In this work, a novel model for hourly PM2.5 time series imputation is proposed for the estimation of missing values in different gap sizes, including 1, 3, 6, 12, and 24 h. The proposed model is based on statistical techniques such as moving averages, linear interpolation smoothing, and linear interpolation. For the experimentation stage, two datasets were selected in Ilo City in southern Peru. Also, five benchmark models were implemented to compare the proposed model results; the benchmark models include exponential weighted moving average (EWMA), autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU). The results show that, in terms of average MAPEs, the proposed model outperforms the best deep learning model (GRU) between 26.61% and 90.69%, and the best statistical model (ARIMA) between 2.33% and 6.67%. So, the proposed model is a good alternative for the estimation of missing values in PM2.5 time series.

Soil organic carbon (SOC) is a crucial component of the planet and is essential for agriculture development. Our region is known for its livestock and agricultural activities. Hence, understanding the spatial distribution of SOC is crucial for sustainable land management of soils in the mountain ecosystems in the Andes. The methodology consisted of obtaining 53 soil samples from depths of 0 to 105 cm, which were analyzed to obtain SOC (Kg/m²) and organic matter (OM) (%). Ordinary kriging, a geostatistical method, was used to determine SOC. Pearson’s statistical method was applied to determine the association between SOC and precipitation, temperature, altitude, and organic matter and gave acceptable correlations of 0.38, −0.32, 0.40, and 0.59. These results were used to apply weighting criteria for climatological and environmental variables. The weighted overlay tool was used for modeling and mapping the spatial variability of SOC. The estimated spatial distribution of SOC in the micro-watershed reveals an increasing trend from south to north, specifically within the 0–20 cm depth profile. The study confirmed through the spatial analysis that regions with intensive agriculture have low reserves (<3 Kg/m²) of SOC, and areas without agricultural activity but with grazing have average resources of 3 Kg/m² to 5 Kg/m² of SOC. Finally, in the upper micro-watersheds where there is no agricultural activity, the reserves are high (5 Kg/m² to 6.8 Kg/m²). Accordingly, we can promote sustainable and responsible land use practices that support long-term productivity, environmental protection, and societal well-being by prioritizing efficient land utilization, soil conservation, biodiversity conservation, land restoration, and informed land use planning in the high Andean ecosystem of Puno–Peru.

The retreats of the planet’s tropical glaciers are natural indicators of the variation of precipitation, temperature, and other variables. The glaciers of the Alto Santa sub-basin are sources of freshwater storage for consumptive and non-consumptive use for different sectors. As a result of climatic variations, it is essential to analyze the dynamics of the snow cover area (SCA). The methodology consisted of processing 6578 MODIS Snow Cover MOD10A1 product images and generating 18-year time series using the Platform Google Earth Engine (GEE). Normalized Difference Snow Index (NDSI) was used to estimate the extent of snow cover, and to validate the MODIS snow cover product, we used the same overlapping date of Landsat 5 and 8 Surface Reflectance Tier 1, to examine the relationships between daily precipitation and temperature. The standardized correlation results gave good results with stations over 4500 m.a.s.l., such as Artesonraju AP2 (4828 m.a.s.l.) of −0.84 and −0.74, precipitation, and temperature. These results show coherent behaviors of the retreat due to the variation of the climatological variables. In some years, there were anomalies in the conduct of the three variables, but these originated from events of natural weather phenomena. Regarding the dynamics of the SCA in 18 years, it decreased from 649 km² to 311.6. km² between 2000 and 2017, representing a retreat of 41%; we can conclude and confirm that the glacier retreat is imminent due to the consequences of climate change, which would affect the security of freshwater from the tropical glaciers of the Peruvian Andes.

Monitoring PM2.5 in mining areas is essential for air quality management; however, most studies focus on single-step forecasts, limiting timely decision making. This work addresses the need for accurate multi-step PM2.5 prediction to support proactive pollution control in mining regions. So, a new model for multi-step PM2.5 time series forecasting is proposed, which is based on historical data such as the last day observed (LDO), retrieved data by correlation levels, and linear interpolation. As case studies, data from three environmental monitoring stations in mining areas of Peru were considered: Tala station near the Cuajone mine, Uchumayo near the Cerro Verde mine, and Espinar near the Tintaya mine. The proposed model was compared with benchmark models, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (BiGRU). The results show that the proposed model achieves results similar to those obtained by the benchmark models. The main advantages of the proposed model over the benchmark models lie in the amount of data required for predictions and the training time, which represents less than 0.2% of that required by deep learning-based models.

This article presents an innovative procedure that combines advanced quality control (QC) methods with machine learning (ML) techniques to produce reliable, continuous, high-resolution meteorological data. The approach was applied to hourly air temperature records from six automatic weather stations located around Lake Titicaca in the Altiplano region of South America. The raw dataset contained time gaps, inconsistencies, and outliers. To address these, the QC stage employed Interquartile Range, Biweight, and Local Outlier Factor (LOF) statistics, resulting in a clean dataset. Two gap-filling methods were implemented: a spatial approach using time series from nearby stations and a temporal approach based on each station’s time series and selected variables from the ERA5-Land reanalysis. Several ML models were also employed in this process: Random Forest (RF), Support Vector Machine (SVM), Stacking (STACK), and AdaBoost (ADA). Model performance was evaluated on a validation subset (30% of station data). The RF model achieved the best results, with R² values up to 0.9 and Root Mean Square Error (RMSE) below 1.5 °C. The spatial approach performed best when stations were strongly correlated, while the temporal approach was more suitable for locations with low inter-station correlation and high local variability. Overall, the procedure substantially improved data reliability and completeness, and it can be extended to other meteorological variables.

This study investigates the application of several machine learning models using PyCaret to forecast the monthly demand for electricity consumption; we analyze historical data of monthly consumption readings for the Cuajone Mining Unit of the company Minera Southern Peru Copper Corporation, recorded in the electricity yearbooks from the decentralized office of the Ministry of Energy and Mines in the Moquegua region between 2008 and 2018. We evaluated the performance of 27 machine learning models available in PyCaret for the forecast of monthly electricity consumption, selecting the three most effective models: Exponential Smoothing, AdaBoost with Conditional Deseasonalize and Detrending and ETS (Error-Trend-Seasonality). We evaluated the performance of these models using eight metrics: MASE, RMSSE, MAE, RMSE, MAPE, SMAPE, R2, and calculation time. Among the analyzed models, Exponential Smoothing demonstrated the best performance with a MASE of 0.8359, an MAE of 4012.24 and an RMSE of 5922.63; among the analyzed models, Exponential Smoothing demonstrated the best performance with a MASE of 0.8359, an MAE of 4012.24 and a RMSE of 5922.63, followed by AdaBoost with Conditional Deseasonalize and Detrending, while ETS also provided competitive results. Forecasts for 2018 were compared with actual data, confirming the high accuracy of these models. These findings provide a robust energy management and planning framework, highlighting the potential of machine learning methodologies to optimize electricity consumption forecasting.