Crop Discrimination Based on Reflectance Spectroscopy Using Spectral Vegetation Indices (SVI)
This paper represents three main objectives of research, including (1) development of crop spectral library for diverse crops, (2) combination of two varying spectral responses for crop benchmarking, (3) interpretation of spectral features using Spectral Vegetation Indices (SVI). Hyperspectral sensors were used for spectral development including Maize, Cotton, Sorghum, Bajara, Wheat and Sugarcane crops with Analytical Spectral Device (ASD) Spectroradiometer and Earth Observing (EO)-1 Hyperion dataset positioned at Aurangabad region by Latitude 19.897827 and Longitude 75.308666. In precision agriculture, the Spectral Vegetation Indices (SVI) delivers valuable information for crop discrimination and growth monitoring; the present research elaborates about five SVI. The spectral responses were collected at the ripening stage of crops at standard darkroom environment in the laboratory. It was found that there was a progressive correlation 0.92 with squared residual value 4.69 amongst ASD and EO-1 Hyperion. The significant spectral features were recognized inAnthrocyanin Reflectance Index 1 (ARI1) with R550, R700, for Moisture Stress Index (MSI) R1599, R819 wavelength respectively. The experimental analysis was performed using ENVI and python open source software and it was concluded that crops types were successfully discriminated based on spectral parameters with different band combinations.
KeywordsHyperspectral remote sensing Precision agriculture Spectral signature Spectral vegetation indices Regression model
Authors would like to acknowledge for providing partial technical support under UGC SAP (II) DRS Phase-II, DST-FIST and NISA to Department of Computer Science & IT, Dr Babasaheb Ambedkar Marathwada University, Aurangabad, Maharashtra, India and also thanks for financial assistance under UGC-BSR research fellowship for this research work.
- 1.Haboudane, D., Tremblay, N., et al.: Estimation of plant chlorophyll using hyperspectral observations and radiative transfer models: spectral indices sensitivity and crop type effects. In: IGARSS. IEEE (2008). 978-1-4244-2808-03Google Scholar
- 2.Hatfield, J.L., Gitelson, A.A., Scherpers, J.S., et al.: Application of remote sensing for agronomic decisions. Agron. J. 100, S-117–S-131 (2006)Google Scholar
- 3.Holecz, F., Barbieri, M., Collivignarelli, F., Gatt, L.: An operational remote sensing based service for rice production estimation at a national scale. In: Proceeding of ESA Living Planet Symposium, pp. 1–11 (2013)Google Scholar
- 5.Ling, C., Liu, H., Ju, H., Zhang, H., You, J., Li, W.: A study on spectral signature analysis of wetland vegetation based on ground imaging spectrum data. J. Phys. 910, 012045 (2017)Google Scholar
- 8.Stanhill, G., Kafkafi, U., Fuchs, M., Kagan, Y.: The effect of fertiliser application on solar reflectance from a wheat crop. Israel J. Agric. 22, 109–118 (1972)Google Scholar
- 10.Reynolds, C.A., Yitayew, M., Slack, D.C., Hutchinson, C.F., Huete, A., Petersen, M.S.: Estimating crop yields and production by integrating the FAO crop specific water balance model with real-time satellite data and ground-based ancillary data. Int. J. Remote Sens. 21, 3487–3508 (2002)CrossRefGoogle Scholar
- 13.Surase, R.R., Varpe, A., Solankar, M., Gite, H., Kale, K.: Development of non-imaging spectral library via Field Spec4 spectroradiometer. Int. J. Res. Eng. Appl. Manage. (IJREAM). ISSN 2454-9150 Special Issue - NCCT – 2018Google Scholar
- 22.Kim, Y., Michael Glenn, D., Park, J., Lehman, B.L.: Hyperspectral image analysis for plant stress detection. An ASABE Meeting presentation, Paper Number-1009114 (2010)Google Scholar