AI Makes Biochar Phosphorus Farming More Predictable

Plant matter that has been charred and incorporated into agricultural soil, known as biochar, is becoming increasingly popular as an inexpensive means of improving soil quality and reducing fertiliser losses.

Farmers using it typically want to make better use of the phosphorus that is already present in their fields.

Yet biochar’s influence on phosphorus has long been difficult to anticipate. It may release nutrients that were previously unavailable, or it may quietly undermine the farmer who has applied it. Fresh research could at last make its effects more predictable.

The hidden waste

Plants are remarkably inefficient at absorbing the phosphorus supplied to them. Just a limited proportion nourishes crops in the season when it is applied, with estimates commonly ranging from 15 to 20 percent.

The remainder does not simply disappear. Part of it attaches to iron, aluminium or calcium, becoming chemically immobilised and unavailable to the crop. What is left can wash into rivers and ponds, where it fuels algal blooms and deprives the water of oxygen.

This runoff is known as eutrophication, a process that can leave once-healthy waterways green and devoid of life. Farmers therefore suffer a largely unseen double cost: money spent on wasted fertiliser and unintended environmental harm downstream.

Phosphorus fertiliser originates in mined rock that required millions of years to develop. Its non-renewable source makes that level of waste even more troubling.

Biochar as charcoal for soil

Biochar offers one possible answer. This charcoal-like substance is created by heating crop residues, timber or other plant material with very little oxygen present. The process produces a porous, carbon-rich black solid that can be mixed into farmland.

However, biochar has an inconsistent reputation. In certain soils, it makes previously locked phosphorus available to plants. In others, it retains phosphorus beyond the reach of roots - an outcome that can reduce pollution but can also be deeply unhelpful.

That lack of certainty is the central difficulty. A farmer considering a bag of biochar has had no dependable way of knowing whether it will benefit a particular field or hinder it, what application quantity to use, or which soil properties will determine the result.

AI predictions for biochar and phosphorus

Yutao Peng, from Sun Yat-Sen University in Shenzhen, China, and colleagues aimed to replace this uncertainty with a more reliable approach.

Using 32 previous studies, the researchers compiled 534 observations documenting how soil phosphorus changed after biochar was added.

They fed this information into three machine-learning systems, which searched for links between the characteristics of biochar, soil conditions and phosphorus outcomes. The models were required to assess 19 variables, a level of complexity that would be difficult to follow manually.

One approach performed noticeably better than the others. The Random Forest model reaches its prediction by carrying out hundreds of individual analyses of the data and then averaging their results.

When tested with information it had not encountered previously, the model achieved an R² of approximately 0.91, accounting for most of the differences in the way biochar affected phosphorus movement.

Heat shapes biochar

When the researchers examined which input mattered most to the model, one factor stood out. The temperature used to produce the biochar - its pyrolysis temperature - had a greater influence on the outcome than any other variable.

Biochar produced at moderate temperatures appeared to have a well-balanced structure, probably creating sufficient small pores and reactive surfaces to regulate phosphorus without an excessive effect.

The model identified an optimal range. The best outcomes were concentrated around production temperatures of 460–482°C, with moderate application rates.

Material produced at hotter temperatures acted differently, reducing phosphorus availability rather than increasing it. This may be useful where the priority is preventing phosphorus from reaching nearby water. In this sense, heat acts as a control dial.

Soil conditions matter

Temperature was not the only important influence. The quantity of biochar applied was the second most significant factor, followed by the soil’s acidity and the amount of total phosphorus it already contained.

Soil pH was found to direct the wider interaction. In acidic soils, phosphorus commonly binds to iron and aluminium, making it hard for plants to obtain, while biochar has less scope to alter the situation.

Biochar has greater potential in neutral or slightly alkaline soil. As those metal ions become less active, the rise in pH caused by biochar can shift phosphorus into forms that crop roots are able to access.

These effects did not follow straightforward patterns. The model revealed complex interactions among the factors that a basic equation would fail to capture.

This helps account for why a framework designed to manage complicated, non-linear relationships outperformed conventional statistical methods.

Simpler biochar works

One result challenges a long-standing assumption in the sector. Chemically modified biochar - material engineered in laboratories to improve performance - has often been regarded as the superior option and the expected gold standard.

The findings indicate that this may not be required. Under suitable conditions, basic untreated biochar can equal or even outperform modified material in regulating phosphorus.

The model also highlighted an unexpected possibility: biochar may be valuable less because of phosphorus contained within the material itself and more because it changes the behaviour of phosphorus already present in the soil.

That alters the economic calculation. Avoiding chemical modification lowers both costs and environmental impacts. Biochars made from crops or wood require less energy to manufacture than manure-based alternatives while delivering comparable results.

A new tool for farming

Before this research, pairing a particular biochar with a particular field was mostly a matter of trial and error, leaving farmers to bear the expense of every incorrect choice. There was no dependable method for forecasting the consequences before application.

There is now one possible route forward. Before even a handful is spread, a data-led model can estimate whether a chosen biochar will make phosphorus available for nutrient-hungry crops or retain it to safeguard a watershed.

Peng characterised the development as a shift in biochar use from guesswork to data-informed decision-making.

For farmers and their advisers, this could bring less fertiliser waste, fewer nutrients escaping into local watercourses and a stronger basis for deciding what to add to the soil.

The model is an initial framework rather than a completed solution, and its predictions will need to be tested in real fields.

Even so, it directs agriculture towards a future in which an affordable, carbon-rich material made from plant waste is used with something nearer to precision than optimism.