New Pistachio Yield Prediction Project Underway at UC Davis

To make this project successful, UC Davis’ Patrick H. Brown said that the researchers need as much individual block yield data from pistachio orchards across the state as possible. All data received will be fully anonymized and private (photo by Demi Schmiederer, Legacy Farm Management.)

UC Davis Pomologist Patrick H. Brown and UC Davis Professor Yufang Jin have begun working on a USDA grant proposal to develop a method to predict pistachio yield by using historic yield data, free satellite imagery, automated climate analysis and individual orchard characteristics. The outcome will be a simple-to-use app or website for yield prediction of any pistachio block, and this can be used to help predict ideal nitrogen fertilization and irrigation as well as plan other yield-dependent activities.

Growers are under constant pressure to properly and efficiently utilize their nitrogen and water. One of the key determinants in an orchard for how much nitrogen/water to use and when to use it, according to Brown, is yield. However, he said, growers don’t know the actual yield until nuts are harvested.

Brown provided some insight to the overarching goals of this project and how it can hopefully benefit the pistachio industry. “Early in the season (April, May), be able to get to growers a realistic estimate of their predicted yield for the remainder of the year so that they can then optimize that water and nitrogen to meet the goal of that particular yield.”

To make this project successful, Brown said that the researchers need as much individual block yield data from pistachio orchards across the state as possible. Important to note is that all data received will be fully anonymized and private. There is no cost to growers, no charge for final product and no need for UC experimentation on orchards. The orchard information survey can be found here.

The researchers, Brown said, would use historic trend data from hundreds of different orchards across the state and ask computer programs to find patterns in the data. Those patterns would then be related to satellite images of the trees and the climate of a particular year.

“We would like from as many growers, from as many individual orchards as possible, historic yield data and, as much as they’re willing to do so, information on the orchard, such as planting distances, planting year, etc.,” Brown said.

Brown said the app or website would ideally be able to estimate a growers’ yield in an already-established location and even a location that doesn’t yet have plantings. Additionally, it would be able to tell growers or researchers why an orchard in one part of the state is getting historically higher yields than an orchard in a different part of the state.
For more information on the project and grower survey, contact Patrick H. Brown.