The research, conducted by Peter Coaguila-Rodriguez and Alberto Franco Cerna-Cueva of the Universidad Nacional Agraria de la Selva in Tingo María, Huánuco, set out to answer a deceptively simple question: can ordinary soil chemistry measurements predict which samples will show aluminium saturation at or above 20 percent, a threshold commonly associated with high or very high toxicity risk? To do so, the team turned to an anonymized institutional soil-monitoring database containing 1,842 records from cacao-growing areas of the central Peruvian Amazon. After filtering for acidity, 1,539 samples with pH below 5.5 formed the analytical cohort, a substantial dataset for a region where such comprehensive soil records are rare.

Aluminium saturation is defined as the proportion of the soil’s exchangeable cation exchange capacity occupied by aluminium rather than by base cations such as calcium, magnesium and potassium. As soils acidify, base cations are leached away and aluminium increasingly dominates the exchange complex, which is why the metric serves as a direct chemical indicator of the intensity of acid-soil stress a plant will experience. Cacao, a crop native to the upper Amazon and economically vital to Peru, is known from prior ecophysiological work to be sensitive to soil acidity, with juvenile plants showing impaired growth and altered nutrition under acidic conditions. Yet the full exchangeable-acidity analysis needed to compute saturation requires titration procedures that many regional laboratories do not routinely offer, whereas pH, organic matter and exchangeable bases are standard fare.

The researchers built six logistic-regression models, comparing predictors drawn from routine soil tests against covariates derived from two publicly available gridded data products: PISCOp, Peru’s high-resolution interpolated rainfall dataset, and SoilGrids, a global digital soil mapping product. The outcome variable in every case was the laboratory-reported aluminium saturation value, dichotomized at the 20 percent threshold. Logistic regression, a workhorse of applied statistics, estimates the probability of a binary outcome as a function of predictor variables, making it well suited to a screening task where the goal is to flag samples for follow-up rather than to measure toxicity directly.

What distinguishes the study methodologically is the rigor of its validation design. All preprocessing steps and the selection of the decision threshold were nested inside a fivefold grouped cross-validation scheme, meaning that the data transformations and cutoff choices were re-learned within each training fold rather than tuned on the full dataset. The grouping was based on surrogate environmental signatures, a strategy designed to prevent information leakage between samples drawn from similar environments, a well-known pitfall in spatially structured ecological and soil data. This kind of careful cross-validation is essential when records may cluster by farm, soil type or microregion, because otherwise a model can appear far more accurate than it truly is when deployed on genuinely new locations.

The performance of the simplest model, built entirely from routine soil test variables, was striking. Across pooled cross-validation folds it achieved a balanced accuracy of 0.876, with a fold-level standard deviation of 0.022 and a group-bootstrap 95 percent confidence interval of 0.856 to 0.896. Balanced accuracy, the average of sensitivity and specificity, is a robust metric when the two outcome classes are unevenly represented. The model’s sensitivity, its ability to correctly flag samples that truly exceed the 20 percent threshold, was 0.868, while its specificity, the ability to correctly clear samples below the threshold, was 0.885. Perhaps most importantly for a screening application, the positive predictive value reached 0.952, meaning that when the model flags a sample as high-risk, that flag is very likely to be confirmed by the full laboratory determination.

Additional metrics reinforced the picture of a well-calibrated classifier. The area under the receiver-operating-characteristic curve, which summarizes discrimination across all possible thresholds, was 0.936, and the area under the precision-recall curve, often more informative when positive cases are the minority, was 0.968. The Brier score, a measure combining discrimination and calibration that penalizes both wrong predictions and misplaced confidence, came in at 0.082, with lower values indicating better overall probabilistic accuracy. Together these figures indicate that routine soil chemistry carries a strong, quantifiable signal about aluminium saturation, enough to triage samples with a high degree of confidence before committing resources to confirmatory analysis.

Just as revealing is what the study found when it added the gridded environmental covariates. Relative to the routine model, the difference in balanced accuracy was 0.000, with a 95 percent confidence interval of −0.010 to 0.010, when PISCOp rainfall covariates were included, and −0.007, with an interval of −0.020 to 0.005, when PISCOp and SoilGrids were combined. In other words, the authors found no evidence of a stable improvement from the remotely sensed and interpolated data layers within the spatial support available. This is a noteworthy result in a field where digital soil mapping and machine learning covariates are frequently promoted as enhancements to local prediction, and it suggests that for this specific screening task, at this spatial resolution, the chemistry already measured in routine tests contains most of the relevant information.

The authors are careful to delineate what the model can and cannot do, and these caveats matter for anyone hoping to apply it. The tool is intended to prioritize confirmatory aluminium-saturation analysis in comparable acidic cacao soils, not to measure plant toxicity directly, not to replace laboratory diagnosis and not to support continuous zoning or mapping of unsampled areas. Aluminium saturation in a soil sample is a chemical property, not a biological endpoint, and actual toxicity to a given cacao genotype depends on root architecture, cultivar-specific tolerance mechanisms and management history. The model’s value lies in triage: laboratories and extension services with limited budgets can use routine test results to decide which samples genuinely need the more elaborate exchangeable-acidity workup, concentrating scarce analytical capacity where it is most likely to change management decisions.

The practical implications extend across the tropical cacao belt, where acid soils cover vast areas and liming decisions hinge on knowing where aluminium stress is severe. Acid soils are estimated to occupy a large share of the world’s potentially arable land, and aluminium toxicity is among the principal chemical constraints on crop production in these regions. A screening approach that leverages data already flowing through regional monitoring programs could accelerate the identification of high-risk fields without new instrumentation or new sampling campaigns. The study’s data and code are available from the corresponding authors upon reasonable request, subject to the confidentiality restrictions of the institutional monitoring database, and the work received no external funding. For the farmers of the central Peruvian Amazon, and potentially for cacao producers far beyond it, the message is quietly transformative: the answers to one of tropical agriculture’s most stubborn soil problems may already be sitting in the routine test reports that laboratories produce every day.

Subject of Research: Predictive screening of high aluminium saturation in acidic cacao soils of the Peruvian Amazon using routine soil test data and logistic regression

Article Title: Routine soil tests support screening of high aluminium saturation in acidic cacao soils

Article References: Coaguila-Rodriguez, P., & Cerna-Cueva, A. F. (2026). Routine soil tests support screening of high aluminium saturation in acidic cacao soils. Environmental Monitoring and Assessment, 198(10), Article 1105. https://doi.org/10.1007/s10661-026-15945-3

Image Credits: AI Generated

DOI: 10.1007/s10661-026-15945-3

Keywords: soil acidity, aluminium saturation, Theobroma cacao, Peruvian Amazon, logistic regression, soil screening, cross-validation, digital soil mapping, SoilGrids, PISCOp, environmental monitoring, soil chemistry

The study was conducted at the Tayan concession of PT ANTAM Tbk’s Bauxite Mining Business Unit in Sanggau Regency, a landscape of rolling hills that receives between 3,000 and 4,000 millimetres of rain each year and sits under a near-constant temperature of about 27 degrees Celsius. The soils there are highly weathered Ultisols and Oxisols, naturally acidic and poor in nutrients, with high levels of exchangeable aluminium that can stunt plant roots. Bauxite mining strips away the topsoil, dismantles nutrient cycles and compacts or reshapes the remaining substrate, leaving a surface that is hostile to natural regeneration. Indonesia ranked fifth among the world’s bauxite producers in 2022, when roughly 380 million dry metric tons were mined globally, and demand for aluminium in electric vehicles and renewable energy infrastructure is only expected to intensify the pressure on such landscapes.

What makes the Tayan site scientifically valuable is its unusually continuous record of restoration. The company established reclamation blocks in eight consecutive planting years, from 2015 to 2022, all under a single reclamation programme involving land contouring, topsoil redistribution and revegetation with a mix of local and fast-growing species such as Acacia mangium, Gliricidia sepium, Paraserianthes falcataria, mahogany and Shorea species. Each block carries an information board documenting the planting year, area, coordinates, tree count and species, allowing researchers to verify the age of every site against company records rather than guess at it. That arrangement permitted a chronosequence design: instead of monitoring a single site for decades, the team sampled sites of different ages simultaneously and read the recovery trajectory across space as a proxy for time.

Between 24 and 26 January 2025, the researchers collected 27 composite soil samples — three observation points per planting year, plus three from an adjacent unmined natural forest block on the same soil type that served as the reference ecosystem. At each point, five sub-samples were taken along a diagonal pattern with roughly 25-metre spacing, composited into a single kilogram of soil drawn from the 0–30 centimetre rooting zone. Vegetation was assessed in twelve nested plots using a four-stage design covering trees, poles, saplings and seedlings, with stem diameters measured at breast height. Soil samples travelled to the Soil Chemistry and Fertility Laboratory at Tanjungpura University within 24 hours, where pH, organic carbon, nitrogen, phosphorus, cation exchange capacity, base saturation and aluminium saturation were measured using standard analytical procedures.

The results revealed a striking asymmetry in recovery. Vegetation structure rebounded quickly: pole and tree density climbed from 175 individuals per hectare in the youngest sites to 1,569 per hectare in the oldest, about 54.6 percent of the reference forest’s 2,875. Mean stem diameter grew from 5.5 to 13.7 centimetres, reaching 80.1 percent of the reference value of 17.1 centimetres. Both measures differed significantly among age classes in the statistical analysis. Species richness, however, told another story, rising only from 5.5 to 7.8 species per plot — just 43.1 percent of the natural forest’s 18 species — a gap that failed to reach statistical significance but remained biologically sobering. Fast-growing planted pioneers had built the skeleton of a forest without rebuilding its diversity.

Soil chemistry followed its own divergent paths. Organic carbon accumulated at an estimated 0.146 percent per year, reaching 1.72 percent in the oldest sites — a meaningful gain, but only 61.1 percent of the reference forest’s 2.82 percent. Available phosphorus showed the strongest temporal trend of any parameter measured, rising 0.802 milligrams per kilogram annually to reach 74.3 percent of the reference value. Total nitrogen and cation exchange capacity showed no significant differences across the chronosequence. Most telling was the chemistry of acidity: soil pH declined steadily from 5.28 in young sites to 4.96 in old ones, at about 0.070 units per year, while aluminium saturation climbed in parallel from 10.4 to 19.9 percent. Rather than exceeding natural levels, the reclaimed soils were simply converging back toward the naturally acidic baseline of the reference forest as the initial liming and amelioration effects faded.

That re-acidification matters because aluminium, abundant in these highly weathered soils, becomes increasingly soluble and toxic as pH drops, constraining root development, nutrient uptake and the recruitment of late-successional native species. The researchers found that available phosphorus was strongly correlated with mean stem diameter (r = 0.90) and with pole and tree density (r = 0.79), linking nutrient availability directly to structural recovery. Yet organic carbon varied enormously among blocks of the same age — from 0.11 to 1.05 percent at three years and from 1.59 to 2.86 percent at four years — suggesting that differences in how the reclamation was executed, particularly the thickness and evenness of redistributed topsoil, mattered as much as elapsed time itself. The chronosequence assumption that all sites started from comparable conditions, the authors acknowledge, can only be partially verified.

The study also exposes a gap in how Indonesia evaluates reclamation. Under Ministerial Regulation No. 7 of 2014, implemented through Regulation No. 26 of 2018 and the assessment matrices of Decree No. 1827 K/30/MEM/2018, reclamation is scored on land management, revegetation and final completion, using indicators such as plant survival, cover crop establishment and canopy closure. No criterion addresses soil chemical stability, and none goes beyond a generic requirement to plant local species. On the strength of such criteria, the Tayan sites would look like a success. The integrated analysis suggests they are only partially one: total nitrogen had reached just 69 percent of reference conditions, and Shannon–Wiener diversity values in the reclamation plots hovered at low to moderate levels across all vegetation layers compared with the reference forest.

The implications stretch well beyond a single concession. Bauxite mining occupies a share of the estimated 57,277 square kilometres of land disturbed by mining worldwide across 102 countries, and tropical bauxite regions with acidic, highly weathered soils may follow recovery trajectories fundamentally different from natural forest development. The authors argue that reclamation monitoring should incorporate soil organic carbon, aluminium saturation and species richness alongside conventional vegetation metrics, and that restoration programmes should move beyond canopy targets toward enrichment planting with native late-successional species, improved habitat connectivity and periodic soil amelioration. Success, they suggest, should be judged not only by similarity to the pre-disturbance forest but by whether the reclaimed ecosystem achieves long-term functionality, stability and resistance to degradation.

The findings come with caveats: the natural forest vegetation reference rested on a single plot, three observation points per planting year limited statistical power, and the study covers only the first decade of recovery. Whether rising aluminium saturation will eventually constrain ecosystem stability, and whether biodiversity continues to accumulate beyond year ten, remain open questions. Future work should extend to microbial communities, soil fauna, hydrological function and ecosystem services. But the central lesson is already clear and transferable to mining regions across the tropics: a young forest can wear the appearance of recovery long before the ground beneath it has healed, and only integrated, long-term monitoring of soil and vegetation together can tell the difference.

Subject of Research: Ecosystem recovery trajectories and reclamation effectiveness following tropical bauxite mining in West Kalimantan, Indonesia

Article Title: Evaluating reclamation effectiveness and ecosystem recovery trajectories following tropical bauxite mining in Indonesia

Article References: Suryadi, U. E., Sulakhudin, & Surachman (2026). Evaluating reclamation effectiveness and ecosystem recovery trajectories following tropical bauxite mining in Indonesia. Environmental Challenges, 25, Article 101647. https://doi.org/10.1016/j.envc.2026.101647

Image Credits: AI Generated

DOI: 10.1016/j.envc.2026.101647

Keywords: bauxite mining, Indonesia, West Kalimantan, ecosystem recovery, reclamation, soil acidity, aluminium saturation, chronosequence, tropical forest restoration, species richness, soil organic carbon, mine closure