https://vitagri.org/ 2026-10-03 weekly 1.0 https://vitagri.org/food-soil-seedlings.webp Seedlings growing in healthy soil — Vitagri https://vitagri.org/food-veg-bowl.webp Nutrient-dense vegetables https://vitagri.org/food-farmland.webp UK regenerative farmland https://vitagri.org/evidence/ 2026-04-26 weekly 0.9 https://vitagri.org/evidence/at-a-glance/ 2026-05-29 weekly 0.85 https://vitagri.org/evidence/explorer/ 2026-05-29 weekly 0.85 https://vitagri.org/evidence/pulse/ 2026-05-29 monthly 0.8 https://vitagri.org/evidence/bulletin/ 2026-05-16 weekly 0.9 https://vitagri.org/evidence/visuals/ 2026-04-19 monthly 0.85 https://vitagri.org/evidence/submit/ 2026-05-16 monthly 0.7 https://vitagri.org/research-partners/ 2026-07-02 monthly 0.85 https://vitagri.org/evidence/pods/ 2026-05-16 monthly 0.85 https://vitagri.org/evidence/pods/vitagri-research-pod/ 2026-05-16 monthly 0.7 https://vitagri.org/evidence/pods/greenfield-foods/ 2026-05-16 monthly 0.5 https://vitagri.org/evidence/pods/soil-seed-collective/ 2026-05-16 monthly 0.5 https://vitagri.org/evidence/example-reports/ 2026-04-26 monthly 0.7 https://vitagri.org/evidence/api/ 2026-04-25 monthly 0.8 https://vitagri.org/pulse-brain/search/ 2026-09-28 weekly 0.85 https://vitagri.org/research/ 2026-04-10 monthly 0.9 https://vitagri.org/research/growing-health-report.html 2026-04-25 monthly 0.95 https://vitagri.org/cover_page_106.webp Growing Health White Paper cover — Vitagri 2026 https://vitagri.org/research/soil-nutrient-density/ 2026-04-10 monthly 0.85 https://vitagri.org/research/human-health/ 2026-04-15 monthly 0.85 https://vitagri.org/research/regenerative-agriculture/ 2026-04-25 monthly 0.85 https://vitagri.org/research/bionutrient/ 2026-05-16 monthly 0.75 https://vitagri.org/research/food-systems/ 2026-04-15 monthly 0.85 https://vitagri.org/framework/ 2026-04-10 monthly 0.9 https://vitagri.org/citations/ 2026-04-20 weekly 0.8 https://vitagri.org/insights/ 2026-04-25 weekly 0.8 https://vitagri.org/insights/antioxidant-variation/ 2026-04-10 monthly 0.8 https://vitagri.org/insights/food-system-quality/ 2026-04-25 monthly 0.8 https://vitagri.org/insights/soil-biology-nutrition/ 2026-04-10 monthly 0.8 https://vitagri.org/insights/nhs-268-billion-soil-health.html 2026-04-10 monthly 0.8 https://vitagri.org/insights/sfi-2026-nutrient-dense-food.html 2026-04-10 monthly 0.8 https://vitagri.org/insights/soil-microbiome-gut-health-axis.html 2026-04-10 monthly 0.8 https://vitagri.org/news/ 2026-04-10 weekly 0.75 https://vitagri.org/news/groundup-framework-launch/ 2026-04-10 monthly 0.75 https://vitagri.org/news/growing-health-published/ 2026-04-10 monthly 0.75 https://vitagri.org/news/innovate-uk-partnership/ 2026-10-14 monthly 0.75 https://vitagri.org/news/frontiers-soil-nutrition-editorial.html 2026-04-10 monthly 0.75 https://vitagri.org/news/mccain-farm-of-future.html 2026-04-10 monthly 0.75 https://vitagri.org/news/regenerative-dairy-soil-carbon.html 2026-04-10 monthly 0.75 https://vitagri.org/news/bionutrient-global-treaty.html 2026-04-10 monthly 0.75 https://vitagri.org/news/hfss-advertising-ban-2026.html 2026-04-10 monthly 0.75 https://vitagri.org/why/ 2026-08-06 monthly 0.9 https://vitagri.org/ontology/ 2026-08-06 monthly 0.8 https://vitagri.org/about/ 2026-04-10 monthly 0.7 https://vitagri.org/about/team.html 2026-04-10 monthly 0.7 https://vitagri.org/faq/ 2026-04-10 monthly 0.7 https://vitagri.org/faq/hard-questions/ 2026-07-02 monthly 0.6 https://vitagri.org/contact/ 2026-04-10 monthly 0.7 https://vitagri.org/events/ 2026-04-10 weekly 0.7 https://vitagri.org/webinar/ 2026-04-25 monthly 0.7 https://vitagri.org/invest/ 2026-04-25 monthly 0.8 https://vitagri.org/international/ 2026-04-10 monthly 0.7 https://vitagri.org/media/ 2026-04-25 monthly 0.5 https://vitagri.org/charts/ 2026-04-10 monthly 0.7 https://vitagri.org/soil/ 2026-04-10 monthly 0.7 https://vitagri.org/references.html 2026-04-25 monthly 0.5 https://vitagri.org/statistics/ 2026-04-15 monthly 0.9 https://vitagri.org/what-is-nutrient-dense-food/ 2026-04-25 monthly 0.9 https://vitagri.org/academy/ 2026-10-24 monthly 0.85 https://vitagri.org/academy/data-agronomy/ 2026-10-24 monthly 0.85 https://vitagri.org/academy/verify/ 2026-10-24 yearly 0.4 https://vitagri.org/pulse/ 2026-05-04 monthly 0.85 https://vitagri.org/pulse-check/ 2026-05-16 monthly 0.85 https://vitagri.org/pulse-check/case-study/ 2026-05-16 monthly 0.7 https://vitagri.org/pulse-check/buy/ 2026-05-16 monthly 0.7 https://vitagri.org/why-pulse/ 2026-05-16 monthly 0.8 https://vitagri.org/workshop/ 2026-06-08 monthly 0.8 https://vitagri.org/workshop/pricing/ 2026-06-08 monthly 0.7 https://vitagri.org/privacy/ 2026-03-21 yearly 0.3 https://vitagri.org/terms/ 2026-03-21 yearly 0.3 https://vitagri.org/anti-spam/ 2026-04-25 monthly 0.3 https://vitagri.org/growing-health-2026.pdf 2026-03-19 monthly 0.9 https://vitagri.org/vitagri-citations-glossary.pdf 2026-03-21 monthly 0.5 https://vitagri.org/vitagri-press-release-oct-2026.pdf 2026-10-15 yearly 0.4 https://vitagri.org/vital-pulse/literature-trends/ 2026-05-16 weekly 0.8 https://vitagri.org/predictive-model/ 2026-10-26 monthly 0.8 https://vitagri.org/predictive-model/trials/ 2026-10-03 monthly 0.8 https://vitagri.org/pulse-cultivate/ 2026-06-22 monthly 0.8 https://vitagri.org/food-farmland.webp Pulse Cultivator — a white-label evidence-backed community channel by Vitagri Pulse https://vitagri.org/pulse-cultivate/pricing/ 2026-07-05 monthly 0.7 https://vitagri.org/pulse-cultivate/case-studies/ 2026-07-05 monthly 0.7 https://vitagri.org/pulse-cultivate/case-studies/fielder-agronomy/ 2026-07-05 monthly 0.6 https://vitagri.org/pulse-cultivate/case-studies/rootstock-advisory/ 2026-07-05 monthly 0.6 https://vitagri.org/pulse-cultivate/case-studies/thrive-nutrition/ 2026-07-05 monthly 0.6 https://vitagri.org/pulse-cultivate/case-studies/greenfield-nutrition/ 2026-07-05 monthly 0.6 https://vitagri.org/pulse-cultivate/case-studies/bramblewood-hotels/ 2026-07-05 monthly 0.6 https://vitagri.org/pulse-cultivate/for-agronomists/ 2026-07-05 monthly 0.7 https://vitagri.org/food-soil-testing.webp Pulse Cultivator for agronomists — your own branded platform for your farmers https://vitagri.org/pulse-cultivate/for-the-food-sector/ 2026-08-11 monthly 0.8 https://vitagri.org/pulse-cultivate/for-the-food-sector/advisors/ 2026-08-11 monthly 0.6 https://vitagri.org/pulse-cultivate/for-nutritionists/ 2026-07-05 monthly 0.7 https://vitagri.org/food-broccoli-closeup.webp Pulse Cultivator for nutritionists — your own branded platform for your food-business clients https://vitagri.org/pulse-cultivate/roles/ 2026-07-02 monthly 0.7 https://vitagri.org/measure-what-matters/ 2026-10-08 monthly 0.7 https://vitagri.org/food-farmland.webp Measure What Matters — by farmers, for farmers https://vitagri.org/field-report/ 2026-10-25 weekly 0.8 https://vitagri.org/field-report/images/show-artwork-1400.jpg The Vitagri Field Report https://vitagri.org/field-report/dashboard/ 2026-10-25 weekly 0.6 https://vitagri.org/field-report/2026-w43/ 2026-10-25 monthly 0.6 https://vitagri.org/field-report/images/2026-w43.jpg The Field Report, Week 43: Calf health leads a new week https://vitagri.org/academy/causal-inference/ 2026-10-26 monthly 0.7 https://vitagri.org/academy/causal-inference/glossary/ 2026-10-26 monthly 0.6 https://vitagri.org/academy/causal-inference/preface/ 2026-10-26 monthly 0.6 https://vitagri.org/academy/causal-inference/images/preface.jpg?v=d81ad728d1 Preface: AI and the question of cause Both start from probabilities. A large language model is trained to learn how likely each next word is, given the words before: what goes together. Causal inference starts from the same probabilities and asks what happens if we change something. Judea Pearl, whose work joined the two, won the 2011 Turing Award, and today each needs the other. https://vitagri.org/academy/causal-inference/films/preface.mp4?v=0ca87a7663 147 2026-10-26 yes https://vitagri.org/academy/causal-inference/introduction/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/introduction.jpg?v=dae3f13165 Introduction: from field to plate 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. https://vitagri.org/academy/causal-inference/films/introduction.mp4?v=9b61120128 222 2026-10-25 yes https://vitagri.org/academy/causal-inference/p1-right-for-the-wrong-reason/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/p1.jpg?v=a20d377d1c P1 Right for the wrong reason Because a model learns whatever pattern best predicts the answer, and a pattern that predicts is not a cause. A pneumonia model learned which hospital an X-ray came from. Feedlot records can make antibiotics look deadly, because vets treat the animals most at risk. To answer “what if I do this?” you need an experiment or a causal model. https://vitagri.org/academy/causal-inference/films/p1.mp4?v=5927f0fdae 273 2026-10-25 yes https://vitagri.org/academy/causal-inference/p2-machines-and-causes/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/p2.jpg?v=755cef146c P2 Machines and causes Causal thinking gives AI advice that holds up when acted on, explanations people can check and, perhaps one day, models that keep working in new places. AI gives causal inference a way to model tangled farm data, find where effects differ and help draft causal maps. Machine learning cleans up what you measured; only design deals with what you didn’t. https://vitagri.org/academy/causal-inference/films/p2.mp4?v=7e43c8200b 347 2026-10-25 yes https://vitagri.org/academy/causal-inference/1-1-1747-twelve-sailors-and-a-cure/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/1-1.jpg?v=37b9a4713f 1.1 1747: twelve sailors and a cure nobody could explain In May 1747, aboard HMS Salisbury, the naval surgeon James Lind took twelve sailors with scurvy, kept them in the same conditions and gave six pairs six different remedies. Within six days the pair on oranges and lemons were recovering. It was a controlled comparison: similar patients, the same conditions, different treatments. https://vitagri.org/academy/causal-inference/films/1-1.mp4?v=7cd63cd2c6 235 2026-10-25 yes https://vitagri.org/academy/causal-inference/1-2-if-the-first-had-not-been/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/1-2.jpg?v=03987eef10 1.2 “If the first had not been” A potential outcome is what would happen to a unit under each possible treatment. A field has one yield if you fertilise it and another if you don’t, and the effect is the difference. But you can farm it only one way at a time, so one outcome always stays hidden: the fundamental problem of causal inference. https://vitagri.org/academy/causal-inference/films/1-2.mp4?v=47b22ac3b0 222 2026-10-25 yes https://vitagri.org/academy/causal-inference/1-3-hidden-in-the-food/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/1-3.jpg?v=e8da38ce40 1.3 Hidden in the food A natural experiment is a change nobody designed that still splits the world into comparable groups. When Christiaan Eijkman’s laboratory chickens were switched from polished white rice to cheaper unpolished rice, they recovered from a beriberi-like paralysis. That accident pointed to something essential in the rice’s outer layers, and led to the idea of vitamins. https://vitagri.org/academy/causal-inference/films/1-3.mp4?v=9acd83bc74 267 2026-10-25 yes https://vitagri.org/academy/causal-inference/1-4-the-wheat-field/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/1-4.jpg?v=ef4d171878 1.4 The wheat field Soil changes across every field, so with one variety on one side and another on the other, you can’t tell the varieties from the soil. Letting chance decide which plot gets which treatment means no gradient, known or unknown, can line up with it except by luck. It is the only method that deals with confounders nobody has thought of. https://vitagri.org/academy/causal-inference/films/1-4.mp4?v=3197e79b8a 233 2026-10-25 yes https://vitagri.org/academy/causal-inference/1-5-arrows-and-instruments/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/1-5.jpg?v=e3cbd8a3e9 1.5 Arrows and instruments An instrument is an outside push that moves the treatment but has no other route to the outcome. In 1928 Philip Wright used growing conditions, which change how much flaxseed reaches the market without changing what buyers want, to trace the demand curve. An instrument fails when the push also reaches the outcome by a back route. https://vitagri.org/academy/causal-inference/films/1-5.mp4?v=c14fa23710 222 2026-10-25 yes https://vitagri.org/academy/causal-inference/1-6-smoking-and-the-sceptic/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/1-6.jpg?v=58156b89c3 1.6 Smoking and the sceptic Nobody randomised smoking. Doll and Hill found heavier smokers died of lung cancer at many times the rate of non-smokers, with risk rising with dose. When Fisher argued an inherited trait might cause both, Cornfield showed in 1959 that such a trait would need to be at least nine times as common in smokers. No plausible trait came close. https://vitagri.org/academy/causal-inference/films/1-6.mp4?v=6686f1c66e 219 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-1-draw-it-before-you-analyse-it/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-1.jpg?v=e8b89317ec 2.1 Draw it before you analyse it A causal map, or directed acyclic graph, draws each thing that varies as a box and each direct effect as an arrow. It has no numbers or equations: it shows which way influence can flow. Drawn before the data are analysed, it puts assumptions where agronomists, vets, nutritionists and farmers can check them. https://vitagri.org/academy/causal-inference/films/2-1.mp4?v=c452e077b6 273 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-2-three-shapes/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-2.jpg?v=3165164970 2.2 Three shapes They are the three shapes every causal map is built from. In a chain, one thing affects a second, which affects a third. In a fork, one thing affects two others. In a collider, two arrows point into the same box. Chains and forks pass association along unless you hold the middle fixed; colliders block it unless you do. https://vitagri.org/academy/causal-inference/films/2-2.mp4?v=3589c201bb 233 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-3-confounders-and-the-back-door/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-3.jpg?v=c0831abf81 2.3 Confounders and the back door Judea Pearl’s rule for estimating an effect from data you didn’t control. List every route between treatment and outcome that starts with an arrow into the treatment: the back doors. Close each one by holding fixed a variable on it. Don’t hold fixed anything the treatment causes, and don’t open a shut door by holding fixed a collider. https://vitagri.org/academy/causal-inference/films/2-3.mp4?v=fe7f55b390 249 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-4-mediators/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-4.jpg?v=d9dc3add5c 2.4 Mediators A mediator sits on the path from treatment to outcome: it is how the effect gets there, like leaf zinc between a foliar spray and the grain. Adjust for it and you block the very route the treatment works through, so a treatment that works can appear to do nothing. The rule: never adjust for anything the treatment causes. https://vitagri.org/academy/causal-inference/films/2-4.mp4?v=430b1f6b34 238 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-5-colliders-and-selection/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-5.jpg?v=e325a94454 2.5 Colliders and selection Collider bias appears when you hold fixed, or select on, something that both the treatment and the outcome, or their causes, feed into. Choosing which data to look at can do it without anyone noticing. Analysing only animals that reached slaughter, only samples sent to a lab or only published studies can create a link that isn’t there. https://vitagri.org/academy/causal-inference/films/2-5.mp4?v=dc345803a9 249 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-6-modifiers-instruments-and-the-unmeasured/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-6.jpg?v=2227add7f1 2.6 Modifiers, instruments and the unmeasured An effect modifier changes how big an effect is. In Ghana, the typical maize response to fertiliser was 2.8 tonnes a hectare in the Sudan Savannah and 0.9 in the Forest–Savannah Transition. You don’t adjust a modifier away and report one number; you report the effect for each group, because a national average would be wrong almost everywhere. https://vitagri.org/academy/causal-inference/films/2-6.mp4?v=060b42fa3b 262 2026-10-25 yes https://vitagri.org/academy/causal-inference/2-7-how-the-map-changes-the-work/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/2-7.jpg?v=9bafa4ca74 2.7 How the map changes the work Before any model runs, a map lists the rival explanations, finds predictions the data could contradict, and asks whether the data can answer the question at all. On Barn Door Farm, a zinc–fibre correlation of 0.98 across five wheat samples became an honest “not yet” and a plan to measure soil, roots and grain at thirty spots. https://vitagri.org/academy/causal-inference/films/2-7.mp4?v=22ba36a3e2 243 2026-10-25 yes https://vitagri.org/academy/causal-inference/3-1-the-trial-on-the-farm/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/3-1.jpg?v=42ca9580ed 3.1 The trial on the farm Treatments are randomised to strips, plots, animals, herds or whole communities and compared side by side. In 113 replicated strip trials in Iowa and New York, a model’s nitrogen advice used 34 per cent less sidedress nitrogen with no significant difference in yield. What you randomise, and the outcome you measure, decide what a trial can tell you. https://vitagri.org/academy/causal-inference/films/3-1.mp4?v=911e571f0c 230 2026-10-25 yes https://vitagri.org/academy/causal-inference/3-2-comparing-like-with-like/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/3-2.jpg?v=1f323029a6 3.2 Comparing like with like A propensity score is a unit’s probability of being treated, given everything you measured. In 1983 Paul Rosenbaum and Donald Rubin showed that units with the same score are, on average, balanced on all those characteristics at once. You can match on that one number, or weight by it, so the groups you compare line up on what you measured. https://vitagri.org/academy/causal-inference/films/3-2.mp4?v=ab6691e9e2 185 2026-10-25 yes https://vitagri.org/academy/causal-inference/3-3-before-and-after-with-a-comparison/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/3-3.jpg?v=e3c09a3385 3.3 Before and after, with a comparison Difference-in-differences compares the change in a treated group with the change in a group that didn’t get the treatment, both measured before and after. If the two were moving in parallel beforehand, the comparison group’s change shows what would have happened anyway, and the extra change in the treated group is the estimate. https://vitagri.org/academy/causal-inference/films/3-3.mp4?v=a1e096bf7e 198 2026-10-25 yes https://vitagri.org/academy/causal-inference/3-4-natures-experiments/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/3-4.jpg?v=32e0954abc 3.4 Nature’s experiments They are designs in which something outside anyone’s choice splits units into comparable groups. John Snow compared houses supplied by two water companies. A regression discontinuity compares units just either side of a rule’s threshold. A synthetic control builds a weighted twin from untreated regions. Mendelian randomisation uses genes dealt out at conception. https://vitagri.org/academy/causal-inference/films/3-4.mp4?v=5cf203a19a 201 2026-10-25 yes https://vitagri.org/academy/causal-inference/3-5-when-neighbours-matter/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/3-5.jpg?v=4f6b36b3e9 3.5 When neighbours matter Interference is when one unit’s treatment changes another unit’s outcome, and on farms it happens all the time: pests, pollinators, spray drift, water and disease don’t stop at the hedge. Bt maize cut European corn borer numbers across whole regions, so growers of ordinary maize benefited too, and comparing Bt with non-Bt fields there would underestimate Bt’s effect. https://vitagri.org/academy/causal-inference/films/3-5.mp4?v=04721cc5c5 169 2026-10-25 yes https://vitagri.org/academy/causal-inference/3-6-when-observation-lied/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/3-6.jpg?v=359b7bbd0f 3.6 When observation lied Writing down the randomised trial you wish you could run, then making an observational analysis copy it as closely as possible: who is eligible, exactly what the treatment is, and a time zero when everyone’s clock starts. Analysed this way, the Nurses’ Health Study data gave answers on hormone therapy much closer to the trial’s. https://vitagri.org/academy/causal-inference/films/3-6.mp4?v=806d94bc7a 230 2026-10-25 yes https://vitagri.org/academy/causal-inference/4-1-double-machine-learning-step-by-step/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/4-1.jpg?v=49e92d1df3 4.1 Double machine learning, step by step Two nuisance models do the cleaning: one predicts which fields get the treatment from their background, the other predicts the outcome from the same background, and the leftovers are compared. The method is built so the two models’ errors matter only when multiplied together, and cross-fitting stops any model being judged on data it has memorised. https://vitagri.org/academy/causal-inference/films/4-1.mp4?v=53ff95449b 238 2026-10-25 yes https://vitagri.org/academy/causal-inference/4-2-who-benefits/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/4-2.jpg?v=b1c59a13c1 4.2 Who benefits? A causal forest finds where a treatment effect is bigger or smaller. A causal tree splits the data with yes-or-no questions to find the groups whose effects differ most, and hundreds of slightly different trees are averaged into a forest. Stefan Wager and Susan Athey set out the method in 2018; a Ghana study used it on randomised fertiliser trials. https://vitagri.org/academy/causal-inference/films/4-2.mp4?v=c7442dea5e 201 2026-10-25 yes https://vitagri.org/academy/causal-inference/4-3-try-to-break-your-own-answer/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/4-3.jpg?v=d487ef0200 4.3 Try to break your own answer Try to break it before anyone relies on it. Run a placebo test with a fake, shuffled treatment; check a negative control, an outcome the treatment can’t possibly affect; ask how strong an unmeasured confounder would need to be, with a sensitivity analysis or the robustness value; and estimate the effect more than one way. https://vitagri.org/academy/causal-inference/films/4-3.mp4?v=32e6afa8f3 193 2026-10-25 yes https://vitagri.org/academy/causal-inference/4-4-can-ai-find-causes/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/4-4.jpg?v=6baf9372d5 4.4 Can AI find causes? Only partly. Causal discovery algorithms read the patterns chains, forks and colliders leave in data, but chains and forks leave the same fingerprint, so observational data usually narrow things to a family of maps, not one. Language models can suggest plausible arrows but make many mistakes on formal causal reasoning. Use AI as a drafting partner. https://vitagri.org/academy/causal-inference/films/4-4.mp4?v=af3176e233 235 2026-10-25 yes https://vitagri.org/academy/causal-inference/5-1-the-chain-from-soil-to-health/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/5-1.jpg?v=334f61709f 5.1 The chain from soil to health Some evidence says so, but each link needs its own. US food tables for 43 garden crops showed apparent falls between 1950 and 1999. In the Broadbalk archive, grain zinc, iron, copper and magnesium held steady until the mid-1960s, then fell as high-yielding varieties arrived, while the soil’s levels did not: pointing to variety and yield, the dilution effect. https://vitagri.org/academy/causal-inference/films/5-1.mp4?v=dae2da8c55 251 2026-10-25 yes https://vitagri.org/academy/causal-inference/5-2-when-farming-changed-the-plate/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/5-2.jpg?v=1c45563115 5.2 When farming changed the plate Yes, when the whole chain is built and measured. From the mid-1980s Finland added selenium to farm fertilisers, and selenium intakes and blood levels rose substantially. Orange-fleshed sweet potato, rich in beta-carotene, raised vitamin A intakes in Mozambique and Uganda. Convincing cases measure more than one link and use a design that fits the question. https://vitagri.org/academy/causal-inference/films/5-2.mp4?v=28c519c500 230 2026-10-25 yes https://vitagri.org/academy/causal-inference/5-3-from-a-pattern-to-a-plan/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/5-3.jpg?v=69e5f0f48f 5.3 From a pattern to a plan Choosing the smallest step that can answer the question. A trial asks the most of a farm: land set aside, time and cost. As the published wheat case puts it, a promising pattern doesn’t always call for a field trial, and many questions need only one or two steps, such as correcting records and measuring what’s missing. https://vitagri.org/academy/causal-inference/films/5-3.mp4?v=ff5e792dc8 235 2026-10-25 yes https://vitagri.org/academy/causal-inference/5-4-what-it-takes-to-do-this-well/ 2026-10-25 monthly 0.6 https://vitagri.org/academy/causal-inference/images/5-4.jpg?v=375187fb45 5.4 What it takes to do this well Seven things: a precise question; the published evidence, read critically; data labelled honestly; a causal map checked by people who know the farm and the food; the right design for the question; methods that fit the data, with their assumptions stated; and checks that try to break the answer, with the discipline to say “not yet”. https://vitagri.org/academy/causal-inference/films/5-4.mp4?v=0b18f43af9 212 2026-10-25 yes