Yield Estimation and Validation of Potatoes Using Remote Sensing based Crop Yield Model

Multispectral aerial and satellite remote sensing plays a major role in crop yield prediction due to its ability to represent crop growth condition on a spatial and temporal scale as well as its cost effectiveness. Multispectral remote sensing significantly helps in exploring the relationships between crop biophysical data namely vegetation development, photosynthetic activity (PAR), biomass accumulation, leaf area index (LAI), and crop evapotranspiration (ET), with crop production. High resolution multispectral airborne and satellite data can be used to improve crop yield models by taking into account areas of soil and crop growth variability within a field and their impact on crop water use and yield. Many empirical relationships have been established in the past between spectral vegetation indices and leaf area index, fractional ground cover and crop growth rates through ground sampling. Various remote sensing based vegetation index (VI) yield models using airborne and satellite data are restricted to grain crops like barley, corn, wheat, cotton, sugarcane etc. So it becomes important to validate and extend the VI based model for tuber crops like potato taking into account of significant parameters that affects the final crop yield to a large extent. This study involves the use of 2004 year high-resolution multispectral aerial data to develop a vegetation index based statistical yield model for potato crop and validate the model using 2005 year airborne spot yield and whole field yield data. Spot yield samples collected from potato fields in the year 2004 was used to develop the yield model based on three date integrated Soil Adjusted Vegetation Index (SAVI). Each yield sample was identified based on soil and crop growth patterns in the study field having 3.63m by 3.03m size. The three date integrated SAVI over the critical stages of crop season correlated well with the measured yields (r-squared of 0.81). The single date SAVI model developed prior to effective full cover best explained the variability in the yields. The yield model developed for airborne data was also applied to satellite data for the same study area and tested. The model predicted quite well with the satellite data and the unexplained variability in the model needs to be further investigated. As potato crop is highly sensitive to water stress, maintaining optimal soil moisture in the root zone is required to obtain high quality yields and profit. An attempt was also made to improve this model by conducting a soil water balance in the root zone of the crop and incorporating actual ET into the yield model as a method to improve yield predictions