A convolutional neural network for acoustic-based intensity rainfall detection in the Amazon rainforest
Year: 2026
Type: conference-paper
Abstract: Accurate rainfall monitoring is vital for agricultural planning and natural disaster prevention.This study introduces a novel convolutional neural network (CNN) architecture for passive acoustic-based rainfall detection in the infrastructurescarce Amazon rainforest.For the binary wet/dry classification task, both the proposed and baseline architectures achieved metric values of approximately 99.00%, with the proposed model showing 36.14%fewer false alarms.Furthermore, on the multiclass rainfall-intensity task, the proposed CNN outperformed the baseline within the ambiguous moderate precipitation class, raising its recall rate from 48.90% to 60.70%.
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7221873422