| CPC G06V 20/13 (2022.01) [G06V 10/80 (2022.01); G06V 10/82 (2022.01)] | 2 Claims |
|
1. An intelligent fusion and processing method for remote sensing products for water quality monitoring of estuaries and bays, comprising the following steps:
S1: setting criteria for image retrieval, performing iterative image retrieval and downloading, and achieving batch downloading of remote sensing images automatically;
a specific process of the S1 is as follows:
S11: setting criteria for image retrieval: using Python and Sentinelsat, Landsatxplore, and Selenium packages to batch download high spatial- and temporal-resolution multi-source remote sensing satellite data; the remote sensing satellite data comes from Sentinel-2, Sentinel-3, Landsat, GOCI2, and VIIRS; when logging into a download website automatically after inputting a valid account and password, a user can retrieve any required product according to the retrieval criteria;
S12: performing iterative retrieval and downloading: performing a plurality of rounds of activation and downloading until all the required data are downloaded, and then terminating the process; for each round of retrieval and downloading, recording IDs of downloaded products, and in a next round of downloading, removing the IDs of already downloaded products, and retrieving and downloading from the IDs of offline products that have not been activated;
S2: performing recursive call of an Acolite settings file in Python to directly perform batch atmospheric correction of multi-source remote sensing satellite data;
a specific process of setting parameters in the settings file in the S2 is as follows:
S21: selecting input: choosing an input directory and files for processing;
S22: selecting output: choosing an output directory;
S23: setting an area of interest: entering boundaries to be processed and storing them in a vector file in a shapefile format;
S24: setting L2W parameters: listing required output parameters; when the output parameters are null, only L1R and L2R files will be generated; choosing Rrs_*, to output remote sensing reflectance;
S25: setting a target resolution: setting the resolution for each satellite;
S26: setting whether to mask land areas: by default, the land areas are masked;
S27: setting a status of wind speed-based interface reflectance correction to: on;
S28: setting a status of residual sunlight reflectance correction to: on;
S29: setting PNG output: using top-of-atmosphere ρt or ρs reflectance to generate RGB composite checkboxes and L2W parameter PNG maps;
setting an image resolution: 300 dpi;
setting whether to include a PNG map scale: yes;
setting a PNG map scale color: white;
S3: fusing multi-source remote sensing data products based on machine learning to generate a layer of high-frequency water quality parameter remote sensing products;
a specific process of the S3 is as follows: based on machine learning, fusing high-spatial-resolution and low-temporal-resolution remote sensing data products with low-spatial-resolution and high-temporal-resolution remote sensing data products, supplementing this with water quality parameter information as input to the machine learning model to generate a layer of high-frequency water quality parameter remote sensing products, wherein the water quality parameter information includes a satellite angle, a wind speed, and an air temperature, and the layer of water quality parameter remote sensing products include turbidity, water temperature, chlorophyll-a, inorganic nitrogen, and reactive phosphate;
S4: superimposing a layer of tidal boundary vectors for different water levels onto the layer of water quality parameter remote sensing products, and adding map elements to generate a thematic map of different water quality parameters;
a specific process of the S4 is as follows:
S41: matching a tidal table according to time of shooting the remote sensing images, calculating water level heights corresponding to extracted high tide, mid-tide, and low tide boundaries, superimposing the tidal boundary vector layer onto the layer of water quality parameter remote sensing products;
S42: adding map elements and other labels to generate a thematic map of water quality parameters for estuary and bay boundaries, where the map elements include transportation networks, major administrative markers, scale bars, and north arrows;
S5: performing intelligent statistical analysis of water quality parameters to generate a statistical chart;
a specific process of S5 is as follows:
S51: selecting an area of interest: the user selects the area of interest using GIS map tools or chooses a default area for automatic statistical analysis;
S52: performing statistical and spatiotemporal analysis and evaluation of water quality parameters: automatically performing statistical analysis on water quality parameters, including a mean, maximum, minimum, and standard deviation of each water quality parameter, to obtain statistical values of water quality parameters; automatically performing spatiotemporal analysis to show temporal trends of water quality parameter statistics and spatial differences of water quality parameter statistics in different regions; evaluating water quality according to national or local standards to generate a statistical chart;
S6: automatically outputting a report sheet based on the thematic map of water quality parameters and the statistical chart;
a specific process of the S6 is as follows:
S61: selecting the thematic map of water quality parameters generated in the S4 and the statistical chart generated in the S5;
S62: choosing a report template: selecting from a plurality of provided report templates or uploading a custom template;
S63: schedule output: the user sets a scheduled task to automatically output report sheets at specified time on a daily, weekly, or monthly basis.
|