This paper addresses the problem of

No abstract

In country like India, where agricultural economy plays major role, understanding and tracking the soil nutrients are essential. However, the chemical analysis, which determines the nutrient contents of soil, is expensive and time consuming. Hence, we attempt to exploit remote sensing imagery for estimating them. This paper analyzes the correlation between the level of soil nutrients and wavelet decompositions of remote sensing imagery of a particular region. Four renowned wavelet transformations such as Daubechies, Symlet, Biorthogonal and Coiflet are used to represent the image in wavelet domain. Subsequently, here exploit a neural network model to predict the soil nutrient content using the principle wavelet components. Experimental analysis on the prediction accuracy and the correlation measure reveals the suitability of each wavelet transformation of remote sensing imagery in predicting the soil nutrients.

Understanding soil nutrients using remote sensing imagery are highly insisted by researchers for a nation with commendatory agricultural landscapes such as India. A robust prediction model is always useful to perform cost efficient prediction using remote sensing imagery. This paper reports a preliminary analysis on wavelet transformations and their correlations with various soil nutrient contents to support and improve the prediction model. Firstly, we provide the chemical analysis report of our study regions, which are Baggi, Ibrahimpur, Mogara and Wai villages from Maharahstra province of India. The report reveals pH level, electrical conductivity, carbon, phosphorous and potassium contents of soil samples. Subsequently, we acquired satellite imagery and perform wavelet decompositions using first order Daubechies, Symlet, Biorthogonal and Coilflet wavelet transformations.Analysis is performed in MA TLAB to determ ine the correlation between the principle wavelet components and the soil nutrients. The analytical outcomes are believed to be a cornerstone for deriving wavelet decomposition based prediction models.