Peanut is considered a crucial economic crop, and accurately identifying its planting areas is regarded as vital for ensuring food and oil security. This study utilizes ultra-high spatial resolution unmanned aerial vehicle (UAV) imagery and the random forest (RF) method to classify multispectral imagery. Three types of features are combined to identify peanut crop and verify accuracy. Results indicate that using only multispectral features yields unsatisfactory accuracy. Introducing texture features significantly improves classification accuracy, particularly for spectral features alone. However, accurately identifying crop pixels at field edges remains challenging due to noise influence. When UAV image spectral and texture features are employed for classification, the principal component analysis (PCA) method, combined with post-classification patch removal, proves to be the best strategy, achieving an overall classification accuracy of 98.17% and a Kappa coefficient of 0.97. The comprehensive peanut recognition accuracy reaches 90.39%.
The research was implemented in a planted area dominated by winter wheat in the Hebi city of Henan Province driving method and EnKF assimilation method were used to coupling the optimized and reconstructed MODIS LAI time series data and the rigorously calibrated wheat growth model WheatSM(Wheat Growth and Development Simulation Model) developed according to the planting varieties of the winter wheat region in North China respectively, the research on winter wheat yield estimation was conducted at field scale and regional scale from 2013 to 2016.The results show that : (1) The coupling simulation precision was inferior to the pre-coupled simulation precision at field scale simulation.(2)When the grid was used for regional scale simulation, the simulation accuracy of 1 km resolution grid point is higher than 5km resolution.(3)At two kinds of grid resolutions, EnKF assimilation simulation has the highest accuracy, followed by the driving method, and the simulation precision before coupling is the lowest. The RMSE of the total output of the EnKF assimilation simulation area and the actual total output at the 1 km resolution grid is 15.1. Assimilation of remote sensing information at fine grid resolution can improve the precision of regionalization application of the WheatSM model.
MERSI data are applied to generate NDVI and RVI change graphs for comparative monitoring of one large-area dry-hot wind disaster in the wheat-growing area of Henan province, analysis of the correlation of the NDVI variation and RVI variation arising from mild and severe dry-hot wind processes to the daily highest temperature, 14:00 ground wind speed of 10m and 14:00 humidity and establishment of a mono-factor and multi-factor regressive forecast model between vegetation index variation and disaster-causing atmospheric elements. The results show that the monitoring results of dry-hot wind disasters on the basis of two vegetation indexes highly conform to each other. In case of severe dry-hot wind process, the two vegetation index variations have a high relevance to the key meteorological elements, with R2 in the trinary linear regression model of meteorological elements being 0.706 and 0.708 respectively and the highest daily mean temperature passing the 0.05 significance level check. In case of mild dry-hot wind process, the two vegetation index variations have a very low relevance to the key meteorological elements and modeling is impossible and there is a high degree of difference between the variations of vegetation indexes of different stations, i.e. the lower the level of meteorological disaster is, the more telemetric data are needed to ensure the truthful disaster loss monitoring results and the more important field management measures as a defense against meteorological disasters.
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.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.