Description:FIELD OF THE INVENTION
This invention relates to Dual-Polarimetric Sentinel-1 SAR Data for Land Use and Land Cover Estimation
BACKGROUND OF THE INVENTION
Existing models were less successful in particular land uses, such as urban environments, where surfaces such as buildings, roads, and paved areas might generate peculiar scattering effects. This could result in misclassification or lower sensitivity to changes in urban surroundings.
The degree of polarization can be considerably altered by surface texture, making it difficult to discriminate between different forms of land cover, particularly in places with heterogeneous surface roughness (forests, agricultural fields, or urban environments).
The polarization of a signal reflected from a surface varies according to the incidence angle. The precise angles employed for measurements effect Normalized Difference Polarization Index (NDPI) estimations. This renders the index vulnerable to changes in sensor geometry, which might result in inconsistencies in NDPI readings if measurements are conducted under various conditions if the angles are not properly calibrated.
In earlier studies, land use and land cover (LULC) were estimated using optical remote sensing signals, primarily relying on the reflectance and absorption characteristics of target features. These methods predominantly focused on individual empirical models, limiting their ability to comprehensively extract features across diverse land types. For instance, techniques such as the Normalized Difference Vegetation Index (NDVI) have been widely used to extract target features. However, NDVI is primarily less effective for detecting higher vegetation, such as forests, and falls short.
No studies are available in microwave remote sensing techniques till date to estimate land use and based on polarization techniques. This method is advantageous since it is capable of predicting above in unfavorable environmental conditions and for large-scale study.
Commercial Practice:
The technological developments in LULC mapping and analysis have given society powerful tools for making educated decisions about land use, environmental protection, disaster management, urbanization, and resource management.
These technologies help to prevent negative consequences, optimize resource usage, and promote sustainability, resulting in higher quality of life, greater climate resilience, and a more sustainable future for both human and biological systems.
As LULC technologies advance, they will become increasingly crucial in solving global issues including climate change, population increase, and urbanization.
A proposed model considers the intensity of the backscatter signal which depends on the surface's material, and moisture. As a result, the cross-polarization and co-polarization varies with target features. A combination of varying responses from co-polarization and cross-polarization concerning constant after deducting the effect of noise from the soil and water content.
The unique capability of SAR data to permeate clouds and function in all weather conditions enables DPLULC to significantly improve traditional Land Use and Land Cover estimation techniques, rendering it a highly reliable tool for monitoring dynamic environments.
The invention outlines a novel methodology and straightforward analysis technique for the processing of dual-polarimetric SAR data. This technique includes feature extraction, classification algorithms that can be performed in computational systems, classifiers, AI-driven models, GIS software, and machine learning, all of which are intended to transform SAR data into actionable insights for LULC mapping.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
A statistical technique, the assumed mean method is used to calculate the arithmetic mean of backscattering values of the various features present with large datasets. Also provides a shortcut for calculating the arithmetic mean of different conditions of soil, water and vegetation data, making the process more efficient and less prone to calculation errors. A mean value of the VV and VH backscattering coefficient of the 11 classes is shown in Fig.1
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Fig. 1. Determining optimal backscattering characteristics for diverse target features through sensitivity analysis
Fig. 2. Deduction of the combined effect of soil water and water vegetation effect from the dual-polarimetric responses
Fig. 3. Statistical assessment of simulated NDVI and DPLULC for water bodies, illustrating the distribution and validation of land cover for water.
Fig. 4. Statistical evaluation of NDVI and DPLULC in rocky terrains, presenting insights from density plots and distribution.
Fig. 5. Density plot analysis of NDVI and DPLULC for soil, highlighting their distribution and statistical validation.
Fig. 6. Comparative statistical analysis of NDVI and DPLULC distribution for vegetation, demonstrating variations from distribution, and density plot.
Fig. 7. Validation of DPLULC using NDVI for forested areas, supported by density plots and statistical metrics
Fig. 8. Statistical analysis of NDVI and DPLULC distribution in urban landscapes, examining validation metrics and distribution with density plots
Fig. 9 Spatial product of the NDVI and DPLULC compared with world imagery
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
1. Assumed mean approach
A statistical technique, the assumed mean method is used to calculate the arithmetic mean of backscattering values of the various features present with large datasets. Also provides a shortcut for calculating the arithmetic mean of different conditions of soil, water and vegetation data, making the process more efficient and less prone to calculation errors. A mean value of the VV and VH backscattering coefficient of the 11 classes is shown in Fig.1
2. Responses of Dual Polarimetric data to Water, Soil, and Vegetation Interactions
In a triangle formulation in the DPSVI simulation based on the behaviour of the water, soil and vegetation, the lower left margin is occupied by the water content and starts to increase (σ_vv^soil-0.1) to the right side and the contribution of the soil starts to increase and their maximum value is (σ_vv^soil-2.9). Also, in the vertical faces of a triangle, the impact of water gets reduced with an increase of cross-polarization from (σ_vh^water- 0.025) and the contribution of vegetation to be the top margin of the triangle with maximum values of (σ_vh^veg- 0.225).
Accordingly, the vertical line represents the vegetation and water behaviour, the bottom horizontal line represents the water and soil behaviour and the connecting lines between the two above lines form the soil vegetation interaction edge which provides the biomass value in the agricultural field. Considering the effect of water, soil and vegetation accounts together in DPSVI leads to decrease a precision of biomass estimation. According to the phonological study, the major factors to cause errors in ISVI biomass are soil and water. Comparing the effect of water and soil based on the behavioural study, the water has minimal value (σ_vv^water- 0.004) and the soil has a high impact resulting in higher values (σ_vv^soil-0.02) of the co-polarized signal. In cross-polarization, the water has minimal values (σ_vh^water- 0.06) and the soil also has lower values (σ_vh^soil- 0.09).
3. Dual polarimetric land use and land cover modeling
Based on the observation from Fig.1 and Fig.2, the value of the σvh starts at 0.08 to end at 0.02 and the σvv starts at 0.02 to ends at 0.1. Once the contribution of the combination of water and the soil has been deducted the triangle theorem constructed between the backscattering coefficient of σvh and σvv to derive the dual polarimetric vegetation edge. A lower left margin of the triangle at O represents the water that follows the soil represented in the triangle from C" to D'. Follows to soil and water vegetation are to be increased in the order from grassland at D' to higher dense vegetation at A representing lower biomass to higher biomass.
A contribution of water to the backscattering co-efficient origin from O to C" and the soil responses to the backscattering from C" to D'. A water-soil interaction ranges from C to D" having higher soil contribution compared to the water as well as the soil-water interaction lesser than C'C" not to be accounted for in the deduction. A water-vegetation responses starts from DD" to BB" to the backscattering coefficient has a higher contribution compared to water and soil responses. Compared to the water vegetation backscattering soil vegetation backscattering from D"D' to B"B' and has higher responses compared to the water vegetation responses to the backscattering. Vegetation response to the backscattering starts from D' and starts to increase to B' and A in co-polarization and cross-polarization. A contribution of the water and the soil interaction to the backscattered coefficient is not to be considered from the total backscattering.
In line AB the effect of the water in cross-polarization (σ_vh) Water has been neglected and the line water-vegetation interaction lines become BB^'' nullified from the triangle AOB and the effect of soil vegetation remains. In the case of vegetation biomass estimation, an effect of soil vegetation interaction B'B" is to be deducted to get the effect of vegetation in cross-polarization by removing soil influence in triangle AC"B". Hereafter the line AD' in the triangle is free from the effect of water and soil in polarization. Triangle AD'B' is used to estimate the above-ground biomass and the line AD' represents the soil vegetation edge. Equation 1 shows the values of biomass considering the triangular theorem. From the dual polarimetric radar vegetation index at the C band, the lower biomass represents 0 and the higher biomass represents 1 after the normalization.
DPLULC = 4([σ_vh^i- σ_vh(w-s)^max ]+[ σ_vv^i ])/√2 (1)
σ_vh^i represents the backscattering coefficient of cross-polarization of the ith pixel, σ_vh(w-s)^max is the maximum cross-polarization of water and soil, and the σ_vvh^i is the backscattering coefficient of co-polarization of the ith pixel.
NOVELTY:
Introduces a conceptual framework where target feature estimation is freed from water and soil influence through deductive spatial analysis in the σVH – σVV space. A new index DPLULC that enhances the separation of vegetated, urban, and aquatic surfaces in dual-pol data.
DPLULC = 4([σ_vh^i- σ_vh(w-s)^max ]+[ σ_vv^i ])/√2

ADVANTAGES OF THE INVENTION
In spatial applications, the proposed approach is useful for image analysis with which the researchers will able to study the land use and land cover.
This invention makes a substantial contribution to the disciplines of urban planning, environmental monitoring, and geospatial analysis. It is especially advantageous for applications that necessitate frequent and dependable LULC updates.
Monitor surface displacements, such as deforestation, urban sprawl, agricultural changes, and environmental deterioration and deformation caused by natural disasters.
DPLULC contributes to identification of the conservation of vital ecosystems and biodiversity, hence promoting sustainable land use practices by identifying areas at danger of environmental deterioration.
, Claims:1. A method for land use and land cover (LULC) estimation using dual-polarimetric Sentinel-1 Synthetic Aperture Radar (SAR) data, comprising the steps of:
a. acquiring backscattering coefficients from Sentinel-1 SAR dual-polarimetric data;
b. applying an assumed mean statistical approach to calculate the arithmetic mean for multiple land surface conditions including soil, water, and vegetation; and
c. estimating land cover features by minimizing the influence of soil and water through a deductive spatial analysis.
2. The method as claimed in claim 1, wherein the assumed mean approach provides a computational shortcut to calculate the arithmetic mean of large datasets representing different land surface conditions, reducing calculation time and error.
3. The method as claimed in claim 1, wherein the proposed technique supports spatial applications including urban planning, environmental monitoring, and geospatial analysis by offering improved accuracy and reliability in LULC classification.