Neural network atmospheric correction method for GOCI satellite morning and evening observation
A neural network and atmospheric correction technology, applied in the field of remote sensing, can solve problems such as lack of high-precision atmospheric correction algorithms
Pending Publication Date: 2020-01-24
SECOND INST OF OCEANOGRAPHY MNR
View PDF4 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Through the analysis and summary of such literature, it can be known that there is no high-precision and general-purpose atmospheric correction algorithm for satellite images with a large solar zenith angle.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] For the neural network atmospheric correction method flow for GOCI satellite morning and evening observations, please refer to the attached figure 1 ,Proceed as follows:
[0038] (1) Screening GOCI satellite data;
[0039] Described step (1) is: the training data set of neural network model should have accuracy, extensiveness and representativeness, therefore will screen high-quality GOCI satellite data as training data. GOCI observes every hour from 8:30 to 15:30 (Beijing time), covering a 2500×2500km area centered on (36°N, 130°E) 2 area with a spatial resolution of 500m. GOCI can effectively monitor the hourly changes of sea surface flow field, chlorophyll concentration or suspended sediment concentration. Analyze the satellite true-color images released by the Korean Ocean Satellite Center (KOSC), and filter out cloudless satellite images. GOCI observes 8 times a day, and the accuracy of the products at 11:30 and 12:30 is obviously high At other times, in order...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a neural network atmospheric correction method for GOCI satellite morning and evening observation. The method comprises: firstly, using Seadas software for processing GOCI satellite data to obtain related data; screening a training data set for training a neural network model; and finally, processing the target satellite image by using Seadas software to obtain related data, inputting the related data into the trained neural network atmospheric correction model, and processing to obtain the remote sensing reflectivity of the target image. At present, an international existing atmospheric correction model is still inapplicable under a zenith angle of the large sun, so that product loss of GOCI water color satellites under the zenith angle of the large sun is extremely serious. According to the method, atmospheric correction of the GOCI satellite image under the zenith angle of the large sun is well achieved. The problem of water color satellite data processing issolved, water color remote sensing products under the zenith angle of the large sun in recent ten years in the polar region can be expected to be recovered, and then the method serves ecological environment change monitoring and scientific research.
Description
technical field [0001] The invention belongs to the technical field of remote sensing, and in particular relates to a neural network atmospheric correction method for morning and evening observations of GOCI satellites. Background technique [0002] Remote sensing of ocean water color from sun-synchronous (or polar-orbiting) and geosynchronous satellites provides valuable data for extracting information on the spatial distribution and temporal variation of regional or global ocean phytoplankton and their associated components. While sun-synchronous satellites are capable of making global ocean color observations with sufficient precision, the sampling frequency (typically once a day) per satellite (especially at low latitudes) is insufficient to resolve dynamic diurnal variations in coastal ocean chemical processes. Zhou Qu et al. evaluated the impact of different sampling strategies (time and frequency) on short-term and long-term trend monitoring of water quality parameter...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T5/00G01N21/17
CPCG01N21/17G01N2021/1793G01N2021/1742G01N2021/1744G06T2207/10032G06T2207/20081G06T2207/20084G06T5/80
Inventor 李豪何贤强白雁朱乾坤王迪峰龚芳
Owner SECOND INST OF OCEANOGRAPHY MNR