Abstract: A system and method processes images of insurance cards to extract information. The images of the insurance cards are processed using OCR to identify characters on the insurance cards. Combinations of characters on each insurance card are identified as tokens, and their relative spatial orientation is determined. Deep learning architectures are utilized to generate a fully connected neural network with a node for each token on each card. The neural network is utilized to extract entities from each insurance card, such as a valid member ID.

Abstract: A gravity irrigation system includes a distribution piping having apertures to distribute water to a field, and a valve located upstream of the distribution piping. The valve is configured to limit a pressure of the water being delivered to the distribution piping. The system also includes a sump configured to receive the water at a lowest elevation of the field, a depth sensor disposed within the sump, and a return pump disposed at least partially within the sump and configured to move the water to an elevated portion of the field. The system also includes a motor configured to drive the return pump, and a power source coupled to a variable frequency drive. The variable frequency drive is configured to power the motor and control a motor speed proportionately to an indication of the depth sensor.