Abstract
Crop yield estimation is a very important aspect in food production as it provides information to policy and decision makers that can guide food supply not only to a nation but also influence its import and export dynamics. Remote sensing has the ability to provide the given tool for crop yield predictions before harvesting. This study utilised canopy reflectance from a multispectral sensor to develop vegetation indices that serve as input variables into an empirical pre-harvest maize (Zea mays) yield prediction model in the north eastern section in Free State province of South Africa. Some fields in this region that were grown of maize under rain-fed conditions were monitored and the grain harvested after 7-8 months with actual yields measured. The acquisition of suitable medium resolution SPOT 5 images over this area was in March and June before the grains were harvested in July of 2014. A number of well known spectral indices were developed using the visible and near infrared bands. Through the random forest algorithm predictive models, maize grain yields were estimated successfully from the March images. The accuracies of these models were of an R2 of 0.92 (RMSEP = 0.11, MBE = -0.08) for the Agnes field and for Cairo the R2 was 0.9 (RMSEP = 0.03, MBE = 0.004). These results were produced by the SAVI and NDVI respectively for both fields. It was therefore evident that the predictive model applied in this study was site specific and would be interesting to be tested for an optimal period during the plant life cycle to predict grain yields of maize in South Africa.Keywords: maize, non-linear regressions, prediction, random forest, spectral indices, SPOT 5, variable importance, yield
Highlights
The Random forest (RF) prediction models for maize grain yield including all the developed spectral vegetation indices in this study proved successful through the varied values of the parameters
In-field maize yield estimation or prediction using multispectral satellite imagery of medium resolution over rain-fed fields proved successful through the use of vegetation spectral indices
The spectral indices derived from SPOT 5 imageries were used as input variables into the random forest algorithm for regression analysis in predicting the grain yield by weight of maize across both fields with a good accuracy of high coefficient of determination (R2) values and low root mean squared error of prediction (RMSEP) as well as mean bias error (MBE) values
Summary
Crop yield prediction is production estimates that are made a couple of months or weeks depending on the crop in question before the actual harvest. This is frequently done through computer programmes that utilize agro-meteorological data, soil data, remotely sensed and agricultural statistics to describe quantitatively the plant-environment interactions (Zere et al, 2004). Meteorological data is included to run some of the yield models. The meteorological data is usually generated from weather stations and cover a given area. Crop yield can be described as involving the effect of biotic and abiotic factors cumulatively which could vary not just across fields but among fields and seasons alike (Bullock, 2004)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
