FIELD: physics.
SUBSTANCE: method involves probing the earth's surface with remote spectral probing apparatus and selecting training and test sections with subsequent training of a neural network. Ground-based investigation of the sections of the earth's surface is carried out to obtain ground-based data on the unknown quantitative characteristic of the investigated surface. Obtained data are divided into test and training data based on results of ground-based investigations and the neural network is trained in order to determine the quantitative characteristic. Using the obtained data, the neural network is trained to evaluate the quantitative characteristic from results of the remote probing of the earth's surface within the entire probing.
EFFECT: fast evaluation of the quantitative characteristic with low labour input.
1 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD OF RECOGNIZING IMAGES OF BIOCHEMICAL GROUND OBJECTS WITH FINE SPECTRAL DIFFERENCES BASED ON HYPERSPECTRAL DATA | 2018 |
|
RU2695963C1 |
METHOD OF ELIMINATION OF REMOTE SCANNED IMAGE DISTORTIONS CAUSED BY COMPLEX TRAJECTORY OF IMAGE SENSOR CARRIER | 2009 |
|
RU2411449C1 |
METHOD OF PLANT OBJECTS IDENTIFICATION BASED ON REMOTE SENSING SATELLITE IMAGES | 2018 |
|
RU2693880C1 |
SYSTEM FOR MONITORING FOREST USE AND FOREST PATHOLOGICAL CHANGES | 2019 |
|
RU2716477C1 |
METHOD OF UPDATING FOREST STOCK DATA BASED ON MACHINE LEARNING | 2020 |
|
RU2739436C1 |
METHOD FOR CORRECTING GEOMETRIC DISTORTIONS OF HYPERSPECTRAL IMAGES | 2023 |
|
RU2806667C1 |
2021 |
|
RU2769575C1 | |
METHOD OF TEMPERATURE ASSESSMENT IN ENTRAILS OF EARTH | 2006 |
|
RU2326413C1 |
IMAGE TRANSFORMATION METHOD | 2015 |
|
RU2586405C1 |
METHOD FOR DETERMINING THE BOUNDARIES OF WATER BODIES AND AREAS OF DISTRIBUTION OF SEMI-AQUATIC SPECIES BASED ON MULTISPECTRAL DATA OF REMOTE SENSING OF THE EARTH | 2020 |
|
RU2750853C1 |
Authors
Dates
2011-02-10—Published
2009-09-21—Filed