Khisa Faith, Musundi Catherine and Otulo Wandera Cyrilus

ABSTRACT

Food insecurity is an extensive problem in Kenya with an estimated 4.4 million facing chronic food shortages. The agricultural sector is vulnerable to food insecurity due to a variety of factors including the impact of climate change. In recent years there has been growing interest in use of spaceborne photography to improve yield estimation and reduce the impact of climate change on agriculture. In agriculture, mapping of crops provides an opportunity for government and research organizations to monitor agricultural activities for growers to understand crop status, and predict yields including the Normalized Difference Vegetation Index method which uses spaceborne photography to measure the amount of green vegetation in a given area. This study applies simple linear regression model to estimate maize yield using normalized difference vegetation index, determines the correlation between normalized difference Index and predicts maize yield using Normalized Difference Vegetation Index. The study employs linear regression model in determining the patterns, trends, and relationship between maize yield and the Normalized Difference Vegetation Index. The data analyzed in this study has been obtained from the Ministry of Agriculture. It consisted of historical yield records, and from Kenya Space Agency consisting of Normalized Difference Vegetation Index measurements. R software has been used for model analysis. A strong correlation between maize yield and Normalized Difference Vegetation Index (correlation coefficient >0.86) was realized. The p-value obtained are lower than 0.05 indicating that Normalized Difference Vegetation Index plays a major role in determining maize yield production. The study has successfully predicted the values of Maize yield using Normalized Difference Vegetation Index.