An improved retrieval method of atmospheric parameter profiles based on the BP neural network

Abstract Surface-based microwave radiometer is used to measure the tropospheric parameter profiles continuously for 24 h. The measurement technology and retrieval methods are described clearly in this study. This paper focuses on the BP network and elaborates on it from a new perspective based on the Jacobian matrices between layers. Gradient descent is achieved by Jacobian matrices to train the network. A layered method is proposed to improve the efficiency and accuracy in training networks to obtain tropospheric water vapor and temperature profiles. Differently from the traditional method, the layered method divides the troposphere of 0–10 km into three layers based on the physical principles of cloud generation. Three networks, named as the bottom, the middle, and the upper network, are developed for the three layers. Therefore, three networks can be trained at the same time,using the same input and different output samples. According to the theories and the radiosonde data of 2012–2015 of Harbin China (45.46°N 126.40°E), a numerical experiment is designed to examine the layered method. The downwelling monochromatic radiative transfer model (MonoRTM) is used to calculate the atmospheric radiation brightness temperatures (BTs) with the radiosonde data. The experimental results show that the RMSEs of temperature and water vapor profiles of the layered method are reduced by 25.6% and 26.2%, respectively, at the altitude above 6 km, respectively, and the efficiency is improved by 20 times compared with the traditional method.

[1]  Yong Han,et al.  Analysis and improvement of tipping calibration for ground-based microwave radiometers , 2000, IEEE Trans. Geosci. Remote. Sens..

[2]  R. Eskridge,et al.  Trends in Low and High Cloud Boundaries and Errors in Height Determination of Cloud Boundaries. , 2001 .

[3]  Jietai Mao,et al.  A Study of a Retrieval Method for Temperature and Humidity Profiles from Microwave Radiometer Observations Based on Principal Component Analysis and Stepwise Regression , 2011 .

[4]  Jun Wang,et al.  Lightning potential forecast over Nanjing with denoised sounding-derived indices based on SSA and CS-BP neural network , 2014 .

[5]  P. Rosenkranz.  Shape of the 5 mm oxygen band in the atmosphere , 1975 .

[6]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[7]  A. Maitra,et al.  Retrieval of atmospheric properties with radiometric measurements using neural network , 2016 .

[8]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[9]  Randolph Ware,et al.  Effect of off-zenith observations on reducing the impact of precipitation on ground-based microwave radiometer measurement accuracy , 2014 .

[10]  Wengang Zhang,et al.  Comparison of atmospheric profiles between microwave radiometer retrievals and radiosonde soundings , 2015 .

[11]  J. Abbot,et al.  Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks , 2014 .

[12]  Michael V. Klibanov,et al.  Adaptivity with relaxation for ill-posed problems and global convergence for a coefficient inverse problem , 2010 .

[13]  E. Gross.  Shape of Collision-Broadened Spectral Lines , 1955 .

[14]  E. Isaksson,et al.  First ice core records of NO3− stable isotopes from Lomonosovfonna, Svalbard , 2015 .

[15]  Zhanqing Li,et al.  The climatology of planetary boundary layer height in China derived fromradiosonde and reanalysis data , 2016 .

[16]  Peter J. Minnett,et al.  Cloud distributions over the coastal Arctic Ocean: surface-based and satellite observations , 2004 .

[17]  M. Valipour.  Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms , 2016 .

[18]  A. Maitra,et al.  Nowcasting of rain events using multi-frequency radiometric observations , 2014 .

[19]  P. Chan.  Performance and application of a multi-wavelength, ground-based microwave radiometer in intense convective weather , 2009 .

[20]  J. Fung,et al.  A multi-scale hybrid neural network retrieval model for dust storm detection, a study in Asia , 2015 .

[21]  Susanne Crewell,et al.  Principles of Surface-based Microwave and Millimeter wave Radiometric Remote Sensing of the Troposphere , 2006 .

[22]  J. Abbot,et al.  Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization , 2017 .

[23]  J. L. Sánchez,et al.  A method to improve the accuracy of continuous measuring of vertical profiles of temperature and water vapor density by means of a ground-based microwave radiometer , 2013 .

[24]  Hafizan Juahir,et al.  Prediction of the Level of Air Pollution Using Principal Component Analysis and Artificial Neural Network Techniques: a Case Study in Malaysia , 2014, Water, Air, & Soil Pollution.

[25]  S. Santhosh Baboo,et al.  An Efficient Weather Forecasting System using Artificial Neural Network , 2010 .

[26]  Yeon‐Hee Kim,et al.  An Application of Brightness Temperature Received from a Ground-based Microwave Radiometer to Estimation of Precipitation Occurrences and Rainfall Intensity , 2009 .

[27]  J. Güldner,et al.  Remote Sensing of the Thermodynamic State of the Atmospheric Boundary Layer by Ground-Based Microwave Radiometry , 2001 .

[28]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[29]  Guido Masiello,et al.  Simultaneous physical retrieval of surface emissivity spectrum and atmospheric parameters from infrared atmospheric sounder interferometer spectral radiances. , 2013, Applied optics.

[30]  M. Imteaz,et al.  Multiple regression and Artificial Neural Network for long-term rainfall forecasting using large scale climate modes , 2013 .