3. Producción
Browse
3 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Forecasting Coastal ENSO Warming in the Niño 1+2 Region Using ConvLSTM: Toward Improved Early Warning in Peru and Ecuador(John Wiley and Sons Inc, 2026-08-01)Accurate forecasting of the El Niño-Southern Oscillation (ENSO) is essential for improving regional climate resilience and managing water-related risks. While most deep learning studies have focused on the Niño 3.4 region, the Niño 1+2 region, closely linked to extreme coastal warming associated with ENSO that impacts water infrastructure, flood risk, and agriculture in Peru and Ecuador, remains underexplored. This study develops a spatiotemporal Convolutional Long Short-Term Memory (ConvLSTM) model to forecast sea surface temperature anomalies (SSTA) at lead times of up to 6 months over the tropical Pacific, with evaluation focused on Niño 1+2 and Niño 3.4. The model is trained using monthly ERSSTv5 sea surface temperature (SST) fields spanning 1854–1996 (with validation over 1997–2013 and testing over 2014–2025) and is assessed using field-based verification (pattern correlation and spatial error metrics), regional indices, and probabilistic diagnostics from a Monte Carlo (MC) Dropout ConvLSTM ensemble. Across major warm events (e.g., 1997–1998, 2015–2016, and 2023), the model reproduces the spatial evolution of the warm tongue and provides coherent regional forecasts, with uncertainty increasing with lead time and largest in Niño 1+2. A targeted comparison with operational dynamical forecast models indicates that the ConvLSTM framework can provide complementary guidance in the El Niño 1+2 region, during rapidly evolving coastal conditions, together with uncertainty intervals that contextualize forecast confidence. By enhancing early detection of coastal warming, this regionally focused deep learning approach provides actionable forecasts to inform national early warning systems, support seasonal water resource planning, optimize infrastructure operations, and strengthen disaster preparedness in climate-sensitive regions of coastal South America. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Long-term basin trends confirm a record 2022–2024 hydrological drought and water-storage losses in western Amazonia(Elsevier BV, 2025-12-01)Western Amazonia, including the Peruvian and Ecuadorian Amazon-Andes transition zone, within the contributing basin of the Tamshiyacu hydrological station near the Marañón–Ucayali confluence, contributing ∼16 % of Amazon discharge (32,000 m³ s⁻¹). This study follows a three-part methodology: (i) establishing a long-term historical baseline by evaluating trends in precipitation (1981–2024), runoff (1984–2024), and high-runoff season timing (1984–2024); (ii) characterizing recent rainfall anomalies in the 2022–2024 period; and (iii) diagnosing the 2022–2024 drought's hydrological impacts using standardized indices (SRI) and water storage anomalies. This study first establishes critical long-term (1981–2024) trends, revealing a significant delay in the onset of the high-runoff season (12 days/decade) and a significant decrease in low-flow season discharge (−116.3 m³ s⁻¹ yr⁻¹). This trend analysis provided the necessary historical context, revealing long-term vulnerability that was exacerbated by the 2022–2024 drought, driven by persistent precipitation deficits. The drought's impacts were unprecedented: the drought lasted a record 24 months (SRI-6), TWS anomalies reached their lowest level on record (below −15 cm), and discharge collapsed below 10,000 m³ s⁻¹ by August 2024. These findings underscore the region's growing vulnerability and the urgent need for adaptive water resource management. • The 2022–2024 Amazon drought lasted 24 months, the longest on record. • High-runoff season onset delayed by 12 days per decade from 1984 to 2024. • Terrestrial and groundwater storage showed depletion, worsening water scarcity.4 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Bayesian Calibration of a 2d Hydraulic Model Using a Convolutional Neural Network Emulator(RELX Group (Netherlands), 2025-01-01)6