Return to Video

Big data, small farms and a tale of two tomatoes

  • 0:01 - 0:05
    So data and analytics are dramatically
    changing our everyday lives.
  • 0:06 - 0:07
    Not just online,
  • 0:07 - 0:09
    not just in some distant future,
  • 0:09 - 0:10
    but in the physical world,
  • 0:10 - 0:13
    and in very real and tangible ways.
  • 0:14 - 0:18
    I spent the past 11 years
    of my life as a geek at MIT,
  • 0:18 - 0:20
    working in big data labs
  • 0:20 - 0:23
    that seek to use data science
    to study the physical world
  • 0:23 - 0:26
    and try to solve society's great problems.
  • 0:27 - 0:31
    The field of big data seeks to analyze
    massive pools of data
  • 0:31 - 0:35
    using computational tools
    to find patterns and trends.
  • 0:36 - 0:39
    Data can be a really
    extraordinary storyteller,
  • 0:39 - 0:42
    unveiling the hidden narratives
    of things in our everyday lives
  • 0:42 - 0:43
    that we never would have seen.
  • 0:43 - 0:47
    I find the personal stories of inanimate
    things brought to life
  • 0:47 - 0:49
    to be extraordinarily compelling.
  • 0:50 - 0:53
    I want to highlight, first,
    two projects from my time at MIT
  • 0:53 - 0:55
    that I think highlight
    this phenomenon really well.
  • 0:56 - 0:58
    The first is called Trash Track,
  • 0:58 - 1:02
    and in this project, we sought to better
    understand the waste-management system,
  • 1:02 - 1:04
    to answer the question
  • 1:04 - 1:06
    "Where does your trash go
    when you throw it away?"
  • 1:06 - 1:09
    Your old coffee cup or that flip phone
  • 1:09 - 1:11
    that you carried around
    in the early 2000s,
  • 1:11 - 1:15
    or a bagel or this morning's paper --
  • 1:15 - 1:16
    where do these things go?
  • 1:17 - 1:20
    This data didn't exist,
    so we had to create it.
  • 1:20 - 1:23
    We answered and then
    visualized this question
  • 1:23 - 1:27
    by installing small sensors
    into pieces of trash
  • 1:27 - 1:29
    and then throwing them
    into the waste system.
  • 1:30 - 1:32
    And what you're seeing here is the data.
  • 1:33 - 1:36
    Every line, every node that you see
  • 1:36 - 1:39
    is a single piece of trash
    moving through the city of Seattle,
  • 1:39 - 1:42
    and then across the state,
  • 1:42 - 1:43
    and then across the country,
  • 1:43 - 1:45
    as weeks and months go by.
  • 1:46 - 1:48
    And it's important to visualize this data,
  • 1:48 - 1:50
    because none of you
    are, probably, sitting here thinking,
  • 1:50 - 1:52
    "Yeah, that looks right."
  • 1:52 - 1:54
    (Laughter)
  • 1:54 - 1:55
    "That's working like it should, right?"
  • 1:55 - 1:57
    Because, no --
  • 1:57 - 1:58
    (Laughter)
  • 1:59 - 2:03
    What the data shows us
    is a highly inefficient system
  • 2:03 - 2:06
    whose inherent brokenness
    I don't think we really would have seen
  • 2:07 - 2:09
    had the sensors not done
    the journalism for us.
  • 2:11 - 2:13
    A second project
    that I'd have to highlight
  • 2:13 - 2:18
    has to do with creating robots
    that dive into sewers
  • 2:18 - 2:20
    and sample wastewater.
  • 2:20 - 2:23
    I know that sewage kind of gets a bad rap,
  • 2:23 - 2:25
    but it's actually kind of awesome,
  • 2:25 - 2:27
    because it can tell us
    an incredible amount
  • 2:27 - 2:29
    about the health of our communities.
  • 2:29 - 2:32
    This technology was spun out
    by a group call Biobot Analytics,
  • 2:32 - 2:35
    who's creating a cutting-edge technology
  • 2:35 - 2:39
    to turn our sewers into modern-day
    health observatories.
  • 2:39 - 2:42
    Their goal is to study opioids
    within the sewage
  • 2:42 - 2:45
    to better understand
    consumption in cities.
  • 2:45 - 2:47
    And this data is key,
  • 2:47 - 2:50
    because it really helps cities understand
    where people are using,
  • 2:50 - 2:52
    how to allocate resources
  • 2:52 - 2:55
    and the effectiveness
    of programming over time.
  • 2:56 - 2:58
    Once again, the technology
    that's built into this machine
  • 2:58 - 3:00
    is pulling back the curtain
  • 3:00 - 3:04
    and showing us something about our cities
    that we never would have seen without it.
  • 3:04 - 3:07
    So it turns out, as we see,
  • 3:07 - 3:09
    that big data is really everywhere --
  • 3:09 - 3:11
    even in your toilet.
  • 3:11 - 3:15
    And so now that we've talked
    about trash and sewage,
  • 3:15 - 3:16
    let's move on ...
  • 3:16 - 3:18
    to food.
  • 3:18 - 3:19
    (Laughter)
  • 3:19 - 3:22
    A year ago, I left MIT
    to pursue a passion in food,
  • 3:22 - 3:24
    and in 2017,
  • 3:24 - 3:27
    started a company with my husband,
    called Family Dinner.
  • 3:27 - 3:31
    The goal of our company
    is to create community around local food
  • 3:31 - 3:33
    and the people who grow it.
  • 3:33 - 3:35
    To make this happen,
    we're using data analytics,
  • 3:35 - 3:38
    automation and technology
  • 3:38 - 3:40
    to build a distributed
    network of local farms
  • 3:40 - 3:43
    and to make improvements
    on the food system.
  • 3:43 - 3:45
    So what we see here
  • 3:45 - 3:48
    is that the broad techniques
    and the mission of what we're trying to do
  • 3:48 - 3:51
    is really not dissimilar
    from the work at the MIT labs.
  • 3:52 - 3:55
    Which brings us to a critical question:
  • 3:55 - 3:59
    Why exactly would someone
    leave a very promising career
  • 3:59 - 4:03
    at one of the top
    urban science labs in the world
  • 4:03 - 4:06
    to drive carrots around
    in her mom's Acura?
  • 4:06 - 4:08
    (Laughter)
  • 4:08 - 4:09
    It's a great car.
  • 4:10 - 4:13
    Because I believe
    that the story of local food
  • 4:13 - 4:17
    needs to be understood, told and elevated,
  • 4:17 - 4:18
    and in many ways,
  • 4:18 - 4:22
    I think that nerds like us
    are really uniquely poised to tell it.
  • 4:22 - 4:24
    So where are we starting?
  • 4:24 - 4:25
    What's our starting point?
  • 4:26 - 4:30
    The current national food system
    is optimized for one thing only,
  • 4:30 - 4:33
    and that's corporate profit, right?
  • 4:33 - 4:34
    And think about that.
  • 4:34 - 4:37
    The most compelling reason
    for food companies to exist
  • 4:37 - 4:39
    is not to feed hungry people,
  • 4:39 - 4:41
    it's not to make delicious-tasting food.
  • 4:42 - 4:43
    It's profit.
  • 4:44 - 4:47
    And that has detrimental effects
    at all levels of our food system.
  • 4:48 - 4:51
    The antibiotics and pesticides
    that are being put into our food
  • 4:51 - 4:53
    are detrimental to our health.
  • 4:53 - 4:56
    Price pressure is forcing
    small farms out of business.
  • 4:56 - 4:59
    In fact, a lot of the things
    that you think about farms
  • 4:59 - 5:00
    no longer exist.
  • 5:00 - 5:03
    Farms don't look like farms,
    they look like factories.
  • 5:03 - 5:04
    And at the end of the day,
  • 5:04 - 5:07
    the quality of the food
    that we're eating really suffers, too.
  • 5:08 - 5:12
    A factory-farm tomato
    may kind of look like a regular tomato:
  • 5:12 - 5:14
    bright red exterior ...
  • 5:14 - 5:15
    But when you bite into it,
  • 5:15 - 5:18
    the taste and texture
    just leave you wanting.
  • 5:19 - 5:22
    And we know that perhaps
    the greatest tragedy in all of this
  • 5:22 - 5:26
    is that between 30 and 40 percent
    of this food is just wasted ...
  • 5:27 - 5:28
    thrown away.
  • 5:28 - 5:31
    That is 1.6 billion tons.
  • 5:31 - 5:33
    I can't even wrap my head
    around that number.
  • 5:33 - 5:36
    1.6 billion tons.
  • 5:36 - 5:39
    That's 1.2 trillion dollars a year
  • 5:39 - 5:41
    in wasted food.
  • 5:42 - 5:44
    That is the cost of on-demand eating
  • 5:44 - 5:45
    and convenience
  • 5:45 - 5:47
    and the broken food system.
  • 5:47 - 5:49
    Now, where's this waste happening?
  • 5:49 - 5:51
    Where's all this waste coming from?
  • 5:51 - 5:53
    Well, we know that it happens in the field
  • 5:53 - 5:55
    when you don't pick
    the sexiest-looking potatoes.
  • 5:55 - 5:58
    We know that it happens in transit,
  • 5:58 - 5:59
    at the warehouses,
  • 5:59 - 6:01
    in the grocery stores.
  • 6:01 - 6:03
    And finally, on our own kitchen counters,
  • 6:03 - 6:08
    when we determine that that spotty,
    brown banana no longer looks so yummy.
  • 6:08 - 6:10
    All that waste, all that effort.
  • 6:11 - 6:12
    Food is planted,
  • 6:12 - 6:15
    grown, harvested, shipped,
  • 6:15 - 6:17
    and then just thrown away.
  • 6:19 - 6:21
    We think that there has to be
    a better way.
  • 6:22 - 6:24
    And so how to we improve upon this?
  • 6:24 - 6:26
    How do we make a better system?
  • 6:27 - 6:28
    In order to do this,
  • 6:28 - 6:30
    we understand that we need
    to eliminate waste
  • 6:30 - 6:32
    in the food supply chain.
  • 6:33 - 6:35
    We need to get data
    in the hands of farmers,
  • 6:35 - 6:37
    so that they can make better predictions.
  • 6:37 - 6:40
    So they can, you know,
    kind of compete with the big guy.
  • 6:40 - 6:41
    And then finally,
  • 6:41 - 6:43
    we need to prize, as a company,
  • 6:43 - 6:46
    quality and taste above everything,
  • 6:46 - 6:49
    so that people really value
    the delicious food on their plates.
  • 6:50 - 6:53
    This, we believe, is the better system.
  • 6:53 - 6:55
    This is the better way.
  • 6:55 - 6:58
    And the path to that better way
    is paved with data.
  • 6:59 - 7:03
    To highlight all of this,
    I want to tell the tale of two tomatoes.
  • 7:04 - 7:06
    We'll talk about them one by one.
  • 7:06 - 7:09
    A tomato in itself contains
    a beautiful snapshot
  • 7:09 - 7:13
    of everything you might want to know
    about the life cycle of that fruit:
  • 7:13 - 7:15
    where it was grown,
    what it was treated with,
  • 7:15 - 7:17
    nutritional value,
  • 7:17 - 7:18
    miles traveled to get to your plate,
  • 7:18 - 7:21
    CO2 emissions along the way.
  • 7:21 - 7:22
    All of that information,
  • 7:22 - 7:25
    all those little chapters
    in one small fruit.
  • 7:25 - 7:26
    It's very exciting.
  • 7:27 - 7:29
    This is tomato number one.
  • 7:29 - 7:33
    This is the guy that you'll find
    in sub shops, supermarkets
  • 7:33 - 7:35
    and fast-food joints around the world.
  • 7:35 - 7:38
    It's got a really long
    and complicated backstory.
  • 7:39 - 7:43
    It's been treated with a cocktail
    of, like, a dozen pesticides
  • 7:43 - 7:48
    and it has traveled at least
    1,600 miles to get to your house.
  • 7:48 - 7:50
    And the image here is green,
  • 7:50 - 7:54
    because these tomatoes are picked
    when green and hard as a rock,
  • 7:54 - 7:56
    and then they are gassed along the way
  • 7:56 - 7:58
    so that when they arrive
    at the destination,
  • 7:58 - 8:01
    they look bright and shiny
    and red and ripe.
  • 8:02 - 8:04
    All of that effort,
  • 8:04 - 8:08
    all of that agricultural
    innovation and technology
  • 8:08 - 8:12
    to create a product
    that is entirely without taste.
  • 8:12 - 8:15
    And onto the second tomato in our tale.
  • 8:15 - 8:17
    This is the local version of the fruit.
  • 8:17 - 8:19
    Its story is much, much shorter.
  • 8:20 - 8:24
    This guy was grown by Luke Mahoney
    and his family at Brookford Farm
  • 8:24 - 8:25
    in Canterbury, New Hampshire.
  • 8:26 - 8:28
    It's got a pretty boring backstory.
  • 8:29 - 8:30
    It was planted,
  • 8:30 - 8:32
    sat in the sun
  • 8:32 - 8:33
    and then it was picked.
  • 8:33 - 8:34
    (Laughter)
  • 8:34 - 8:36
    That's it.
  • 8:36 - 8:37
    Like, you wouldn't want to --
  • 8:37 - 8:39
    yeah, there's not much more to that.
  • 8:39 - 8:43
    And it traveled maybe 70 miles
    to get your plate.
  • 8:43 - 8:44
    But the difference is dramatic.
  • 8:45 - 8:48
    I want you think about the last time
    you ate a fresh, summer tomato.
  • 8:48 - 8:50
    And I know we're all
    covered in our jackets,
  • 8:50 - 8:51
    but think about it.
  • 8:51 - 8:54
    The last time you ate
    a tomato from the garden.
  • 8:54 - 8:55
    It's warm from the sun,
  • 8:55 - 8:57
    it's richly red,
  • 8:57 - 8:58
    maybe it smells like dirt.
  • 8:58 - 9:02
    There's something nostalgic
    and almost magical in that experience.
  • 9:02 - 9:05
    The taste and the flavor are incomparable.
  • 9:06 - 9:09
    And we really don't have to travel
    super far to get it.
  • 9:11 - 9:13
    Now this story extends up the food chain,
  • 9:13 - 9:16
    from the fruits and the vegetables
    that are on our plate
  • 9:16 - 9:19
    to the animals and the animal
    products that we consume.
  • 9:20 - 9:21
    What goes into raising them,
  • 9:21 - 9:25
    and more importantly,
    what doesn't go into raising them,
  • 9:25 - 9:27
    is critically important.
  • 9:28 - 9:30
    Luke and his family have 60 cows.
  • 9:31 - 9:32
    They use traditional methods.
  • 9:32 - 9:34
    They do it the old way:
  • 9:34 - 9:35
    pasture-raised,
  • 9:35 - 9:38
    no hormones, no antibiotics,
  • 9:38 - 9:39
    hay for days.
  • 9:40 - 9:44
    And what they're doing here
    is just treating cows like they're cows,
  • 9:44 - 9:46
    not like they're in a science experiment.
  • 9:46 - 9:49
    He's raising animals the way
    that his grandfather
  • 9:49 - 9:51
    and his grandfather would have.
  • 9:51 - 9:53
    And at the end, it's just better.
  • 9:53 - 9:54
    It's better for the animals;
  • 9:54 - 9:56
    it's better for the environment.
  • 9:56 - 9:58
    Luke is not optimizing
    for profit or price,
  • 9:58 - 10:00
    but for taste and for humanity.
  • 10:01 - 10:05
    And what you're thinking is,
    "There's already a solution to this.
  • 10:05 - 10:06
    It's the farmer's markets."
  • 10:06 - 10:08
    The ones that many of you visit
  • 10:08 - 10:10
    and the ones that I really enjoy.
  • 10:10 - 10:14
    They are a wonderful, but,
    in many ways, suboptimal solution.
  • 10:14 - 10:17
    For us as the consumers,
    it's kind of great, right?
  • 10:17 - 10:18
    You go,
  • 10:18 - 10:20
    there's this beautiful bounty of food,
  • 10:20 - 10:23
    you get the warm and fuzzies
    for supporting a local farm
  • 10:23 - 10:28
    and you get the experience of trying
    something new and trying diverse products.
  • 10:28 - 10:30
    And inevitably, there's some guy
    playing the ukulele
  • 10:30 - 10:31
    somewhere in the background.
  • 10:31 - 10:32
    (Laughter)
  • 10:34 - 10:37
    But for the farmers,
    this presents a lot of risk, right?
  • 10:37 - 10:38
    You wake up at four.
  • 10:38 - 10:40
    You pack your truck, you hire a team,
  • 10:40 - 10:42
    you get to your stall,
  • 10:42 - 10:44
    but you have no guarantees
  • 10:44 - 10:46
    that you're going to move
    your product that day.
  • 10:46 - 10:48
    There's too many variables in New England.
  • 10:48 - 10:50
    For example, the weather,
  • 10:50 - 10:53
    which is just, like,
    a little bit unpredictable here.
  • 10:54 - 10:56
    The weather is one of the many X factors
  • 10:56 - 11:00
    that determine whether or not
    a market will be worth it for the farmers.
  • 11:01 - 11:03
    Every time, they roll the dice.
  • 11:04 - 11:06
    And there's another option.
  • 11:06 - 11:08
    Here, we're talking about CSAs:
  • 11:08 - 11:10
    community-supported agriculture.
  • 11:10 - 11:12
    In this model, customers pay up front,
  • 11:13 - 11:15
    bearing the financial risk for the farms.
  • 11:15 - 11:16
    Farmers grow what they can
  • 11:16 - 11:19
    and the customers enjoy that bounty.
  • 11:19 - 11:21
    This also has a couple issues.
  • 11:21 - 11:22
    It's great for the farmer,
  • 11:22 - 11:25
    because they're ensuring
    that they'll sell what they buy,
  • 11:25 - 11:26
    but for us,
  • 11:26 - 11:28
    we still have to go
    and pick up that share,
  • 11:28 - 11:32
    and we know that a lot of farms
    can't grow a huge diversity of products,
  • 11:32 - 11:35
    so sometimes, you're stuck with a mountain
    of any one particular thing.
  • 11:36 - 11:38
    Maybe this has happened to some of you.
  • 11:38 - 11:42
    And what do you do with 25 pounds
    of rutabaga in the dead of winter?
  • 11:42 - 11:44
    I still don't know.
  • 11:45 - 11:47
    So back to the question.
  • 11:47 - 11:49
    How do we fix this?
  • 11:49 - 11:51
    What we're hoping to do
    and what we're hoping to build
  • 11:51 - 11:53
    is just a better way to CSA.
  • 11:54 - 11:59
    And there are three core innovations
    that make this thing hum.
  • 11:59 - 12:01
    The first of which
  • 12:01 - 12:04
    is a subscription-based
    e-commerce platform,
  • 12:04 - 12:06
    which helps us create
    a consistent demand for our farmers
  • 12:06 - 12:08
    throughout the year.
  • 12:08 - 12:10
    The subscription part here is key.
  • 12:10 - 12:12
    Orders process weekly,
  • 12:12 - 12:14
    customers opt out instead of opt in --
  • 12:14 - 12:17
    that means we've got kind of the same
    number of orders week to week.
  • 12:18 - 12:22
    Second, this means
    that if farmers can sell online,
  • 12:22 - 12:25
    they're no longer limited to the geography
    directly around their farm
  • 12:25 - 12:28
    or to the number of markets
    that they can sell.
  • 12:28 - 12:30
    We've blown the doors
    off of that for them.
  • 12:31 - 12:33
    Second: demand forecasting.
  • 12:33 - 12:36
    We're using analytics to allow
    ourselves to look into the future
  • 12:36 - 12:37
    and forecast demand.
  • 12:37 - 12:41
    This lets farmers know
    how much to harvest in the near-term,
  • 12:41 - 12:43
    but also what to plant going forward.
  • 12:44 - 12:46
    If 200 orders process on Monday,
  • 12:46 - 12:48
    then we buy to meet that exact demand.
  • 12:49 - 12:50
    200 heads of broccoli,
  • 12:50 - 12:52
    200 pieces of salmon,
    et cetera, et cetera.
  • 12:53 - 12:54
    This automation in ordering
  • 12:54 - 12:59
    means that here, we are eliminating
    the waste in the food system
  • 12:59 - 13:01
    that bothers us all so much,
  • 13:01 - 13:05
    because we are ensuring that the supply
    meets the exact demand.
  • 13:06 - 13:08
    It also allows us to look
    into the future with the farmers
  • 13:08 - 13:10
    and do crop planning.
  • 13:10 - 13:12
    So if we can say to them,
    in June of this year,
  • 13:12 - 13:14
    "I'm going to need 400 pounds of asparagus
  • 13:15 - 13:17
    and 500 pounds of berries every week,"
  • 13:17 - 13:19
    they can plant that accordingly,
  • 13:19 - 13:21
    knowing with confidence
    that they will sell
  • 13:21 - 13:23
    everything that they have grown.
  • 13:23 - 13:25
    And finally, we use
    a route-optimization software
  • 13:25 - 13:28
    to help us solve the problem
    of the traveling salesman.
  • 13:28 - 13:32
    We get a fleet of workers to come in
    and help us go the last mile,
  • 13:32 - 13:34
    bringing all these goodies
    directly to your door.
  • 13:34 - 13:36
    Without data science
  • 13:36 - 13:38
    and a super-capable, wonderful team,
  • 13:38 - 13:40
    none of this would be possible.
  • 13:41 - 13:42
    So maybe you've seen
  • 13:42 - 13:46
    that we've got some sort of fiery,
    passionate core beliefs.
  • 13:46 - 13:48
    Yes, we're trying to build
    a sustainable business,
  • 13:49 - 13:51
    but our eye is not only on profit,
  • 13:51 - 13:53
    it's on building a better,
    holistic system of food.
  • 13:54 - 13:56
    And here's what we value.
  • 13:56 - 13:58
    People first.
  • 13:58 - 14:00
    We're trying to build
    community around food,
  • 14:00 - 14:02
    the people who love it
    and the people who grow it.
  • 14:02 - 14:05
    We built this company
    to support small farms.
  • 14:06 - 14:07
    Zero waste.
  • 14:07 - 14:10
    We all hate wasting food,
    it just feels wrong --
  • 14:10 - 14:11
    even that weirdo banana
  • 14:11 - 14:14
    that's been sitting around
    on your coffee table for too long.
  • 14:14 - 14:16
    And lastly, taste.
  • 14:16 - 14:18
    If it doesn't taste good,
  • 14:18 - 14:21
    if it's not that, like,
    perfect summer tomato,
  • 14:21 - 14:22
    why bother?
  • 14:23 - 14:25
    So what we've done
    is worked with all these local farms
  • 14:25 - 14:27
    to bring their things in
  • 14:27 - 14:29
    and then to drop them
    directly at your door,
  • 14:29 - 14:31
    so that we're connecting you right to them
  • 14:31 - 14:34
    and making, again, a more holistic system.
  • 14:34 - 14:36
    This is our vision of the future.
  • 14:36 - 14:40
    To extend this model beyond Boston,
    beyond New England
  • 14:40 - 14:42
    and across the country.
  • 14:42 - 14:46
    To create a nationwide
    distributed network of local farms
  • 14:46 - 14:48
    and to connect all these farmers
  • 14:48 - 14:50
    with the people like you
    who will love their food.
  • 14:52 - 14:53
    We believe, at the end of the day,
  • 14:53 - 14:58
    that really insisting on eating local food
    is a revolutionary act.
  • 14:58 - 15:00
    And we invite you to join us.
  • 15:00 - 15:02
    And who knows?
  • 15:02 - 15:05
    You may even make
    some friends along the way.
  • 15:06 - 15:07
    Thank you very much.
  • 15:07 - 15:08
    (Applause)
Title:
Big data, small farms and a tale of two tomatoes
Speaker:
Erin Baumgartner
Description:

The path to better food is paved with data, says entrepreneur Erin Baumgartner. Drawing from her experience running a farm-to-table business, she outlines her plan to help create a healthier, zero-waste food system that values the quality and taste of small, local farm harvests over factory-farmed produce.

more » « less
Video Language:
English
Team:
closed TED
Project:
TEDTalks
Duration:
15:21
  • I think she meant (5:53):

    when you [only] pick
    the sexiest-looking potatoes.

    or

    when you don't pick
    [the least sexy-looking] potatoes.

  • I think she meant (5:53):

    when you [only] pick
    the sexiest-looking potatoes.

    or

    when you don't pick
    [the least sexy-looking] potatoes.

English subtitles

Revisions Compare revisions