A long short-term memory model for sub-hourly temporal disaggregation of precipitation

Download

• Paper (Open Access)

Abstract

High-resolution precipitation data is crucial for modern hydrological and building hygrothermal performance simulation models. In Australia, historical observations are inadequate, as half-hourly recordings only replaced daily observations at many stations from the early 2000s. Moreover, existing machine learning approaches are limited to generating hourly time series data. This paper presents a recurrent neural network using long short-term memory to disaggregate daily precipitation observations into half-hourly intervals. The model leverages temporal dependencies and hourly weather measurements. Our results, based on stations across five Australian climate zones, demonstrate that the model effectively preserves key half-hourly precipitation statistics, including variance and the quantity and distribution of wet half-hours. When aggregated to hourly intervals, our model outperforms other models in most measured metrics.

Citation

Oates, Harrison, Nayan Arora, Hong Gic Oh, and Trevor Lee. “A Long Short-Term Memory Model for Sub-Hourly Temporal Disaggregation of Precipitation.” Stochastic Environmental Research and Risk Assessment, May 7, 2025. https://doi.org/10.1007/s00477-025-02996-0 .

@article{oatesLongShorttermMemory2025,
  title = {A Long Short-Term Memory Model for Sub-Hourly Temporal Disaggregation of Precipitation},
  author = {Oates, Harrison and Arora, Nayan and Oh, Hong Gic and Lee, Trevor},
  year = {2025},
  month = may,
  journal = {Stochastic Environmental Research and Risk Assessment},
  issn = {1436-3259},
  doi = {10.1007/s00477-025-02996-0},
  urldate = {2025-05-07},
  langid = {english},
  keywords = {Half-hourly precipitation,Long short-term memory,Machine learning,Neural networks,Stochastic precipitation generation,Temporal disaggregation},
}