Global climate change is contributing to significant water reduction, evident in Lake Titicaca, where water levels have declined markedly in recent years. This study employs ten advanced machine learning algorithms to improve the prediction accuracy of water level behavior in the Lake Titicaca basin. The models utilize year, month, day, precipitation, maximum temperature, and minimum temperature as input variables. Accurate predictions are crucial for informing multidisciplinary planning related to agricultural and livestock production and for developing contingency strategies against droughts and floods. Historical data were sourced from the SENAMHI ENAFER pier station in Puno. Comparative evaluation indicates that the Gradient Boosting Regressor algorithm achieves superior performance based on multiple metrics: MAE = 0.00035279, MSE = 0.00000247, RMSE = 0.0015725, Coefficient of Determination R² = 0.99999706, and Cross-Validation (average RMSE = 0.00199047). This research underscores the potential of machine learning algorithms in hydrology, offering valuable insights applicable to basin modeling worldwide.

Digital education access encounters considerable obstacles in Peru, where technological, social, and geographical issues restrict internet connectivity and educational prospects. The World Bank reports that Peru ranks poorly compared to other Latin American nations in terms of internet bandwidth. In remote areas, children may trek up to three hours to reach in-person classes, while in urban centers like Puno and Juliaca, universities have provided subsidized internet access for students during COVID-19 due to families' limited financial means. This study explores the pandemic's impact on poverty and educational internet access in Peru. Our research indicates that schoolteachers exhibit low levels of ICT competency, yet the Ministry of Education does not offer evaluation or training programs for technology integration. We analyze a case study of an Andean school and assess state initiatives aimed at enhancing internet connectivity infrastructure. The results underscore the ongoing digital divide that hampers educational equity in Peru.

High-altitude lakes are increasingly exposed to nutrient enrichment, organic loading and wastewater-derived contamination, while predictive performance can be overstated when temporally ordered observations are randomly partitioned or target-defining measurements are reused as predictors. We analyzed 177 consecutive monthly water-quality records from the Inner Bay of Lake Titicaca, Peru (January 2011–September 2025), integrating Carlson’s composite trophic state index (CTSI), Hamed–Rao modified Mann–Kendall tests, block-bootstrap Sen slopes, Pettitt change point detection with 12-month block permutation, nutrient stoichiometry, correlation, principal component analysis, leakage-aware contemporaneous classification and one-month-ahead forecasting. Total phosphorus was treated as elemental P and phosphate as PO₄. The bay remained chronically hypereutrophic (mean CTSI 74.08 ± 4.07; 83.1% of months). BOD₅ increased by 0.547 mg L⁻¹ yr⁻¹, chlorophyll-a by 3.254 mg m⁻³ yr⁻¹, total suspended solids by 0.752 mg L⁻¹ yr⁻¹ and conductivity by 13.13 µS cm⁻¹ yr⁻¹, whereas total phosphorus declined by 0.085 mg P L⁻¹ yr⁻¹. Block-supported shifts occurred in chlorophyll-a in November 2016 (21.81 to 54.18 mg m⁻³) and BOD₅ in June 2018 (6.54 to 11.77 mg L⁻¹). After removing target-defining variables and preserving temporal order, the best trophic-state classifier had balanced accuracy 0.575 and MCC 0.257. Organic pollution classification had a balanced accuracy of 0.624 but a sensitivity of only 0.271, whereas the fecal-indicator model was unstable (MCC 0.130; ROC-AUC 0.460). Persistence was the best BOD₅ forecast (RMSE 4.193 mg L⁻¹; R² 0.390). The best CTSI model explained only 4.8% of future variance, and all thermotolerant coliform forecasts had negative out-of-time R². Persistent ecological degradation was therefore evident, but monthly observations alone were insufficient for deployment-ready early warning. Higher-frequency sensing, hydrometeorological and wastewater load covariates, spatial replication, direct microbiological measurements and prospective validation are required.

High-altitude lakes are increasingly exposed to nutrient enrichment, organic loading and wastewater-derived contamination, while predictive performance can be overstated when temporally ordered observations are randomly partitioned or target-defining measurements are reused as predictors. We analyzed 177 consecutive monthly water-quality records from the Inner Bay of Lake Titicaca, Peru (January 2011–September 2025), integrating Carlson’s composite trophic state index (CTSI), Hamed–Rao modified Mann–Kendall tests, block-bootstrap Sen slopes, Pettitt change-point detection with 12-month block permutation, nutrient stoichiometry, correlation, principal component analysis, leakage-aware contemporaneous classification and one-month-ahead forecasting. Total phosphorus was treated as elemental P and phosphate as PO4. The bay remained chronically hypereutrophic (mean CTSI 74.08 ± 4.07; 83.1% of months). BOD5 increased by 0.548 mg L⁻¹ yr⁻¹, chlorophyll a by 3.254 mg m⁻³ yr⁻¹, total suspended solids by 0.752 mg L⁻¹ yr⁻¹ and conductivity by 13.13 µS cm⁻¹ yr⁻¹, whereas total phosphorus declined by 0.085 mg P L⁻¹ yr⁻¹. Block-supported shifts occurred in chlorophyll-a in November 2016 (21.81 to 54.18 mg m⁻³) and BOD5 in June 2018 (6.54 to 11.77 mg L⁻¹). After removing target-defining variables and preserving temporal order, the best trophic-state classifier had balanced accuracy 0.575 and MCC 0.257. Organic-pollution classification had balanced accuracy 0.624 but sensitivity only 0.271, whereas the fecal-indicator model was unstable (MCC 0.130; ROC-AUC 0.460). Persistence was the best BOD5 forecast (RMSE 4.193 mg L⁻¹; R² 0.390). The best CTSI model explained only 4.8% of future variance, and all thermotolerant-coliform forecasts had negative out-of-time R². Persistent ecological degradation was therefore evident, but monthly observations alone were insufficient for deployment-ready early warning. Higher-frequency sensing, hydrometeorological and wastewater-load covariates, spatial replication, direct microbiological measurements and prospective validation are required.

This study presents an innovative pedagogical approach to cybersecurity education through the development of an interactive malware propagation simulation. The system integrates a hybrid detection model, combining SHA-256 signature analysis, a proprietary heuristic engine, and file verification using the WinTrust API, in addition to system-level monitoring through Microsoft Defender’s command-line interface. Its main contribution lies in a dynamic visualization module that represents malware propagation in a virtual network of nodes, displaying states such as healthy, infected, or immune through color-coded graphics. This interactive component allows real-time observation and experimentation with infection dynamics, effectively bridging theory and practice. Tests demonstrated its ability to identify suspicious files and simulate various propagation scenarios, validating its potential as an educational resource in cybersecurity.

This research introduces a method to help improve quinoa farming in Puno Perú area by blending programming and machine learning methods to tackle issues faced in today’s global agricultural markets efficiently and effectively using information from a span of 26 years. Through our work and study details over these years we formulated a model that balances maximizing profits while handling market fluctuations effectively and efficiently Our results highlighted that market prices for quinoa are heavily impacted by market dynamics rather, than local production conditions (correlation coefficient; 0.147; significance level; p > 0.05).The understanding influenced the linear approach that determined the best prices for selling and break even points effectively surpass traditional techniques by utilizing machine learning models while ensemble approaches showed better performance outcomes surpass the average methods used in the industry. Moreover, reactionary models identified changes in market trends accurately while long short-term memory networks forecasted price fluctuation tendencies.