GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm
<p>The Global Precipitation Measurement (GPM) mission measures global precipitation at a temporal resolution of a few hours to enable close monitoring of the global hydrological cycle. GPM achieves this by combining observations from a spaceborne precipitation radar, a constellation of passive...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-09-01
|
| Series: | Atmospheric Measurement Techniques |
| Online Access: | https://amt.copernicus.org/articles/15/5033/2022/amt-15-5033-2022.pdf |
| _version_ | 1818035663310684160 |
|---|---|
| author | S. Pfreundschuh S. Pfreundschuh P. J. Brown C. D. Kummerow P. Eriksson T. Norrestad T. Norrestad |
| author_facet | S. Pfreundschuh S. Pfreundschuh P. J. Brown C. D. Kummerow P. Eriksson T. Norrestad T. Norrestad |
| author_sort | S. Pfreundschuh |
| collection | DOAJ |
| description | <p>The Global Precipitation Measurement (GPM) mission measures global precipitation at a temporal resolution of a few hours to enable close monitoring of the global hydrological cycle. GPM achieves this by combining observations from a
spaceborne precipitation radar, a constellation of passive microwave (PMW)
sensors, and geostationary satellites. The Goddard Profiling Algorithm (GPROF) is used operationally to retrieve precipitation from all PMW sensors of the GPM constellation. Since the resulting precipitation rates serve as input for many of the level 3 retrieval products, GPROF constitutes an essential component of the GPM processing pipeline.</p>
<p>This study investigates ways to improve GPROF using modern machine learning
methods. We present two neural-network-based, probabilistic implementations of GPROF: GPROF-NN 1D, which (just like the current GPROF implementation) processes pixels individually, and GPROF-NN 3D, which employs a convolutional neural network to incorporate structural information into the retrieval. The accuracy of the retrievals is evaluated using a test dataset consistent with the data used in the development of the GPROF and GPROF-NN retrievals. This allows for assessing the accuracy of the retrieval method isolated from the representativeness of the training data, which remains a major source of uncertainty in the development of precipitation retrievals. Despite using the same input information as GPROF, the GPROF-NN 1D retrieval improves the accuracy of the retrieved surface precipitation for the GPM Microwave Imager (GMI) from 0.079 to 0.059 mm h<span class="inline-formula"><sup>−1</sup></span> in terms of mean absolute error (MAE), from 76.1 % to 69.5 % in terms of symmetric mean absolute percentage error (SMAPE)
and from <span class="inline-formula">0.797</span> to <span class="inline-formula">0.847</span> in terms of correlation. The improvements for the Microwave
Humidity Sounder (MHS) are from 0.085 to 0.061 mm h<span class="inline-formula"><sup>−1</sup></span> in terms
of MAE, from 81 % to 70.1 % for SMAPE, and from <span class="inline-formula">0.724</span> to <span class="inline-formula">0.804</span> in terms of correlation. Comparable improvements are
found for the retrieved hydrometeor profiles and their column integrals, as well
as the detection of precipitation. Moreover, the ability of the retrievals to
resolve small-scale variability is improved by more than 40 % for
GMI and 29 % for MHS. The GPROF-NN 3D retrieval further improves
the MAE to 0.043 mm h<span class="inline-formula"><sup>−1</sup></span>; the SMAPE to 48.67 %;
and the correlation to <span class="inline-formula">0.897</span> for GMI and 0.043 mm h<span class="inline-formula"><sup>−1</sup></span>,
63.42 %, and <span class="inline-formula">0.83</span> for MHS.</p>
<p>Application of the retrievals to GMI observations of Hurricane Harvey shows
moderate improvements when compared to co-located GPM-combined and ground-based radar measurements indicating that the improvements at least partially carry over to assessment against independent measurements. Similar retrievals for MHS do not show equally clear improvements, leaving the validation against independent measurements for future investigation.</p>
<p>Both GPROF-NN algorithms make use of the same input and output data as the
original GPROF algorithm and thus may replace the current implementation in a
future update of the GPM processing pipeline. Despite their superior accuracy,
the single-core runtime required for the operational processing of an orbit of
observations is lower than that of GPROF. The GPROF-NN algorithms promise to be
a simple and cost-efficient way to increase the accuracy of the PMW
precipitation retrievals of the GPM constellation and thus improve the
monitoring of the global hydrological cycle.</p> |
| first_indexed | 2024-12-10T06:58:38Z |
| format | Article |
| id | doaj.art-4c2206166cee477d9576d8c98420a5e0 |
| institution | Directory Open Access Journal |
| issn | 1867-1381 1867-8548 |
| language | English |
| last_indexed | 2024-12-10T06:58:38Z |
| publishDate | 2022-09-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Measurement Techniques |
| spelling | doaj.art-4c2206166cee477d9576d8c98420a5e02022-12-22T01:58:23ZengCopernicus PublicationsAtmospheric Measurement Techniques1867-13811867-85482022-09-01155033506010.5194/amt-15-5033-2022GPROF-NN: a neural-network-based implementation of the Goddard Profiling AlgorithmS. Pfreundschuh0S. Pfreundschuh1P. J. Brown2C. D. Kummerow3P. Eriksson4T. Norrestad5T. Norrestad6Department of Space, Earth and Environment, Chalmers University of Technology, 41296 Gothenburg, SwedenDepartment of Atmospheric Science, Colorado State University, Fort Collins, CO 80523, United States of AmericaDepartment of Atmospheric Science, Colorado State University, Fort Collins, CO 80523, United States of AmericaDepartment of Atmospheric Science, Colorado State University, Fort Collins, CO 80523, United States of AmericaDepartment of Space, Earth and Environment, Chalmers University of Technology, 41296 Gothenburg, Swedenindependent researcherformerly at: Department of Space, Earth and Environment, Chalmers University of Technology, 41296 Gothenburg, Sweden<p>The Global Precipitation Measurement (GPM) mission measures global precipitation at a temporal resolution of a few hours to enable close monitoring of the global hydrological cycle. GPM achieves this by combining observations from a spaceborne precipitation radar, a constellation of passive microwave (PMW) sensors, and geostationary satellites. The Goddard Profiling Algorithm (GPROF) is used operationally to retrieve precipitation from all PMW sensors of the GPM constellation. Since the resulting precipitation rates serve as input for many of the level 3 retrieval products, GPROF constitutes an essential component of the GPM processing pipeline.</p> <p>This study investigates ways to improve GPROF using modern machine learning methods. We present two neural-network-based, probabilistic implementations of GPROF: GPROF-NN 1D, which (just like the current GPROF implementation) processes pixels individually, and GPROF-NN 3D, which employs a convolutional neural network to incorporate structural information into the retrieval. The accuracy of the retrievals is evaluated using a test dataset consistent with the data used in the development of the GPROF and GPROF-NN retrievals. This allows for assessing the accuracy of the retrieval method isolated from the representativeness of the training data, which remains a major source of uncertainty in the development of precipitation retrievals. Despite using the same input information as GPROF, the GPROF-NN 1D retrieval improves the accuracy of the retrieved surface precipitation for the GPM Microwave Imager (GMI) from 0.079 to 0.059 mm h<span class="inline-formula"><sup>−1</sup></span> in terms of mean absolute error (MAE), from 76.1 % to 69.5 % in terms of symmetric mean absolute percentage error (SMAPE) and from <span class="inline-formula">0.797</span> to <span class="inline-formula">0.847</span> in terms of correlation. The improvements for the Microwave Humidity Sounder (MHS) are from 0.085 to 0.061 mm h<span class="inline-formula"><sup>−1</sup></span> in terms of MAE, from 81 % to 70.1 % for SMAPE, and from <span class="inline-formula">0.724</span> to <span class="inline-formula">0.804</span> in terms of correlation. Comparable improvements are found for the retrieved hydrometeor profiles and their column integrals, as well as the detection of precipitation. Moreover, the ability of the retrievals to resolve small-scale variability is improved by more than 40 % for GMI and 29 % for MHS. The GPROF-NN 3D retrieval further improves the MAE to 0.043 mm h<span class="inline-formula"><sup>−1</sup></span>; the SMAPE to 48.67 %; and the correlation to <span class="inline-formula">0.897</span> for GMI and 0.043 mm h<span class="inline-formula"><sup>−1</sup></span>, 63.42 %, and <span class="inline-formula">0.83</span> for MHS.</p> <p>Application of the retrievals to GMI observations of Hurricane Harvey shows moderate improvements when compared to co-located GPM-combined and ground-based radar measurements indicating that the improvements at least partially carry over to assessment against independent measurements. Similar retrievals for MHS do not show equally clear improvements, leaving the validation against independent measurements for future investigation.</p> <p>Both GPROF-NN algorithms make use of the same input and output data as the original GPROF algorithm and thus may replace the current implementation in a future update of the GPM processing pipeline. Despite their superior accuracy, the single-core runtime required for the operational processing of an orbit of observations is lower than that of GPROF. The GPROF-NN algorithms promise to be a simple and cost-efficient way to increase the accuracy of the PMW precipitation retrievals of the GPM constellation and thus improve the monitoring of the global hydrological cycle.</p>https://amt.copernicus.org/articles/15/5033/2022/amt-15-5033-2022.pdf |
| spellingShingle | S. Pfreundschuh S. Pfreundschuh P. J. Brown C. D. Kummerow P. Eriksson T. Norrestad T. Norrestad GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm Atmospheric Measurement Techniques |
| title | GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm |
| title_full | GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm |
| title_fullStr | GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm |
| title_full_unstemmed | GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm |
| title_short | GPROF-NN: a neural-network-based implementation of the Goddard Profiling Algorithm |
| title_sort | gprof nn a neural network based implementation of the goddard profiling algorithm |
| url | https://amt.copernicus.org/articles/15/5033/2022/amt-15-5033-2022.pdf |
| work_keys_str_mv | AT spfreundschuh gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm AT spfreundschuh gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm AT pjbrown gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm AT cdkummerow gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm AT periksson gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm AT tnorrestad gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm AT tnorrestad gprofnnaneuralnetworkbasedimplementationofthegoddardprofilingalgorithm |