US 10,949,972 B2Granted

Analyzing operational data influencing crop yield and recommending operational changes

AssigneeX Development LLC

InventorsCheng-en Guo, Wilson Zhao, Jie Yang, Zhiqiang Yuan, Elliott Grant

Life of this patent

Estimating the term…

Loading patent…

Abstract

Implementations relate to diagnosis of crop yield predictions and/or crop yields at the field- and pixel-level. In various implementations, a first temporal sequence of high-elevation digital images may be obtained that captures a geographic area over a given time interval through a crop cycle of a first type of crop. Ground truth operational data generated through the given time interval and that influences a final crop yield of the first geographic area after the crop cycle may also be obtained. Based on these data, a ground truth-based crop yield prediction may be generated for the first geographic area at the crop cycle's end. Recommended operational change(s) may be identified based on distinct hypothetical crop yield prediction(s) for the first geographic area. Each distinct hypothetical crop yield prediction may be generated based on hypothetical operational data that includes altered data point(s) of the ground truth operational data.

Claims20

Dependent claims

A method implemented using one or more processors, comprising:

obtaining a first temporal sequence of high-elevation digital images, wherein the first temporal sequence of high elevation digital images capture a first geographic area under consideration over a given time interval through a crop cycle of a first type of crop growing in the first geographic area;
obtaining ground truth operational data generated through the given time interval that influence a final crop yield of the first geographic area after the crop cycle, wherein the ground truth operational data is induced or controlled by humans, and is grouped into temporal chunks, each temporal chunk of the ground truth operational data corresponding temporally with a respective high-elevation digital image of the first temporal sequence of high-elevation digital images;
generating a ground truth-based crop yield prediction of the first geographic area at the end of the crop cycle by applying the high-elevation digital images of the first temporal sequence and the temporal chunks of the ground truth operational data as input across a machine learning model;
identifying one or more recommended operational changes, wherein the identifying includes:
generating one or more distinct hypothetical crop yield predictions of the first geographic area, wherein each distinct hypothetical crop yield prediction is generated by applying the high-elevation digital images of the first temporal sequence and temporal chunks of hypothetical operational data as input across the machine learning model, wherein the hypothetical operational data includes one or more altered data points of the ground truth operational data, and
identifying the one or more recommended operational changes based on one or more of the altered data points that were used to generate one or more of the hypothetical crop yield predictions that are greater than the ground truth-based crop yield prediction;
and
causing one or more output components of one or more computing devices to audibly or visually convey one or more of the recommended operational changes.

5 more elements

At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:

obtaining a first temporal sequence of high-elevation digital images, wherein the first temporal sequence of high elevation digital images capture a first geographic area under consideration over a given time interval through a crop cycle of a first type of crop growing in the first geographic area;
obtaining ground truth operational data generated through the given time interval that influence a final crop yield of the first geographic area after the crop cycle, wherein the ground truth operational data is induced or controlled by humans, and is grouped into temporal chunks, each temporal chunk of the ground truth operational data corresponding temporally with a respective high-elevation digital image of the first temporal sequence of high-elevation digital images;
generating a ground truth-based crop yield prediction of the first geographic area at the end of the crop cycle by applying the high-elevation digital images of the first temporal sequence and the temporal chunks of the ground truth operational data as input across a machine learning model;
identifying one or more recommended operational changes, wherein the identifying includes:
generating one or more distinct hypothetical crop yield predictions of the first geographic area, wherein each distinct hypothetical crop yield prediction is generated by applying the high-elevation digital images of the first temporal sequence and temporal chunks of hypothetical operational data as input across the machine learning model, wherein the hypothetical operational data includes one or more altered data points of the ground truth operational data, and
identifying the one or more recommended operational changes based on one or more of the altered data points that were used to generate one or more of the hypothetical crop yield predictions that are greater than the ground truth-based crop yield prediction;
and
causing one or more output components of one or more computing devices to audibly or visually convey one or more of the recommended operational changes.

5 more elements

A system comprising one or more processors and memory storing instructions that, in response to execution of the instructions by the one or more processors, cause the one or more processors to perform the following operations:

obtaining a first temporal sequence of high-elevation digital images, wherein the first temporal sequence of high elevation digital images capture a first geographic area under consideration over a given time interval through a crop cycle of a first type of crop growing in the first geographic area;
obtaining ground truth operational data generated through the given time interval that influence a final crop yield of the first geographic area after the crop cycle, wherein the ground truth operational data is induced or controlled by humans, and is grouped into temporal chunks, each temporal chunk of the ground truth operational data corresponding temporally with a respective high-elevation digital image of the first temporal sequence of high-elevation digital images;
generating a ground truth-based crop yield prediction of the first geographic area at the end of the crop cycle by applying the high-elevation digital images of the first temporal sequence and the temporal chunks of the ground truth operational data as input across a machine learning model;
identifying one or more recommended operational changes, wherein the identifying includes:
generating one or more distinct hypothetical crop yield predictions of the first geographic area, wherein each distinct hypothetical crop yield prediction is generated by applying the high-elevation digital images of the first temporal sequence and temporal chunks of hypothetical operational data as input across the machine learning model, wherein the hypothetical operational data includes one or more altered data points of the ground truth operational data, and
identifying the one or more recommended operational changes based on one or more of the altered data points that were used to generate one or more of the hypothetical crop yield predictions that are greater than the ground truth-based crop yield prediction;
and
causing one or more output components of one or more computing devices to audibly or visually convey one or more of the recommended operational changes.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/236,743Filed 31 Dec 2018 · us provisional application
Priority: 19 Oct 2018
Published: US 2020/0126232 A123 Apr 2020
Granted: 16 Mar 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification44 codes

G06T 3/4007
Scaling of whole images or parts thereof, e.g. expanding or contracting: based on interpolation, e.g. bilinear interpolation
A01D 41/127
Details of combines: control or measuring arrangements specially adapted for combines
G06N 3/044
Architecture, e.g. interconnection topology: recurrent networks, e.g. Hopfield networks
G06N 3/0442
Recurrent networks, e.g. Hopfield networks: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]