Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Rice Yield Estimation of South Korea from Year 2003-2016 Using Stacked Sparse AutoEncoder

SSAE 알고리즘을 통한 2003-2016년 남한 전역 쌀 생산량 추정

  • Ma, Jong Won (School of Civil and Environmental Engineering, Yonsei University) ;
  • Lee, Kyungdo (National Institute of Agricultural Science, RDA) ;
  • Choi, Ki-Young (Fisheries and Agriculture Department, Statistics Korea) ;
  • Heo, Joon (School of Civil and Environmental Engineering, Yonsei University)
  • 마종원 (연세대학교 건설환경공학과) ;
  • 이경도 (농촌진흥청 국립농업과학원) ;
  • 최기영 (통계청 농어업통계과) ;
  • 허준 (연세대학교 건설환경공학과)
  • Received : 2017.08.29
  • Accepted : 2017.09.20
  • Published : 2017.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

The estimation of rice yield affects the income of farmers as well as the fields related to agriculture. Moreover, it has an important effect on the government's policy making including the control of supply demand and the price estimation. Thus, it is necessary to build the crop yield estimation model and from the past, many studies utilizing empirical statistical models or artificial neural network algorithms have been conducted through climatic and satellite data. Presently, scientists have achieved successful results with deep learning algorithms in the field of pattern recognition, computer vision, speech recognition, etc. Among deep learning algorithms, the SSAE (Stacked Sparse AutoEncoder) algorithm has been confirmed to be applicable in the field of forecasting through time series data and in this study, SSAE was utilized to estimate the rice yield in South Korea. The climatic and satellite data were used as the input variables and different types of input data were constructed according to the period of rice growth in South Korea. As a result, the combination of the satellite data from May to September and the climatic data using the 16 day average value showed the best performance with showing average annual %RMSE (percent Root Mean Square Error) and region %RMSE of 7.43% and 7.16% that the applicability of the SSAE algorithm could be proved in the field of rice yield estimation.

쌀 생산량 예측 및 조사는 농가 소득 보전 및 농업 분야 기관에 영향을 주고 수급 조절과 가격 예측 등 정부의 정책 수립과 관련하여 중요한 의미를 갖는다. 이에 따라 작황 추정 모델의 구축이 필요하며 과거로부터 기상 자료 및 위성 자료를 통해 경험적 통계 모델 또는 인공신경망 알고리즘을 기반으로 한 연구가 다수 진행되었다. 현재 인공신경망 모델을 기반으로 개발된 딥 러닝 알고리즘이 패턴 인식, 컴퓨터 비전, 음성 인식 등의 분야에서 폭넓게 사용되며 뛰어난 성능을 보이고 있다. 최근 다양한 딥 러닝 알고리즘 중 SSAE 알고리즘이 시계열 자료를 통한 예측 분야에서 적용 가능성이 확인되었으며 본 연구에서는 SSAE를 통해 남한 전역에 대한 쌀 생산량 추정 연구를 진행하였다. 입력 변수로 기상자료와 위성자료를 사용하였으며 남한 벼의 생육 기간을 고려하여 입력 자료를 기간별로 나누고 최적의 입력 자료롤 찾고자 하였다. 실험 결과, 5월부터 9월까지의 위성 자료와 16일 평균값을 사용한 기상 자료와의 조합을 사용하였을 경우 평균 연도별 %RMSE, 시군구 %RMSE 각각 7.43%, 7.16%로 가장 좋은 성능을 보였으며 이를 통해 쌀 생산량 추정 분야에 대한 SSAE 알고리즘의 적용 가능성을 확인할 수 있었다.

Keywords

References

  1. Alvarez, R., 2009. Predicting average regional yield and production of wheat in the Argentine Pampas by an artificial neural network approach, European Journal of Agronomy, 30(2): 70-77. https://doi.org/10.1016/j.eja.2008.07.005
  2. Ahn, J., J. Hur, and K. Shim, 2010. A Simulation of Agro-Climate Index over the Korean Peninsula Using Dynamical Downscaling with a Numerical Weather Prediction Model, Korean Journal of Agricultural and Forest Meteorology, 12(1): 1-10 (in Korean with English abstract). https://doi.org/10.5532/KJAFM.2010.12.1.001
  3. Busseti, E., I. Osband, and S. Wong, 2012. Deep learning for time series modeling, Technical report, Stanford University, Stanford, CA, USA.
  4. Fang, H., S. Liang, and G. Hoogenboom, 2011. Integration of MODIS LAI and vegetation index products with the CSM CERES Maize model for corn yield estimation, International Journal of Remote Sensing, 32(4): 1039-1065. https://doi.org/10.1080/01431160903505310
  5. Hong, S. Y., J. Hur, J. B. Ahn, J. M. Lee, B. K. Min, C. K. Lee, ... and K. M. Shim, 2012. Estimating rice yield using MODIS NDVI and meteorological data in Korea, Korean Journal of Remote Sensing, 28(5): 509-520 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2012.28.5.4
  6. Irmak, A., J. Jones, W. Batchelor, S. Irmak, K. Boote, and J. Paz, 2006. Artificial neural network model as a data analysis tool in precision farming, Transactions of the American Society of Agricultural and Biological Engineeres, 49(6): 2027-2037.
  7. Jaikla, R., S. Auephanwiriyakul, and A. Jintrawet, 2008. Rice yield prediction using a support vector regression method, Proc., Electrical Engineering/ Electronics, Computer, Telecommunications and Information Technology, 5th International Conference on, IEEE, Krabi, Thailand, May 14-17, vol. 1, pp. 29-32.
  8. Ji, B., Y. Sun, S. Yang, and J. Wan, 2007. Artificial neural networks for rice yield prediction in mountainous regions, The Journal of Agricultural Science, 145(3): 249-261. https://doi.org/10.1017/S0021859606006691
  9. Kaul, M., R. L. Hill, and C. Walthall, 2005. Artificial neural networks for corn and soybean yield prediction, Agricultural Systems, 85(1): 1-18. https://doi.org/10.1016/j.agsy.2004.07.009
  10. Khodayar, M. and M. Teshnehlab, 2015. Robust deep neural network for wind speed prediction, Fuzzy and Intelligent Systems (CFIS), 2015 4th Iranian Joint Congress, Zahedan, Iran, Sep. 9-11, pp. 1-5.
  11. Kim, J. S., S. H. Lee, H. S. Choi, G. S. Choi, J. D. Cho, and B. N. Chung, 2008. Survey of viral diseases occurrence on major crops in 2007, Research in Plant Disease, 14(14): 1-9 (in Korean with English abstract). https://doi.org/10.5423/RPD.2008.14.1.001
  12. Kim, Y., H. Lee, and S. Hong, 2013. Continuous monitoring of rice growth with a stable groundbased scatterometer system, IEEE Geoscience and Remote Sensing Letters, 10(4): 831-835. https://doi.org/10.1109/LGRS.2012.2225595
  13. KMA, 2017. Korea Meteorological Administration -Domestic climatic information, http://www.kma.go.kr/weather/climate/average_south.jsp, Accessed Jul. 1, 2017.
  14. KOSIS, 2017. Korean Statistic - Administrative District rice yield production, http://kosis.kr/statHtml/statHtml.do?orgId=101&tblId=DT_1ET0034, Accessed Jul. 1, 2017.
  15. Li, A., Liang, S., Wang, A., and J. Qin, 2007. Estimating crop yield from multi-temporal satellite data using multivariate regression and neural network techniques, Photogrammetric Engineering & Remote Sensing, 73(10): 1149-1157. https://doi.org/10.14358/PERS.73.10.1149
  16. Liu, J. N., Y. Hu, J. J. You, and P. W. Chan, 2014. Deep neural network based feature representation for weather forecasting, Proceedings on the International Conference on Artificial Intelligence (ICAI), The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp), Las Vegas, NV, Jul. 21-24, p. 1.
  17. Lv, Y., Y. Duan, W. Kang, Z. Li, and F. Y. Wang, 2015. Traffic flow prediction with big data : a deep learning approach, IEEE Transactions on Intelligent Transportation Systems, 16(2): 865-873. https://doi.org/10.1109/TITS.2014.2345663
  18. Na, S.-I., J. H. Park, and J. K. Park, 2012. Development of Korean Paddy Rice yield Prediction Model (KRPM) using meteorological element and MODIS NDVI, Journal of the Korean Society of Agricultural Engineers, 54(3): 141-148 (in Korean with English abstract). https://doi.org/10.5389/KSAE.2012.54.3.141
  19. Na, S. I., S. Y. Hong, Y. H. Kim, K. D. Lee, and S. Y. Jang, 2013. Prediction of rice yield in Korea using paddy rice NPP index-Application of MODIS data and CASA model, Korean Journal of Remote Sensing, 29(5): 461-476 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2013.29.5.2
  20. Ng, A., 2011. Sparse autoencoder. CS294A Lecture notes, Stanford University, Stanford, CA, USA.
  21. Nuarsa, I. W., F. Nishio, and C. Hongo, 2011. Rice yield estimation using Landsat ETM+ data and field observation, Journal of Agricultural Science, 4(3): 45-56.
  22. Prasad, A. K., L. Chai, R. P. Singh, and M. Kafatos, 2006. Crop yield estimation model for Iowa using remote sensing and surface parameters, International Journal of Applied Earth Observation and Geoinformation, 8(1): 26-33. https://doi.org/10.1016/j.jag.2005.06.002
  23. Ranzato, M, Huang, F. J., Boureau, Y. L., and Y. LeCun, 2007. Unsupervised learning of invariant feature hierarchies with applications to object recognition, Computer Vision and Pattern Recognition (CVPR), 2007 IEEE Computer Society, Minnesota, USA, Jun.18-23, pp. 1-8.
  24. Yoo, S. H., J. Y. Choi, S. H. Lee, Y. G. Oh, and D. K. Yun, 2013. Climate change impacts on water storage requirements of an agricultural reservoir considering changes in land use and rice growing season in Korea, Agricultural Water Management, 117: 43-54. https://doi.org/10.1016/j.agwat.2012.10.023
  25. Uno, Y., S. O. Prasher, R. Lacroix, P. K. Goel, Y. Karimi, A. Viau, and R. M. Patel, 2005. Artificial neural networks to predict corn yield from Compact Airborne Spectrographic Imager data, Computers and Electronics in Agriculture, 47(2): 149-161. https://doi.org/10.1016/j.compag.2004.11.014
  26. USDA, 2017. Crop Explorer, http://www.pecad.fas.usda.gov/cropexplorer/, Accessed Jul. 1, 2017.
  27. Yun, J. I., 2003. Predicting regional rice production in South Korea using spatial data and crop-growth modeling, Agricultural Systems, 77(1): 23-38. https://doi.org/10.1016/S0308-521X(02)00084-7