RETRACTED ARTICLE: Development of a crop‐specific spectral library and discrimination of various agricultural crop varieties using hyperspectral imagery

Nidamanuri, ‪Rama Rao

doi:10.1080/01431160701241779

Cited by 59 publications

(44 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The most common method for collecting hyperspectral data was through the use of handheld spectroradiometers [14][15][16][17][18], however, reflectance data were also simulated using spectral reflectance models [19] or collected via hyperspectral satellite imagery [20][21][22]. Typically, studies that used handheld devices were conducted in the visible (350-700 nm) and near-infrared (NIR) portions of the electromagnetic spectrum (EMS).…”

Section: Introductionmentioning

confidence: 99%

“…Typically, studies that used handheld devices were conducted in the visible (350-700 nm) and near-infrared (NIR) portions of the electromagnetic spectrum (EMS). A number of studies have focused on discriminating weed species [5,7], different strands or cultivars of the same crop such as wheat, rice and cotton [6,23,24] and finally different species of crop altogether [8,22,25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Separating Crop Species in Northeastern Ontario Using Hyperspectral Data

2014

View full text Add to dashboard Cite

Abstract:The purpose of this study was to examine the capability of hyperspectral narrow wavebands within the 400-900 nm range for distinguishing five cash crops commonly grown in Northeastern Ontario, Canada. Data were collected from ten different fields in the West Nipissing agricultural zone (46°24'N lat., 80°07'W long.) and included two of each of the following crop types; soybean (Glycine max), canola (Brassica napus L.), wheat (Triticum spp.), oat (Avena sativa), and barley (Hordeum vulgare). Stepwise discriminant analysis was used to assess the spectral separability of the various crop types under two scenarios; Scenario 1 involved testing separability of crops based on number of days after planting and Scenario 2 involved testing crop separability at specific dates across the growing season. The results indicate that select hyperspectral bands in the visual and near infrared (NIR) regions (400-900 nm) can be used to effectively distinguish the five crop species under investigation. These bands, which were used in a variety of combinations include B465, B485, B495, B515, B525, B535, B545, B625, B645, B665, B675, B695, B705, B715, B725, B735, B745, B755, B765, B815, B825, B885, and B895. In addition, although species classification could be achieved at any point during the growing season, the optimal time for satellite image acquisition was determined to be in late July or approximately 75-79 days after planting with the optimal wavebands located in the red-edge, green, and NIR regions of the spectrum.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Separating Crop Species in Northeastern Ontario Using Hyperspectral Data

2014

View full text Add to dashboard Cite

show abstract

“…To find out the relation between different crops types and hyperspectral data various methods like discriminant analysis, principal components analysis, partial least square regression analysis are used. The significant wave bands vary location to location and crop species however red edge and NIR region of spectra plays a major role in crop species discrimination as noticed by Jeffrey et al, 2014 and The studies have concentrated on identifying cultivar levels or strands of a crop like cotton, wheat (Zhang Mahesh, 2008) and overall mixture of these crop species (Rao et al, 2008). However these studies are often constricted to limited observations for a certain growth stage through out the growing season and didn't take care of chances of noise which couldn't be ignored.…”

Section: Hyperspectral Remote Sensing Perspectivementioning

confidence: 99%

“…For this study, ground based hyperspectral measurements were taken by following the methodology of Rao, 2008 andWang et al, 2009. It was made possible by using an ASD hand held portable Spectroradiometer with a spectral range of 350-1050 nm.…”

Section: Data Usedmentioning

confidence: 99%

Hyperspectral remote sensing of paddy crop using insitu measurement and clustering technique

Moharana

Dutta

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Rice Agriculture, mainly cultivated in South Asia regions, is being monitored for extracting crop parameter, crop area, crop growth profile, crop yield using both optical and microwave remote sensing. Hyperspectral data provide more detailed information of rice agriculture. The present study was carried out at the experimental station of the Regional Rainfed Low land Rice Research Station, Assam, India (26.1400°N, 91.7700°E) and the overall climate of the study area comes under Lower Brahmaputra Valley (LBV) Agro Climatic Zones. The hyperspectral measurements were made in the year 2009 from 72 plots that include eight rice varieties along with three different level of nitrogen treatments (50, 100, 150 kg/ha) covering rice transplanting to the crop harvesting period. With an emphasis to varieties, hyperspectral measurements were taken in the year 2014 from 24 plots having 24 rice genotypes with different crop developmental ages. All the measurements were performed using a spectroradiometer with a spectral range of 350-1050 nm under direct sunlight of a cloud free sky and stable condition of the atmosphere covering more than 95% canopy. In this study, reflectance collected from canopy of rice were expressed in terms of waveforms. Furthermore, generated waveforms were analysed for all combinations of nitrogen applications and varieties. A hierarchical clustering technique was employed to classify these waveforms into different groups. By help of agglomerative clustering algorithm a few number of clusters were finalized for different rice varieties along with nitrogen treatments. By this clustering approach, observational error in spectroradiometer reflectance was also nullified. From this hierarchical clustering, appropriate spectral signature for rice canopy were identified and will help to create rice crop classification accurately and therefore have a prospect to make improved information on rice agriculture at both local and regional scales. From this hierarchical clustering, spectral signature library for rice canopy were identified which will help to create rice crop classification maps and critical wave bands like green (519,559 nm), red (649 nm), red edge (729 nm) and NIR region (779,819 nm) were marked sensitive to nitrogen which will further help in nitrogen mapping of paddy agriculture over therefore have the prospect to make improved informed decisions.

show abstract

“…In order to identify different types of crops, several approaches have been proposed. For example, Zhang et al [57] made use of Fast Fourier Transforms on MODIS NDVI series, Blaes et al [58] discussed the synergy of optical and Synthetic Aperture Radar (SAR) image time series for this purpose and Rao [59] developed a spectral library from in situ hyperspectral data to carry out classification of a remote sensing image.…”

Section: Land Use From Remote Sensing Datamentioning

confidence: 99%

Potential of Using Remote Sensing Techniques for Global Assessment of Water Footprint of Crops

Romaguera

Hoekstra

et al. 2010

Remote Sensing

View full text Add to dashboard Cite

Abstract:Remote sensing has long been a useful tool in global applications, since it provides physically-based, worldwide, and consistent spatial information. This paper discusses the potential of using these techniques in the research field of water management, particularly for 'Water Footprint' (WF) studies. The WF of a crop is defined as the volume of water consumed for its production, where green and blue WF stand for rain and irrigation water usage, respectively. In this paper evapotranspiration, precipitation, water storage, runoff and land use are identified as key variables to potentially be estimated by remote sensing and used for WF assessment. A mass water balance is proposed to calculate the volume of irrigation applied, and green and blue WF are obtained from the green and blue evapotranspiration components. The source of remote sensing data is described and a simplified example is included, which uses evapotranspiration estimates from the geostationary satellite Meteosat 9 and precipitation estimates obtained with the Climatic Prediction Center Morphing Technique (CMORPH). The combination of data in this approach brings several limitations with respect to discrepancies in spatial and temporal resolution and data availability, which are discussed in detail. This work provides new tools for global WF assessment and represents an innovative approach to global irrigation mapping, enabling the estimation of green and blue water use. OPEN ACCESSRemote Sens. 2010, 2 1178

show abstract

RETRACTED ARTICLE: Development of a crop‐specific spectral library and discrimination of various agricultural crop varieties using hyperspectral imagery

Cited by 59 publications

References 8 publications

Separating Crop Species in Northeastern Ontario Using Hyperspectral Data

Separating Crop Species in Northeastern Ontario Using Hyperspectral Data

Hyperspectral remote sensing of paddy crop using insitu measurement and clustering technique

Potential of Using Remote Sensing Techniques for Global Assessment of Water Footprint of Crops

Contact Info

Product

Resources

About