Researchers at North Carolina State are working with Lenovo to utilize artificial intelligence to tackle the growing challenge of meeting freshwater needs for agriculture in these days of climate change. Why use AI?

The scale of the data involved is daunting.

The NCSU team is “collecting and processing big geospatial data from satellites and sensors. Very high-resolution imagery at global scale constitutes more than 500 trillion multidimensional observations (pixels) that then need to be sorted and analyzed so the team can gain insights about crop growing patterns,” Lenovo explained in a blog post.

“The computational problem is further compounded by the need to analyze petabytes of climate data in order to understand the climate change impacts (e.g., floods, droughts) on food and water systems. The research team’s data analysis workflow demands high-end computing resources due to algorithmic complexity of artificial intelligence methods such as multiple instance learning and deep learning, and I/O [input/output] needs stemming from the big data.”

  • VIDEO: Watch an overview at https://www.youtube.com/watch?v=MmBgKoZB6II

Lenovo announced the effort at a supercomputing conference in Denver at the same time it disclosed the opening of an AI center at its campus in the Triangle.

Meeting growing ag water demand

“We’re very pleased with the work we are doing around such a global issue like freshwater supply. As we look to leverage more advanced computational processes and deep learning methods, our existing infrastructure is no longer sufficient,” said Ranga Raju, Associate Professor in Geospatial Analytics at NCSU, in the announcement.

“By partnering with Lenovo and its AI innovation center in Morrisville, we’ve not only gained access to infrastructure that has been optimized for machine learning workloads, but also a wealth of knowledge from Lenovo and its partners whose engineers and consultants are skilled in AI.”

Lenovo points out that agriculture already is responsible for 70 percent of freshwater usage around the world. That percentage is expected to grow by 10 points over the next three decades.

In a blog post, Lenovo noted that the joint NCSU-Lenovo effort could “help minimize the disruption to food production” by helping farmers “prepare for anticipated regions that will experience drought (or flooding) which will negatively impact crop growth.”

What AI means to project

Here’s how Lenovo explained the AI project:

“Using an artificial intelligence-enabled geospatial image analysis process, NCSU applies deep learning algorithms to recognize farmland, identify the farm crops, monitor soil conditions and calculate water requirements against available water resources to create maps of drought areas.

“The same AI techniques help local and global farmers to examine crop and soil health for efficiently managing water and energy resources in irrigation, improving their profitability while conserving scarce natural resources.”