TY - JOUR
T1 - Prediction of rice crop yield using MODIS EVI-LAI data in the Mekong Delta, Vietnam
AU - Son, N. T.
AU - Chen, C. F.
AU - Chen, C. R.
AU - Chang, L. Y.
AU - Duc, H. N.
AU - Nguyen, L. D.
N1 - Funding Information:
This research was supported by National Central University and National Science Council (NSC100-2221-E-008-103), Taiwan. Their financial support is acknowledged. We are grateful to the staff of the Faculty of Agriculture and Natural Resources, An Giang University, and the GIS and Remote Sensing Research Centre, Academy of Science and Technology, Vietnam, for help in the collection of rice yield statistics and field-related data.
PY - 2013/10
Y1 - 2013/10
N2 - Predicting rice crop yield at the regional scale is important for production estimates that ensure food security for a country. This study aimed to develop an approach for rice crop yield prediction in the Vietnamese Mekong Delta using the Moderate Resolution Imaging Spectroradiometer (MODIS) enhanced vegetation index (EVI) and leaf area index (LAI). Data processing consisted of four main steps: (1) constructing time-series vegetation indices, (2) noise filtering of time-series data using the empirical mode decomposition (EMD), (3) establishment of crop yield models, and (4) model validation. The results indicated that the quadratic model using two variables (EVI and LAI) produced more accurate results than other models (i.e. linear, interaction, pure quadratic, and quadratic with a single variable). The highest correlation coefficients obtained at the ripening period for the spring-winter and autumn-summer crops were 0.70 and 0.74, respectively. The robustness of the established models was evaluated by comparisons between the predicted yields and crop yield statistics for 10 sampling districts in 2006 and 2007. The comparisons revealed satisfactory results for both years, especially for the spring-winter crop. In 2006, the root mean squared error (RMSE), mean absolute error (MAE), and mean bias error (MBE) for the spring-winter crop were 10.18%, 8.44% and 0.9%, respectively, while the values for the autumn-summer crop were 17.65%, 14.06%, and 3.52%, respectively. In 2007, the spring-winter crop also yielded better results (RMSE = 10.56%, MAE = 9.14%, MBE = 3.68%) compared with the autumn-summer crop (RMSE = 17%, MAE = 12.69%, MBE = 2.31%). This study demonstrates the merit of using MODIS data for regional rice crop yield prediction in the Mekong Delta before the harvest period. The methods used in this study could be transferable to other regions around the world.
AB - Predicting rice crop yield at the regional scale is important for production estimates that ensure food security for a country. This study aimed to develop an approach for rice crop yield prediction in the Vietnamese Mekong Delta using the Moderate Resolution Imaging Spectroradiometer (MODIS) enhanced vegetation index (EVI) and leaf area index (LAI). Data processing consisted of four main steps: (1) constructing time-series vegetation indices, (2) noise filtering of time-series data using the empirical mode decomposition (EMD), (3) establishment of crop yield models, and (4) model validation. The results indicated that the quadratic model using two variables (EVI and LAI) produced more accurate results than other models (i.e. linear, interaction, pure quadratic, and quadratic with a single variable). The highest correlation coefficients obtained at the ripening period for the spring-winter and autumn-summer crops were 0.70 and 0.74, respectively. The robustness of the established models was evaluated by comparisons between the predicted yields and crop yield statistics for 10 sampling districts in 2006 and 2007. The comparisons revealed satisfactory results for both years, especially for the spring-winter crop. In 2006, the root mean squared error (RMSE), mean absolute error (MAE), and mean bias error (MBE) for the spring-winter crop were 10.18%, 8.44% and 0.9%, respectively, while the values for the autumn-summer crop were 17.65%, 14.06%, and 3.52%, respectively. In 2007, the spring-winter crop also yielded better results (RMSE = 10.56%, MAE = 9.14%, MBE = 3.68%) compared with the autumn-summer crop (RMSE = 17%, MAE = 12.69%, MBE = 2.31%). This study demonstrates the merit of using MODIS data for regional rice crop yield prediction in the Mekong Delta before the harvest period. The methods used in this study could be transferable to other regions around the world.
UR - http://www.scopus.com/inward/record.url?scp=84881637523&partnerID=8YFLogxK
U2 - 10.1080/01431161.2013.818258
DO - 10.1080/01431161.2013.818258
M3 - 期刊論文
AN - SCOPUS:84881637523
SN - 0143-1161
VL - 34
SP - 7275
EP - 7292
JO - International Journal of Remote Sensing
JF - International Journal of Remote Sensing
IS - 20
ER -