Since Tacna is a hyper-arid region, greywater is a potential alternative water source. This study aimed to quantify and characterize greywater in a university building with 732 students, as well as assess their perception of greywater reuse. Water meters were used to calculate greywater quantity. To assess untreated greywater quality, physical–chemical and microbiological parameters were analyzed. Questionnaires were used to measure students’ acceptance regarding greywater reuse using a Likert scale. The greywater quantity recorded in this study was 426.85 L/d, which is less than reported in previous global research. The greywater quality showed relatively low values regarding physical–chemical parameters; however, microbial contamination was higher compared to international permissible limits for wastewater reuse. Furthermore, it was found that the generated greywater has little biodegradability (0.38). Students disclosed a lower acceptance of reusing untreated greywater compared to a 77.05% acceptance of reusing treated greywater for green areas. According to the greywater characterization, biological treatment will not be enough to ensure environmental protection and user health; thus, physical–chemical treatment will also be needed. The produced greywater quantities would generate a 12.67% water saving if used for toilet flushing. The greywater volume fulfills the whole demand for watering green areas or green roofs. Students would assent to the reuse of treated greywater.

Agricultural drought represents a critical threat to water-dependent economies in arid Andean regions; however, forecasting tools tailored to data-scarce, high-altitude basins remain limited. This study developed and evaluated a multi-model spatiotemporal framework for agricultural drought forecasting in Candarave, in the northern Atacama Desert; we forecast the 3-month Standardized Precipitation–Evapotranspiration Index (SPEI-3) one month ahead (lead time t + 1) for an agricultural, data-scarce Andean basin. Seven modeling approaches were compared: three machine learning baselines (XGBoost, Random Forest, and Elastic Net), two statistical time-series models (ARIMA and ARIMAX), and two deep learning architectures (CNN-LSTM and ConvRNN). A driver analysis based on Elastic-Net coefficients identified spatiotemporal persistence (SPEI_neighbor, SPEI_lag1), precipitation, maximum temperature, and the Coastal El Niño Index (ICEN) as the dominant drought predictors. ARIMAX achieved the best overall performance (RMSE = 0.377; R² = 0.909; NSE = 0.909; KGE = 0.889), demonstrating that incorporating exogenous climatic drivers substantially enhances forecasting skill. Among machine learning baselines, Elastic Net outperformed tree-based models (KGE = 0.924). Deep learning models revealed the weakest performance, with very low R² values, attributed to insufficient training data, overparameterization, and the predominantly linear and persistence-driven nature of drought dynamics in Candarave. Under an operationally realistic configuration (all predictors lagged to forecast time), the approach provides a useful decision-support tool for one-month-ahead agricultural drought early warning, rather than a turnkey operational system.