Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning
Accurate, real-time estimation of rainfall from Doppler radars remains a challenging problem, particularly over complex terrain where vertical beam sampling, atmospheric effects, and radar quality limitations introduce significant biases. In this work, we leverage citizen science rain gauge observat...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/12/3719 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849431587341467648 |
|---|---|
| author | Marshall Rosenhoover John Rushing John Beck Kelsey White Sara Graves |
| author_facet | Marshall Rosenhoover John Rushing John Beck Kelsey White Sara Graves |
| author_sort | Marshall Rosenhoover |
| collection | DOAJ |
| description | Accurate, real-time estimation of rainfall from Doppler radars remains a challenging problem, particularly over complex terrain where vertical beam sampling, atmospheric effects, and radar quality limitations introduce significant biases. In this work, we leverage citizen science rain gauge observations to develop a deep learning framework that corrects biases in radar-derived surface precipitation rates at high temporal resolution. A key step in our approach is the construction of piecewise-linear rainfall accumulation functions, which align gauge measurements with radar estimates and allow for the generation of high-quality instantaneous rain rate labels from rain gauge observations. After validating gauges through a two-stage temporal and spatial consistency filter, we train an adapted ResNet-101 model to classify rainfall intensity from sequences of surface precipitation rate estimates. Our model substantially improves precipitation classification accuracy relative to NOAA’s operational radar products within observed spatial regions, achieving large gains in precision, recall, and F1 score. While generalization to completely unseen regions remains more challenging, particularly for higher-intensity rainfall, modest improvements over baseline radar estimates are still observed in low-intensity rainfall. These results highlight how combining citizen science data with physically informed accumulation fitting and deep learning can meaningfully improve real-time radar-based rainfall estimation and support operational forecasting in complex environments. |
| format | Article |
| id | doaj-art-ec911a259c7b4f44ae2ff12179919aae |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-ec911a259c7b4f44ae2ff12179919aae2025-08-20T03:27:36ZengMDPI AGSensors1424-82202025-06-012512371910.3390/s25123719Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep LearningMarshall Rosenhoover0John Rushing1John Beck2Kelsey White3Sara Graves4Information Technology and Systems Center, University of Alabama in Huntsville, Huntsville, AL 35899, USAInformation Technology and Systems Center, University of Alabama in Huntsville, Huntsville, AL 35899, USAInformation Technology and Systems Center, University of Alabama in Huntsville, Huntsville, AL 35899, USAInformation Technology and Systems Center, University of Alabama in Huntsville, Huntsville, AL 35899, USAInformation Technology and Systems Center, University of Alabama in Huntsville, Huntsville, AL 35899, USAAccurate, real-time estimation of rainfall from Doppler radars remains a challenging problem, particularly over complex terrain where vertical beam sampling, atmospheric effects, and radar quality limitations introduce significant biases. In this work, we leverage citizen science rain gauge observations to develop a deep learning framework that corrects biases in radar-derived surface precipitation rates at high temporal resolution. A key step in our approach is the construction of piecewise-linear rainfall accumulation functions, which align gauge measurements with radar estimates and allow for the generation of high-quality instantaneous rain rate labels from rain gauge observations. After validating gauges through a two-stage temporal and spatial consistency filter, we train an adapted ResNet-101 model to classify rainfall intensity from sequences of surface precipitation rate estimates. Our model substantially improves precipitation classification accuracy relative to NOAA’s operational radar products within observed spatial regions, achieving large gains in precision, recall, and F1 score. While generalization to completely unseen regions remains more challenging, particularly for higher-intensity rainfall, modest improvements over baseline radar estimates are still observed in low-intensity rainfall. These results highlight how combining citizen science data with physically informed accumulation fitting and deep learning can meaningfully improve real-time radar-based rainfall estimation and support operational forecasting in complex environments.https://www.mdpi.com/1424-8220/25/12/3719radar precipitation estimationradar-rain gauge rainfall accumulationcitizen sciencedeep learningrainfall accumulationradar calibration |
| spellingShingle | Marshall Rosenhoover John Rushing John Beck Kelsey White Sara Graves Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning Sensors radar precipitation estimation radar-rain gauge rainfall accumulation citizen science deep learning rainfall accumulation radar calibration |
| title | Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning |
| title_full | Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning |
| title_fullStr | Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning |
| title_full_unstemmed | Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning |
| title_short | Improving Doppler Radar Precipitation Prediction with Citizen Science Rain Gauges and Deep Learning |
| title_sort | improving doppler radar precipitation prediction with citizen science rain gauges and deep learning |
| topic | radar precipitation estimation radar-rain gauge rainfall accumulation citizen science deep learning rainfall accumulation radar calibration |
| url | https://www.mdpi.com/1424-8220/25/12/3719 |
| work_keys_str_mv | AT marshallrosenhoover improvingdopplerradarprecipitationpredictionwithcitizenscienceraingaugesanddeeplearning AT johnrushing improvingdopplerradarprecipitationpredictionwithcitizenscienceraingaugesanddeeplearning AT johnbeck improvingdopplerradarprecipitationpredictionwithcitizenscienceraingaugesanddeeplearning AT kelseywhite improvingdopplerradarprecipitationpredictionwithcitizenscienceraingaugesanddeeplearning AT saragraves improvingdopplerradarprecipitationpredictionwithcitizenscienceraingaugesanddeeplearning |