Big Data Analytics

From IoT and vines grow the fruits of innovation

Share this post:

Innovation is a company principle shared by both IBM and E. & J. Gallo Winery, the world’s largest family-owned winery, headquartered in Modesto, California. While the Internet of Things (IoT) and wine don’t seem like obvious partners, the two companies found a common purpose focused on growing the best quality grapes while optimizing the amount of water applied to the vineyard.

At the core of E. & J. Gallo Winery is a strong commitment to produce high quality wines while being mindful of how the land is farmed.  This is only possible by paying careful attention to each step in the grape growing process. It also requires an intimate understanding of vineyard site and growing conditions including climate, sunlight exposure, soil quality, slope and topography.  Gallo has a long tradition of encouraging and adhering to sustainable practices that are environmentally sound.  Paramount to this objective is the conservation of water at all of their vineyards in California and Washington.

Gallo was working in 2012 on improving water use efficiency using remote sensing.  The concept utilized NASA satellite imagery to determine vine canopy size and water status, as well as to determine vine water use.  The Gallo team noticed a high degree of variability in vine water use across their vineyards, which led them to find a collaborator in IBM Research.  IBM applied its expertise in IoT, physical analytics and cognitive computing technologies to co-develop a precision irrigation method and prototype system and install it in a ten-acre vineyard. This work provided the first large scale scientific evaluation of grapevine response to hyper-local precision irrigation, and showed that that this method could reduce water usage by 25 percent.

Vineyard at Gallo Winery

Vineyard at Gallo Winery

At the heart of the method, data on weather and soil conditions was integrated with satellite imagery and other sensor data to determine precisely how much water each section of the vineyard required in order to produce the highest quality grapes. Before the prototype was developed, irrigation levels could only be adjusted at the vineyard block level and did not account for individual vine requirements.  A common farming practice prior to this finding was to irrigate all vines in the vineyard at the same level, leading to some vines getting too much irrigation and others not enough.

From an infrastructure and IoT perspective, IBM scientists conceived an advanced irrigation system built with a series of sensors and actuators in the ten-acre plot that communicated with a central vineyard control system.  Using geo-spatial data such as soil, climate and imagery from hyperspectral satellites, the system predicted vine irrigation needs that sent signals to open valves and released the precise amount of water to each vine. Physics-inspired machine learning technologies were used to establish the irrigation schedules.

IBM and Gallo received a Vintage Report Innovation Award for their collaborative efforts on the prototype in 2015. Today, Gallo is still experimenting with the technology. In fact, since 2015, Gallo has installed precision irrigation systems in six different vineyard blocks encompassing nearly 250 acres in California.  They are experiencing a 20 percent increase in water use efficiency – meaning that they use 20 percent less water for each pound of grapes that they produce.

Although this IoT technology was pioneered in vineyards, it has potential to be applied to other perennial crops such as citrus and almonds. If this technology could be used across all irrigated farmland in the U.S., it could result in significant water conservation and also help to optimize crop production. Gallo has plans underway to commercialize the system and its components to bring this to other farm commodities.

IBM, for its part, has taken the learnings from this project and is applying them to an ambitious experimental research effort that involves aggregating, indexing and analyzing terabytes of open geo spatial data that could pave the way to let winemakers and others perform precision analytics on a global scale.

What began as a seed of an idea has blossomed into a ripe opportunity for E. & J. Gallo Winery and IBM to continue to innovate and advance ideas based on big data that could transform not just the wine industry, but provide valuable insights to tackle some of our world’s biggest challenges, including the availability of food, water, and sustainable energy sources.

More Big Data Analytics stories

Research Unveils Innovations for IBM’s Cloud for Financial Services

IBM Research played a central role in developing the technology underpinnings of IBM’s financial services public cloud, including the new IBM Cloud Security and Compliance Center, an IBM Cloud service.

Continue reading

Reducing Speech-to-Text Model Training Time on Switchboard-2000 from a Week to Under Two Hours

Published in our recent ICASSP 2020 paper in which we successfully shorten the training time on the 2000-hour Switchboard dataset, which is one of the largest public ASR benchmarks, from over a week to less than two hours on a 128-GPU IBM high-performance computing cluster. To the best of our knowledge, this is the fastest training time recorded on this dataset.

Continue reading

IBM Research uses AI to automate Mono2Micro application refactoring

IBM Mono2Micro application modernization efforts take another step forward with the release of an updated beta version that automatically generates API services and related code to activate Mono2Micro microservice recommendations.

Continue reading