AI predicts how biochar affects soil phosphorus

Biochar, made by charring plant material and mixing it into agricultural soil, is increasingly seen as an inexpensive means of improving soil quality and reducing fertiliser losses.

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

Yet biochar’s influence on phosphorus has long been difficult to forecast. It may release nutrients that are chemically locked away, or it may subtly undermine the grower who applies it. Fresh research could at last make its effects more predictable.

The hidden waste

Plants are remarkably inefficient at absorbing the phosphorus intended for them. During a single growing season, only a limited proportion nourishes the crop – commonly estimated at 15 to 20 percent.

The remainder does not simply disappear. Part attaches to iron, aluminium or calcium, becoming chemically fixed 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, known as eutrophication, can leave previously healthy waterways green and lifeless. Farmers therefore face two largely unseen costs: money spent on wasted fertiliser and damage downstream that they did not mean to cause.

Phosphorus is obtained from rock deposits that took millions of years to form. Its non-renewable source makes such waste more troubling still.

Biochar as charcoal for soil

Biochar offers one possible answer. This charcoal-like substance is produced by heating crop residues, wood or other plant matter with very little oxygen. The process leaves a porous, carbon-rich black material that can be incorporated into farmland.

However, biochar has an inconsistent reputation. In certain soils, it makes fixed phosphorus available to plants; in others, it retains phosphorus beyond the reach of roots. That can be helpful when reducing pollution is the goal, but otherwise it can be frustrating.

This uncertainty is the central difficulty. A farmer considering a bag of biochar has had no dependable method of knowing whether it will benefit a particular field or prove counterproductive, what quantity to apply, or which soil conditions determine the result.

AI predictions for biochar and phosphorus

Yutao Peng, of Sun Yat-Sen University in Shenzhen, China, and colleagues sought to replace this uncertainty with reliable predictions.

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

They fed these data into three machine-learning systems designed to identify links between biochar properties, soil conditions and phosphorus outcomes. The models had to assess 19 variables, far more than a person could realistically follow manually.

One approach performed distinctly better than the others. The Random Forest model reaches an answer by carrying out hundreds of separate analyses of the data and averaging their findings.

When tested on data it had not previously encountered, the model achieved an R² of roughly 0.91, accounting for most of the variation in the way biochar redistributed phosphorus.

Heat shapes biochar

When the researchers asked which variable mattered most, one stood out. The pyrolysis temperature – the heat at which the biochar had originally been produced – influenced the outcome more than any other factor.

Biochar produced at moderate temperatures had a more balanced structure, probably forming sufficient minute pores and reactive surfaces to regulate phosphorus without going too far.

The model identified an optimum range. The best outcomes were concentrated at production temperatures of 460–482 °C, alongside modest application rates.

Biochar produced at higher temperatures acted differently, reducing rather than increasing phosphorus availability. This may be useful where the concern is phosphorus reaching nearby water. In that sense, temperature acts as a control dial.

Soil conditions matter

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

Soil pH was found to guide the entire interaction. In acidic soils, phosphorus commonly binds to iron and aluminium, making it hard to access, while leaving biochar with less opportunity to act.

Neutral and slightly alkaline soils offer biochar greater scope. As these metal ions become less active, even a small increase in pH caused by biochar can shift phosphorus into forms that roots can access.

These influences did not follow simple straight-line patterns. The model revealed complex interactions between them that a basic equation would overlook.

This helps clarify why a framework capable of handling complicated, non-linear relationships performed better than conventional statistical methods.

Simpler biochar works

One result challenges a long-standing assumption in the field. Chemically modified biochar – engineered in laboratories to improve performance – has often been viewed as the superior option and presumed benchmark.

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

The model also highlighted an unexpected possibility: biochar may deliver its main benefit not through phosphorus it contains itself, but by changing the behaviour of phosphorus already in the soil.

That alters the calculation. Avoiding chemical treatment lowers costs and reduces environmental impact. Biochars made from crops or wood require less energy to produce than manure-based versions while providing comparable results.

A new tool for farming

Before this research, pairing a particular biochar with a particular field relied largely on trial and error, leaving farmers to bear the cost of every incorrect choice. There was no reliable means of forecasting results before application.

There is now one. Before even a handful is spread, a data-led model can predict whether a particular biochar will release phosphorus for nutrient-hungry crops or retain it to safeguard a watershed.

Peng described the development as a shift in biochar use from guesswork towards data-guided decisions.

For farmers and their advisers, this could mean less fertiliser wasted, fewer nutrients escaping into nearby waters, and a clearer basis for deciding what to put into the soil.

The model is an initial framework, not a completed product, and field conditions will show how well its predictions stand up in practice.

Nevertheless, it directs agriculture towards a future in which an affordable, carbon-rich material created from plant waste is used with something much closer to precision than hope.