scholarly journals Estimating Fractional Vegetation Cover of Row Crops from High Spatial Resolution Image

2021 ◽  
Vol 13 (19) ◽  
pp. 3874
Author(s):  
Xu Ma ◽  
Lei Lu ◽  
Jianli Ding ◽  
Fei Zhang ◽  
Baozhong He
Keyword(s):  
Spatial Resolution ◽  
Precision Agriculture ◽  
Vegetation Cover ◽  
High Spatial Resolution ◽  
World View ◽  
Canopy Reflectance ◽  
Row Crops ◽  
High Spatial Resolution Image ◽  
Fractional Vegetation Cover ◽  
Reflectance Model

With high spatial resolution remote sensing images being increasingly used in precision agriculture, more details of the row structure of row crops are captured in the corresponding images. This phenomenon is a challenge for the estimation of the fractional vegetation cover (FVC) of row crops. Previous studies have found that there is an overestimation of FVC for the early growth stage of vegetation in the current algorithms. When the row crops are a form in the early stage of vegetation, their FVC may also have overestimation. Therefore, developing an algorithm to address this problem is necessary. This study used World-View 3 images as data sources and attempted to use the canopy reflectance model of row crops, coupling backward propagation neural networks (BPNNs) to estimate the FVC of row crops. Compared to the prevailing algorithms, i.e., empirical method, spectral mixture analysis, and continuous crop model coupling BPNNs, the results showed that the calculated accuracy of the canopy reflectance model of row crops coupling with BPNNs is the highest performing (RMSE = 0.0305). Moreover, when the structure is obvious, we found that the FVC of row crops was about 0.5–0.6, and the relationship between estimated FVC of row crops and NDVI presented a strong exponential relationship. The results reinforced the conclusion that the canopy reflectance model of row crops coupled with BPNNs is more suitable for estimating the FVC of row crops in high-resolution images.

scholarly journals CubeSats Enable High Spatiotemporal Retrievals of Crop-Water Use for Precision Agriculture

2018 ◽  
Vol 10 (12) ◽  
pp. 1867 ◽  
Author(s):  
Bruno Aragon ◽  
Rasmus Houborg ◽  
Kevin Tu ◽  
Joshua B. Fisher ◽  
Matthew McCabe
Keyword(s):  
Remote Sensing ◽  
Eddy Covariance ◽  
Water Use ◽  
Spatial Resolution ◽  
Precision Agriculture ◽  
High Spatial Resolution ◽  
Assessment Tools ◽  
Optical Data ◽  
Crop Water ◽  
Crop Water Use

Remote sensing based estimation of evapotranspiration (ET) provides a direct accounting of the crop water use. However, the use of satellite data has generally required that a compromise between spatial and temporal resolution is made, i.e., one could obtain low spatial resolution data regularly, or high spatial resolution occasionally. As a consequence, this spatiotemporal trade-off has tended to limit the impact of remote sensing for precision agricultural applications. With the recent emergence of constellations of small CubeSat-based satellite systems, these constraints are rapidly being removed, such that daily 3 m resolution optical data are now a reality for earth observation. Such advances provide an opportunity to develop new earth system monitoring and assessment tools. In this manuscript we evaluate the capacity of CubeSats to advance the estimation of ET via application of the Priestley-Taylor Jet Propulsion Laboratory (PT-JPL) retrieval model. To take advantage of the high-spatiotemporal resolution afforded by these systems, we have integrated a CubeSat derived leaf area index as a forcing variable into PT-JPL, as well as modified key biophysical model parameters. We evaluate model performance over an irrigated farmland in Saudi Arabia using observations from an eddy covariance tower. Crop water use retrievals were also compared against measured irrigation from an in-line flow meter installed within a center-pivot system. To leverage the high spatial resolution of the CubeSat imagery, PT-JPL retrievals were integrated over the source area of the eddy covariance footprint, to allow an equivalent intercomparison. Apart from offering new precision agricultural insights into farm operations and management, the 3 m resolution ET retrievals were shown to explain 86% of the observed variability and provide a relative RMSE of 32.9% for irrigated maize, comparable to previously reported satellite-based retrievals. An observed underestimation was diagnosed as a possible misrepresentation of the local surface moisture status, highlighting the challenge of high-resolution modeling applications for precision agriculture and informing future research directions. .

scholarly journals Comparison of supervised classifiers in the discrimin ation of preservation areas in a hydroelectric reservoir

2019 ◽  
Vol 11 (3) ◽  
Author(s):  
Jefferson Francisco Soares ◽  
Gláucia Miranda Ramirez ◽  
Mirléia Aparecida de Carvalho ◽  
Marcelo de Carvalho Alves ◽  
Christiany Mattioli Sarmiento ◽  
...  
Keyword(s):  
Land Use ◽  
Spatial Resolution ◽  
Nearest Neighbor ◽  
High Spatial Resolution ◽  
Object Oriented ◽  
Visual Object ◽  
Hydroelectric Power ◽  
K Nearest Neighbor ◽  
High Spatial Resolution Image ◽  
Resolution Image

The maintenance of riparian forests is considered one of the main vegetative practices for mitigating the degradation of water resources and is mandatory by law. However, in Brazil there is still a progressive and constant decharacterization of these areas. Facing this reality, it is necessary to broaden researches that identify the occurring changes and provide efficient solutions at a fast pace and low cost. Remote sensing techniques show great application potential in characterizing natural resources. The objective of this work was to map, to characterize the land use and occupation and to verify the best method of high spatial resolution image classification of the Permanent Preservation Areas of the Funil Hydroelectric Power Plant reservoir, located between the municipalities of Lavras, Perdões, Bom Sucesso, Ibituruna, Ijací and Itumirim, in the state of Minas Gerais. The methods used to classify the high spatial resolution image from the Quickbird satellite were visual, object-oriented and pixel-by-pixel. Results showed the best method for mapping land use and occupation of the study area was object-oriented classification using the K-nearest neighbor algorithm, with kappa coefficient of 0.88 and global accuracy of 91.40%.

Sign in / Sign up

Export Citation Format

Share Document