Hyper Spectral Measurements as a Method for Potato Crop Characterization
Abstract
The main objectives of this research is to determine the optimal hyperspectral range and waveband/s in the spectral range of (400–2500 nm) to discriminate between four different varieties of Potato crop (Diamond, Everest, Mondial and Rosetta) that are cultivated in old and newly cultivated lands of Egypt and to propose detailed spectral reflectance characterization for these four varieties which will enable more accurate surveying of these varieties through satellite imagery. Hyperspectral ground measurements of ASD field Spec3 spectroradiometer was used to monitor the spectral reflectance profile during the period of the maximum growth stage of the crop. An average of thirty measurements for each variety was considered in the process. After accounting for atmospheric windows and/or areas of significant noise, a total of 2150 narrow bands in 400–2500 nm were used in the analysis. Spectral reflectance was divided into six spectral zones: blue, green, red, near-infrared, shortwave infrared-I and shortwave infrared-II. One Way ANOVA and Tukey’s HSD analysis was used to choose the optimal spectral zone that could be used to differentiate between the four varieties. Then, linear discrimination analysis (LDA) was used to identify the specific optimal wavebands in the spectral zones in which each variety could be spectrally identified. The results of Tukey’s HSD showed that NIR is the best spectral zone for the discrimination between the four varieties. The other five spectral zones showed close spectral characterizations between at least two varieties. The results of (LDA) showed the optimal waveband to identify each variety. These results will be used in machine learning process to improve the performance of the existing remote sensing software's to estimate potato crop acreage. The study was carried out in AlBuhayrah governorate of Egypt.
Keywords
Refbacks
- There are currently no refbacks.


This work is licensed under a Creative Commons Attribution 3.0 License.
*2016 Journal Impact Factor was established by dividing the number of articles published in 2014 and 2015 with the number of times they are cited in 2016 based on Google Scholar, Google Search and the Microsoft Academic Search. If ‘A’ is the total number of articles published in 2014 and 2015, and ‘B’ is the number of times these articles were cited in indexed publications during 2016 then, journal impact factor = A/B. To know More: (http://en.wikipedia.org/wiki/Impact_factor)