# US 12,008,447 B1 · Methods and systems for sub-field soil nutrient management

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,008,447 B1
- Document ID: US12008447B1
- Status: Granted
- Kind: B1
- Application number: 18/136,186
- Filed: 2023-04-18
- Granted: 2024-06-11
- Earliest claimed: 2023-04-18
- Applicants: Advanced Agrilytics Holdings, LLC
- Inventors: Jon J. Fridgen; William Kess Berg; Aaron W. Gault
- Web page: https://patentgrep.com/patent/US12008447B1

## CPC

- G06N 20/00: Machine learning
- A01C 21/005: {Following a specific plan, e.g. pattern}
- A01C 21/007: {Determining fertilization requirements}
- A01G 7/00: Botany in general
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- A01C: PLANTING; SOWING; FERTILISING (parts, details or accessories of agricultural machines or implements, in general A01B51/00 - A01B75/00)
- A01G: HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING (picking of fruits, vegetables, hops or the like A01D46/00; propagating unicellular algae C12N1/12)

## Abstract

A computing system includes a processor and a memory having instructions stored thereon that, when executed by the one or more processors, cause the computing system to: determine a geographic field boundary, obtain topographic data, generate a digital elevation model including derivative data, determine critical level data and generate soil nutrients recommendations data. A method includes determining a geographic field boundary, obtaining topographic data, generating a digital elevation model including derivative data, determining critical level data; and generating the soil nutrients recommendations data. obtaining, by one or more processors, topographic data within an area of land. A non-transitory computer readable medium includes program instructions that when executed by one or more processors, cause a computer to determine a geographic field boundary, obtain topographic data, generate a digital elevation model including derivative data, determine critical level data and generate soil nutrients recommendations data.

## Claims

### Claim 1

A computing system for generating improved soil nutrient recommendations data, the computing system comprising:
one or more processors; and
a memory having instructions stored thereon that, when executed by the one or more processors, cause the computing system to:
determine a geographic field boundary of a field;
obtain topographic data corresponding to the field boundary of the field;
generate, based on the topographic data, a digital elevation model including derivative data corresponding to slope data, soil wetness index data, and catchment area data;
determine, based on the derivative data, critical level data for the area of the land; and
generate, using a model that receives the critical level data as input, the soil nutrients recommendations data.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the soil nutrients recommendation data includes one or more of:
a fertilizer recommendation, a plant density recommendation, or a planting location recommendation.

### Claim 3 (depends on 1)

The computer system of claim 1, the memory having stored thereon instructions that when executed, cause the computer system to:
obtain plant data for one or more plants to be grown within the area of the land; and
determine the critical level data for the area of the land based on the plant data for the one or more plants.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the model is the Tri-State Fertilizer Recommendation model.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein the topographic data is (i) obtained via one or more of LiDAR data sources or RTK data sources and (ii) represented as hexagrids.

### Claim 6 (depends on 1)

The computer system of claim 1, the memory having stored thereon instructions that when executed, cause the computer system to:
determine the critical level data for the area of the field using a machine learning model that receives the derivative data as input and predicts water movement within the field.

### Claim 7 (depends on 1)

The computer system of claim 1, the memory having stored thereon instructions that when executed, cause the computer system to:
generate a report including at least one identification of an area of the field based on the critical level data.

### Claim 8

A computer-implemented method for generating soil nutrients recommendation data, the method comprising:
determining, via one or more processors, a geographic field boundary of a field;
obtaining, via one or more processors, topographic data corresponding to the field boundary of the field;
generating, based on the topographic data, a digital elevation model including derivative data corresponding to slope data, soil wetness index data, and catchment area data;
determining, based on the derivative data, critical level data for the area of the land; and
generating, using a model that receives the critical level data as input, the soil nutrients recommendations data.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein the soil nutrients recommendation data includes one or more of:
a fertilizer recommendation, a plant density recommendation, or a planting location recommendation.

### Claim 10 (depends on 8)

The computer-implemented method of claim 8, further comprising:
obtaining, by the one or more processors, plant data for one or more plants to be grown within the area of the land; and
determining the critical level data for the area of the land is further based on the plant data for the one or more plants.

### Claim 11 (depends on 8)

The computer-implemented method of claim 8, wherein the model is the Tri-State Fertilizer Recommendation model.

### Claim 12 (depends on 8)

The computer-implemented method of claim 8, wherein the topographic data is (i) obtained via one or more of LiDAR data sources or RTK data sources and (ii) represented as hexagrids.

### Claim 13 (depends on 8)

The computer-implemented method of claim 8, further comprising:
determining the critical level data for the area of the using a machine learning model that receives the derivative data as input and predicts water movement within the field.

### Claim 14 (depends on 8)

The computer-implemented method of claim 8, further comprising
generating a report including at least one identification of an area of the field based on the critical level data.

### Claim 15

A non-transitory computer readable medium containing program instructions that when executed by one or more processors, cause a computer to:
obtain topographic data corresponding to the field boundary of the field;
generate, based on the topographic data, a digital elevation model including derivative data corresponding to slope data, soil wetness index data, and catchment area data;
determine, based on the derivative data, critical level data for the area of the land; and
generate, using a model that receives the critical level data as input, the soil nutrients recommendations data.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the soil nutrients recommendation data includes one or more of a fertilizer recommendation, a plant density recommendation, or a planting location recommendation.

### Claim 17 (depends on 15)

The non-transitory computer readable medium of claim 15, including further instructions that, when executed by one or more processors, cause a computer to:
obtain plant data for one or more plants to be grown within the area of the land; and
determine the critical level data for the area of the land based on the plant data for the one or more plants.

### Claim 18 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the topographic data is (i) obtained via one or more of LiDAR data sources or RTK data sources and (ii) represented as hexagrids.

### Claim 19 (depends on 15)

The non-transitory computer readable medium of claim 15, including further instructions that, when executed by one or more processors, cause a computer to:
determine the critical level data for the area of the field using a machine learning model that receives the derivative data as input and predicts water movement within the field.

### Claim 20 (depends on 15)

The non-transitory computer readable medium of claim 15, including further instructions that, when executed by one or more processors, cause a computer to:
generate a report including at least one identification of an area of the field based on the critical level data.