Podcast
Big Ideas Only
Hosted by Montanus · EN
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.
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.
23episodes
Episodes
Newest firstAll episodes
Seagrass | Practice: Saving an ecosystem most people have never heard of
Mar 200:37:02Tap to summarizeIn 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 foodHow seagrass meadows store carbon for up to 200,000 years — and release it rapidly when destroyedThe governance gap between marine and terrestrial management that makes coastal protection so difficultWhy restoring seagrass sometimes means planting fruit trees along riverbanks insteadHow Wales created the world's first National Seagrass Action Plan through cross-party dialogueWhat everyday actions (diet, driving, citizen science) actually connect to seagrass healthEpisode Content 00:54 Project Seagrass milestones: from undergraduate idea to global organization02:28 Why seagrass was called the "ugly duckling" of marine conservation04:36 Bajo communities in Indonesia: fishing families who live on seagrass meadows06:58 Local knowledge: how coastal communities track seagrass changes over generations11:34 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 everywhere17:48 Fruit trees as seagrass conservation: solving sedimentation through riparian planting20:32 The governance problem: marine and terrestrial agencies that don't talk to each other23:02 Citizen science and the Seagrass Spotter app31:19 Political progress: Wales' National Seagrass Action Plan33:17 Why nature will recover faster than humans can replant — if given the right conditions This podcast is produced by Montanus.
Transcribe →
Seagrass | Theory: The underwater ecosystem you've never thought about (but probably should)
Mar 200:46:26Tap to summarizeIn 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 sedimentsThe mechanism that turns nutrient pollution into plant-killing hydrogen sulfideWhy stressed seagrass meadows can start producing methane and nitrous oxide instead of capturing carbonWhat makes restoration in Danish fjords so challenging — and why seeds might work better than transplantsThe bacterial partnerships happening underground that help seagrass access nitrogenEpisode Content 01:13 Why seagrass is a big idea03:11 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 channels08:56 Epiphytes explained10:17 What healthy conditions look like15:09 The eureka moment: discovering seagrass provides more ecosystem value than coral reefs19:26 Below-ground interactions: how oxygen release acidifies sediment and mobilizes nutrients20:22 The greenhouse gas twist30:32 Why restoration is still so hard41:04 What's happening in the rhizosphereThis podcast is produced by Montanus.
Transcribe →
Computer Vision | Theory: How Computers See in the Real World
Nov 1700:36:03Tap to summarizeIn 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 data3. CNNs: how computers spot shapes and textures in images4. Training, fine-tuning, and adding context to make models smarter5. From hand-crafted features to fully data-driven learning6. Explainability: the “ruler in skin-cancer photos” bias trap and what it teaches us7. Multimodal systems: models combining text, images, and tools8. Depth sensing with stereo, lidar, radar, and time-of-flight — and when 3D is essential9. Privacy and governance: why real risk lies in implementation, not vision itself10. Open challenges: fine-grained recognition, explainability, and machine unlearning11. The pace of progress: steady research with headline-making leapsEpisode Content01:09 How computer vision differs from other AI fields01:16 The 2012 breakthrough: neural networks in vision that spread to speech and text04:05 Neural networks 101: neurons, weights, and simple math scaled up to complex decisions07:06 Training at scale: millions of images, pretraining, and fine-tuning for specific tasks10:39 Fine-tuning vs. adding context in large language models; backpropagation explained16:52 Layered learning: from edges to shapes, faces, and full objects18:22 Before deep learning: feature engineering and why it hit its limits20:44 How it’s built: data collection, architecture design, training loops, and learning plateaus22:54 Bias pitfalls: the “ruler in skin-cancer photos” example and why explainability matters25:23 Regulation and trust: high-risk uses and the demand for transparency26:13 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 images30:17 AGI reflections: embodiment, experience, and the limits of data32:44 Human vision vs. computer vision: depth of field, aperture, and why machines see everything in focus34:40 Is progress slowing or steady? Research milestones versus quiet, continuous work36:43 Public perception: many versions, but most still see “just ChatGPT”37:41 Why the research pace feels natural — more people means faster progressThis podcast is produced by Montanus.
Transcribe →
Computer Vision | Practise: How Computers See in the Real World
Nov 1000:32:28Tap to summarizeIn this episode of Big Ideas Only, host Mikkel Svold explores how computers “see” with Andreas Møgelmose (Associate Professor of AI, Aalborg University; Visual Analysis & Perception Lab). We unpack what computer vision is, where it already works at scale, what’s still hard, and the real-world trade-offs around privacy and surveillance - from self-driving cars and robots to hospital X-rays and trash sorting.In this episode, you’ll learn about:What computer vision really is: turning camera input into understanding and actionWhen vision alone is enough, and when you need lidar, radar or time-of-flight sensorsThe biggest driver: industrial automationHow automated triage of X-rays can cut ER waiting times with a doctor reviewing the final resultWhy the classic “who should the car hit?” dilemma misses how real autonomy works3D understanding with stereo cameras and other depth-sensing methodsWhy sorting messy, mixed real-world waste remains one of the hardest vision challengesHumanoid robots — what already works and what’s still far from realityWhere research is headed: from fine-grained recognition to explainability and machine unlearningOn-device versus cloud processing, and how that choice shapes privacy riskEpisode Content 00:01 Why it matters that computers can “see”02:04 When vision alone is enough — and when it isn’t04:40 Healthcare in practice: automated X-ray checks for faster casts and shorter ER waits05:39 Accuracy, human oversight, and how every case gets double-checked in morning rounds07:20 The trolley-problem myth: how real autonomous systems minimize risk instead of choosing victims12:32 Choosing the right approach: classification versus 3D navigation13:36 Getting depth: stereo vision, lidar, radar, and time-of-flight sensors16:01 Why sorting mixed, messy waste is still one of the hardest vision problems18:03 Humanoid robots: balance, stairs, and why sight is the foundation for movement19:21 Status check: “solved” in some areas, far from it in others20:40 Privacy and ethics: on-device versus cloud processing, and who controls the data27:37 What’s still missing: fine-grained recognition, explainability, and machine unlearning32:28 Current projects: pre-anesthesia screening, color detection in video, and robust segmentation33:32 Outro and teaser for a deeper theoretical dive next episodeThis podcast is produced by Montanus.
Transcribe →
3D Printing | Theory: Going deeper into the Print
Nov 300:38:25Tap to summarizeIn this episode of Big Ideas Only, host Mikkel Svold will dive deeper into the theory and science behind additive manufacturing or 3D printing. Mikkel is joined again by Kristoffer Ryelund Nielsen (former Head of Engineering at the Danish Technological Institute) and Karl Frederik Fischer (PhD, Materials Science) from the Danish Technological Institute.We will unpack how layer-by-layer manufacturing really works, why powder-bed fusion delivers near-finished parts, how patent expiries reshape the market, and where materials science is pushing the limits from multi-material prints to meta-stable alloys you can’t make any other way.In this episode, you’ll learn about:Additive vs. subtractive manufacturing, and why “layers” matter.Powder bed fusion with lasers: tiny layers, fine features, and strong parts.What materials get printed today (PA12, 316L, Ti-6Al-4V) and why.How patent expiries drove prices down and access up.Multi-material printing for better cooling, cost and performance.Topology optimization and why design freedom + simulation = lighter parts.Printing in extreme places (ISS, Moon/Mars) and why logistics drive adoption.The realistic future: more availability, faster machines, and targeted high-value parts.Episode Content01:39 The basics with additive manufacturing 03:04 What is powder bed fusions?10:30 The printing range today 14:24 Why additive manufacturing is great for weight and thermal/flow 26:38 First metal prints in space27:40 Bioprinting in micro-gravity28:24 Next 5 years with 3D printing35:08 Start with the problem, not the material list35:59 Why patent cycles reshape the market This podcast is produced by Montanus.
Transcribe →
3D Printing | Practice: From Hobby Tech to Industrial Workhorse
Oct 2700:32:08Tap to summarize3D printing isn’t just for fragile prototypes or weekend gadgets anymore.In this episode of Big Ideas Only, host Mikkel Svold visits the Center for Industrial 3D Printing at the Danish Technological Institute (DTI) to explore how additive manufacturing is used in real production today.The Guests of this episode Kristoffer Ryelund Nielsen (previously Head of Engineering) and Karl Frederik Fischer (PhD, Materials Science) will walk us through the machines, parts and business cases that make 3D printing a serious tool for industry.In this episode, you’ll learn about:1. Why “additive manufacturing” is more than prototyping and where it shines in production.2. Powder-based processes for plastics and metals3. How the industries are adopting 3D printing today4. The Concrete advantages in printing 3D5. Real printing examples, such as rocket components.6. Certifications and standards for medical and food-grade parts7. How does the future look like with 3D PrintingEpisode content00:04 3D printing beyond the Wish-printer stereotype01:58 “3D printing” vs “additive manufacturing” and why the term matters02:45 From prototyping to full-scale production parts06:37 When printing wins: faster lead times and optimized designs 16:57 The biggest opportunities haven't yet been discovered 18:02 Space example: consolidated rocket engines with fewer parts and better cooling 25:38 Enabling designs that were previously impossible 29:30 The future: mass customization and digital inventories This podcast is produced by Montanus.
Transcribe →
Dynamic Power-to-X: Turning Surplus Wind & Solar into Ammonia.
Oct 2001:02:17Tap to summarizeWhat happens when wind and solar deliver more power than the grid can handle and batteries aren’t the answer?In this episode of Big Ideas Only, host Mikkel Svold sits down with Pat Han, Technical Director at Skovgaard Energy, the company behind what is called the world’s first dynamic Power-to-X (PtX) ammonia plant.Pat explains how “dynamic” PtX rides the ups and downs of wind and solar, turning excess electricity into ammonia. The ammonia process can start and stop quickly, that’s why ammonia is a strong first “X”, and how the sector coupling can turn rural areas into thriving energy hubs.In this episode, you’ll learn about:1. What “dynamic” PtX means and why flexibility is the missing piece for high-renewables grids.2. Why hydrogen-to-ammonia enables storage and transport.3. How the process works from water to hydrogen plus nitrogen to ammonia.4. How PtX is a flexible consumer that balances variability and prevents curtailment.5. Why market design, ESG, and value-chain planning matter more than tech.6. The social benefits with a PtX plant, such as jobs, industrial neighbors and revitalizing rural regions.7. How good local cases unlock permits, public support and future regulation.Episode content:01:20 What is Power-to-X? 08:31 Limits of batteries for grid-scale storage10:35 Why ammonia?11:56 Maritime propulsion and industrial demands 22:01 How "dynamic” is dynamic? Matching power markets without second-by-second thrash28:20 Turning stored energy back into electricity 39:34 Why real projects create the political runway for better rules.43:09 Jobs, keeping young talent local and making rural locations an advantage.48:40 Industrial symbiosis and sector coupling 51:11 Strong renewables, grid access, neighbors for heat/power synergies, supportive permitting. This podcast is produced by Montanus.
Transcribe →
Fusion Energy | Practice: The Future of Power or Just a Scientific Dream?
Oct 1300:38:03Tap to summarizeFusion has long carried the reputation of being “30 years away”. Forever on the horizon but never quite arriving. That perception may finally be changing.In this episode of Big Ideas Only, host Mikkel Svold is joined once again by Søren Bang-Korsholm, senior scientist at the Department of Physics at DTU. This time, the focus is on the practical future of fusion energy: what private companies are doing differently, how huge global projects like ITER fit into the picture, and what role fusion could play in the broader energy transition.From billionaire-backed startups to the promise of grid-ready plants, Mikkel and Søren explore whether fusion can move beyond test facilities and become a true energy source for the 21st century.In this episode, you'll learn about:1. Why private investment is accelerating fusion research.2. The scale and goals of the ITER project—the world’s biggest science collaboration.3. How fusion could integrate into existing grids and even replace coal plants directly.4. The role of fusion as a clean, reliable base load alongside renewables.5. Potential use cases beyond electricity, including hydrogen production and desalination.6. The biggest technical hurdles still standing in the way.7. Why fusion’s commercialization might be closer than we think.Episode content:01:11 Why the “30 years away” joke may be outdated 05:14 Fusion’s role in the global energy transition09:13 ITER: the world’s largest fusion project explained12:27 Timelines: demonstration reactors in the 2030s13:22 How fusion could plug straight into existing grids18:25 What still needs solving before commercialization 30:16 Safety, waste, and why fusion differs from fission31:50 The need for public-private collaboration in energy34:17 How fusion could change daily life and global development This podcast is produced by Montanus.
Transcribe →
Fusion Energy | Theory: The Future of Power or Just a Scientific Dream?
May 13, 202500:34:28Tap to summarizeWhat if we could power the world the same way the sun does? No carbon, no meltdown risks – just clean energy from smashing atoms together.In this episode, I sit down with Søren Bang Korsholm, Senior Scientist at the Technical University of Denmark, to talk about fusion energy. You’ve probably heard it called the “holy grail” of power, but—weird metaphors aside—what does that actually mean? And are we any closer to making it work outside a lab?We cover how a tiny bit of fusion fuel could keep your lights on for a lifetime, why plasma is such a pain to control, and whether this whole thing is still sci-fi or finally getting real.If you like science, big ideas, or just want your energy bill to stop looking like your rent, give it a listen.In this episode, you'll learn about:1. Discover why fusion energy could provide unlimited, clean energy.2. Understand the fundamental nuclear process behind fusion energy.3. Learn how fusion energy mimics the sun’s power production.4. Hear how magnetic and inertial methods can contain fusion reactions.5. Explore the historical journey from fission to fusion research.6. Find out how fusion might transform the global energy landscape soon.Episode Content00:17 Introduction to fusion energy with Mikkel Svold 01:21 Why is fusion energy a big idea? 02:11 The potential of unlimited energy sources 03:06 Comparison of fusion energy to coal energy 04:33 Understanding the basic processes of fusion 05:28 How do fusion reactions actually work? 09:03 What fuels are commonly used in fusion? 12:47 Evolution of fusion research and technology 20:54 Magnetic confinement fusion vs. inertial confinement fusion 31:30 The role of the private sector in fusion developmentThis podcast is produced by Montanus, https://montanus.coThis podcast is produced by Montanus.
Transcribe →
Artificial Intelligence: Maybe the Most Significant Thing Since the Wheel
Jan 11, 202300:47:28Tap to summarizeIn this episode—which is also going to be the last episode of this season—we'll try to understand artificial intelligence, or AI. I want to know what we can expect from AI, why we should care, and why it’s a big idea.Now, to understand the intricacies of artificial intelligence and where it’s going, I’ve once again invited the very knowledgeable Thomas Schmidt into the studio.Thomas is the founder and Managing Director of Schmidt Innovation, an engineering company specialised in automation, mathematical modelling, software architecture, and of course, innovation. Producing this podcast is Montanus – a company where we specialize in producing high quality content for marketing department in engineering and knowledge driven companies.Learn more about Montanus here: www.montanus.coFind the Shownotes here: www.montanus.co/bigideasonly/This podcast is produced by Montanus.
Transcribe →