Prediction of Prime Wavelengths for the Estimation of Age Based Water Requirement of Arecanut Cropby Hyperspectral Data and VIP
Bhojaraja B E1, Amba Shetty2, M K Nagaraj3

1Bhojaraja B E, Civil Engineering Department, NMAMIT, Nitte-574110, Udupi Karnataka, India.
2Amba Shetty, Applied Mechanics and Hydraulics Department NITK-Surathkal, Mangalore Karnataka India.
3M K Nagaraj, Applied Mechanics and Hydraulics Department NITK-Surathkal, Mangalore Karnataka India.

Manuscript received on 29 June 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 July 2019 | PP: 1778-1783 | Volume-8 Issue-9, July 2019 | Retrieval Number: I7823078919/19©BEIESP | DOI: 10.35940/ijitee.I7823.078919

Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: In the world India is the highest producer and consumer of Arecanut. Also it is widely grown plantation crop in the coastal regions as well other parts of Karnataka. It has a great commercial value both in terms of export potential and revenue generation to the government. The crop sustains for a longer decade and demands huge amount of irrigation water throughout its life span. Assessment of exact amount of crop water requirement in different stages of the plant growth reduces the excessive irrigation. It increases crop yield thereby conserves both ground and surface water. The study targets to identify important wavelengths to predict age based crop water requirement. For this a small portion of the Channagiritaluk is considered for the study. The methodology adopted in this study uses the Hyperspectral data for age based classification of Arecanut crop to map its corresponding water requirement using NDVI based KC method. From the map pixel wise age based crop water requirement values were extractedand regressed with the corresponding spectral signatures from pre-processed satellite imagery. The PLSR model yielded a coefficient of determination of 0.98. The output of PLSR model results were used in VIP. Total of eight wavelengths, spanning across VNIR and SWIR regions were identified as significant in modeling the ACWR these were 1043, 1053, 1033, 1083, 1023, 1013, 1104, and 854nm. The identified wavelengths are useful to develop a model to estimate the water demand of the study area. The study helps for optimized planning of the water resources.
Keywords: Age Based Crop Water Requirement; Classification; Hyperspectra; PSLR; VIP.
Scope of the Article: Classification