Forestry has a long-standing perception of being a pretty low-tech, primitive industry — after all, they just “chop trees and sell the wood.”
While the business at the core is exactly as simple as that, a big fat element of detail we often forget is that when you have to manage millions of hectares of wild forest land as a company, the challenge is anything but simple!
So when I heard about a budding niche of tech companies building full-fledged ML products to change how this industry operates, you can be sure it caught my attention.
Because forests are wild and open by definition, and too big and dense to study manually, it can be very hard to make intelligent data-backed decisions. And as you’ll learn in the episode, forestry is a business where the right or wrong data can directly cause the bottom line to swing by double-digit percentages.
To shed light on this industry, I invited none other than Rolf Schmitz, CEO of Collective Crunch: a company that provides data analytics solutions to forestry companies. They have spent the last 5 years building an extensive suite of ML products and have customers all over the Nordics and beyond (visit their website for more).
In this episode of The Age of AI Series, we learn how AI is transforming forest inventories and carbon monitoring.
Rolf and I get into the weeds (pun intended) of forestry and carbon economics, and give you the full picture:
- 01:45 — What’s going on in the forestry industry, and the concept of “forest inventory”
- 05:57 — How forest yields and inventory are measured
- 09:32 — Conventional methods of taking inventory of a forest, their error rates, pros and cons
- 13:47 — How new data can improve the error rates of conventional methods
- 16:13 — Brief history of LiDAR and machine learning methods in forestry — and the key factors affecting adoption rates
- 22:12 — Why building tech products for an un-sexy industry like forestry has suddenly started gathering more attention recently
- 24:54 — What makes one forest more “sustainable” than another, and why businesses are finally paying more attention
- 31:05 — What Collective Crunch provides to their customers and how it works
- 35:55 — The evolution of Collective Crunch; why they chose their current business model (big strategic decisions and reasoning for them)
- 40:34 — The key technical challenges in building Collective Crunch, explained simply
(Thanks Rolf for being generous and open to sharing your knowledge!)
While I highly recommend that you listen to the whole episode, if you’re pressed for time, here’s a quick tl;dr of the 45 minute episode:
Aman’s 2-Minute Summary and Key Takeaways
The forestry business at its heart is about selling wood. This means, their core “merchandise” is lumber or wood pulp. Given that forests are huge, non-uniform and constantly changing (species, density, heights of trees, changing seasons, etc), the process of taking an accurate “inventory” of their merchandise is a challenge. (Here’s a link to United Nations’ FAO reports.)
The dominant, age-old method of taking inventory is “sampling” — physically traveling around the forest, measuring tree heights using the shadow length, circumference, and whatnot, and making very bold extrapolations from the limited data you gather. This is both labor-intensive and requires a high level of knowledge, skill, and experience in the forest, while still being very prone to errors. Another traditional way is to fly a drone over the forest with a LiDAR sensor, creating a very high-definition point cloud of the entire forest. But this is also expensive and has its own suite of technical issues (especially with the absence of deep learning, which only recently came into the picture).
There are pros and cons to each method. Rolf says that they can have error rates swinging as much as 20-40%, which is staggering but also intuitively believable to me given the nature of the problem.
Collective Crunch’s approach to solving this problem was, why not combine as many possible sources of data you could get about the forest, use cutting-edge machine learning to make sense of all of them, and get the best estimations? So they took everything from publicly available satellite imagery to sampling to LiDAR scans, creating up to 20 layers of information.
Rolf claims that the solution they’ve built performs much better than conventional methods. I believe him because, one, they have real paying customers, and two, the technology definitely works as long as you feed it with the right data!
Naturally, this is a hard problem. From an ML standpoint, getting high-quality data is the big headache, and then there’s the question of how you deliver the predictions and other outputs in an interactive, flexible, user-friendly interface.
From a business standpoint, Rolf’s team made some key decisions in the beginning — they only do data analytics, and let the customer fly their own drones to collect raw data. They didn’t want to be an all-in-one services company that sends people to travel around jungles around the world and gather data on behalf of customers.
Having a SaaS model makes the company much more scalable, but Rolf confesses that they could have had faster growth and expansion into more markets if they were a “full stack” solution that included data collection services. At the same time, doing that would open a whole new can of worms that a lean company can’t handle without excessive cash burn, so I’m inclined to think that this was the right decision.
I’m also curious about how much the perceived value of their product in the eyes of customers (or company in the eyes of investors) is directly influenced by the commodity price trends of lumber, which is a natural resource. Rolf and I didn’t have enough time to discuss how this affects the way they define their market and product roadmap over the long term.
Lastly, I also found it interesting that sustainability is quickly becoming a real business focus in forestry, due to the growing market for carbon credits. Planting trees is the cheapest form of carbon capture, and forestry companies are using this to create a new source of revenue. But doing this profitably still requires having accurate inventory of the forest, which brings us back to companies like Collective Crunch — and if this trend continues, I’m optimistic that Rolf and his team are only at the beginning of a long successful journey with the technology they’ve built!
(Ethics Policy: These opinions are 100% my own as an independent observer and educator. I don’t own stock in guests’ companies, nor do I get paid by them in any form for any reason at the time of publishing, unless specifically stated. Episodes are also not intended to be an automatic endorsement of any company or its products and services.)