US-12622347-B2 - System and method for turning irrigation pivots into a network of robots for optimizing fertilization

US12622347B2US 12622347 B2US12622347 B2US 12622347B2US-12622347-B2

Abstract

A method and system for autonomously varying fertilization levels within a field, the field being divided into a plurality of segments, using an autonomous pivot, may include: applying an amount of fertilizer using a fertilizer applicator to each segment; capturing images of each segment in at least two different spectral ranges after a time period; calculating a Normalized Difference Vegetation Index (NDVI) value for each segment of the field based on the captured images; and varying the amount of fertilizer applied to each segment after the time period, wherein the amount of fertilizer is varied based on re-captured images and re-calculated NDVI values for each segments after the time period.

Inventors

Eyal Neistein
Ran YIFA
Yaroslav DON
Yair Sharf
Yuval Aviel
Yossi Haran

Assignees

AUTONOMOUSPIVOT LTD

Dates

Publication Date: 20260512
Application Date: 20230110

Claims (20)

1 . A method of varying fertilization levels within a field, the field being divided into a plurality of segments, the method comprising: applying, by a mobile platform with a ground-penetrating radar sensor, at a first time an amount of fertilizer to each segment; capturing images of each segment in at least two different spectral ranges after a time period; calculating a reference Normalized Difference Vegetation Index (NDVI) value for each segment based on the captured images, wherein the calculation of the NDVI value incorporates a determination of one or more of: (i) specific locations of leaves within each plant, and (ii) specific regions within each leaf; and varying the amount of fertilizer applied to each segment after the time period, wherein the amount of fertilizer is varied based on re-captured images and re-calculated NDVI values for each segment after the time period, wherein the NDVI value is calculated according to the formula: N ⁢ D ⁢ V ⁢ I = ( α ⁢ A + β ⁢ B + γ ⁢ C + δ ) / ( φ ⁢ A + χ ⁢ B + ψ ⁢ C + ξ ) where A, B and C are spectral reflectance measurements acquired from the images captured in the infrared, red and green spectral ranges, and where α, β, γ, δ, φ, χ, ψ and ξ are constants.
2 . The method according to claim 1 , wherein the amount of fertilizer applied at the first time is according to a prescription which defines an amount of fertilizer that is applied to a first subset of the plurality of segments, comparative to a remainder of the plurality of segments.
3 . The method according to claim 2 , wherein no further fertilizer is applied to one or more of the plurality of the first subset of segments when the re-calculated NDVI value of a subset of a plurality of the first subset of segments remains the same as the NDVI value of the remainder of the plurality of segments.
4 . The method according to claim 2 , wherein additional fertilizer is applied to one or more of the plurality of the first subset of segments when the re-calculated NDVI value of a subset of a plurality of the first subset of segments is lower than the NDVI value of a subset of a plurality of the remainder of the plurality of segments.
5 . The method according to claim 2 , wherein the prescription of fertilizer applied to each of the plurality of the segments at a start of a next growing season is reduced when the NDVI value for all of the plurality of the first subset of segments is calculated to fall above a predefined threshold value.
6 . The method according to claim 1 , wherein the images of each segment are captured and recaptured in the infrared, red and green spectral ranges.
7 . The method according to claim 1 , wherein the captured images of each segment are collected from multiple different positions from within the plurality of segments, and wherein the NDVI value of each segment is averaged over all NDVI values obtained for each set of images captured of that segment to improve statistical accuracy.
8 . The method according to claim 1 , wherein the calculation of the NDVI value is corrected in relation to one or more of: (i) a number of leaves within a plant, (ii) a total leaf area, (iii) an estimate of a total plant-mass, (iv) a respective leaf angular orientation, (v) a relative distance from a camera, (vi) an accurate seeding time, (vii) an irrigation history, and (viii) a field history from previous seasons.
9 . A system for varying fertilization levels within a field, the field being divided into a plurality of segments, the system comprising: a memory component configured to store computer implementable instructions; a mobile platform with a ground-penetrating radar sensor, wherein the mobile platform is configured to move about the field; and a processor configured to implement the computer implementable instructions, such that the mobile platform is operable to: apply at a first time an amount of fertilizer, using a fertilizer applicator, to each segment; capture images of each segment in at least two different spectral ranges after a time period; calculate a Normalized Difference Vegetation Index (NDVI) value for each segment of the field based on the captured images, wherein the calculation of the NDVI value incorporates a determination of one or more of: (i) specific locations of leaves within each plant, and (ii) specific regions within each leaf; and vary the amount of fertilizer applied to each segment after the time period, wherein the amount of fertilizer is varied based on re-captured images and re-calculated NDVI values for each segment after the time period.
10 . The system according to claim 9 , the mobile platform comprising: a motor and a plurality of wheels for maneuvering the mobile platform; a multispectral camera configured to capture images in at least two different spectral ranges; a fertilizer applicator; a collection unit; a transponder; a geolocation and time sensor; and a cloud server, comprising: a memory component configured to store computer implementable instructions; a control unit; and an analytical unit.
11 . The system according to claim 10 , wherein the amount of fertilizer applied at the first time is according to a prescription which defines an amount of fertilizer that is applied to a first subset of the plurality of segments comparative to a remainder of the plurality of segments.
12 . The system according to claim 11 , wherein no further fertilizer is applied to one or more of the plurality of the first subset of segments when the calculated NDVI value of the subset of a plurality of the first subset of segments remains the same as the NDVI value of the remainder of the plurality of segments.
13 . The system according to claim 11 , wherein additional fertilizer is applied to one or more of the plurality of the first subset of segments when the NDVI value is lower than the NDVI value of the remainder of the plurality of segments.
14 . The system according to claim 11 , wherein the prescription of fertilizer applied to each of the plurality of segments at a start of a next growing season is reduced when the NDVI value for all of the plurality of the first subset of segments is calculated to fall above a predefined threshold value.
15 . The system according to claim 10 , wherein the images of each segment captured using the multispectral camera are in the infrared, red and green spectral ranges.
16 . The system according to claim 10 , wherein the mobile platform is maneuvered about the field such that the images of each segment are captured from multiple different positions from within the segments, and wherein the NDVI value of each segment is averaged over all images captured of that segment to improve statistical accuracy.
17 . The system according to claim 10 , wherein the system comprises a communications subsystem, and wherein the mobile platform is remotely controlled by a human operator using the communications subsystem.
18 . The system according to claim 12 , wherein the system comprises one or more proximity sensors, and wherein the processor is configured to autonomously navigate the mobile platform about the field using the proximity sensors.
19 . The system according to claim 10 , wherein the mobile platform comprises one or more of: a rain sensor, a temperature sensor, a chlorophyll camera, and a pressure sensor.
20 . The system according to claim 10 , wherein the cloud server is configured to receive data from a plurality of connected mobile platforms of a plurality of fields.

Description

TECHNICAL FIELD OF THE INVENTION The present invention relates generally to the detection of fertilization levels within fields and the application of fertilizers onto a field to facilitate crop growth, more specifically to the autonomous monitoring of crop growth and the autonomous variation of fertilizer application within a field. BACKGROUND OF THE INVENTION Most modern agricultural practices rely on the application of fertilizers. Thereby, soil is supplied with plant nutrients, for example nitrogen, phosphorus and potassium nutrients. In particular, since the development of the Haber process in the early 20th century, nitrogen fertilizers have been among the most prominent fertilizers. Whilst providing beneficial nutrients to a crop generally lead to high yields in the harvest, the provision of fertilizers may have negative environmental effects. Commonly, only a fraction of fertilizer is converted to plant matter and the remainder may accumulate in the soil or may be lost as runoff. Excessive fertilizer usage in crop production may cause soil to become enriched with mineral and nutrients. As a result, e.g. in the application of nitrogen fertilizers, nitrogen not taken up by plants may be transformed into nitrates. This form of nutrient pollution may result in the eutrophication of water bodies and ultimately could have severe ecological effects such as decreased biodiversity and increased toxicity of drinking water, resulting in a high demand for water treatment processes. SUMMARY OF THE INVENTION The following is a simplified summary providing an initial understanding of the invention. The summary does not necessarily identify key elements nor limit the scope of the invention, but merely serves as an introduction to the following description. Embodiments of the present invention may autonomously monitor the application and impact of fertilizers, e.g. nitrogen fertilizers, for example applied on a field in relation to the crop growth of a field and autonomously vary the provided amount of applied fertilizer throughout a growing season or within a plurality of growing seasons to the growth of crops with the intention to reduce fertilizer application for a field. Embodiments of the present invention may include the autonomous fertilization of agricultural land and for the optimization of fertilizer levels applied to land such as agricultural land. Advantages and improvements of the invention may include automatically adapting an amount of fertilizer applied to a field based on data crop growth autonomously measured for a field using an autonomous pivot. Embodiments may improve fertilization technology by for example including communication between autonomous pivots within a network of autonomous pivots using a data cloud server in the assessment of fertilizer levels and prediction of fertilizer levels for agricultural land by autonomously evaluating crop growth within a plurality of fields in relation to agricultural parameters such as fertilizer levels. An embodiment of the present invention may include a method of varying fertilization levels within a field, the field being divided into a plurality of discrete segments, the method comprising: applying an amount of fertilizer to each segment at the start of a growing season based on a prescription: capturing images of each segment in at least two different spectral ranges at various discrete time periods: calculating a reference Normalized Difference Vegetation Index (NDVI) value for each segment based on the captured images; and varying the amount of fertilizer applied to each segment after each discrete time period, wherein the amount of fertilizer is varied based on re-captured images and re-calculated NDVI values for each segments after each discrete time period. An embodiment of the present invention may include a system for varying fertilization levels within a field, the field being divided into a plurality of discrete segments, the system comprising: a mobile platform configured to move about the field, the mobile platform comprising: a motor and a plurality of wheels for maneuvering the mobile platform; a multispectral camera configured to capture images in at least two different spectral ranges; a fertilizer applicator; a collection unit: a transponder: a geolocation sensor: a time sensor: a cloud server, comprising a control unit, an analytical unit, a memory component configured to store computer implementable instructions and a processor configured to implement the computer implementable instructions, such that the system is operable to: apply an amount of fertilizer using a fertilizer applicator to each segment at the start of a growing season based on a prescription, e.g. using a network of fields: capture images of each segment in at least two different spectral ranges after a discrete time period; calculate a reference NDVI value for each segment of the field based on the captured images; and vary the amount of fertilizer applied to eac