Estimating crop growth based on interferometric synthetic aperture radar

Patent metadata

Field	Value
Publication number	US-2025308232-A1
Application number	US-202418617640-A
Country	US
Kind code	A1
Filing date	Mar 26, 2024
Priority date	Mar 26, 2024
Publication date	Oct 2, 2025
Grant date	—

Abstract

A computerized method estimates crop growth in a geographic area using satellite-collected synthetic aperture radar (SAR) data. SAR data of the geographic area is obtained from a plurality of satellite passes by one or more satellites. The obtained SAR data is processed into coherence data and interferometric data. The processed data is associated with a comparison between a first SAR data subset from a first satellite pass of the plurality of satellites passes and a second SAR data subset from a second satellite pass of the plurality of satellite passes. The processed data is provided to a trained crop growth estimation model and a crop growth prediction associated with the geographic area is generated using the trained crop growth estimation model. In some examples, the obtained SAR data is processed into additional data types, such as amplitude data and/or polarimetric SAR data.

First claim

What is claimed is:

1 . A system comprising:
a processor; and a memory comprising computer program code, the memory and the computer program code configured to cause the processor to: obtain synthetic aperture radar (SAR) data of a geographic area from a plurality of satellite passes by a satellite; calculate a coherence value for a SAR data subset pair including a first SAR data subset and a second SAR data subset, wherein the first SAR data subset is associated with a first satellite pass of the plurality of satellite passes and the second SAR data subset is associated with a second satellite pass of the plurality of satellite passes; process the obtained SAR data into interferometric data using the calculated coherence value; provide the coherence value and the interferometric data to a trained crop growth estimation model; and generate, using the trained crop growth estimation model, a crop growth prediction associated with the geographic area.

2 . The system of claim 1 , wherein calculating the coherence value for the SAR data subset pair includes:
generating a small baseline subset (SBAS) weight value based on a baseline distance between the first satellite pass and the second satellite pass and a time difference between the first satellite pass and the second satellite pass; and weighting the coherence value using the generated SBAS weight value, wherein the weighted coherence value is provided to the trained crop growth estimation model.

3 . The system of claim 1 , wherein calculating the coherence value for the SAR data subset pair including the first SAR data subset and the second SAR data subset further includes:
determining a plurality of observed SAR data subset pairs included in the obtained SAR data; calculating observed coherence values for the observed SAR data subset pairs; determining a plurality of unobserved SAR data sequential pairs based on a time interval length of the obtained SAR data and the observed SAR data subset pairs; defining a matrix with entries for each sequential SAR data subset pair, wherein observed SAR data subset pairs are represented by ones and unobserved SAR data subset pairs are represented by zeros; and calculating estimated coherence values for the unobserved SAR data subset pairs by finding a least square solution of a matrix equation using the defined matrix and logarithmic values determined from the calculated observed coherence values for the observed SAR data subset pairs, wherein the calculated observed coherence values and calculated estimated coherence values are provided to the trained crop growth estimation model.

4 . The system of claim 1 , wherein the memory and the computer program code are configured to further cause the processor to:
process the obtained SAR data into additional processed SAR data, wherein the additional processed SAR data includes at least one of the following: amplitude data or polarimetric SAR data; and wherein the additional processed SAR data is provided to the trained crop growth estimation model.

5 . The system of claim 4 , wherein the obtained SAR data includes reflected signal data from a reflector structure positioned on a ground surface of the geographic area, wherein the reflector structure includes at least one of a global navigation satellite system (GNSS) station, a corner reflector structure, or a structure with a vertical wall; and
wherein processing the obtained SAR data into the additional processed SAR data includes reducing noise in the additional processed SAR data using the reflected signal data from the reflector structure.

6 . The system of claim 1 , wherein the memory and the computer program code are configured to further cause the processor to:
obtain ground truth data of the geographic area using light detection and ranging (LIDAR); and adjust the trained crop growth estimation model based on a comparison of the obtained ground truth data to the generated crop growth prediction.

7 . The system of claim 1 , wherein processing the obtained SAR data into the interferometric data includes:
converting the obtained SAR data into the interferometric data; and applying a phase unwrapping algorithm to the interferometric data, wherein the phase unwrapped interferometric is provided to the trained crop growth estimation model.

8 . The system of claim 1 , wherein the generated crop growth prediction includes estimated parameters of a sigmoidal growth curve associated with crops growing in the geographic area.

9 . The system of claim 1 , wherein the obtained SAR data includes polarimetric SAR (PolSAR) data associated with at least one of VV polarization, VH polarization, HH polarization, and HV polarization;
wherein the PolSAR data includes polarization rotation data indicating a polarization rotation effect associated with plant matter in the geographic area; wherein the polarization rotation data is provided to the trained crop growth estimation model; and wherein the trained crop growth estimation model generates the crop growth prediction based at least in part on the polarization rotation data.

10 . The system of claim 1 , wherein the obtained SAR data includes first frequency data associated with a first radar frequency and second frequency data associated with a second radar frequency;
wherein the first frequency data and the second frequency data are provided to the trained crop growth estimation model; and wherein the trained crop growth estimation model generates the crop growth prediction based at least in part on the first frequency data and the second frequency data.

11 . A computerized method comprising:
obtaining synthetic aperture radar (SAR) data of a geographic area from a plurality of satellite passes by a satellite; calculating a coherence value for a SAR data subset pair including a first SAR data subset and a second SAR data subset, wherein the first SAR data subset is associated with a first satellite pass of the plurality of satellite passes and the second SAR data subset is associated with a second satellite pass of the plurality of satellite passes; processing the obtained SAR data into interferometric data using the calculated coherence value; generating a small baseline subset (SBAS) weight based on a baseline distance between the first satellite pass and the second satellite pass and a time difference between the first satellite pass and the second satellite pass; weighting the coherence value using the generated SBAS weight value; providing the weighted coherence value and the interferometric data to a trained feature change estimation model; and generating, using the trained feature change estimation model, a feature change prediction associated with the geographic area.

12 . The computerized method of claim 11 , wherein calculating the coherence value for the SAR data subset pair including the first SAR data subset and the second SAR data subset further includes:
determining a plurality of observed SAR data subset pairs included in the obtained SAR data; calculating observed coherence values for the observed SAR data subset pairs; determining a plurality of unobserved SAR data sequential pairs based on a time interval length of the obtained SAR data and the observed SAR data subset pairs; defining a matrix with entries for each sequential SAR data subset pair, wherein observed SAR data subset pairs are represented by ones and unobserved SAR data subset pairs are represented by zeros; and calculating estimated coherence values for the unobserved SAR data subset pairs by finding a least square solution of a matrix equation using the defined matrix and logarithmic values determin

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Olsen Peder Andreas
• Jog Suraj Sanjay
• Ranganathan Vaishnavi Nattar
• Priyantha Nissanka Arachchige Bodhi
• De Moura Estevao Filho Roberto
• Chandra Ranveer
• Varshney Debvrat
• Kapetanovic Zerina

Classifications

• G06V10/70

  using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) · CPC title

• G06V20/13

  Satellite images · CPC title

• G06V20/188 Primary

  Vegetation · CPC title