Academic Journal
DeepPrecip: a deep neural network for precipitation retrievals
| Title: | DeepPrecip: a deep neural network for precipitation retrievals |
|---|---|
| Authors: | F. King, G. Duffy, L. Milani, C. G. Fletcher, C. Pettersen, K. Ebell |
| Source: | Atmospheric Measurement Techniques, Vol 15, Pp 6035-6050 (2022) |
| Publisher Information: | Copernicus Publications, 2022. |
| Publication Year: | 2022 |
| Collection: | LCC:Environmental engineering LCC:Earthwork. Foundations |
| Subject Terms: | Environmental engineering, TA170-171, Earthwork. Foundations, TA715-787 |
| More Details: | Remotely-sensed precipitation retrievals are critical for advancing our understanding of global energy and hydrologic cycles in remote regions. Radar reflectivity profiles of the lower atmosphere are commonly linked to precipitation through empirical power laws, but these relationships are tightly coupled to particle microphysical assumptions that do not generalize well to different regional climates. Here, we develop a robust, highly generalized precipitation retrieval algorithm from a deep convolutional neural network (DeepPrecip) to estimate 20 min average surface precipitation accumulation using near-surface radar data inputs. DeepPrecip displays a high retrieval skill and can accurately model total precipitation accumulation, with a mean square error (MSE) 160 % lower, on average, than current methods. DeepPrecip also outperforms a less complex machine learning retrieval algorithm, demonstrating the value of deep learning when applied to precipitation retrievals. Predictor importance analyses suggest that a combination of both near-surface (below 1 km) and higher-altitude (1.5–2 km) radar measurements are the primary features contributing to retrieval accuracy. Further, DeepPrecip closely captures total precipitation accumulation magnitudes and variability across nine distinct locations without requiring any explicit descriptions of particle microphysics or geospatial covariates. This research reveals the important role for deep learning in extracting relevant information about precipitation from atmospheric radar retrievals. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 1867-1381 1867-8548 |
| Relation: | https://amt.copernicus.org/articles/15/6035/2022/amt-15-6035-2022.pdf; https://doaj.org/toc/1867-1381; https://doaj.org/toc/1867-8548 |
| DOI: | 10.5194/amt-15-6035-2022 |
| Access URL: | https://doaj.org/article/51713e4b0c114b3eabc9d61a1419227f |
| Accession Number: | edsdoj.51713e4b0c114b3eabc9d61a1419227f |
| Database: | Directory of Open Access Journals |
| Full text is not displayed to guests. | Login for full access. |
| ISSN: | 18671381 18678548 |
|---|---|
| DOI: | 10.5194/amt-15-6035-2022 |
| Published in: | Atmospheric Measurement Techniques |
| Language: | English |