The team’s central tool was ensemble species distribution modeling, implemented in the widely used biomod2 platform. Rather than relying on a single algorithm, the researchers calibrated multiple machine-learning models against 403 quality-controlled presence records of cacao in the region, each one verified to reduce the errors that plague many mapping exercises. The predictor variables drew on three distinct data streams: bioclimatic layers describing temperature and precipitation regimes, topographic information such as elevation and slope, and edaphic data capturing soil properties. On top of the statistical machinery, the authors applied spatial exclusion criteria that removed biophysically unsuitable zones, legal conservation constraints that protect protected areas, and regulatory filters tied to the European Union Deforestation-Free Products Regulation, known as EUDR, which will increasingly govern whether Peruvian cacao can enter European markets.

The modeling pipeline was deliberately strict about quality. Each candidate algorithm was evaluated under cross-validation, and only models exceeding demanding thresholds were retained: an area under the receiver operating characteristic curve, or AUC, greater than 0.9, and a true skill statistic, or TSS, greater than 0.7. These metrics matter because species distribution models can look impressive while hiding serious weaknesses. AUC above 0.9 indicates near-excellent discrimination between suitable and unsuitable locations, while TSS above 0.7 signals strong agreement between predicted and observed distributions after correcting for the prevalence of the species. Among the individual algorithms, decision tree-based approaches performed best, with Random Forest and XGBoost standing out as the strongest single predictors. Random Forest builds many decision trees on random subsets of the data and averages their votes, while XGBoost builds trees sequentially, each one correcting the errors of the last. Their dominance suggests that the relationships between cacao suitability and environmental gradients are nonlinear and interactive, precisely the kind of structure tree ensembles capture well.

Yet the study’s most consequential finding came not from any single model but from the consensus. When the researchers merged the retained models into an ensemble, the resulting suitability map showed greater spatial stability and overall accuracy than any individual algorithm. This is a recurring lesson in predictive ecology: individual models disagree at the edges of their training data, but a well-constructed consensus dampens those idiosyncrasies. For policymakers, that stability is what transforms a scientific map into a planning instrument. A boundary drawn on a consensus surface is far less likely to shift dramatically when new data arrive than one drawn on a single model’s output.

So where does the chocolate tree want to grow in Amazonas? Under current climatic conditions, approximately 14.8 percent of the regional territory shows high suitability for cacao. That footprint is not spread evenly across the landscape. It concentrates in inter-Andean valleys and in low- to mid-elevation zones, where temperatures remain warm and relatively stable and moisture is adequate through the year. The single most important environmental predictor, according to the model’s variable importance analysis, was thermal seasonality, the degree of variation in temperature across the year. Cacao, a tropical understory species, tolerates little in the way of cold stress or wide temperature swings, so it makes intuitive sense that the steadiness of the thermal regime, more than total rainfall or soil chemistry, defines the crop’s climatic envelope in this part of the Andes-Amazon transition.

Here, however, the study delivers its sharpest and most policy-relevant twist. The 14.8 percent figure describes climatic suitability, but climate is not permission. When the researchers overlaid territorial and regulatory constraints, the effectively available area shrank substantially. Protected conservation areas came off the map, as did zones excluded on biophysical grounds. Most striking was the impact of the EUDR scenario: because the European regulation prohibits products grown on land deforested after a defined cutoff date, large portions of the climatically suitable territory become ineligible for export-oriented cacao under the new rules. The gap between where cacao could grow and where cacao may legally be grown is, in other words, wide, and it is widening as environmental due-diligence requirements harden in major consumer markets.

This regulatory squeeze does not leave the region empty-handed. The analysis identified high-priority degraded areas that emerge as focal opportunities for productive restoration through agroforestry systems. Agroforestry, the practice of growing cacao beneath and alongside native trees, offers a way to rebuild canopy cover, restore ecological function, and produce a marketable crop simultaneously. Because these degraded lands are not subject to the same deforestation concerns as intact forest frontiers, they represent the sweet spot where farmer livelihoods, restoration goals, and EUDR compliance converge. In effect, the study reframes cacao expansion not as a question of finding new land to clear, but of finding old, damaged land to heal.

The third layer of the analysis is the one least often seen in suitability mapping: plant health. The researchers conducted a phytosanitary validation covering 2021 through 2024, comparing the modeled suitability surface against field records of the prevalence and incidence of major cacao pathogens and pests. The result was a high spatial concordance that carries an uncomfortable implication. The areas of greatest climatic suitability for cacao are also the areas where the crop’s worst enemies thrive, particularly the fungi Moniliophthora roreri, the agent of frosty pod rot, and Moniliophthora perniciosa, which causes witches’ broom disease. Both pathogens have devastated cacao production across Latin America for decades, and both flourish under the same warm, humid conditions that cacao itself prefers. The finding confirms that an optimal climatic niche for cultivation is simultaneously an optimal niche for biotic pressure, meaning that any expansion strategy must build disease management, resistant varieties, and integrated pest control into its foundations rather than treating them as afterthoughts.

Taken together, the study offers something rarer than another suitability map: an integrative framework in which climatic modeling, territorial management, and phytosanitary risk are assessed in a single pipeline. The authors position the work as a scientific input for public policy, land-use planning, and sustainable cacao production strategies across the Amazon. The practical chain of reasoning is clear. Climate models identify where the crop can grow; legal and conservation filters identify where it may grow; degraded-area analysis identifies where it should grow; and phytosanitary data identify where it will need the most protection once it does. Each layer disciplines the next, and the final product is a map of opportunity that is honest about its own limits.

For Peru, whose cacao has earned a reputation among fine-flavor chocolate makers, and for tropical agricultural science more broadly, the message is twofold. Ensemble machine-learning models, fed with multisource data and validated against ground truth, can now deliver planning-grade precision at the regional scale. But the era in which suitability could be defined by climate alone is over. Trade regulations written in Brussels, conservation commitments made in Lima, and fungi evolving in Amazonian pods all shape the same map. The future of chocolate in its birthplace will be decided not by where the tree can survive, but by where the full weight of science, law, and biology allows it to flourish.

Subject of Research: Ensemble predictive modeling of climatic, regulatory, and phytosanitary suitability for cacao cultivation in Amazonas, Peru

Article Title: Geospatial suitability of cacao in Amazonas (Peru): An ensemble predictive modeling approach (BIOMOD2) integrating multisource data, territorial management, and plant health

Article References: Zabaleta-Santisteban, J. A., Medina-Medina, A. J., Tuesta-Trauco, K. M., Rivera-Fernandez, A. S., Silva-Melendez, T. B., Grandez-Alberca, M. A., Puscan-Rojas, J., Salas López, R., Oliva-Cruz, M., Cotrina-Sanchez, A., Rojas-Briceño, N. B., Silva-López, J. O., Gómez-Fernández, D., Leiva-Espinoza, S. T., Huaman-Pilco, A. F., & Barboza, E. (2026). Geospatial suitability of cacao in Amazonas (Peru): An ensemble predictive modeling approach (BIOMOD2) integrating multisource data, territorial management, and plant health. PLOS One, 21(10), e0360376. https://doi.org/10.1371/journal.pone.0360376

Image Credits: AI Generated

DOI: 10.1371/journal.pone.0360376

Keywords: cacao, Amazonas, Peru, BIOMOD2, ensemble modeling, species distribution models, EUDR, deforestation, agroforestry, Moniliophthora roreri, witches' broom, land-use planning

The study’s conceptual backbone is Sustainable Supply Chain Management, a research tradition that insists sustainability must be assessed across every tier of a supply network rather than at the level of a single mill or brand. In forest-risk sectors, the authors argue, commercially significant supply chains can look efficient downstream while the bulk of their environmental burden sits upstream, embedded in plantation concessions, drained peatlands, and sourcing geographies that conventional reporting never surfaces. Aggregate indicators such as export value, certification uptake, and legality compliance, they note, provide little guidance for policy targeting because they conceal how downstream commercial performance connects to upstream ecological exposure.

To close that gap, the researchers built their analysis on the SEI-PCS Indonesia wood pulp v3.1 dataset from Trase, a system that links individual mills and trading entities to specific sourcing landscapes through modeled supply allocation. On the economic side they tracked cumulative export volume and free-on-board export value for the three corporate groups that together control approximately 96 percent of Indonesia’s pulp production capacity: Sinar Mas, Royal Golden Eagle (APRIL), and the Japanese trading house Marubeni. On the environmental side they assembled recorded deforestation exposure and concession-related emissions, including emissions from peat subsidence, peat burning, and net land-use change across traced concession portfolios.

The raw numbers alone make clear how concentrated the sector is. Between 2015 and 2022 the three groups exported 37.19 million tonnes of pulp worth 19.69 billion US dollars. Sinar Mas alone accounted for 18.44 million tonnes of exports and 10.30 billion dollars in value, alongside 41,697 hectares of recorded deforestation exposure and roughly 556.7 million tonnes of CO2-equivalent in concession-related emissions. APRIL exported 15.89 million tonnes valued at 7.86 billion dollars, associated with 34,464 hectares of deforestation exposure and 133.9 million tonnes of CO2-equivalent. Marubeni, a much smaller export channel at 2.86 million tonnes, recorded no traceable deforestation exposure or concession-related emissions within the dataset’s analytical boundary, a finding the authors interpret strictly as an absence of recorded exposure rather than proof of zero environmental impact.

Absolute figures, however, can mislead: larger actors will almost always show larger total burdens. The study therefore derives four intensity indicators that normalize recorded environmental burden by export volume and value, allowing actors of very different commercial scale to be compared against a common sectoral benchmark. When emissions are measured per tonne of exported pulp, the divergence between the two dominant groups becomes dramatic. Sinar Mas records 30.19 tonnes of CO2-equivalent per tonne of pulp, well above the sector-wide benchmark of 22.23, while APRIL records just 8.43 tonnes, placing it far below the threshold. A decomposition of the emissions data shows the contrast is driven primarily by peat-related components: Sinar Mas’s traced portfolio includes approximately 373.9 million tonnes of CO2-equivalent from peat subsidence and 189.4 million tonnes from peat burning, compared with 98.2 million and 28.4 million tonnes respectively for APRIL.

Positioning these profiles on a two-axis diagnostic matrix that plots export scale against emissions intensity, the authors assign Sinar Mas to a pronounced trade-off profile, in which high commercial performance coincides with above-threshold environmental intensity. APRIL falls into a comparatively more favorable configuration, combining high export volume with emissions intensity well below the sectoral average. Marubeni occupies a low-impact position constrained by its smaller export contribution. The authors are emphatic that these labels are heuristic screening categories, not statistical rankings, causal classifications, or determinations of regulatory compliance, and their sensitivity analysis shows that while exact quadrant assignments shift under alternative threshold specifications, the relative ordering of the actors remains stable.

The paper’s most consequential conceptual contribution is what the authors call shadow risk: the share of recorded annual deforestation across traced concession portfolios that falls outside the annual wood-pulp deforestation classification used in the SEI-PCS methodology. Of the 359,900 hectares of total recorded annual deforestation across traced portfolios during 2015 to 2022, only 102,765 hectares were classified as annual wood-pulp deforestation, leaving 257,135 hectares, or about 71.45 percent, in the coverage gap. Crucially, the authors stress that shadow risk does not imply illegal activity, concealed misconduct, or unrecorded deforestation, nor does it establish that the unclassified deforestation was caused by pulp production. It identifies, instead, a classification-coverage gap: recorded environmental exposure that current commodity-attribution systems may systematically underrepresent when assessments rely exclusively on direct pulp-linked indicators.

The implications ripple outward in two directions. Domestically, Indonesia’s carbon-governance architecture, now anchored by Presidential Regulation No. 110 of 2025 and the FOLU Net Sink 2030 target of reaching net emissions of minus 140 million tonnes of CO2-equivalent by 2030, demands verifiable links between commercial activity and upstream emissions. The authors position their intensity indicators as an upstream diagnostic support tool that can flag where verification, peatland assessment, and emissions scrutiny may be most warranted, while cautioning that the area-based shadow-risk figure cannot be converted into carbon quantities without spatially intersecting land-cover data, biomass densities, peat maps, fire records, and appropriate emission factors. Internationally, the framework speaks directly to tightening due-diligence regimes such as the European Union Deforestation Regulation, under which corporate groups with higher recorded intensity or large classification gaps may face greater evidentiary burdens in documenting the integrity of their sourcing, even though a trade-off profile demonstrates no violation in itself.

The study is candid about its limits. It rests on one traceability architecture and its modeled allocation of wood supply to mills, rather than physical tracing of individual fibres; community suppliers appear only as province-level aggregates; peat-subsidence estimates rely on standardized emission factors that recent field research suggests may overestimate emissions in some settings; and with only three corporate groups observed, no statistical generalization is possible. Social dimensions of sustainability, from labour conditions to Indigenous land rights, fall outside the operational boundary entirely. The findings are a historical comparative diagnostic for 2015 to 2022, not a real-time audit or a compliance verdict.

Even with those caveats, the research marks a meaningful shift in how forest-risk supply chains can be evaluated. By aggregating traceability data to the corporate-group level, normalizing environmental burden by economic scale, and explicitly quantifying the gap between direct commodity attribution and broader concession-portfolio exposure, the framework converts transparency data into actionable screening metrics. The authors propose extending the approach to palm oil, rubber, soy, timber, and cattle, integrating near-real-time satellite monitoring, and independently validating the shadow-risk estimate against alternative remote-sensing products. If replicated across commodities and countries, the message for regulators, buyers, and investors is clear: the deforestation footprint of a product may be far larger, or structured very differently, than its certified label suggests, and accountability systems that look only at directly linked deforestation are seeing roughly a quarter of the recorded picture.

Subject of Research: Traceability-based environmental burden and shadow-risk assessment of Indonesia's corporate pulp supply chains

Article Title: Traceability-based environmental burden indicators for Indonesia's pulp sector: Corporate-group evidence from forest-risk supply chains

Article References: Butar Butar, M. B., Nasution, S., Parinduri, A. H., & Zaen, M. (2026). Traceability-based environmental burden indicators for Indonesia's pulp sector: Corporate-group evidence from forest-risk supply chains. Environmental and Sustainability Indicators, 32, Article 101526. https://doi.org/10.1016/j.indic.2026.101526

Image Credits: AI Generated

DOI: 10.1016/j.indic.2026.101526

Keywords: Indonesia, pulp industry, deforestation, supply chain traceability, shadow risk, SEI-PCS, peatland emissions, sustainable supply chain management, corporate-group accountability, EUDR, carbon governance, forest-risk commodities