Francisco Parra

Copper mine tailings are hazardous environments characterized by high metal bioavailability, acidic pH, and long-term risks to surrounding ecosystems. Although in-situ phytomanagement is increasingly documented, the way contrasting plant ecological strategies shape rhizosphere microbial assembly and translate structural shifts into realized metabolic functions remains poorly resolved. To address this structure-to-function gap, we compared two phylogenetically divergent pioneer trees that spontaneously co-colonized the Cauquenes Cu tailings (Chile): a deciduous angiosperm (willow) and an evergreen gymnosperm (pine). We evaluated their associations with soluble metal pools, plant metal partitioning, and the taxonomic, network, assembly, and functional attributes of soil bacterial communities. Vegetated soils showed a pH increase from ~4 to ~7 and a >300-fold reduction in soluble Cu relative to unvegetated tailings. The two tree strategies were associated with contrasting metal-partitioning pathways: willow favored Cu retention in roots, whereas pine showed stronger Cu and Zn translocation to shoots. Vegetation also restructured bacterial communities, increasing Proteobacteria dominance, enriching Actinobacteria under willow, and promoting more modular, positively associated networks governed by deterministic assembly (βNTI < -2), in contrast to the stochastic patterns of unvegetated soils. This ecological restructuring was coupled to enhanced functional capacity: PICRUSt2 predictions and EcoPlate assays consistently indicated broader substrate use and higher C/N metabolic potential in vegetated soils, particularly under pine. Together, these findings show that, within the same extreme Cu-tailings substrate, contrasting pioneer tree strategies are associated with coordinated divergence in geochemical hazard attenuation, microbial assembly, network topology, and realized community-level metabolism. This integrative signal provides an ecological framework for tracking revegetation-associated recovery trajectories in extreme mine tailings.

Landslides represent one of the main geological hazards, especially in Chile. The main purpose of this study is to evaluate the application of machine learning algorithms (SVM, RF, XGBoost and logistic regression) and compare the results for the modeling of landslide susceptibility in the province of Chañaral, III region, Chile. A total of 86 sites are identified using various sources, in addition to 86 non-landslide sites. This spatial data management and analysis are conducted using QGIS software. The sites are randomly divided, and then a cross-validation process is applied to calculate the accuracy of the models. After that, from 22 conditioning factors, 12 are chosen based on the information gain ratio (IGR). Subsequently, five factors are excluded by the correlation criterion. After this analysis, two indices not previously utilized in the literature, the NDGI (normalized difference glacier index) and EVI (enhanced vegetation index), are employed for the final model. The performance of the models is evaluated through the area under the ROC (receiver operating characteristic) curve (AUC). To study the statistical behavior of the model, the Friedman nonparametric test is performed to compare the performance with the other algorithms and the Nemenyi test for pairwise comparison. Of the algorithms used, RF (AUC = 0.957) and XGBoost (AUC = 0.955) have the highest accuracy values measured in AUC compared to the other models and can be used for the same purpose in other geographic areas with similar characteristics. The findings of this investigation have the potential to assist in land use planning, landslide risk reduction, and informed decision making in the surrounding zones.

Landslides represent one of the main geological hazards, especially in Chile. The main purpose of this study is to evaluate the application of machine learning algorithms (Support vector vachine, Random forest, XGBoost and logistic regression) and compare the results for the modeling of landslides susceptibility in the province of Chañaral, III region, Chile. A total of 86 sites are identified using various sources, plus another 86 sites as non-landslides, which are randomly divided, and then a cross-validation process is applied to calculate the accuracy of the models. After that, from 23 conditioning factors, 12 were chosen based on the information gain ratio (IGR). Subsequently, 5 factors are excluded by the correlation criterion, of which 2 that have not been used in the literature (Normalized difference glacier index, enhanced vegetation index) are used. The performance of the models is evaluated through the area under the ROC curve (AUC). To study the statistical behavior of the model, the Friedman non-parametric test is performed to compare the performance with the other algorithms and the Nemenyi test for pairwise comparison. Of the algorithms used, the RF (AUC = 0.9095) and the SVM (AUC = 0.9089) has the highest accuracy values measured in AUC compared to the other models and can be used for the same purpose in other geographic areas with similar characteristics. The findings of this investigation have the potential to assist in land use planning, landslide risk reduction, and informed decision making in the surrounding zones.