Extreme precipitation in the western tropical Andes have significant socio-economic impacts in northern Peru and Ecuador. Previous investigations have shown that high impact episodes were caused by atmospheric moisture flux convergence associated with strong El Niño events in the eastern Pacific Ocean, identifying two patterns: the one emerging during the 1982/1983 and 1997/1998 events, and the one emerging during the 2015/2016 event.In this contribution, we discuss the ability of CMIP6 global climate models to represent these two types of extreme El Niño events, by analyzing the associated atmospheric moisture transport patterns. Based on SST observations, we identified historical extreme El Niño events using the relative Niño34 index, an index recently proposed for addressing ENSO in a warming climate. We also use ERA5 to compare with the moisture flux of CMIP6. We compared 13 CMIP6 models with the historical record (1901-2014). We found the following: (1) six of the models simulated the two extremes El Niño patterns; (2) 62% of the models identify 4.5 extreme El Niño events; and (3) only 27% of the models represent the seasonality of the moisture flux convergence overestimating the moisture flux convergence branch located to the south (4° S) of its normal position (4° N).Our results provide a starting point to investigate the impacts of climate change and its impacts on atmospheric dynamics and associated extreme events at the regional level in tropical South America.
Particulate matter (PM) pollution represents a significant public health concern, in Lima, Peru. This issue is further compound by the lack of accurate forecasting tools due to limited monitoring networks. This study addresses this gap by developing and validating a hybrid model combining a Multilayer Perceptron (MLP) neural network and a type of rule-based Cellular Automata (CA) simulation. This model simulates and forecasts the spatiotemporal dispersion of PM10 and PM2.5. Using a decade of historical PM data (2015-2024) from seven monitoring stations and NASA's meteorological data, an optimized MLP was trained to learn the complex, non-linear transition rules from 47 engineered features. The model demonstrated remarkable performance in historical validation (R2 > 0.90), outperforming standard baseline models. When fed with weather forecast data, the model can operate as an Early Warning System (EWS), providing a reliable prediction horizon to anticipate the exceedance of Air Quality Standards. The resulting hotspot maps accurately identify high-risk areas, confirming the potential of this hybrid model as a robust, proactive, and quantitative tool for air quality management and public health protection in complex urban environments.