Soil health, read by its smallest animals
AI-assisted microscopy to read the nematode communities that signal how healthy a soil is.
Why it matters
Soil decides what a farm can grow, but most farmers only find out it is failing when the crop does. Nematodes, microscopic soil worms, respond to soil condition early: some damage roots, others signal a living, healthy soil. Counting them by hand is slow, specialist work, so the signal is rarely used.
What we are doing
A university and industry research proposal to read nematode communities in commercial potato soils with AI-assisted microscopy, and turn the readings into early, practical signals for growers. Uthando's role is research design support, data governance and the route from findings to farmers.
Stage: A three-year research proposal was submitted in February 2026. The outcome is pending.
What the technology does
Described at the level of what it does, not how it is built. Methods, models and data stay private until their owners decide how to protect and share them.
- AI-assisted microscopy that identifies and counts nematodes from slide images
- A shared field-trial data model, so every sample keeps its site, date and treatment
- ALOODA evidence rules: a result counts only as strongly as its weakest input
- Plain-language grower reports, written from verified results only
The ALOODA path for this programme
Every Uthando programme runs on the same standard operating procedure: six steps and a confidence gate before anything is acted on or published. Read the ALOODA white paper.
- AAttention
Soil problems surface too late for growers to act on them.
- LListening
Growers, soil scientists and an industry body, on what they need to know, and when.
- OObserve
Existing nematode surveys, and what manual counting costs in time and skill.
- OOrient
Treat the soil's living community as an early-warning signal, measured the same way at every site.
- DDecide
Propose a multi-season study with AI microscopy, a common data model and data ownership agreed up front.
- 95The 95% gate
No finding is shared until the research team has verified and published it.
- AAct
Run the study, then publish with the research partners.
From proof to scale, gate by gate
Nothing moves to the next stage until its gate is passed and evidenced. Honest about where it stands today.
Prove
Show that the problem is real and the approach works: research, a prototype, ethics approvals and first evidence.
Gate: The core claim passes the ALOODA 95% gate.
Pilot
Run it with real people in one setting, under a written agreement, against a baseline.
Gate: Pilot results are verified and every safeguard has worked in practice.
Blueprint
Write the model down so others can run it: the SOP, data standard, training, costs, legal checklist and licence terms.
Gate: An independent partner runs it from the blueprint alone.
Scale
Replicate through partners across sites and countries, under each country's law and with local consent.
Gate: A local compliance check passes before each new country.
Next gate for this programme: A funding decision, then ethics and data agreements signed before any sampling.
The rules this programme follows
- Research partners own and publish the science. Intellectual property follows the lead university's policy, and South Africa's IPR Act where public funds apply.
- Data ownership and access agreed in writing before any sample is taken.
- Soil sampled only with each landowner's consent.
- No results, sites or partner names published before the research team agrees.
How these laws and standards apply across Uthando: Standards and governance.
Dated, on file, checkable
| When | Record | Status |
|---|---|---|
| Feb 2026 | Three-year research proposal submitted to an industry funder | Outcome pending |
Held back on purpose
- The consortium, the funder and the budget
- The research design
- All data and results
Records are available to funders and partners under a non-disclosure agreement.
Fund it, partner on it, or test the evidence
Tell Thando what you have in mind. Uthando replies personally.