Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0926
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-08-30T06:05:58.387326Z
status: published
lens: g_space
sector: climate
headline: Quantitative decoupling of source-pathway-receptor driving mechanisms for integrated soil risk via interpretable machine learning
dek: Most existing concentration-based risk assessments of potentially toxic elements (PTEs) in farmland soils tend to overlook source-specific transport pathways and receptor-related risks. In this study, an integrated risk index-machine learning framework based on the source-pathway-receptor concept is developed to comprehensively evaluate PTE risks in a typical mining city. The framework integrates the improved Nemerow index (INI), potential ecological risk index, Monte Carlo simulation-based health risk assessmen…
gain_title: An integrated source-pathway-receptor framework using XGBoost and SHAP improved differentiation of industrial versus agricultural PTE risks in farmland soils and supported targeted zoned control to avoid excessive remediation.
problem_title: (none)
trace_subject: (none)
gain_reading: An integrated source-pathway-receptor framework using XGBoost and SHAP improved differentiation of industrial versus agricultural PTE risks in farmland soils and supported targeted zoned control to avoid excessive remediation.
gain_evidence: may help avoid excessive remediation in low-risk areas while ensuring sufficient control in high-risk areas
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built an integrated risk index-machine learning framework based on source-pathway-receptor concepts to evaluate potentially toxic elements in farmland soils of a mining city, combining improved Nemerow index, potential ecological risk index, Monte Carlo health risk assessment, and XGBoost regression with SHAP interpretation.

The work matters because it moves beyond concentration-based assessment to source-specific pathways and receptor vulnerability, showing distinct industrial and agricultural risk mechanisms and enabling zoned control; uncertainty remains because validation was internal only and the findings are tied to one mining city context as of the August 2026 publication date.
limitation: Predictive performance was evaluated only under internal 8:2 training-testing validation without reported external validation in other regions or time periods.
tag: Evidence-backed gain
key_points: Study developed source-pathway-receptor framework integrating INI, ecological risk index, Monte Carlo health risk assessment, and machine learning in a typical mining city. | Industrial sources showed higher INI values than agricultural sources and were linked to atmospheric deposition and surface runoff pathways. | Receptor assessment found children highly vulnerable to industrial PTEs with chromium as dominant contributor to carcinogenic risk. | Agricultural risks attributed to internal receptors (26.80%) and irrigation, fertilizers and animal manure (23.20%), with dietary exposure via oilseed rape exceeding acceptable thresholds.
rundown: The authors applied the framework in a typical mining city, finding industrial sources had higher INI values than agricultural sources and were predominantly associated with atmospheric deposition and surface runoff, while agricultural zones were driven by internal receptors and inputs from irrigation, fertilizers and animal manure.

Health risk results showed children were highly vulnerable to industrial PTEs with chromium as the dominant carcinogenic contributor, and among crops oilseed rape demonstrated the highest potential health risks with carcinogenic and non-carcinogenic risks exceeding acceptable thresholds, while SHAP analysis revealed different dominant factors governing the two risk types.
sources:
- peer_reviewed | Environmental Pollution | https://doi.org/10.1016/j.envpol.2026.129052 | 2026-08-26
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

b41aadfdebf2687aed369de1e59c58f6cc176fb8daa42499a3450b2e2baa6527

previous

0000000000000000000000000000000000000000000000000000000000000000