Open Geosciences (Jan 2016)
Comparison of MODIS 250 m products for early corn yield predictions: a case study in Vojvodina, Serbia
Abstract
The aim of the paper is to compare Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) products with different compositing periods (8-day, 16-day and 8-day-dual) at 250 m spatial resolution for early corn yield estimation. In order to achieve this objective, several regression models were used where the average yield was the dependent variable and the different values of NDVI were independent variables. The various inputs in the regression models included: (i) maximum NDVI value (peak value) during the season or heading date value, (ii) NDVI values from the first date after heading date, (iii), NDVI values from the second date after heading date, (iv) Seasonally integrated NDVI values. Results showed that the 16-day composite was better yield predictor than the 8-day composite when using maximum NDVI value during the season, which is the value from the most significant earliest period for yield estimation, which is called the heading date. The 8-day composites were more useful than 16-day composites later in the season for yield estimation when NDVI values from first date after heading date and values from second date after heading were used. However, the 8-day-dual was not useful for yield prediction. In order to validate the results, the authors used the leave-one-year-out approach, which trains the remaining years for the left out year and is used for yield prediction for missing year. It was found that the inverse regression model produced the best yield estimates. After excluding the anomalous 2012 year, the R2 values for the regression model were > 0.5 for all remaining years and products, with statistical significant at 0.05. The smallest difference between predicted and actual corn yield when using 8-day composite was 0.05% while the largest difference was 34.47%, whilst in the case of 16-day composite the smallest difference between predicted and actual yield was 1.67% and the largest difference was 44.12%.
Keywords