エピソード

  • How Bloomberg's Data Scientists use Satellite Images for Reporting: Krishna Karra - MBM78
    2024/12/16

    Krishna Karra is a data scientist & report for Bloomberg, having used machine learning & satellite images for reporting. Recent stories from him & his team include mapping refugee camps in Rafah & exposing illegal ship oil transfers in the middle of the Ocean.

    Sponsor: Beemaps by Hivemapper

    Get access to high quality, fresh map data at https://beemaps.com/minds
    Use promo code MINDS to get 50% off your API credits through Dec. 31 2024

    About Krishna
    • Twitter
    • LinkedIn
    Shownotes

    Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

    • Bloomberg: The Clandestine Oil Shipping Hub Funneling Iranian Crude to China
    • Bloomberg: A Detailed Map Shows How Airstrikes and Refugees Reshaped Rafah
    • How Radar Satellites See through Clouds (Synthetic Aperture Radar Explained)
    • National Land Cover Database (NLCD)
    • What Ukraine Has Lost
    • Graves in Suda by Joe Morrison
    • Jean Martin Bauer on Minds Behind Maps
    • Books & Podcast:
      • Overstory by Richard Powers (Affiliate Link)
      • Ezra Klein Show
    Timestamps

    (00:00) - Intro

    (00:34) - Sponsor: Beemaps

    (01:51) - Krishna describes himself

    (03:27) - Example stories: Illegal Oil transfers

    (05:29) - Stories are the goal

    (07:07) - Why publish the data set?

    (12:24) - How Journalism has and hasn't changed

    (14:04) - How data changes a story

    (18:23) - Putting the datasets together

    (20:37) - Conveying trust

    (24:07) - Showing the limitations of the data

    (26:11) - Why is journalism important for satellite data?

    (30:14) - News room process

    (32:57) - Building custom tools

    (38:19) - Timeline of a news story

    (39:47) - What Krishna has learned as a data scientist in a news room

    (40:49) - Stories that have stuck out

    (42:57) - Different ways of showing the data

    (44:19) - Krishna's wishlist

    (51:12) - Book & podcast recommendation

    (53:16) - Paid podcasts & media

    (55:19) - Support the podcast on Patreon

    • Support the podcast on Patreon
    • My Twitter
    • Podcast Twitter
    • Read Previous Issues of the Newsletter
    • Edited by Peter Xiong
    • Find more of his work
    続きを読む 一部表示
    57 分
  • How Ex-Vox Video Producer Phil Edwards thinks about Maps to tell stories - MBM77
    2024/11/23
    Phil Edwards is a video producer who worked at Vox for nearly 10 years, and now runs his own Youtube channel exploring the history of businesses, and lately has been using more and more maps. We go over one of his latest videos, “The Secret Economics of Google Street View” as a case study of how Phil thinks about maps to tell stories. We also talk about journalism on Youtube, and the business behind running a Youtube channel today.Sponsor: Beemaps by HivemapperGet access to high quality, fresh map data at https://beemaps.com/mindsUse promo code MINDS to get 50% off your API credits through Dec. 31 2024About PhilTwitterPhil's BlueskyPhil’s YoutubeShownotesNote: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.Phil’s trivia siteGeoGuessrPhil’s video about Google Street ViewBook & Podcast recommendations:3 Scientists & Their Gods by Robert Wright (Affiliate Link)The Evolution of God by Robert Wright (Affiliate Link)On the Edge by Nate Silver (Affiliate Link)Freakonomics podcastAcquired PodcastMy conversation with Ashlee VanceWild Wild Space documentaryNeoHoogTimestamps(00:00) - Intro(00:52) - Sponsor: Beemaps(02:08) - Who is Phil Edwards?(03:13) - What does a Video Producer do?(04:29) - Chosing topics & stories(06:38) - Maps in video production(10:14) - Bringing a different element to maps stories(12:15) - Explaining Complicated Things(15:49) - Case Study: Google Street View Video(20:07) - Geoguessr(23:03) - Story & Journalism on Youtube(27:25) - Stories that Phil wants to work on(30:54) - Importance of visuals(34:58) - Learning Curve in Mapping & Animation(40:26) - Balancing Scientific Rigour and Story(49:53) - The Business of Youtube(54:09) - Choosing to scale or not(59:14) - Creating "content"(01:01:56) - Authenticity(01:05:00) - Valuing High Quality Journalism(01:10:18) - Succeeding on Patreon(01:13:46) - Creators that Phil admires(01:16:56) - Books & podcasts Recommendations(01:28:54) - Reporting On Vs Working In a field(01:31:40) - Where Phil finds inspiration(01:35:14) - Support the podcast on PatreonSupport the podcast on PatreonMy TwitterMy BlueskyRead Previous Issues of the NewsletterEdited by Peter XiongFind more of his work
    続きを読む 一部表示
    1 時間 36 分
  • What Hyperspectral constellations have to offer: Pixxel’s example - Awais Ahmed #MBM76
    2024/11/01

    Awais Ahmed is the co-founder & CEO of Pixxel, a company building a constellation of hyperspectral imaging satellites. Unlike “traditional” cameras, these satellites can see across hundreds of bands, opening up a lot more applications. We talk about the engineering -and funding- required to pull this off and how Awais manages a company between India (where Awais is from) and the US. But that’s just the 1st part of the interview. Then we talk about his vision for the company, which goes way, way beyond sending imaging satellites.

    Sponsor: OpenCage

    Use OpenCage for your geocoding needs with their API
    Geomob

    About Awais
    • Twitter
    • LinkedIn
    Shownotes
    • Awais’s personnal website
    • Pixxel’s 3 phase vision
    • Maxar HD machine learning upscaling
    • Book & Podcast Recommendation
      • The Beginning of Infinity by David Deutsch (Affiliate Link)
      • Profiles of the Future by Arthur C. Clarke (only found it in ebook here, Affiliate Link)
      • Hitchhiker’s guide to the Galaxy by Douglas Adams (Affiliate Link)
    Timestamps

    (00:00) - Introduction

    (01:09) - Sponsor: OpenCage

    (02:34) - Awais describes himself

    (03:46) - Pixxel

    (05:07) - What is hyperspectral?

    (10:36) - Spacial, Temporal & Spectral Resolution tradeoffs

    (18:01) - Hardest part of building satellites

    (22:58) - The resolution spotlight

    (28:38) - Image Quality Rabbit Hole

    (30:42) - The tricky part of raising money

    (38:52) - Awais has a big, big vision

    (50:42) - Likeliness of Awais's vision within 10 years

    (54:14) - Working between India & USA

    (59:04) - Personnal investing

    (01:01:20) - Importance of Reading

    (01:05:36) - Sci-Fi & History

    (01:08:33) - Book recommendation

    (01:10:43) - Awais in space?

    (01:11:54) - Pushing the boundaries of humanity

    (01:13:14) - Optimism in a cynical world

    (01:19:11) - Support the podcast on Patreon

    • Support the podcast on Patreon
    • My video on an introduction to satellite images
    • Website
    • My Twitter
    • Podcast Twitter
    • Read Previous Issues of the Newsletter
    • Edited by Peter Xiong
    • Find more of his work
    続きを読む 一部表示
    1 時間 21 分
  • The Ex-Uber Data Scientist Who wants to simplify Data Science with Serverless Computing: Sina Kashuk
    2024/10/15

    Sina Kashuk is the co-founder & CEO of Fused, who wants to make iterating & deploying in Python faster with serverless computing. We break down what that actually means, why it matters and what data science workflows could look like over the next few years.

    This also isn’t Sina’s first company, a few years ago he started Unfolded.ai, focused on making visualisations for data scientists faster. The company was acquired by Foursquare in 2021.

    Sponsor: Beemaps by Hivemapper

    Get access to high quality, fresh map data at https://beemaps.com/minds
    Use promo code MINDS to get 50% off your API credits through Dec. 31 2024

    About Sina
    • Twitter
    • LinkedIn
    Shownotes

    Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

    • My blogpost joining the team
    • Uber’s H3 tiling grid
    • Foursquare acquires Unfolded
    • AWS Lambda
    • My conversation with Ib Green
    • Fused.io
    • Book & Podcast recommendation
      • Awaken the Giant Within by Tony Robbins Affiliate Link
      • I’m pretty sure you can find Minds Behind Maps by yourself if you’re here
    Timestamps

    (00:00) - Intro
    (02:38) - Sponsor: Beemaps
    (03:55) - Hacking
    (06:07) - Fused.io
    (07:23) - Why run your algorithm in the cloud?
    (10:06) - Serverless computing
    (12:40) - Optimizing for iteration speed
    (18:52) - Breaking Fused into smaller parts
    (23:27) - "User Defined Functions: UDF"
    (31:08) - How do you make money?
    (31:56) - Why start companies?
    (42:41) - Convincing people to use your tools
    (49:44) - Speed isn't all: Train / Plane analogy
    (54:36) - Going beyond geospatial
    (57:33) - Building a team
    (59:54) - Podcast/book recommendation
    (01:01:11) - Building a Long Term Vision
    (01:06:59) - Support the podcast on Patreon

    • Support the podcast on Patreon
    • My Twitter
    • Podcast Twitter
    • Read Previous Issues of the Newsletter
    • Edited by Peter Xiong
    • Find more of his work
    続きを読む 一部表示
    1 時間 9 分
  • Meet the man trying to build a 20cm 3D map of the world: Andrew Peterson - #MBM74
    2024/09/15

    Andrew Peterson is the Co-Founder & CEO of Array Labs, with a simple mission: Mapping the whole world in 3D, at 20cm in near real time.

    We peel the layers as to what it takes to get there: the engineering that’s required, how to build a constellation to do that, how you fund such a project.

    Sponsor: OpenCage

    Use OpenCage for your geocoding needs with their API
    Geomob

    About Andrew
    • LinkedIn
    • Array Labs
    Shownotes

    Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

    • My 20min video explaining radar satellite images
    • Find USGS 1m LiDAR data across the US
    • Y Combinator
    • My episode with Ashlee Vance
    • My episode with Brian McClendon
    • Albedo
    • Book & Podcast recommendation
      • Spin Selling by Neil Rackham (Affiliate Link)
      • Acquired
    Timestamps

    (00:00) - Intro

    (01:08) - Sponsor: OpenCage

    (02:34) - "Being a Recovering Engineer"

    (03:15) - Mapping the world in 3D

    (09:59) - "Near Real Time"

    (15:46) - Applications will only use what's available, by definition

    (18:15) - Why use radar for 3D images?

    (22:23) - The coolest Space Shuttle mission, period

    (27:19) - Tradeoff between resolution & coverage

    (36:26) - Building cheap radar satellites

    (39:46) - Array Labs's image resolution

    (45:10) - A GPU Analogy

    (50:34) - A story of image processing & computers

    (56:07) - Array Labs today

    (57:57) - Let's talk $$$

    (01:06:38) - Low barrier to entry: Comparing XRay & MRI

    (01:12:09) - Why stop at 10 satellites?

    (01:15:50) - Focus

    (01:19:53) - Max & Andrew's 1st chat during covid

    (01:23:22) - Subscription model for satellite images?

    (01:32:50) - Convincing the rest of the world your idea is worth something

    (01:43:58) - Engineer to Founder

    (01:47:30) - Book & Podcast recommendation

    (01:51:06) - Array Labs's next 4 years?

    (01:53:45) - Support the podcast on Patreon

    • Support the podcast on Patreon
    • My video on an introduction to satellite images
    • Website
    • My Twitter
    • Podcast Twitter
    • Read Previous Issues of the Newsletter
    • Edited by Peter Xiong
    • Find more of his work
    続きを読む 一部表示
    1 時間 55 分
  • Jamie McMichael-Phillips: How We're Planning to Map All our Oceans by 2030 - #MBM73
    2024/09/02

    Jamie McMichael-Phillips is the Director of the Seabed 2030 Project, which aims to map all of the world's oceans, by 2030. For context, in 2024, we’re at 26.1%. This is conversation is about why, how we get to 100% and why it’s important in the first place.

    Sponsor: SatCamp
    SatCamp is a different kind of conference, from October 1st to October 3rd 2024, in Boulder Colorado

    About
    • Bio on Seabed 2030 website
    • LinkedIn
    Shownotes

    Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

    • Seabed 2030 Project (You can check out their interactive map here)
    • GEBCO Grid
    • 2024 Seabed 2030 Progress
    • Point Nemo
    • Book & Podcast Recommendations:
      • The Deepest Map by Laura Trethewey (Amazon Affiliate)
      • Seabed 2030 Podcast
    Timestamps

    (00:00) - Intro
    (01:04) - Sponsor: SatCamp
    (02:55) - Jamie Describes Himself
    (03:53) - State of Ocean mapping in 2024
    (06:19) - Difficulties with mapping the ocean
    (08:22) - Why map the seabed?
    (10:24) - What does mapping the seabed actually mean?
    (15:01) - Comparing Land & Sea mapping
    (18:55) - Seabed 2030 is a policy project
    (20:42) - Incentives to map the oceans
    (24:05) - If we've only mapped ~25%, what does the 75% other look like?
    (27:49) - What are the coarse measurements for the ocean right now?
    (29:31) - How we actually map the seabed
    (33:14) - Patches of unmapped areas of the ocean
    (35:38) - Getting there by 2030
    (38:21) - How much has already been mapped?
    (43:00) - Maps as Human Knowledge
    (45:27) - Jamie's most anticipated, yet unmapped, area
    (48:03) - Public Engagement
    (53:01) - Book/podcast Recommendations
    (55:04) - Support the podcast on Patreon

    • Support the podcast on Patreon
    • My video on an introduction to satellite images
    • Website
    • My Twitter
    • Podcast Twitter
    • Read Previous Issues of the Newsletter
    • Edited by Peter Xiong
    • Find more of his work
    続きを読む 一部表示
    57 分
  • [Bonus] Books, Tech & Life: A Long conversation with Jed Sundwall
    2024/08/31

    Check out Jed’s Techs on Text podcast

    Jed has also been on Minds Behind Maps before. We talked open data, AI, and the role of books for people building things

    続きを読む 一部表示
    2 時間 4 分
  • Jean-Martin Bauer: How the World Food Program tackles Hunger - #MBM72
    2024/08/22

    Jean-Martin Bauer has been working at the World Food Program for over 20years, and the author of the “The New Breadline”. Most recently he was the Country Director for Haiti, in charge of helping make sure the country doesn’t run out of food.

    Sponsor: SatCamp
    SatCamp is a different kind of conference, from October 1st to October 3rd 2024, in Boulder Colorado

    About Jean-Martin
    • LinkedIn
    • Jean-Martin’s book: The New Breadline (Affiliate Link)
    Shownotes

    Note: Links to books are Amazon Affiliate links. I earn a small commission if you buy any of these books.

    • WFP working with Mbala Pinda producers
    • Masters of the Dew by Jacques Roumain (Affiliate Link)
    • Jordan Habinger episode about Haiti’s ongoing situation
    • Book & Podcast recommendation
      • The one-straw Revolution by Masanobu Fukuoka (Affiliate Link)
      • Between the World and Me by Ta-Nehisi Coates (Affiliate Link)
      • FiveThirtyEight podcasts
    Timestamps

    (00:00) - Intro

    (01:15) - Sponsor: SatCamp

    (03:42) - Haiti's past 2 years

    (05:57) - Day to day in a humanitarian crisis

    (08:17) - Jean-Martin's ties to Haiti

    (18:27) - Stats versus Stories: The picture of a starving girl sparking uprise

    (21:30) - The Origins of Hunger

    (27:31) - Impact of Covid on Food Security in the US

    (35:05) - Europe's current food supplies after WWII

    (40:11) - Why write a book?

    (42:56) - Who is your book for?

    (45:22) - Finding local Solutions

    (53:39) - Creating a resilient food supply

    (55:33) - Technology is not the silver bullet

    (01:01:23) - Advice for Young Engineers & Data Scientists

    (01:05:28) - What's next for Jean-Martin

    (01:12:04) - Social Media Outreach

    (01:19:08) - Optimism

    (01:23:49) - Defining Acute Hunger

    (01:25:37) - Book & podcast Recommendation

    (01:31:07) - Support the podcast on Patreon

    • Support the podcast on Patreon
    • My Twitter
    • Podcast Twitter
    • Read Previous Issues of the Newsletter
    • Edited by Peter Xiong
    • Find more of his work
    続きを読む 一部表示
    1 時間 33 分