Sugarcane Land Change Pattern and Yield Prediction Using Landsat Imagery and Unmanned Aerial Vehicle Photos
Abstract
This study aimed to 1) analyze sugarcane land change pattern before and after having sugarcane planting promotion project using Moran’s I distribution method and 2) predict yield by Unmanned Aerial Vehicle (UAV) photos and ground data. The Landsat image time series were classified land use maps using Nearest Neighbor (NN), and 93 farmers were interviewed. Hierarchy classification with Excessive Green Index (ExG) conducted to define sugarcane density in stages. These maps and 100 sampling plots as 1.5x.1.5 m include the number of stalks and harvested yield to investigate the correlation (r). Simple regression model was created for correlation analysis and used to estimate yield. The result of model was measured using statistic method. The land use of 2004, 2010 and 2018 were overall accuracy as 86.18, 87.41 and 98.72%. Land use change during 2004 - 2010 and 2010 - 2018 after having the encouraged project, the other cultivations have mostly changed to sugarcane of 5.55% as random and 19.63% as cluster distribution. Ripening phase shown high correlation than others (r: 0.84). Yield prediction was RMSE and absolute error as 0.90 and 0.06%, this method had estimated yield of 396.60 tons, compare to harvest yield as 413 tons. The result can use to plan and develop estimated yield for consistency of sugarcane and sugar industry toward commercial level.
Keywords : sugarcane land change, Moran’s I, OBIA, Unmanned Aerial Vehicle (UAV), yield estimation
Full Text:
PDFReferences
Boonserm. E. (2011). The application of remote sensing data for the study change of natural green space
inThe area. Retrieved June 29, 2018, from http://www.arts.chula.ac.th/~geography/TSG2015/docs/.../2.6% 20paper _Eakapan.pdf.
Bruno, M., Hilton Luis Ferraz da Silveira, Ieda Del’Arco Sanche & Thales Sehn Körting. (2017). Identification of
gaps in sugarcane plantations using UAV images: Faculty of Mechanical Engineering, University of
Campinas, 1169-1176.
Bunlue, T. (2018). Applying Drone for Generated Building Information Modeling (BIM) for Urban Architecture,
the Case study of That Phanom District. (pp.137-148). Nakhon Phanom.
Chuchip, K. (2018). Accuracy Assessment in Remote Sensing. Faculty of Forestry. Kasetsart University.
(pp 18). Bangkok.
Coppin, Pol R., & Marvin E. Bauer. (1996). Digital change detection in forest ecosystems with remote sensing
imagery. Remote sensing reviews, 13,(3-4), 207-234.
Department of Agriculture. (2011a). Receiving rainfall and suitable temperature for sugarcane growth.
Retrieved January 14, 2018, from http://www.ocsb.go.th/upload/journal/fileupload/144-4003.
Department of Agriculture. (2011b). Drought problems in the eastern region. Retrieved April 3, 2018,
from http://www.ocsb.go.th/upload/journal/fileupload/144-4003.
Department of Agriculture. (2012c). Sugarcane cultivation manual and sustainable sugarcane management.
Retrieved January 23, 2018. from http://www.ocsb.go.th/upload/journal/fileupload.
Department of Agriculture. (2017). Test and Development on Sugarcane Production Technology for Specific
area, Retrieved April 3, 2018, from http://www.ocsb.go.th/upload/journal/fileupload/144-4003
International Sugar Organization. (2013). Report on climate change affecting Chae Oi production, Retrieved
January 2, 2017, from http://www.ocsb.go.th/uplo ad/executive/fileupload/4784-3548.
Jansen, H., & Stoorvogell. J. (1998). Quantification of aggregation biasin regional agricultural lanuse models
application to guacimocounty. Agricutural systems, 58, 417-439.
Kanjanasut, P., Tangtham, N., & Tokritana, R. (2014). Dry-Season Rice Yield Estimation with SMMS Data by
Using Normalize Difference Vegetation Index: A Case Study of Muang District Suphan Buri.
Thai Science and Technology Journal, 55-66.
Khansila, T., & Mongkonthum, W. (2014). Factors affecting the selection of growing sugarcane in Nam Phong
District. Graduate Research Conference, 6, 449-460.
Kumphawapi Agriculture Office. (2012). Statistical data sugarcane plantation in Kumphawapi district.
Udon Thani province. Retrieved January 31, 2017, from
http://kumphawapi.udonthani.doae.go.th/kaset-60.html.
Lan, Y., Thomson, S. J., Huang, Y., Hoffmann, W. C., & Zhang, H. (2010). Current status and future directions
of precision aerial application for site-specific crop management in the USA. Computers and
electronics in agriculture, 74(1), 34-38.
Land Development Department. (2009). Type of land use, level 1 of the Department of Land Development.
Retrieved January 22, 2017, from https://siriwanwebsite.wordpress.com
Lee, J., & Wong DW. (2000). Statistical with ArcView GIS. (2005), 260-264
Malczewski, J., (1999). GIS and multicriteria decision analysis. Department of Geography. (pp. 98-31452).
University of Western Ontario.
Moonlamani, J., Karnchanasutham, S., & Nualchawee, K. (2018). Application of geoinformation technology
for classification of para rubber plantation areas, the case study of Borikhamxai province, Lao, PDR,
Journal of Geoinformation Technol, 3, 13-26. (in Thai)
Office of the Cane and Sugar Board. (2013), The project under the evaluation of the development and
expansion of sugar cane varieties, Ministry of Industry, Bangkok, 35 p. (in Thai)
Office of the Cane and Sugar Board. (2014). Material of training of project to reduce the cost of sugarcane
production for farmer, Retrieved February 16, 2018, from
http://www.ocsb.go.th/upload/download/uploadfile/48-6461.
Office of the Cane and Sugar Board. (2017a). Sugarcane cultivation in the world, Retrieved June 6, 2017,
from http://www.ocsb.go.th/th/cms/detail.php?ID=9027&SystemModuleKey=international.
Office of the Cane and Sugar Board. (2017b). Sugarcane cultivation situation, production year 2008-2016.
Retrieved March 15, 2018, from http://www.ocsb.go.th/upload/journal/fileupload/923-9999.
Office of the Cane and Sugar Board. (2017c). Sugarcane plantation situation in Thailand, Director Cane and
Sugar Industry Policy Bureau, Retrieved February 18, 2017, from
http://www.ocsb.go.th/upload/journal/fileupload/923-9999.
Office of the Cane and Sugar Board. (2018). The satellite data analysis by computer program for sugarcane
classification. Retrieved February April 9, 2018, from
http://www.ocsb.go.th/upload/journal/fileupload/923-9999.
Pairot, V. (2015). Land use and Land Cover Change Simulation a Case Study of IndoChina Intersection
Development Scenario Phitsanulok. Retrieved March 23, 2018, from
http://www.arts.chula.ac.th/~geography/TSG2015/docs/FullPaper/FullPaper/2.8.pdf.
Phischayangkul, T. (2007). Examination the Accuracy of Data from Satellite Image Classification. Faculty of
Engineering. Technol Journal, (3), 24-26. (in Thai)
Rinthaisong, I. (2016). Multilevel Regression Models: Hierarchical Data Analysis Techniques in Organization
and Social, journal of Education Prince, (27) 3-17. (in Thai)
Som-ard, J. (2020). Rice Security Assessment Using Geo-Spatial Analysis. International Journal of
Geoinformatics.
Som-ard, J., Hossain, M. D., Ninsawat, S., & Veerachitt, V. (2018). Pre-harvest sugarcane yield estimation
using UAV-based RGB images and ground observation. Sugar Tech, 20(6), 645-657.
The North Eastern Sugarcane Farmers Group. (2016). Problems and obstacles encountered with sugarcane
farmers. Retrieved April 5, 2018, from https://www.homecable.co.th.
The North-Isan Sugarcane Planters Association. (2017). Spatial impact from sugarcane expansion. Retrieved
February 22, 2018, from http://www.ocsb.go.th/th/institute/detail.php?ID=105&GID=4.
Yamane, Taro.(1967). Statistics, An Introductory Analysis, 2nd Ed., New York: Harper and Row.
Refbacks
- There are currently no refbacks.