Forecasting Regional Sugarcane Yield Based on Time Integral and Spatial Aggregation of MODIS NDVI

Abstract

This study explored the suitability of the Normalized Difference Vegetation Index (NDVI) from the Moderate Resolution Imaging Spectrometer (MODIS) obtained for six sugar management zones, over nine years (2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010), to forecast sugarcane yield on an annual and zonal base. To take into account the characteristics of the sugarcane crop management (15-month cycle for a ratoon, accompanied with continuous harvest in Western Kenya), the temporal series of NDVI was normalized through an original weighting method that considered the growth period of the sugarcane crop (wNDVI), and correlated it with historical yield datasets. Results when using wNDVI were consistent with historical yield and significant at P-value = 0.001, while results when using traditional annual NDVI integrated over the calendar year were not significant. This correlation between yield and wNDVI is mainly drawn by the spatial dimension of the data set (R 2 = 0.53, when all years are aggregated together), rather than by the temporal dimension of the data set (R 2 = 0.1, when all zones are aggregated). A test on 2012 yield estimation with this model realized a RMSE less than 5 t· ha −1 . Despite progress in the methodology through the weighted OPEN ACCESSRemote Sens. 2013, 5 2185 NDVI, and an extensive spatio-temporal analysis, this paper shows the difficulty in forecasting sugarcane yield on an annual base using current satellite low-resolution data. This is particularly true in the context of small scale farmers with fields measuring less than the size of MODIS 250 m pixel, and in the context of a 15-month crop cycle with no seasonal cropping calendar. Future satellite missions should permit monitoring of sugarcane yields using image resolutions that facilitate extraction of crop phenology from a group of individual plots.

A Production Efficiency Model-Based Method for Satellite Estimates of Corn and Soybean Yields in the Midwestern US

“…One approach develops regression models that relate satellite-derived vegetation indices directly to historical yield data [15][16][17]. These models are essentially retrospective and are based empirically on indirect inferences, whereby changes in vegetation indices can determine variations in plant productions [14,18].…”

Remote Sensing Based Yield Estimation in a Stochastic Framework — Case Study of Durum Wheat in Tunisia

“…However, the best timing cannot be known a priori and must be determined from the data. Alternatively, time series of RS indicators can be further manipulated to derive more physiologically sound BPs, for example, by retrieving their peak level or amplitude during the season (e.g., [ 11]), expressing the RS indicator as a function of thermal instead of calendar time [ 12], or cumulating their values during an appropriate time period (e.g., [ 13]). …”

Advances in Remote Sensing of Agriculture: Context Description, Existing Operational Monitoring Systems and Major Information Needs

“…Strong reference is made to the excellent publication of Kastens et al [7]. It has also to be noted that time integration analysis generally increases the prediction accuracy, as, for example, presented in this special issue ( [32,46]). …”

“…Intensification, on the other hand, achieves higher yields through increased inputs, improved agronomic practices (e.g., drop irrigation), improved crop varieties and other innovations. Papers [30][31][32][33] demonstrate how remote sensing can contribute to the mapping of land under agricultural production. The review paper of Rembold et al (this issue) [34] provides an overview of remote sensing techniques for yield mapping.…”

“…The data recorded by current remote sensing satellites can be used to assess the two components of crop production [53]: yield [30][31][32]34,46,54] and acreage [10,37]. In addition, crop phenological information [12,55], stress situations [14,34,56] and disturbances [13,57] can be detected.…”