What is causal inference, and why does it matter for food and farming?
Causal inference is the discipline of telling a cause from a pattern: working out what would actually happen if you changed something, and how sure you can be. In farming and food it matters at every link from soil to crop, food, diet and health, because a pattern that predicts is not the same as a cause.
Every season, farms make decisions that end up on someone's plate. Which variety to sow. How much nitrogen. When to harvest, how to store, how to mill. Somewhere along that chain, from the soil to the crop, to the food, to what people eat, those decisions change how nourishing the food turns out to be.
The question is which ones, and by how much. That's a question about cause and effect. Data can show you patterns. On Barn Door Farm, the zinc in the grain rose and fell with its fibre, almost perfectly, across five samples. It's tempting to act on a pattern like that.
But a pattern that predicts is not the same as a cause. Something else may be driving both. Change one, and the other may not follow. Causal inference is the discipline of telling the two apart: working out what would actually happen if you changed something, and how sure you can be.
This series is for anyone who makes those decisions, or advises on them: farmers, food businesses, agronomists and nutritionists, and our own team at Vitagri. You don't need any statistics. Each film is about four minutes, and teaches one idea. Here's the journey. The prologue starts with an AI that was right for the wrong reason, and asks what machine learning and causal thinking each bring. Module one goes back to where the ideas came from: a ship in 1747, a wheat field in Hertfordshire, and the long argument over smoking. Module two teaches you to draw a causal map, and to recognise the roles that variables play in it. Module three is about study designs: trials on real farms, fair comparisons, and the experiments nature runs for us. Module four looks at the methods in depth, machine learning included, and at how to test an answer before you trust it. And module five follows the chain itself, from soil to health, and ends with how to plan the next step.
Why are we making it? At Vitagri, we've built Vitagri Vitals, our causal engine linking agriculture and food nutrition. It brings together published evidence, farm and food data and causal maps, helps choose a proportionate next step, and says plainly when the evidence isn't there yet.
This series won't show you how Vitals works inside. It shows you what any careful causal analysis has to get right, and why the shortcuts fail. Think of it as showing you the mountain, not the map. Once you understand the method, you can judge the work, ours included. So let's begin with a pattern that fooled a machine: an AI that was right for the wrong reason.
Anyone who makes decisions along the chain from farm to plate, or advises on them: farmers, food businesses, agronomists and nutritionists, and the Vitagri team. No statistics are needed. Each film is about four minutes long, teaches one idea and builds on the one before.
Six parts: a prologue on why prediction is not causation; where the ideas came from, from a ship in 1747 to the argument over smoking; causal maps and the roles variables play; study designs; the methods in depth, machine learning included; and the chain from soil to health, ending with how to plan the next step.
No. Vitagri Vitals is Vitagri’s causal engine linking agriculture and food nutrition: it brings together published evidence, farm and food data and causal maps, helps choose a proportionate next step, and says plainly when the evidence isn’t there yet. The series shows what any careful causal analysis has to get right, not how Vitals works inside.
Causal evidence is changing how farming is measured and rewarded. Leave your email and we will tell you when new films, courses and findings are published.
Prefer to read online? Vitagri also writes on Substack. See our privacy policy for how we use your email.