Big Ideas Only

About Big Ideas Only

In Big Ideas Only, we explore all things science. Why? Because science is probably the most fascinating thing on the planet – and off the planet! In the podcast, we talk to leading scientists and experts, and try to grasp some of the deep knowledge they work with every day. This podcast is produced by Montanus (https://montanus.co).

Publisher

Montanus

Category

education · science

Language

en

Explicit

No

First episode

25 Apr 2022

Latest episode

2 Mar 2026

Latest episodes

23 episodes in the feed.

1. 

   2 Mar 2026

   Seagrass | Practice: Saving an ecosystem most people have never heard of

   In this episode of Big Ideas Only, Mikkel Svold reconnects with Dr. Benjamin Jones, Chief Conservation Officer and co-founder of Project Seagrass, to explore what happens when seagrass theory meets real-world conservation. Moving beyond the science of carbon capture and marine ecology, this conversation digs into the practical challenges of protecting an ecosystem that most people have never thought about. Benjamin shares stories from fishing communities in Indonesia and Florida, explains why government departments struggle to coordinate land and sea management, and describes how citizen science and political engagement have become surprisingly effective tools. The discussion reveals that saving seagrass often has little to do with planting seagrass — and everything to do with what happens on shore. In this episode, you'll learn about: Why 13.5 million people living below the poverty line depend directly on seagrass for their daily food How seagrass meadows store carbon for up to 200,000 years — and release it rapidly when destroyed The governance gap between marine and terrestrial management that makes coastal protection so difficult Why restoring seagrass sometimes means planting fruit trees along riverbanks instead How Wales created the world's first National Seagrass Action Plan through cross-party dialogue What everyday actions (diet, driving, citizen science) actually connect to seagrass health Episode Content 00:54 Project Seagrass milestones: from undergraduate idea to global organization 02:28 Why seagrass was called the "ugly duckling" of marine conservation 04:36 Bajo communities in Indonesia: fishing families who live on seagrass meadows 06:58 Local knowledge: how coastal communities track seagrass changes over generations 11:34 The indirect dependencies most people don't realize (cod, pollock, Mediterranean fisheries) 15:04 Carbon time bomb: the 200,000-year-old seagrass meadow in Ibiza 16:18 Restoration approaches: why you can't just plant seagrass everywhere 17:48 Fruit trees as seagrass conservation: solving sedimentation through riparian planting 20:32 The governance problem: marine and terrestrial agencies that don't talk to each other 23:02 Citizen science and the Seagrass Spotter app 31:19 Political progress: Wales' National Seagrass Action Plan 33:17 Why nature will recover faster than humans can replant — if given the right conditions This podcast is produced by Montanus (https://montanus.co/).

2. 

   2 Mar 2026

   Seagrass | Theory: The underwater ecosystem you've never thought about (but probably should)

   In this episode of Big Ideas Only, host Mikkel Svold sits down with Kasper Elgetti Brodersen, Associate Professor at Roskilde University, to explore the science behind one of our most overlooked coastal ecosystems: seagrass meadows. What looks like an annoyance when it brushes against your legs while swimming turns out to be a biological powerhouse — nursery grounds for fish, carbon storage systems, and water quality filters all in one. Kasper explains how seagrass interacts with sediments and bacteria, why nutrient runoff from farmland is suffocating Danish fjords, and the surprising discovery that stressed seagrass can flip from climate helper to greenhouse gas emitter. The conversation covers what makes restoration so difficult, why seeds might be better than transplants, and what still needs solving before we can successfully garden the sea. In this episode, you'll learn about: Why seagrass provides four times the ecosystem services of coral reefs (measured in economic value) How seagrass creates its own oxygen supply to survive in toxic, oxygen-free sediments The mechanism that turns nutrient pollution into plant-killing hydrogen sulfide Why stressed seagrass meadows can start producing methane and nitrous oxide instead of capturing carbon What makes restoration in Danish fjords so challenging — and why seeds might work better than transplants The bacterial partnerships happening underground that help seagrass access nitrogen Episode Content 01:13 Why seagrass is a big idea 03:11 Global distribution and the 70% loss in Danish waters over the last century 05:07 The main stressor: eutrophication from agricultural nutrient runoff 07:15 How seagrass survives in anoxic sediment by pumping oxygen through internal channels 08:56 Epiphytes explained 10:17 What healthy conditions look like 15:09 The eureka moment: discovering seagrass provides more ecosystem value than coral reefs 19:26 Below-ground interactions: how oxygen release acidifies sediment and mobilizes nutrients 20:22 The greenhouse gas twist 30:32 Why restoration is still so hard 41:04 What's happening in the rhizosphere This podcast is produced by Montanus (https://montanus.co/).

3. 

   17 Nov 2025

   Computer Vision | Theory: How Computers See in the Real World

   In this episode of Big Ideas Only, host Mikkel Svold takes a theoretical deep dive into how computers “see” with Andreas Møgelmose (Associate Professor of AI, Aalborg University; Visual Analysis & Perception Lab). We unpack the neural-network ideas behind modern vision, why 2012 was a turning point, how convolutional networks work, the difference between training, fine-tuning and adding context, plus explainability, bias traps, multimodality, and what still needs solving. In this episode, you’ll learn about: How a 2012 vision breakthrough reshaped speech and language research2. Neural networks explained simply — how they learn patterns from data 3. CNNs: how computers spot shapes and textures in images 4. Training, fine-tuning, and adding context to make models smarter 5. From hand-crafted features to fully data-driven learning 6. Explainability: the “ruler in skin-cancer photos” bias trap and what it teaches us 7. Multimodal systems: models combining text, images, and tools 8. Depth sensing with stereo, lidar, radar, and time-of-flight — and when 3D is essential 9. Privacy and governance: why real risk lies in implementation, not vision itself 10. Open challenges: fine-grained recognition, explainability, and machine unlearning 11. The pace of progress: steady research with headline-making leaps Episode Content 01:09 How computer vision differs from other AI fields 01:16 The 2012 breakthrough: neural networks in vision that spread to speech and text 04:05 Neural networks 101: neurons, weights, and simple math scaled up to complex decisions 07:06 Training at scale: millions of images, pretraining, and fine-tuning for specific tasks 10:39 Fine-tuning vs. adding context in large language models; backpropagation explained 16:52 Layered learning: from edges to shapes, faces, and full objects 18:22 Before deep learning: feature engineering and why it hit its limits 20:44 How it’s built: data collection, architecture design, training loops, and learning plateaus 22:54 Bias pitfalls: the “ruler in skin-cancer photos” example and why explainability matters 25:23 Regulation and trust: high-risk uses and the demand for transparency 26:13 Connecting vision to action: from black-box outputs to robots with “vision in the loop” 27:41 Ensemble systems: language models coordinating other models (e.g., text-to-image) 29:03 True multimodality: training models jointly on text and images 30:17 AGI reflections: embodiment, experience, and the limits of data 32:44 Human vision vs. computer vision: depth of field, aperture, and why machines see everything in focus 34:40 Is progress slowing or steady? Research milestones versus quiet, continuous work 36:43 Public perception: many versions, but most still see “just ChatGPT” 37:41 Why the research pace feels natural — more people means faster progress This podcast is produced by Montanus (https://montanus.co/).

Who has been a guest on Big Ideas Only

Names identified in recent episode analyses. Showing up to five guests.

• Søren Bang Korsholm
• Thomas Schmidt
• Tomas Utaravičius
• Filip Aničić
• Rasmus Risager Lindegaard

Reach and audience

Public platform figures. Ratings count people who left a rating, not total listeners.

YouTube views

3,794

Score snapshot 15 Sept 2025

Podcast Authority Score: 33 / 100

A composite of feed quality, social presence, YouTube performance and engagement. Read the methodology.

Quality

39

Social presence

0

YouTube

68

Engagement

0

Contact Big Ideas Only

Guest appearances

Books guests

Based on episode analysis; this does not confirm that the show is currently accepting guests.