Earth Observing-1 (EO-1) Hyperion images were used to study five globally dominant crops (corn, cotton, rice, soybean, and winter wheat) and their growth stages in the United States, where they occupy about 75% of all the cropland areas occupied by the principal crops.
The researchers from USGS (United States Geological Survey) conducted this research to evaluate the suitability of hyperspectral satellite data to estimate the agricultural area under different major crop. The study identifies 30 optimal bands overcoming the data redundancy of Hyperion satellite data then linear discriminant analysis and support vector machines Regression was applied to classify crops. Global hyperspectral imaging spectral-library of agricultural crops (GHISA) was also developed for future use.
Study area and satellite data - The study was conducted in seven agro ecological zones of the United States using 99 Earth Observing-1 (EO-1) Hyperion hyperspectral images from 2008–2015 at 30 m resolution. The authors first developed a first-of-its-kind comprehensive Hyperion-derived Hyperspectral Imaging Spectral Library of Agricultural crops (HISA) of these crops in the US based on USDA Cropland Data Layer (CDL) reference data. Principal Component Analysis was used to eliminate redundant bands by using factor loadings to determine which bands most influenced the first few principal components. This resulted in the establishment of 30 optimal hyperspectral narrow bands (OHNBs) for the study of agricultural crops.
Spectral library development- Spectroscopy is a tool that detects the absorption or emission of light as a function of wavelength (USGS). Airborne and orbital spectrometers can detect, differentiate, and map subtle chemical differences in crops, minerals and other compounds. This digital representative pure spectrum of a particular feature is called it’s spectral library, in that particular environment. In this research authors first identified 30 optimal hyperspectral narrow bands out of 242 bands. It was found that 212 band were uncalibrated and poor for analysis. Then further processing of hyperspe3 library creation was performed
Contribution of the research work- 15–20 hyperspectral narrow bands (HNBs) achieved about 90% overall, producer’s, and user’s accuracies in classifying crop types and/or crop growth stages using llinear discriminant analysis (LDA) and/or the support vector machine (SVM) classifier. However, when complex situations occurred (e.g., 4 or more crops within a Hyperion image), up to 30 HNBs were required to best classify and characterize these crops. This study showed that hyperspectral satellite imagery, when analyzed on the GEE cloud computing platform using machine learning algorithms like SVMs, provides a fast and accurate means of classifying agricultural crops and their characteristics such as crop growth stages, which can help advance global food security information derived from satellites.
Future scope- This research makes a significant contribution toward understanding modeling, mapping, and monitoring agricultural crops using data from upcoming hyperspectral satellites, such as NASA’s Surface Biology and Geology mission (formerly HyspIRI mission) and the recently launched HysIS (Indian Hyperspectral Imaging Satellite, 55 bands over 400–950 nm in VNIR and 165 bands over 900–2500 nm in SWIR), and contributions in advancing the building of a novel, first-of-its-kind global hyperspectral imaging spectral-library of agricultural crops (GHISA: www.usgs.gov/WGSC/GHISA).
Gopal Krishna
Doctoral Researcher
New Delhi, India
