Remote Sensing Algorithms for Mapping Regenerative Agriculture
AssigneeIndigo N.V.
InventorsEli Kellen Melaas, Bobby Harold Braswell, Douglas Kane Bolton
Life of this patent
Estimating the term…
Abstract
This invention relates to methods for determining adoption and impact of regenerative farming practices. Embodiments of these methods, take satellite imagery and weather data as inputs, process those data according to methods of the present invention, and produce outputs which indicate whether a specific farming practice (for example, no-till or cover cropping) was adopted for a particular field or region for a particular season.
Claims20
A method of detecting a cover crop, the method comprising:
- based on a time-series of satellite imagery, determining a plurality of peaks in a vegetation index;
- for a candidate peak, determining a first inflection point between the candidate peak and a preceding peak and a second inflection point between the candidate peak and a subsequent peak;
- determining a plurality of time segments between the first inflection point and the candidate peak, wherein:
- a first time segment of the plurality of time segments is determined to extend from the first inflection point to a first interim point, the first interim point being at a first predefined percentage of a normalized amplitude of the candidate peak in the vegetation index;
- and
- a second time segment of the plurality of time segments is determined to extend from the first interim point to a second interim point, the second interim point being at a second predefined percentage of the normalized amplitude of the candidate peak in the vegetation index, the second predefined percentage being less than the normalized amplitude of the candidate peak;
- determining one or more summary statistics for each of the plurality of time segments between the first inflection point and the candidate peak and between the second inflection point and the candidate peak;
- and
- providing the one or more summary statistics to a trained classifier, and receiving therefrom an indication of a presence or absence of a cover crop at the candidate peak.
A non-transitory computer-readable medium comprising memory with instructions encoded thereon for detecting a cover crop, the instructions, when executed by one or more processors, causing the one or more processors to perform operations comprising:
- based on a time-series of satellite imagery, determining a plurality of peaks in a vegetation index;
- for a candidate peak, determining a first inflection point between the candidate peak and a preceding peak and a second inflection point between the candidate peak and a subsequent peak;
- determining a plurality of time segments between the first inflection point and the candidate peak, wherein:
- a first time segment of the plurality of time segments is determined to extend from the first inflection point to a first interim point, the first interim point being at a first predefined percentage of a normalized amplitude of the candidate peak in the vegetation index;
- and
- a second time segment of the plurality of time segments is determined to extend from the first interim point to a second interim point, the second interim point being at a second predefined percentage of the normalized amplitude of the candidate peak in the vegetation index, the second predefined percentage being less than the normalized amplitude of the candidate peak;
- determining one or more summary statistics for each of the plurality of time segments between the first inflection point and the candidate peak and between the second inflection point and the candidate peak;
- and
- providing the one or more summary statistics to a trained classifier, and receiving therefrom an indication of a presence or absence of a cover crop at the candidate peak.
A system comprising:
- a non-transitory computer-readable medium with instructions encoded thereon for detecting a cover crop;
- and
- one or more processors that, when executing the instructions, are caused to perform operations comprising:
- based on a time-series of satellite imagery, determining a plurality of peaks in a vegetation index;
- for a candidate peak, determining a first inflection point between the candidate peak and a preceding peak and a second inflection point between the candidate peak and a subsequent peak;
- determining a plurality of time segments between the first inflection point and the candidate peak, wherein:
- a first time segment of the plurality of time segments is determined to extend from the first inflection point to a first interim point, the first interim point being at a first predefined percentage of a normalized amplitude of the candidate peak in the vegetation index;
- and
- a second time segment of the plurality of time segments is determined to extend from the first interim point to a second interim point, the second interim point being at a second predefined percentage of the normalized amplitude of the candidate peak in the vegetation index, the second predefined percentage being less than the normalized amplitude of the candidate peak;
- determining one or more summary statistics for each of the plurality of time segments between the first inflection point and the candidate peak and between the second inflection point and the candidate peak;
- and
- providing the one or more summary statistics to a trained classifier, and receiving therefrom an indication of a presence or absence of a cover crop at the candidate peak.
Dependencies are inferred from the claim text.