Enhanced management zones for precision agriculture
The present invention is a system and method for agricultural management-zone delineation to be done over broad geographic extents without overly-localized field-specific data. The instant innovation guides precision agricultural sampling and management by delineating enhanced management zones based upon remote sensing and artificial intelligence and combining the two with data derived from an existing countrywide soil survey database. In an embodiment, the instant innovation uses artificial intelligence from multiple sources to provide granular zone detail. Output of the present innovation can be aggregated to produce management zone sizes that have a level of uncertainty compatible with the needs of the customer-fanner and implementable given the capabilities of available equipment.
1. A system for optimizing agricultural zone attributes comprising:
a data processor in communication with a data server;
a user device, in communication with the data server, displaying data representations to a user from the following steps;
constructing a first input dataset of geospatial images for the data processor from remote sensing of field conditions subjected to digital analysis, collected multi-temporal satellite or aerial imagery bands and calculated soil indices from the collected multi-temporal satellite or aerial imagery bands, and a SSURGO Soil Parent Material Data;
training, by the data processor, a first soil property model with the first input data set using a supervised learning algorithm;
generating, with the first soil property model by the data processor, predictions for a first soil property; and, in parallel, applying, by the data processor, an unsupervised artificial intelligence algorithm to the first input dataset, and
outputting, by the data processor, a plurality of potential sets of management zones for the first soil property;
geospatially joining, by the data processor, the predictions for the first soil property from the output of the first soil property model generated using the supervised learning algorithm with each of the plurality of potential sets of management zones generated from the unsupervised artificial intelligence algorithms;
comparing, by the data processor, each of the plurality of potential sets of management zones that have been geospatially joined with the predictions for the first soil property from the output of the first soil property model to optimize intra-zone differences and maximize inter-zone differences of the first soil property; and
wherein the data processor calculates a change in at least one set of soil zone attributes from an aggregated zone comprised of two or more of the plurality of potential sets of management zones and one or more zone patches and/or inclusions;
wherein the data processor dissolves zone boundaries of the aggregated zone and the one or more zone patches and/or inclusions; and
delivering, by the data processor, an optimized management zone for the first soil property to the user from the plurality of potential sets of management zones.
2. The system of claim 1 , wherein the unsupervised artificial intelligence algorithms are Deep Learning algorithms, Unsupervised Learning algorithms, or a combination of Deep Learning and Unsupervised Learning algorithms.
3. The system of claim 1 , wherein an evaluation of zone effectiveness incorporates ground truth or Deep Learning algorithm output.
4. A method for optimizing agricultural zone attributes comprising:
constructing a first input dataset of geospatial images using remote sensing of field conditions subjected to digital analysis, collected multi-temporal satellite or aerial imagery bands and calculated soil indices from the collected multi-temporal satellite or aerial imagery bands, and SSURGO Soil Parent Material Data;
training with the first input data set using supervised learning a first soil property model;
generating predictions for a first soil property with the first soil property model; and, in parallel,
applying an unsupervised artificial intelligence algorithm to the first input dataset, and outputting a plurality of potential sets of management zones for the first soil property;
geospatially joining the predictions the predictions for the first soil property from the output of the first soil property model generated using the supervised learning algorithm with each of the plurality of potential sets of management zones generated from the unsupervised artificial intelligence algorithm;
comparing each of the plurality of potential sets of management zones that have been geospatially joined with the predictions for the first soil property from the output of the first soil property model to optimize intra-zone differences and maximize inter-zone differences of the first soil property
calculating a change in at least one set of soil zone attributes from an aggregated zone comprised of two or more of the plurality of potential sets of management zones and one or more zone patches and/or inclusions;
dissolving zone boundaries of the aggregated zone and the one or more zone patches and/or inclusions; and
delivering an optimized management zone for the first soil property to a user.
5. The method of claim 4 , wherein an evaluation of zone effectiveness incorporates ground truth or Deep Learning algorithm output.
6. The method of claim 4 , where the unsupervised artificial intelligence algorithms are Deep Learning algorithms, Unsupervised Learning algorithms, or a combination of Deep Learning and Unsupervised Learning algorithms.
7. The method of claim 4 , where an evaluation of zone effectiveness incorporates ground truth or Deep Learning algorithm output.