OPTIMIZED SOIL SAMPLING FOR DIGITAL SOIL FERTILITY MAPPING USING MACHINE LEARNING AND REMOTELY-SENSED INFORMATION

A soil modeling and mapping framework for use in precision agriculture analyzes remotely-sensed data pertaining to characteristics of one or more agricultural fields, and determines optimal sampling locations from information in remotely-sensed information, terrain derivatives and satellite imagery, to develop a customized sampling design for modeling soil properties in such agricultural fields that optimized for the particular landscape in such fields. The soil modeling and mapping framework then analyzes soil samples collected based on the customized sampling design in machine learning-based models that predict soil properties in sampled, semi-sampled, and unsampled target fields. The predicted soil properties are used to develop highly-accurate maps of soil properties such as fertility maps, which may further be used for defining and creating one or more management zones with recommendations for applying the right amount of nutrients at variable rates in the correct areas.