Abstract: A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value.

Abstract: A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value.

Abstract: In an embodiment, radar observation data for time points are received at an input layer of a rain rate prediction neural network. The radar observations are forward propagated via hidden layers of the network to determine rain rates for the time points. The rain rates are integrated over a time period, determined based on the time points, to determine a predicted rainfall amount. The predicted rainfall amount is compared with an actual rainfall amount, determined based on received rainfall measurements, to determine an error. If the error does not satisfy certain criteria, then the error is apportioned to each of the time points, the apportioned errors are back propagated via the hidden layers, and weights associated with nodes in the hidden layers are updated. The radar observation data is again forward propagated via the layers, multiplied by the updated weights, and used to determine new rain rates.

Abstract: A method for estimating confidence bounds for adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then used to estimate adjusted rainfall values for a set of geo-locations. Rainfall confidence bounds instructions estimate a set of confidence bounds for each of the adjusted rainfall values for the set of geo-locations. The set of confidence bounds provide a range for each of the adjusted rainfall values that represents a particular level of confidence associated with each of the adjusted rainfall values.

Abstract: A method and system for generating probabilistic estimates of precipitation intensity from radar reflectivity measurements is provided. In an embodiment, an agricultural intelligence computer system receives radar reflectivity measurements for a particular location from an external data source. The agricultural intelligence computer system constructs a probability distribution of drop sizes describing the probability that the precipitation included drops of various sizes based on the radar reflectivity measurements. The agricultural intelligence computer system samples a plurality of values from the probability of distribution of drop sizes and uses the plurality of values and the radar reflectivity measurements to compute a plurality of rainfall rates. Based on the plurality of rainfall rates, the agricultural intelligence computer system constructs a probability distribution of rainfall rates for the particular location.

Abstract: A method for estimating adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then transformed into one or more distribution sets. The distribution sets are then used to determine regression parameters for a digital rainfall regression model. The digital rainfall regression model then is used to estimate adjusted rainfall values for a new set of geo-locations. The server computer system then generates a digital image that includes the geo-locations and the adjusted rainfall values.

Abstract: In an embodiment, a system receives first data comprising precipitation gauge measurements at a plurality of gauge locations. The system obtains second data comprising radar based precipitation estimates at the plurality of gauge locations. For each radar based precipitation value at the plurality of gauge locations, the system identifies one or more corresponding precipitation gauge measurement, computes a gauge radar differential value for the radar based precipitation estimate, and stores the gauge radar differential value with location data identifying a corresponding location of the plurality of gauge locations. The system then obtains a particular radar based precipitation estimate at a non-gauge location.

Abstract: A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value.

Abstract: A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value.

Abstract: In an embodiment, radar observation data for time points are received at an input layer of a rain rate prediction neural network. The radar observations are forward propagated via hidden layers of the network to determine rain rates for the time points. The rain rates are integrated over a time period, determined based on the time points, to determine a predicted rainfall amount. The predicted rainfall amount is compared with an actual rainfall amount, determined based on received rainfall measurements, to determine an error. If the error does not satisfy certain criteria, then the error is apportioned to each of the time points, the apportioned errors are back propagated via the hidden layers, and weights associated with nodes in the hidden layers are updated. The radar observation data is again forward propagated via the layers, multiplied by the updated weights, and used to determine new rain rates.

Abstract: A method for estimating confidence bounds for adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then used to estimate adjusted rainfall values for a set of geo-locations. Rainfall confidence bounds instructions estimate a set of confidence bounds for each of the adjusted rainfall values for the set of geo-locations. The set of confidence bounds provide a range for each of the adjusted rainfall values that represents a particular level of confidence associated with each of the adjusted rainfall values.

Abstract: A system and method for computing radar based precipitation estimates using inverse distance weighting is provided. In an embodiment, an agricultural intelligence computer system receives first electronic digital data comprising a first plurality of values representing precipitation gauge measurements at a plurality of gauge locations. The agricultural intelligence computer system obtains second electronic digital data comprising a second plurality of values representing radar based precipitation estimates at the plurality of gauge locations.

Abstract: A system and method for improving radar based precipitation estimates using spatiotemporal interpolation is provided. In an embodiment, an agricultural intelligence computer system receives a plurality of radar based precipitation rate values representing precipitation rate measurements at a plurality of locations and a plurality of times. The agricultural intelligence computer system identifies a first non-zero radar based precipitation rate value associated with a first location of the plurality of locations and a first time of the plurality of times. The agricultural intelligence computer also identifies a second non-zero radar based precipitation rate value associated with a second location of the plurality of locations and a second time of the plurality of times. The agricultural intelligence computer system determines that the first non-zero radar based precipitation rate value corresponds to the second non-zero radar based precipitation rate value.

Abstract: A method for estimating adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then transformed into one or more distribution sets. The distribution sets are then used to determine regression parameters for a digital rainfall regression model. The digital rainfall regression model then is used to estimate adjusted rainfall values for a new set of geo-locations. The server computer system then generates a digital image that includes the geo-locations and the adjusted rainfall values.

Abstract: A method and system for generating probabilistic estimates of precipitation intensity from radar reflectivity measurements is provided. In an embodiment, an agricultural intelligence computer system receives radar reflectivity measurements for a particular location from an external data source. The agricultural intelligence computer system constructs a probability distribution of drop sizes describing the probability that the precipitation included drops of various sizes based on the radar reflectivity measurements. The agricultural intelligence computer system samples a plurality of values from the probability of distribution of drop sizes and uses the plurality of values and the radar reflectivity measurements to compute a plurality of rainfall rates. Based on the plurality of rainfall rates, the agricultural intelligence computer system constructs a probability distribution of rainfall rates for the particular location.