Monitoring nutrient status in vineyard by drone Imagery

Aerial view of the experimental vineyard located at the central valley of California
Aerial view of the experimental vineyard located at the central valley of California

Principal Investigator: Alireza Pourreza

Project Sponsor: California Table Grape Commission

Project Team:  Ali MoghimiGerman Zuniga-Ramirez

Collaborator: Matthew Fidelibus

 

Future agricultural and food production systems must make better use of limited resources to ensure that farmers can economically produce more high-quality food for the growing world population while minimizing impact on the environment. A nitrogen (N) management plan helps growers make the best use of N fertilizers, and an important part of such plans involves monitoring vine N status. Presently, monitoring vine N requires collecting plant tissue samples and submitting them to a laboratory for analysis. This is a laborious practice that, at best, provides an average value for the entire vineyard. In contrast, remote sensing has the potential to provide more detailed data about entire vineyards, potentially for every vine. The recent introduction of sophisticated, more affordable and user-friendly drone-based aerial imaging equipment has made it possible for growers to consider collecting frequent large-scale data for monitoring vineyards. However, what’s lacking is a well-established aerial image processing pipeline, a comprehensive calibration procedure, and accurate data interpretation models. Until those exist, it will be difficult for growers to fully capitalize on aerial imaging applications. In this project, we aim to develop a data-driven decision support tool that will enable growers to accurately monitor vine nutrient status. This tool will enable growers to use drone imagery to obtain site-specific insight about nutrient status throughout the entire vineyard while all data analytic steps (including data calibration, processing, and interpretation) will be done automatically in a web application. Over the last two seasons we have been pairing aerial imaging and proximal sensing with laboratory analysis of tissue samples to develop calibrated models that should enable us to use remote sensing to estimate vine N status. The ultimate goal of this study is a web application that automates most of the processing and data analytics steps and provides per-vine nutrient status at different stages of the growing season. Currently, growers need to hire an expert in remote sensing and data science for conducting the data analytics, if they want to employ drone-based vineyard monitoring. 

Study in 2019-2020

 

Study in 2018-2019

Grapevines have lower mineral nutrient requirements than many other crops but vine nutrient status should be monitored to help prevent deficiencies that could reduce vine capacity, yield, and fruit quality. Monitoring nutrient status can also provide information to help prevent unnecessary fertilizer applications which needlessly increase production cost, and could cause unintended nutrient imbalances or environmental contamination. Tissue sampling is one of the best way to monitor nitrogen in grapevine. However, it is an imperfect monitoring method because it is based on laboratory assessment which is destructive, costly and time consuming.

Aerial imaging system used for multispectral image acquisition
Aerial imaging system used for multispectral image acquisition

In this project, we used aerial multispectral images to predict vine nitrogen status. Experimental block was designed with three different nitrogen application rates of (0, X, and 2.5X) applied in either two (Slugs) or 10 (Spoonfeed) applications.

Experimental table grape block in a vineyard
Different treatments of nitrogen application in the experimental block located in the north side of a table grape vineyard in central valley of California

Leaf tissues from selected vines were collected and assessed for nitrogen status. The nitrogen content values were used as labels for multispectral data from the corresponding vines. Various vegetation indices were extracted from aerial multispectral data:

Vegetation indices used in this study
List of vegetation indices extracted from 5-band aerial imagery

Correlation between leaf nitrogen and vegetation indices were calculated and plotted in the figure bellow. The best correlation happens when R-squared is high and p-value is low, that means that the model significantly explains a lot of variation within the data.

Correlation between leaf nitrogen and vegetation indices at bloom and harvest
Correlation between leaf nitrogen and vegetation indices at bloom (mid-May) and harvest (early-July)

Based on the correlation results, CRM and NDRE are the best indicators of nitrogen in table grape

Regression results for predicting Nitrogen by remote sensing
Regression results for predicting Nitrogen by CRM and NDRE
NDRE vegetation index of a vineyard shows spatial variability of Nitrogen status in table grape
NDRE vegetation index of a vineyard shows spatial variability of Nitrogen status in table grape