Zulfa, A., Norizah, K., Hamdan, O., Faridah-Hanum, I., Rhyma, P., & Fitrianto, A. (2021). Spectral signature analysis to determine mangrove species delineation structured by anthropogenic effects. Ecological Indicators, 130, 108148.
