การพัฒนาแบบจำลองการจำแนกพื้นที่ปลูกอ้อยด้วยภาพถ่ายจากดาวเทียม Sentinel-1 และ Sentinel-2
คำสำคัญ:
อ้อย, ภาพถ่ายจากดาวเทียมเซ็นติเนล-1/2, ช่วงคลื่นขอบแดง, กูเกิลเอิร์ธเอนจิน, อัลกอริทึมป่าสุ่มบทคัดย่อ
อำเภอภูเขียว จังหวัดชัยภูมิ เป็นพื้นที่ปลูกอ้อยที่มีความสำคัญของภาคตะวันออกเฉียงเหนือ ทั้งในด้านขนาดพื้นที่และปริมาณผลผลิตที่ใช้เป็นวัตถุดิบหลักของอุตสาหกรรมน้ำตาล อย่างไรก็ตาม การจัดทำข้อมูลพื้นที่ปลูกอ้อยยังคงพึ่งพาการสำรวจภาคสนามเป็นหลัก ส่งผลให้การวางแผนจัดการอ้อยขาดความต่อเนื่องและความละเอียดเชิงพื้นที่ การศึกษานี้พัฒนาแบบจำลองการจำแนกพื้นที่ปลูกอ้อยด้วยอัลกอริทึมป่าสุ่ม (Random Forest) โดยใช้ข้อมูล Sentinel-1 และ Sentinel-2 จำนวน 21 features ประกอบด้วย Spectral Bands 13 Bands ดัชนีพืชพรรณ 6 ดัชนี และโพลาไรเซชัน VV และ VH บนแพลตฟอร์ม Google Earth Engine โดยใช้แปลงตัวอย่าง 400 แปลง (54,304 จุดภาพ) สำหรับฝึกสอน และจุดตรวจสอบอิสระ 400 จุดสำหรับประเมินความถูกต้องการศึกษาได้เปรียบเทียบชุดข้อมูล 4 รูปแบบ ได้แก่ (1) ข้อมูลเชิงแสง RGB (2) ดัชนีพืชพรรณ (VIs) (3) ดัชนีพืชพรรณร่วมกับข้อมูลเรดาร์ (VIs + SAR) และ (4) ข้อมูลเรดาร์ (SAR) ผลการศึกษาพบว่าการบูรณาการดัชนีพืชพรรณร่วมกับข้อมูลเรดาร์ (VIs + SAR) ให้ผลดีที่สุด โดยมีค่าตวามถูกต้องโดยรวม (Overall Accuracy) ที่ 88.50% และสัมประสิทธิ์แคปปา (Kappa Coefficient) ที่ 81.90% และค่าความถูกต้องของผู้ผลิต (Producer Accuracy) สำหรับอ้อย 94.0% โดยดัชนีกลุ่มคลื่นขอบแดง ได้แก่ CIred-edge และ SAREI มีบทบาทสำคัญในการลดการทับซ้อนเชิงคลื่น เนื่องจากอ้อยในช่วงก่อนเปิดหีบมีปริมาณคลอโรฟิลล์สูงและสม่ำเสมอทั่วแปลง ทำให้ค่า CIred-edge ของอ้อยมีช่วงการกระจายของข้อมูลต่ำและแยกออกจากพืชชนิดอื่นได้ชัดเจนกว่าดัชนีความเขียวทั่วไป ผลการศึกษาชี้ให้เห็นว่าการบูรณาการข้อมูลหลายเซนเซอร์ร่วมกับดัชนีกลุ่มคลื่นขอบแดงมีความเหมาะสมต่อการจำแนกพื้นที่ปลูกอ้อย และสามารถนำไปประยุกต์ใช้เป็นต้นแบบสำหรับการติดตามพื้นที่ปลูกอ้อยต่อไป
เอกสารอ้างอิง
Ayhan, B., & Kwan, C. (2020). Tree, shrub, and grass classification using only RGB images. Remote Sensing, 12(8), 1333. Form https://doi.org/10.3390/rs12081333
Badruzzaman, A., Wulandari, P., Sainal, S., Ashley, M., Jobling, S., Austen, M. C., & Praptiwi, R. A. (2025). Satellite imagery pre-processing and feature extraction for the mapping of coastal ecosystems using Google Earth Engine: A workflow for practitioners. MethodsX, 103516. Form https://doi.org/10.1016/j.mex.2025.103516
Bantchina, B. B., & Gündoğdu, K. S. (2024). Crop type classification using Sentinel 2A-derived normalized difference red edge index (NDRE) and machine learning approach. Bursa Uludağ Üniversitesi Ziraat Fakültesi Dergisi, 38(1), 89–105.
Chabalala, Y., Adam, E., & Ali, K. A. (2022). Machine learning classification of fused Sentinel-1 and Sentinel-2 image data towards mapping fruit plantations in highly heterogenous landscapes. Remote Sensing, 14(11), 2621. Form https://doi.org/10.3390/rs14112621
Dagne, S. S., Hirpha, H. H., Tekoye, A. T., Dessie, Y. B., & Endeshaw, A. A. (2023). Fusion of Sentinel-1 SAR and Sentinel-2 MSI data for accurate urban land use-land cover classification in Gondar City, Ethiopia. Environmental Systems Research, 12(1), 40. Form https://doi.org/10.1186/s40068-023-00324-5
De Swaef, T., Maes, W. H., Aper, J., Baert, J., Cougnon, M., Reheul, D., ... & Lootens, P. (2021). Applying RGB- and thermal-based vegetation indices from UAVs for high-throughput field phenotyping of drought tolerance in forage grasses. Remote Sensing, 13(1), 147. Form https://doi.org/10.3390/rs13142702
Jena, J., Misra, S. R., & Tripathi, K. P. (2019). Normalized difference vegetation index (NDVI) and its role in agriculture. Agriculture and Food: E-Newsletter, 1(12), 387–389.
Jensch, K., Ghazaryan, G., Ernst, S., Hostert, P., & Nendel, C. (2025). Integrating Landsat, Sentinel-2 and Sentinel-1 time series for mapping intermediate crops. European Journal of Remote Sensing, 58(1), 2507738. Form https://doi.org/10.1080/22797254.2025.2507738
Kang, Y., Meng, Q., Liu, M., Zou, Y., & Wang, X. (2021). Crop classification based on red edge features analysis of GF-6 WFV data. Sensors, 21(13), 4328. Form https://doi.org/10.3390/s21134328
Kareem, H. H., Attaee, M. H., & Omran, Z. A. (2023). Evaluation the soil-adjusted vegetation indices SAVI and MSAVI for Bristol city, United Kingdom using Landsat 8-OLI through geospatial technology. Ecological Engineering & Environmental Technology, 24. Form https://doi.org/10.12912/27197050/169749
Keawtungmuang, S., Srisombat, I., & Bothisarn, W. (2017). Study of life-way of cane farm community in Bannongdindum, Phukieow District, Chaiyaphum Province. Academic MCU Buriram Journal, 2(2), 108–118. (in Thai)
Kwang Jhone Subdistrict Administrative Organization. (n.d.). Economic conditions of Kwang Jhone Subdistrict, Phu Khiao District, Chaiyaphum Province. Form https://www.kwangjhone.go.th/data.php?content_id=3
Laohapattanalert, K., Jamjamroon, K., & Kobpuleaw, L. (2016). Ethanol production from cassava pulp using diluted acid and alkaline solution pretreatment and simultaneous saccharification and fermentation. In Proceedings of the RSU National Research Conference 2016 (p. 281). Rangsit University. (in Thai)
Li, N., Guo, Y., Wang, L., Wang, Q., Yan, D., Zhao, S., & Lei, T. (2024). Evaluation and quantitative characterization for the ecological environment impact of open pit mining on vegetation destruction from Landsat time series: A case study of Wulishan limestone mine. Ecological Indicators, 158, 111371. Form https://doi.org/10.1016/j.ecolind.2024.111371
Liu, M., Zhan, Y., Li, J., Kang, Y., Sun, X., Gu, X., ... & Yang, J. (2024). Validation of red-edge vegetation indices in vegetation classification in tropical monsoon region—a case study in Wenchang, Hainan, China. Remote Sensing, 16(11), 1865. Form https://doi.org/10.3390/rs16101865
Magidi, J., Nhamo, L., Mpandeli, S., & Mabhaudhi, T. (2021). Application of the random forest classifier to map irrigated areas using Google Earth Engine. Remote Sensing, 13(5), 876. Form https://doi.org/10.3390/rs13071376
Mitr Phol Modern Farm. (2025, August 22). Precise water management to enhance sustainable sugarcane productivity. Form https://www.mitrpholmodernfarm.com/news/2025/08/
Mullissa, A., Vollrath, A., Odongo-Braun, C., Slagter, B., Balling, J., Gou, Y., Gorelick, N., & Reiche, J. (2021). Sentinel-1 SAR backscatter analysis ready data preparation in Google Earth Engine. Remote Sensing, 13(10), 1954. Form https://doi.org/10.3390/rs13101954
Nodthaisong, C., Saengprachathanarug, K., Chea, C., Posom, J., Wongpichet, S., Konyai, S., & Wongphati, M. (2019). Feasibility study of sugarcane yield prediction using NDVI and CI red-edge indices associated with volume of digital surface model (DSM). Khon Kaen Agriculture Journal, 47(4), 679–694. Form https://doi.org/10.14456/kaj.2019.65 (in Thai)
Nsiah, R. A., Mantey, S., & Ziggah, Y. Y. (2024). Assessing the contribution of RGB VIs in improving building extraction from RGB-UAV images. Mersin Photogrammetry Journal, 6(1), 9–21. Form https://doi.org/10.53093/mephoj.1399083
Nyamekye, C., Ghansah, B., Agyapong, E., Obuobie, E., Awuah, A., & Kwofie, S. (2021). Examining the performances of true color RGB bands from Landsat-8, Sentinel-2 and UAV as stand-alone data for mapping artisanal and small-scale mining (ASM). Remote Sensing Applications: Society and Environment, 24, 100655. Form https://doi.org/10.1016/j.rsase.2021.100655
Office of Agricultural Research and Development Region 5. (2017). Knowledge management: Management of sugarcane white leaf disease in the central and western regions using clean planting materials. Department of Agriculture, Ministry of Agriculture and Cooperatives. (in Thai)
Office of the Cane and Sugar Board. (2025). Report on sugarcane cultivation status for the 2024/2025 production year. Office of the Cane and Sugar Board, Ministry of Industry, Thailand. (in Thai)
Pflumm, L., Kang, H., Wilting, A., & Niedballa, J. (n.d.). GEE-PICX: Generating cloud-free Sentinel-2 and Landsat image composites and spectral indices for custom areas and time frames—A Google Earth Engine web application. EarthArXiv. (preprint).
Phan, T. N., Kuch, V., & Lehnert, L. W. (2020). Land cover classification using Google Earth Engine and random forest classifier—The role of image composition. Remote Sensing, 12(15), 2411. Form https://doi.org/10.3390/rs12152411
Rekha, B. U., Desai, V. V., Kuri, S., Ajawan, P. S., Jha, S. K., & Patil, V. C. (2025). Field-level sugarcane yield estimation utilizing Sentinel-2 time-series and machine learning. Indonesian Journal of Electrical Engineering and Computer Science, 37(1), 475–487. Form https://doi.org/10.11591/ijeecs.v37.i1.pp475-487
Ruenrom, S., Ket-ord, R., & Iamchuen, N. (2024). Multi-scenario satellite drought assessment using moisture stress index (MSI) in Mae Suk Watershed, Mae Chai District, Phayao Province. Journal of Spatial Innovation Development (JSID), 5(3), 93–105. (in Thai)
Sanchez, A., Barboza, L. A., Watson, D., & Alfaro, E. J. (2023). Machine learning techniques applied to atmospheric sciences: a systematic review. Frontiers in Climate, 5, 1250605.
Selvaraj, S., Bargiel, D., Htitiou, A., & Gerighausen, H. (2024). Analyzing temporal characteristics of winter catch crops using Sentinel-1 time series. Remote Sensing, 16(19), 3737. Form https://doi.org/10.3390/rs16193737
Shamsoddini, A., & Trinder, J. C. (2011). Edge-detection-based filter for SAR speckle noise reduction. International Journal of Remote Sensing, 33(8), 2296–2320. Form https://doi.org/10.1080/01431161.2011.614286
Shi, L., Fan, H., Yang, L., Jiang, Y., Sun, Z., & Zhang, Y. (2023). NDVI-based spatial and temporal vegetation trends and their response to precipitation and temperature changes in the Mu Us Desert from 2000 to 2019. Water Science & Technology, 88(2), 430–442. Form https://doi.org/10.2166/wst.2023.212
Som-ard, J., Suwanlee, S. R., Pinasu, D., Keawsomsee, S., Kasa, K., Seesanhao, N., ... & Immitzer, M. (2022). Monitoring three decades of crop type dynamics in Thailand using multi-temporal satellite imagery and random forest classifier. Computers and Electronics in Agriculture, 198, 107083. Form https://doi.org/10.1016/j.compag.2022.107083
Som-ard, J., Suwanlee, S. R., Pinasu, D., Keawsomsee, S., Kasa, K., Seesanhao, N., ... & Sarvia, F. (2024). Evaluating sugarcane yield estimation in Thailand using multi-temporal Sentinel-2 and Landsat data together with machine-learning algorithms. Land, 13(9), 1481. Form https://doi.org/10.3390/land13091481
Som-ard, J., Suwanlee, S. R., Keawsomsee, S., Kasa, K., Seesanhao, N., Izquierdo-Verdiguier, E., Moreno-Martínez, Á., Ninsawat, S., & Atzberger, C. (2025a). Mapping sugarcane plantations in Northeast Thailand using multi-temporal data from multi-sensors and machine-learning algorithms. Big Earth Data, 9(2), 187–216. Form https://doi.org/10.1080/20964471.2025.2463730
Som-ard, J., Hossain, M. D., Keawsomsee, S., Suwanlee, S. R., Veerachitt, V., Heawchaiyaphum, P., Puntura, A., Izquierdo-Verdiguier, E., Immitzer, M., & Atzberger, C. (2025b). Integrating multi-temporal satellite data and machine learning approaches for crop rotation pattern mapping in Thailand. Remote Sensing, 17(18), 3156. Form https://doi.org/10.3390/rs17183156
Sonobe, R., Sano, T., & Horie, H. (2018). Using spectral reflectance to estimate leaf chlorophyll content of tea with shading treatments. Biosystems Engineering, 175, 168–182. Form https://doi.org/10.1016/j.biosystemseng.2018.09.018
Suwanlee, S. R., Keawsomsee, S., Izquierdo-Verdiguier, E., Moreno-Martínez, Á., Ninsawat, S., & Som-ard, J. (2025). Synergistic use of multi-sensor satellite data for mapping crop types and land cover dynamics from 2021 to 2023 in Northeast Thailand. International Journal of Applied Earth Observation and Geoinformation, 141, 104673. Form https://doi.org/10.1016/j.jag.2025.104673
Thaicharoen, K., & Majandang, J. (2022). The development of an equation for sugarcane yield prediction using vegetation indices from Sentinel-2 satellite imagery: A case study in Chaiwan District, Udon Thani Province. Journal of Science and Technology Mahasarakham University, 41(6), 317–324. (in Thai)
Tomppo, E., Ronoud, G., Antropov, O., Hytönen, H., & Praks, J. (2021). Detection of forest windstorm damages with multitemporal SAR data—A case study: Finland. Remote Sensing, 13(3), 383. Form https://doi.org/10.3390/rs13020383
Tsuchiya, Y., & Sonobe, R. (2025). Crop classification using time-series Sentinel-1 SAR data: A comparison of LSTM, GRU, and TCN with attention. Remote Sensing, 17(12), 2095. Form https://doi.org/10.3390/rs17122095
Vera-Esmeraldas, A., Pizarro-Oteíza, S., Labbé, M., Rojo, F., & Salazar, F. (2025). UAV-based spectral and thermal indices in precision viticulture: A review of NDVI, NDRE, SAVI, GNDVI, and CWSI. Agronomy, 15(11), 2569. Form https://doi.org/10.3390/agronomy15112569
Vizzari, M., Antonielli, F., Bonciarelli, L., Grohmann, D., & Menconi, M. E. (2025). Urban greenery mapping using object-based classification and multi-sensor data fusion in Google Earth Engine. Urban Forestry & Urban Greening, 105, 128697. Form https://doi.org/10.1016/j.ufug.2025.125697
Vora, A. P., Dudhagara, R. C., Kathiriya, D. R., & Pundir, R. S. (2023). Applications of Google Earth Engine for big data analytics. The Pharma Innovation Journal, 12(3), 2054–2062.
Wijitthanasarn, P., & Obpaet, A. (2023). Evaluation of harvest status in sugarcane fields in Khon Kaen Province, Thailand using Sentinel-1 SAR data. In Proceedings of the 28th National Convention on Civil Engineering (NCE28), May 24–26, 2023, Phuket, Thailand. (in Thai).
Wolfe, J. D. (2017). Using ENVI for agriculture research: Optical remote sensing of sugarcane development. NV5 Geospatial Software. Form https://www.nv5geospatialsoftware.com/Learn/Whitepapers/Whitepaper-Detail/using-envi-for-agriculture-research-optical-remote-sensing-of-sugarcane-development
Xu, L., Zhang, H., Wang, C., Zhang, B., & Liu, M. (2019). Crop classification based on temporal information using Sentinel-1 SAR time-series data. Remote Sensing, 11(1), 53. Form https://doi.org/10.3390/rs11010053
Ye, J., Bao, W., Liao, C., Chen, D., & Hu, H. (2023). Corn phenology detection using the derivative dynamic time warping method and Sentinel-2 time series. Remote Sensing, 15(14), 3456. Form https://doi.org/10.3390/rs15143456
Yuan, X., Shi, J., & Gu, L. (2023). A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Systems with Applications, 169, 114417.
Zhao, C., Pan, Y., Ren, S., Gao, Y., Wu, H., & Ma, G. (2024). Accurate vegetation destruction detection using remote sensing imagery based on the three-band difference vegetation index (TBDVI) and dual-temporal detection method. International Journal of Applied Earth Observation and Geoinformation, 127, 103669. Form https://doi.org/10.1016/j.jag.2024.103669
