Producción científica

Permanent URI for this communityhttps://cris.pucp.edu.pe/handle/123456789/20173

Browse

Settings

Author: search.filters.author.Ken Takahashi

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Real-time automated quality control of extreme precipitation data from automatic weather stations in Peru using deep learning and geostationary satellite images
    (American Meteorological Society, 2026-08-17)
    Abstract Accurate and timely extreme precipitation data is crucial for effectively predicting and mitigating the impacts of natural phenomena. In Peru, automatic weather stations operated by the National Meteorological and Hydrological Service (SENAMHI) collected approximately 3.5 million precipitation data points between 2020 and 2021. The automated phase of the quality control (QC) system at SENAMHI flagged 4% of the data as suspect due to extreme values, but only 53% of this suspect data was validated in the manual QC phase in a timely fashion, even though 98.8% of these were ultimately classified as correct. To address this, we propose a deep-learning model using satellite images and auxiliary inputs to validate extreme precipitation data more efficiently in real-time, trained with human flags from the manual QC phase. We utilized a CNN-RNN architecture and satellite images to determine whether an extreme precipitation value is correct. The model yields a true positive rate of 95.9% considering the default threshold probability (0.5), so this suspect data could be automatically approved and published with a low false positive (error) rate of 0.329%, which would strongly reduce the workload of the human meteorologists in the manual QC. This could be optimized further by lowering the threshold, increasing the automatic approval rate while keeping the error rate at an acceptable level for SENAMHI. Additionally, an Out-of-Time validation using data for 2023-2024, obtained after the original development and testing, showed a relatively good generalization to new climatological conditions, including the 2023-2024 El Nino, albeit with a somewhat reduced performance, highlighting the need for continuous monitoring and readjusting the model.
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Impacts of the future Amazon deforestation on the precipitation over the Peruvian central Andes and related atmospheric features
    (Elsevier BV, 2026-10-01)
    This study investigates the impact of a 40% Amazon deforestation scenario (projected for 2050) on precipitation over the central Peruvian Andes during five austral summer seasons (DJF 2001–2006) using high-resolution (1 km) WRF simulations. While a widespread rainfall reduction pattern is observed over the Amazon-Andes transition zone, statistically significant decreases ( p < 0.10) at the gridpoint level are primarily concentrated near rainfall hotspots in the Amazon-Andes transitions zone, reaching an average reduction of 12% (−1.4 mm day −1 ). This drying signal is physically associated with a weakening of the South American Low-Level Jet (LLJ) and reduced moisture influx, which specifically inhibits convective activity during the morning peak hours (23–11 LT). In the high-altitude Mantaro Basin, we observe a consistent drying pattern (−5%) that extends from the transition zone; although these changes are not statistically significant due to high interannual variability, the physical signal of precipitation reduction and dry air advection remains clear. Conversely, the western Andean ridges exhibit a localized precipitation increase (up to 20%) linked to intensified cross-barrier easterly wind anomalies reinforcing diurnal anabatic circulation. We further find that while 5 km resolution captures broad basin-scale patterns, convection-permitting scales (1 km) are essential for resolving these complex topographic effects. These findings highlight a critical vulnerability concentrated along the eastern slopes and the high Andes. The identified drying patterns, which are particularly pronounced in the Andes-Amazon transition zone (a global biodiversity hotspot) and extend into the highlands, pose a significant threat to endemic ecosystems and regional water security, specifically through reservoir inflow reduction and negative impacts on agriculture.
      4