A Neural Network for Real-Time Retrievals of PWV and LWP From Arctic Millimeter-Wave Ground-Based Observations

This paper presents a new neural network (NN) algorithm for real-time retrievals of low amounts of precipitable water vapor (PWV) and integrated liquid water from millimeter-wave ground-based observations. Measurements are collected by the 183.3-GHz G-band vapor radiometer (GVR) operating at the Atmospheric Radiation Measurement (ARM) Program Climate Research Facility, Barrow, AK. The NN provides the means to explore the nonlinear regime of the measurements and investigate the physical boundaries of the operability of the instrument. A methodology to compute individual error bars associated with the NN output is developed, and a detailed error analysis of the network output is provided. Through the error analysis, it is possible to isolate several components contributing to the overall retrieval errors and to analyze the dependence of the errors on the inputs. The network outputs and associated errors are then compared with results from a physical retrieval and with the ARM two-channel microwave radiometer (MWR) statistical retrieval. When the NN is trained with a seasonal training data set, the retrievals of water vapor yield results that are comparable to those obtained from a traditional physical retrieval, with a retrieval error percentage of ~5% when the PWV is between 2 and 10 mm, but with the advantages that the NN algorithm does not require vertical profiles of temperature and humidity as input and is significantly faster computationally. Liquid water path (LWP) retrievals from the NN have a significantly improved clear-sky bias (mean of ~2.4 g/m2) and a retrieval error varying from 1 to about 10 g/m2 when the PWV amount is between 1 and 10 mm. As an independent validation of the LWP retrieval, the longwave downwelling surface flux was computed and compared with observations. The comparison shows a significant improvement with respect to the MWR statistical retrievals, particularly for LWP amounts of less than 60 g/m2. This paper shows that the GVR alone can provide overall improved PWV and LWP retrievals when the PWV amount is less than 10 mm, and, when combined with the MWR, can provide improved retrievals over the whole water-vapor range.

[1]  E. Mlawer,et al.  Radiative transfer for inhomogeneous atmospheres: RRTM, a validated correlated-k model for the longwave , 1997 .

[2]  Hans J. Liebe,et al.  Propagation Modeling of Moist Air and Suspended Water/Ice Particles at Frequencies Below 1000 GHz , 1993 .

[3]  Domenico Cimini,et al.  Ground-Based Millimeter- and Submillimeter-Wave Observations of Low Vapor and Liquid Water Contents , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Shepard A. Clough,et al.  Atmospheric radiative transfer modeling: a summary of the AER codes , 2005 .

[5]  F. X. Kneizys,et al.  Line shape and the water vapor continuum , 1989 .

[6]  Clive D Rodgers,et al.  Inverse Methods for Atmospheric Sounding: Theory and Practice , 2000 .

[7]  M. Shupe,et al.  Cloud Radiative Forcing of the Arctic Surface: The Influence of Cloud Properties, Surface Albedo, and Solar Zenith Angle , 2004 .

[8]  Alan F. Murray,et al.  Confidence estimation methods for neural networks : a practical comparison , 2001, ESANN.

[9]  Patrick Minnis,et al.  Comparison of cloud liquid water paths derived from in situ and microwave radiometer data taken during the SHEBA/FIREACE , 2001 .

[10]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[11]  F. Aires,et al.  Neural network uncertainty assessment using Bayesian statistics with application to remote sensing : 1 . Network weights , 2004 .

[12]  Shepard A. Clough,et al.  Thin Liquid Water Clouds: Their Importance and Our Challenge , 2007 .

[13]  Edward J. Kim,et al.  Measurement of Low Amounts of Precipitable Water Vapor Using Ground-Based Millimeterwave Radiometry , 2005 .

[14]  Shepard A. Clough,et al.  Retrieving Liquid Wat0er Path and Precipitable Water Vapor From the Atmospheric Radiation Measurement (ARM) Microwave Radiometers , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[15]  John P. Burrows,et al.  Ozone profile retrieval from Global Ozone Monitoring Experiment (GOME) data using a neural network approach (Neural Network Ozone Retrieval System (NNORSY)) , 2003 .

[16]  Shepard A. Clough,et al.  Improved Daytime Column-Integrated Precipitable Water Vapor from Vaisala Radiosonde Humidity Sensors , 2008 .

[17]  William J. Blackwell,et al.  A neural-network technique for the retrieval of atmospheric temperature and moisture profiles from high spectral resolution sounding data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Gang Li,et al.  The HITRAN 2008 molecular spectroscopic database , 2005 .

[19]  F. Aires,et al.  A new neural network approach including first guess for retrieval of atmospheric water vapor, cloud liquid water path, surface temperature, and emissivities over land from satellite microwave observations , 2001 .

[20]  David D. Turner,et al.  Arctic Mixed-Phase Cloud Properties from AERI Lidar Observations: Algorithm and Results from SHEBA , 2005 .

[21]  Patrick Minnis,et al.  The Mixed-Phase Arctic Cloud Experiment. , 2007 .

[22]  Peter Bauer,et al.  Over-Ocean Rainfall Retrieval from Multisensor Data of the Tropical Rainfall Measuring Mission. Part II: Algorithm Implementation , 2001 .

[23]  Fabio Del Frate,et al.  Neural networks for the retrieval of water vapor and liquid water from radiometric data , 1998 .

[24]  Chris Bishop,et al.  Exact Calculation of the Hessian Matrix for the Multilayer Perceptron , 1992, Neural Computation.

[25]  Andrew L. Pazmany,et al.  Measurements and Retrievals From a New 183-GHz Water-Vapor Radiometer in the Arctic , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[26]  David D. Turner,et al.  Improved ground‐based liquid water path retrievals using a combined infrared and microwave approach , 2007 .

[27]  Andrew L. Pazmany,et al.  A Compact 183-GHz Radiometer for Water Vapor and Liquid Water Sensing , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Shepard A. Clough,et al.  Effect of the Oxygen Line-Parameter Modeling on Temperature and Humidity Retrievals From Ground-Based Microwave Radiometers , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Shepard A. Clough,et al.  Air-Broadened Half-Widths of the 22- and 183-GHz Water-Vapor Lines , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Filipe Aires,et al.  Neural network uncertainty assessment using Bayesian statistics with application to remote sensing: 3. Network Jacobians , 2004 .

[31]  J. C. Liljegren,et al.  Application of microwave radiometry to improving climate data records. , 2007 .

[32]  David D. Turner,et al.  Dry Bias in Vaisala RS90 Radiosonde Humidity Profiles over Antarctica , 2008 .

[33]  Robert Tibshirani,et al.  A Comparison of Some Error Estimates for Neural Network Models , 1996, Neural Computation.