This study addresses the importance of conducting mass movement susceptibility mapping and hazard assessment using quantitative techniques, including machine learning, in the Northern Lima Commonwealth (NLC). A previous exploration of the topographic variables revealed a high correlation and multicollinearity among some of them, which led to dimensionality reduction through a principal component analysis (PCA). Six susceptibility models were generated using weights of evidence, logistic regression, multilayer perceptron, support vector machine, random forest, and naive Bayes methods to produce quantitative susceptibility maps and assess the hazard associated with two scenarios: the first being El Niño phenomenon and the second being an earthquake exceeding 8.8 Mw. The main findings indicate that machine learning models exhibit excellent predictive performance for the presence and absence of mass movement events, as all models surpassed an AUC value of >0.9, with the random forest model standing out. In terms of hazard levels, in the event of an El Niño phenomenon or an earthquake exceeding 8.8 Mw, approximately 40% and 35% respectively, of the NLC area would be exposed to the highest hazard levels. The importance of integrating methodologies in mass movement susceptibility models is also emphasized; these methodologies include the correlation analysis, multicollinearity assessment, dimensionality reduction of variables, and coupling statistical models with machine learning models to improve the predictive accuracy of machine learning models. The findings of this research are expected to serve as a supportive tool for land managers in formulating effective disaster prevention and risk reduction strategies.

The aim of the study was to evaluate the geochemistry of the Winchos Gabbro and its association with magnetite mineralization at the Winchospunta prospect located in Carhuamayo-Junin, Peru. The methodology included systematic sampling of 24 rock and mineralization samples, petrographic and geochemical laboratory analyses using X-ray diffraction and inductively coupled plasma mass spectrometry (ICP-MS), with emphasis on the mineralogical composition and geochemistry of major elements (Fe₂O₃, SiO₂, MgO), trace elements (V, Cr, Cu), and rare earth elements (LREE and HREE). The results indicated that the Winchos Gabbro contains 12–16% Fe₂O₃, while the Mitu Group volcanics contain 16–23%, in contrast with the massive magnetite in the region, which reaches Fe₂O₃ concentrations between 69% and 87%. These observations suggest a strong genetic connection between the Winchos Gabbro, the Mitu volcanics, and the formation of magnetite, reinforced by the association of trace elements such as V, Cr, and Cu, typical of magmatic and hydrothermal processes. Principal component analysis showed clear groupings, where elements like Cu and U are associated with hydrothermal phases, while Fe and Zn exhibit affinities with metal oxides. These results confirm that the magnetite mineralization in Winchospunta formed under conditions of hydrothermal-magmatic interaction, with differential contributions of elements from the intrusive and volcanic rocks, consolidating its potential as a significant mineral deposit.

This study addresses the importance of conducting mass movement susceptibility mapping and hazard assessment using quantitative techniques, including machine learning, in the Northern Lima Commonwealth (NLC). Previous exploration of the topographic variables revealed high correlation and multicollinearity among some of them, which led to dimensionality reduction through principal component analysis (PCA). Six susceptibility models were generated using weights of evidence, logistic regression, multilayer perceptron, support vector machine, random forest, and naive Bayes methods to produce quantitative susceptibility maps and assess the hazard associated with two scenarios: the first being an El Niño phenomenon and the second being an earthquake exceeding 8.8Mw. The main findings indicate that machine learning models exhibit excellent predictive performance for the presence and absence of mass movement events, as all models surpassed an AUC value of >0.9, with the random forest model standing out. In terms of hazard levels, in the event of an El Niño phenomenon or an earthquake exceeding 8.8Mw, approximately 40% of the NLC area would be exposed to the highest hazard levels. It also highlights the importance of integrating methodologies to reduce model uncertainty, such as comprehensive analysis of variables supported by high quality data and organized workflows. The findings of this research are expected to serve as a supportive tool for land managers in formulating effective disaster prevention and risk reduction strategies.