Donald J. Patterson

Greenhouse Grant for Gutter Gardening

prototype gutter garden

This prototype gutter garden retained water and grew 8 heads of lettuce.

The Westmont Inspired Computing Lab just got a “seed” grant to launch a greenhouse powered by Artificial Intelligence! Our plan is to see if a machine learning algorithm with access to sensor data can beat a human at growing food in drought conditions. This work is inspired by a paper that I coauthored with colleagues about the idea of Computational Agroecology and is in partnership with Joy Patterson.

growlights arranged in a block

Five grow lights that we will use to extend the winter daylight

Why build a greenhouse?

It is widely understood that today’s industrial agriculture, which is central to our civilization, but reliant on non-renewable resources (e.g., fossil fuels, chemical fertilizers, and pesticides) and causing increasing damage to the ecosystem effects (e.g., erosion, oceanic dead zones, greenhouse gas emissions), cannot persist indefinitely [The Ecology of Agoecosystems, Vandermeer 2011]. However, none of the existing alternative agricultural systems is currently able to meet the challenge of feeding the 7.4 billion people in the world, much less the added billions that demographers project. We believe that we have an opportunity at this juncture to change the way future food systems are structured through the design of technologies to implement sustainable new ecosystems for food production.   This is a broad problem, but locally in Southern California we have the additional pressing problem of dealing with a very limited water supply.

painted cinder blocks

The foundation will anchor the greenhouse against the wind, give it a little more height, and a touch of style.

Computational Agroecology

Scientists in the field of agroecology have identified approaches to reconcile human food needs with the broader planetary ecosystem and its limits. Agroecology has failed to scale due to the information and logistical challenges of adapting agroecological techniques to millions of unique potential sites of food production.  Especially in urban environments where there is quite a bit of space to grow food, but a great variety of site specific details. This is in contrast to industrial agriculture’s approach of using external inputs to standardize sites and increase yields: think hundreds of acres of monoculture.

We have proposed a new approach, Computational Agroecology, that seeks to make agroecology viable at a global scale. Our approach entails computational systems that enable the design of new ecosystems 
for food production using agroecological techniques.

foundation of the greenhouse

The greenhouse is under construction on a south facing patio at Winter Hall

Internet of Things

This greenhouse will combine technology developed for the Internet of Things (IoT) with artificial intelligence and hydroponics to automatically learn watering policies that compete with hand-made policies to grow more food, faster, with less water.

We are going to prototype a small temporary greenhouse that has 5 eight-foot rain gutters in it, arranged in a stair step pattern. Each gutter will contain soil and will be planted with lettuce seeds for this experiment. Each gutter will have an associated water tank and solenoid that will release water into the gutter to hydrate the plants as dictated by a micro-controller.  Each gutter will have a competing algorithm controlling it whose strategy was learned from the previous round of lettuce growing.

Principal Investigator investigating

Prototyping the sensors with an Arduino

Ultimately we would like to deploy many greenhouses around Santa Barbara, controlled by Raspberry Pi’s, to enable people in urban environments to have a very local food supply.

Principal Investigators

If all goes well it will be published in a peer-reviewed venue and as a science fair project!


C.V.: G-29

4 comments for “Greenhouse Grant for Gutter Gardening

  1. Kevin
    December 21, 2016 at 12:43 am

    Professor Patterson this is a really amazing idea that using Raspberry pi to controll greenhouse. But I still want to ask few questions.
    1 why should we use artificial intelligence algorithm instead of certain program that repeat the same program? Is this because the environment of the greenhouse functions change every year so the simple program can not handle?
    2 When using the gutter, how many lettuce seeds should be put in the gutter? When put into practical, do we follow certain ratio like 1 lettuce seed, one square of soil supply. Then 1000 lettuce seeds, 1000 squares of soil squares? Or the ratio will change?
    3 I am,really interested in that project, is there any way I can be part of it?

    • December 21, 2016 at 11:18 am

      1. So the question is what program should we use to control the garden? The machine learning is being used to discover that program and if it is robust enough, then that one program will be the one that everyone uses. Once it is learned it stops learning and we just use it.
      2. The ratio is about 1 seed every 6-8 inches. Since it’s a gutter we use linear measures, not area.
      3. Yes! Come talk to me in the spring.

  2. Philip Schlesinger
    April 16, 2017 at 5:33 pm

    How’s progress?

    • April 17, 2017 at 8:38 am

      So actually we had our first harvest this weekend. It wasn’t very “smart” yet, but we are understanding the greenhouse environment better. I need to get more updates up on the Tumblr blog.
      Here is a picture of the first harvest (link). I don’t think I can embed pictures directly here.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.