The Climate Corporation

Ying Xu

Lijuan Xu

Erik Andrejko

Wei Guan

Hao Zhong

Ankur Gupta

Jiunn-Ren Chen

Methods are provided for improving performance of a computing system used to model potential crop yield. In one example embodiment, a computer-implemented method includes generating a model of potential crop yield, as a function of planting date and relative maturity based, at least in part, on one or more relative maturity maps, one or more planting date maps, and one or more actual production history maps, and storing the model in a memory of the server computer system. The method also includes receiving, via an interface at a field manager computing device, a selection of a particular field and computing, from the model of potential crop yield, a potential yield for the particular field based, at least in part, on a planting date for the particular field, a relative maturity value, and values representing actual production history for the particular field.

Generating digital models of crop yield based on crop planting dates and relative maturity values

A method for determining national crop yields during the growing season is provided. In an embodiment, a server computer system receives agricultural data records for a particular year that represent covariate data values related to plants at a specific geo-location at a specific time. The system aggregates the records to create geo-specific time series for a geo-location over a specified time. The system creates aggregated time series from a subset of the geo-specific time series. The system selects a representative feature from the aggregated time series and creates a covariate matrix for each specific geographic area in computer memory. The system determines a specific crop yield for a specific year using linear regression to calculate the specific crop yield from the covariate matrix. The system determines a forecasted crop yield for the specific year using a sum of the specific crop yields for the specific year, as adjusted.

Forecasting national crop yield during the growing season

Systems and methods for scalable comparisons between two pixel maps are provided. In an embodiment, an agricultural intelligence computer system generates pixel maps from non-image data by transforming a plurality of values and location values into pixel values and pixel locations. The non-image data may include data relating to a particular agricultural field, such as nutrient content in the soil, pH values, soil moisture, elevation, temperature, and/or measured crop yields. The agricultural intelligence computer system converts each pixel map into a vector of values. The agricultural intelligence computer system also generates a matrix of metric coefficients where each value in the matrix of metric coefficients is computed using a spatial distance between to pixel locations in one of the pixel maps. Using the vectors of values and the matrix of metric coefficients, the agricultural intelligence computer system generates a difference metric identifying a difference between the two pixel maps. In an embodiment, the difference metric is normalized so that the difference metric is scalable to pixel maps of different sizes. The difference metric may then be used to select particular images that best match a measured yield, identify relationships between field values and measured crop yields, identify and/or select management zones, investigate management practices, and/or strengthen agronomic models of predicted yield.

Generating pixel maps from non-image data and difference metrics for pixel maps

A computer implemented method for generating digital models of relative crop yield based on nitrate values in the soil is provided. In an embodiment, nitrate measurements from soil during a particular portion of a crop's development and corresponding crop yields are received by an agricultural intelligence computing system. Based, at least in part, on the nitrate measurements and corresponding crop yields, the system determines maximum yields for each location of a plurality of locations. The system then converts each crop yield value into a relative crop yield by dividing the crop yield value by the maximum crop yield for the location. Using the relative crop yields and the corresponding nitrate values in the soil, the system generates a digital model of relative crop yield as a function of nitrate in the soil during the particular portion of the crop's development. When the system receives nitrate measurements from soil in a particular field during the particular portion of a crop's development, the system computes a relative yield value for the particular field using the model of relative crop yield.

Generating digital models of relative yield of a crop based on nitrate values in the soil

A method for generating digital models of potential crop yield based on planting date, relative maturity, and actual production history is provided. In an embodiment, data representing historical planting dates, relative maturity values, and crop yield is received by an agricultural intelligence computer system. Based on the historical data, the system generates spatial and temporal maps of planting dates, relative maturity, and actual production history. Using the maps, the system creates a model of potential yield that is dependent on planting date and relative maturity. The system may then receive actual production history data for a particular field. Using the received actual production history data, a particular planting date, and a particular relative maturity value, the agricultural intelligence computer system computes a potential yield for a particular field.

A method for determining national crop yields during the growing season is provided. In an embodiment, a server computer system receives agricultural data records for a particular year that represent covariate data values related to plants at a specific geo-location at a specific time. The system aggregates the records to create geo-specific time series for a geo-location over a specified time. The system creates aggregated time series from a subset of the geo-specific time series. The system selects a representative feature from the aggregated time series and creates a covariate matrix for each specific geographic area in computer memory. The system determines a specific state crop yield for a specific year using linear regression to calculate the specific state crop yield from the covariate matrix. The system determines a national crop yield for the specific year using the sum of the state crop yields for the specific year nationally adjusted.

In an approach, hyperspectral and/or multispectral remote sensing images are automatically analyzed by a nitrogen analysis subsystem to estimate the value of nitrogen variables of crops or other plant life located within the images. For example, the nitrogen analysis subsystem may contain a data collector module, a function generator module, and a nitrogen estimator module. The data collector module prepares training data which is used by the function generator module to train a mapping function. The mapping function is then used by the nitrogen estimator module to estimate the values of nitrogen variables for a new remote sensing image that is not included in the training set. The values may then be reported and/or used to determine an optimal amount of fertilizer to add to a field of crops to promote plant growth.

Estimating nitrogen content using hyperspectral and multispectral images

A method for predicting field specific crop yield recommendations is disclosed. A computer system receives data records, including remotely sensed spectral property of plant records and soil moisture records. The system aggregates the records to create geo-specific time series over a specified time. The system selects representative features from the geo-specific time series and creates, for each specific geographic area, a covariate matrix in computer memory comprising the representative features. The system assigns a probability value to a component group in a set of parameter component groups, where each component group includes one or more regression coefficients and an error term calculated from probability distributions. The system is programmed to generate generates the probability distributions used to determine the regression coefficients and the error term, the probability distribution used to generate the error term is defined with a mean parameter set at zero and a variance parameter set to a field specific bias coefficient.

Forecasting field level crop yield during a growing season

A method for determining national crop yields during a growing season is accomplished using a server computer system that receives observed agricultural data records for a specific geo-location at a specific time. The server calculates weather index values from the agricultural data records that represent crop stress on plants. Geo-specific weather indices are generated from the weather index values, which then are aggregated to generate aggregated weather index data series. Representative features are selected from each aggregated weather index data series to create a covariate matrix for each geographic area. Crop yield for the geographic area is calculated using a linear regression model based on the covariate matrix for the specific geographic area. The server determines a national crop yield for the specific year as a sum of the crop yields for the specific geographic areas nationally adjusted using national yield adjustment instructions.

Forecasting national crop yield during the growing season using weather indices

A computer system and computer-implemented techniques for determining crop harvest times during a growing season based upon hybrid seed properties, weather conditions, and geo-location of planted fields is provided. In an embodiment, determining crop harvest times for corn fields may be accomplished using a server computer system that receives over a digital communication network, electronic digital data representing hybrid seed properties, including seed type and relative maturity, and weather data for the specific geo-location of the agricultural field.

Computer-implemented calculation of corn harvest recommendations

A method for determining national crop yields during the growing season using regional agricultural data is provided. In an embodiment, determining national crop yields during the growing season may be accomplished using a server computer system that receives, via a network, agricultural data records that are used to forecast a national crop yield for a particular year. Within the server computer system an agricultural time series module receives one or more agricultural data records that represent a type of covariate data value related to plants at a specific geo-location at a specific time. The agricultural time series module then aggregates the agricultural data records to create one or more geo-specific time series that represent a specific geo-location over a specified time. The agricultural time series module creates one or more aggregated time series that represent geographic areas from a subset of the one or more geo-specific time series. A crop yield estimating module selects a representative feature from the one or more aggregated time series and creates a covariate matrix for each specific geographic area in computer memory of the server computer system. The crop yield estimating module determines a specific state crop yield for a specific year by using a linear regression module to calculate the specific state crop yield from the covariate matrix that represents the specific state for that specific year. The crop estimation module determines a national crop yield for the specific year by using the distribution generation module to calculate the national crop yield for a specific year from the sum of the specific state crop yields for the specific year nationally adjusted using a national yield adjustment module.

Growing community of inventors

Boston, MA, United States of America

Ying Xu