The purpose of this study is to effectively implement random forest algorithm for crop classification of large areas and to check the classification capability of different variables. To incorporate dependency of crops in different variables namely, texture, phenological, parent material and soil, soil moisture, topographic, vegetation, and climate, 35 digital layers are prepared using different satellite data (ALOS DEM, Landsat-8, MODIS NDVI, RISAT-1, and Sentinel-1A) and climatic data (precipitation and temperature). The importance of variables is also calculated based on mean decrease in accuracy and mean decrease in Gini score. Importance and capabilities of variables for crop mapping have been discussed. Variables associated with spectral responses have shown greater importance in comparison to topographic and climate variables. The spectral range (0.85 to 0.88 μm) of the near-infrared band is the most useful variable with the highest scores. The topographic variable and elevation have secured the second place rank in the both scores. This indicates the importance of spectral responses as well as of topography in model development. Climate variables have not shown as much importance as others, but in association with others, they cause a decrease in the out of bag (OOB) error rate. In addition to the OOB data, a 20% independent dataset of training samples is used to evaluate RF model. Results show that RF has good capability for crop classification.
Timely and accurate information about land cover is an important and extensively used application of remote sensing
data. After successful launch of Landsat 8 is providing a new data source for monitoring land cover, which has the
potential to improve the earth surface features characterization. Mapping of Leaf area Index (LAI) in larger area may be
impossible when we rely on field measurements. Remote sensing data have been continuing efforts to develop different
methods to estimate LAI. In this present study, an attempt has been made to discriminate various land cover features and
empirical equation is used for retrieve biophysical parameter (LAI) for satellite NDVI data. Support vector machine
classification was performed for Muzaffarnagar district using LANDSAT 8 operational land imager data to separate out
major land cover classes (water, fallow, built up, sugarcane, orchard, dense vegetation and other crops). Ground truth
data was collected using JUNO GPS which was used in developing the spectral signatures for each classes. The LAI-NDVI
existing empirical equation is used to prepare LAI map. It is found that the LAI values in village foloda region
maximum LAI pixels in the range 3.10 and above and minimum in the range 1.0 to 1.20. It is also concluded that the
LAI values between 1.70 and 3.10 is having most of the sugarcane crop pixels at maximum vegetative growth stage. It
shows that the sugarcane crop condition in the study area was very good.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.