Browse > Article
http://dx.doi.org/10.7780/kjrs.2014.30.4.7

Early Production of Large-area Crop Classification Map using Time-series Vegetation Index and Past Crop Cultivation Patterns - A Case Study in Iowa State, USA -  

Kim, Yeseul (Department of Geoinformatic Engineering, Inha University)
Park, No-Wook (Department of Geoinformatic Engineering, Inha University)
Hong, Sukyoung (Climate Change & Agroecology Division, National Academy of Agricultural Science, Rural Development Administration)
Lee, Kyungdo (Climate Change & Agroecology Division, National Academy of Agricultural Science, Rural Development Administration)
Yoo, Hee Young (Geoinformatic Engineering Research Institute, Inha University)
Publication Information
Korean Journal of Remote Sensing / v.30, no.4, 2014 , pp. 493-503 More about this Journal
Abstract
A hierarchical classification scheme, which can reduce the spectral ambiguity and also reflect crop cultivation patterns from past land-cover maps, is presented for the purpose of the early production of crop classification maps in large-scale crop areas. Specifically, the effects of mixed pixels are minimized not only by applying a hierarchical classification approach based on different spectral characteristics from crop growth cycles, but also by considering temporal contextual information derived from past crop cultivation patterns. The applicability of the presented classification scheme was evaluated by a case study of Iowa State in USA with time-series MODIS 250 m Normalized Difference Vegetation Index(NDVI) data sets and past Cropland Data Layers(CDLs). Corn and soybean, which are major crop types in the study area and also display spectral similarity, could be properly classified by applying different classification stages and accounting for past crop cultivation patterns. The classification result by the presented scheme showed increases of minimum 7.68%p and maximum 20.96%p in overall accuracy, compared with one based on purely spectral information. In addition, the combination of temporal contextual information during classification was less affected by the number of NDVI data sets and the best overall accuracy of 86.63% was achieved. Thus, it is expected that this classification scheme can be effectively used for the early production of large-area crop classification maps in major feed-grain importing countries.
Keywords
Classification; Crop; Temporal Information; NDVI;
Citations & Related Records
Times Cited By KSCI : 6  (Citation Analysis)
연도 인용수 순위
1 Hong, S., B.-K. Min, J.-M. Lee, Y. Kim, and K. Lee, 2012. Estimation of paddy field area in North Korea using RapidEye images, Korean Journal of Soil Science and Fertilizer, 45(6): 1194-1202 (in Korean with English abstract).   과학기술학회마을   DOI   ScienceOn
2 Jang, J.-D., 2006. Rural land cover classification using multispectral image and LIDAR data, Korean Journal of Remote Sensing, 22(2): 101-110 (in Korean with English abstract).   과학기술학회마을   DOI
3 Krishnan, S., 2008. The tau model for data redundancy and information combination in earth sciences: theory and application, Mathematical Geology, 40(6): 705-727.
4 Lee, K., S. Hong, and Y. Kim, 2012. Farmland use mapping using high resolution images and land use change analysis, Korean Journal of Soil Science and Fertilizer, 45(6): 1164-1172 (in Korean with English abstract).   과학기술학회마을   DOI
5 Lee, M.-S., S.-J. Kim, H.-S. Shin, J.-K. Park, and J.-H. Park, 2009. Extraction of agricultural land use and crop growth information using KOMPSAT-3 resolution satellite image, Korean Journal of Remote Sensing, 25(5): 411-421 (in Korean with English abstract).   과학기술학회마을   DOI
6 Lee, S.-W. and N.-W. Park, 2011. Application of Bayesian probability rule to the combination of spectral and temporal contextual information in land-cover classification, Korean Journal of Remote Sensing, 27(4): 445-455 (in Korean with English abstract).   과학기술학회마을   DOI
7 McNairn, H., J. Shang, C. Champagne, and X. Jiao, 2009. TerraSAR-X and RADARSAT-2 for crop classification and acreage estimation, Proc. of 2009 IEEE International Geoscience and Remote Sensing Symposium, Cape Town, July 12-17, vol. 2, pp. 898-901.
8 Park, N.-W., 2010. Accounting for temporal contextual information in land-cover classification with multi-sensor SAR data, International Journal of Remote Sensing, 31(2): 281-298.   DOI   ScienceOn
9 Turker, M. and M. Arikan, 2005. Sequential masking classification of multi-temporal Landsat7 ETM+ images for field-based crop mapping in Karacabey, Turkey, International Journal of Remote Sensing, 26(17): 3813-3830.   DOI   ScienceOn
10 Wardlow, B.D. and S.L. Egbert, 2008. Large-area crop mapping using time-series MODIS 250m NDVI data: An assessment for the U.S. Central Great Plains, Remote Sensing of Environment, 112(3): 1096-1116.   DOI
11 Yoo, S.-H., J.-B. Im, J.-Y. Choi, and S.-H. Lee, 2012. Estimation of agricultural water and land required to substitute the import of feed-grain for domestic production, Journal of the Korean Society of International Agriculture, 24(3): 259-264 (in Korean with English abstract).
12 Boryan, C., Z. Yang, R. Mueller, and M. Craig, 2011. Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, Cropland Data Layer program, Geocarto International, 26(5): 341-358.   DOI
13 Chang, J., M.C. Hansesn, K. Pittman, M. Carroll, and C. Dimiceli, 2007. Corn and soybean mapping in the United States using MODIS time-series data sets, Agronomy Journal, 99(6): 1654-1664.   DOI
14 Cristianini, N. and J. Shawe-taylor, 2000. An Introduction to Support Vector Machines, Cambridge University Press, Cambridge, UK.
15 Hall, F.G. and G.D. Badwar, 1987. Signature-extendible technology: global space-based crop recognition, IEEE Transactions on Geoscience and Remote Sensing, 25(1): 93-103.