基于神经网络技术的地球自转变化预报
|
摘要
地球自转变化的预报具有重要的科学意义和实际应用价值。然而由于地球自转变化复杂的时变特性，传统的线性时间序列分析方法往往难以取得良好的预报效果。本文采用非线性的人工神经网络技术预报地球自转变化。
由于固体地球及环绕着它的流体圈层构成一个近似封闭的动力学系统，角动量守恒原理表明，大气或海洋角动量的任何变化都会影响固体地球的自转变化。现代测地技术获得的高精度地球自转变化和全球大气环流模式的研究结果表明，与日长变化成强相关的是大气角动量函数的轴向分量X_3，与极移激发相关的是大气角动量函数的赤道向分量X_1、X_2。将大气角动量时间序列引入到地球自转变化预报中，相当于增加一个物理约束条件。正是基于此，本文着重研究和探索应用非线性的神经网络技术，将大气角动量时间序列引入到地球自转变化预报中，改善地球自转参数(ERP)的预报精度，以及应用神经网络技术预报El Nino／南方涛动(ENSO)事件。
本文主要研究内容如下：
(1)分析了神经网络的拓扑结构算法，提出选用最小均方误差法确定网络的拓扑结构。研究探讨了适合于本研究的网络算法流程。
(2)基于神经网络技术，对地球自转速率变化分别进行了单独、联合和实时快速预报。a)结果证实了神经网络具有良好的非线性预报能力；b)大气是日长变化主要的激发源，联合大气角动量序列作日长变化预报，结果表明，预报精度得到显著的提高，特别是对于时间跨度较大的预报；c)实时快速预报具有重要的科学意义和实际应用价值，本文首次在网络的预报过程中引入美国环境预报中心(NCEP)全球分析与预报系统的X_3实时预报序列，结果表明，本工作所作的联合实时预报是成功的。
(3)基于神经网络技术，对极移分别进行了单独和联合预报。联合预报和单独预报相比，对于时间跨度为1-7日的预报，联合预报的精度略低于单独预报；但从8—40日，联合预报的精度均明显高于单独预报。由于大气仅是极移的主要激发源之一，海洋和地下水等激发源由于资料的原因目前尚未计及，所以，综合考虑大气、海洋和地下水等激发因素对极移进行联合预报，值得作深入的研究和探讨。
(4) 2006年6月起，西太平洋海表水温的异常变化(SSTA)已连续4个月超过0.5℃，极有可能演化成为新的ENSO事件。我们利用最新的SSTA观测资料，应用神经网络技术，对此次ENSO事件进行试验预报。本文根据CPC每月发布的最新观测数据，在2006年9月至2007年4月期间，对赤道太平洋Nino_(3.4)海区的SSTA进行神经网络的非线性预报，每次都预报12个月的SSTA值。通过与CPC网站发布的预报结果相比较，我们的结果接近于所有动力学模型和统计学模型的平均值。这表明我们的预报具有一定的可靠性和参考价值。
Prediction of the variations of the Earth's variable rotation is of great scientificand practical importance. However, due to the complicated time-variablecharacteristics of the Earth's variable rotation, it's usually difficult to obtainsatisfied predictions by conventional linear time series analysis methods. This studyemploys the non-linear artificial neural networks (ANN) to predict the variations ofthe Earth's rotation.
As the solid Earth and its surrounding fluid layers form an approximately closedynamic system, changes of atmospheric or oceanic angular momentum will resultin variations in the solid Earth's rotation, based on the law of conversation ofangular momentum. The high-accuracy Earth rotation observations and researcheson global atmospheric models reveal that the axial atmospheric angular momentum(AAM)χ_3 correlates strongly with the LOD changes and the equatorial AAM 2χ_1andχ_2 correlate with the polar motion excitation. Thus, when the AAM series isincorporated into the prediction of the Earth's variable rotation, it will add aphysical constraint to the prediction. The present study focuses on incorporating theAAM series into the prediction of the Earth's variable rotation to improveaccuracies of the ERP predictions by ANN. In addition, the technology is alsoapplied to predict the E1 Nino/Southern Oscillation (ENSO) event.
The main research work of this thesis can be summarized as follows:
(1) The algorithms of determining the topology of an ANN is analyzed, and theRoot Mean Squared Error (RMSE) is chosen as the criterion to determine thetopology of the network. The network algorithm flow that is suitable for our work is investigated.
(2) Based on the ANN technique, the variations of the Earth's rotational rate (i.e.,length of day, LOD) are predicted in three ways, i.e., using LODR only, using bothLODR and AAM data, and real-time rapid approach, respectively, a) The resultsshow that ANN has effective non-linear prediction ability, b) As the atmosphere isthe main excitation source of the LOD change, the accuracies of predictions aresignificantly improved after introducing the AAM into the LOD prediction,especially for the long prediction intervals, c) Real-time rapid prediction is of greatscientific and practical importance. In this thesis we introduce the operationalprediction series ofχ_3, which is from National Centers for EnvironmentalPrediction (NCEP), to the prediction set of ANN model for the first time. Theresults show that our work about real-time rapid prediction is successful.
(3) Based on the ANN technique, the polar motion (PM) are predicted in twoways, i.e., using PM only and using both PM and AAM data. The results show thatfor 1 to 7 days forward prediction, the accuracy is not improved after introducingthe AAM data, but for 8 to 40 days forward prediction the accuracy is significantlyimproved after introducing the AAM data. Because the ocean and the ground waterare also the polar motion excitation sources except for the atmosphere, it awaitsfurther investigations for incorporating the atmosphere, oceans and ground waterinto the polar motion prediction.
(4) Since June of 2006, the sea surface temperature anomaly (SSTA) of the westPacific has exceeded 0.5℃for 4 continuous months, it maybe evolve into a newENSO event. We apply the up-t0-date SSTA data to predict this event by AAN. Wepredict the SSTA of Nino_(3.4) sea area, based on the monthly data released by theClimate Prediction Center (CPC) of NECP. We conducted 8 predictions fromSeptember, 2006 to April, 2007. Every prediction was made 12 months forward.We compare our results with those of CPC. Our work is closer to the average of alldynamical and statistical models. This demonstrates that our prediction has certainreliability and reference values.
由于固体地球及环绕着它的流体圈层构成一个近似封闭的动力学系统，角动量守恒原理表明，大气或海洋角动量的任何变化都会影响固体地球的自转变化。现代测地技术获得的高精度地球自转变化和全球大气环流模式的研究结果表明，与日长变化成强相关的是大气角动量函数的轴向分量X_3，与极移激发相关的是大气角动量函数的赤道向分量X_1、X_2。将大气角动量时间序列引入到地球自转变化预报中，相当于增加一个物理约束条件。正是基于此，本文着重研究和探索应用非线性的神经网络技术，将大气角动量时间序列引入到地球自转变化预报中，改善地球自转参数(ERP)的预报精度，以及应用神经网络技术预报El Nino／南方涛动(ENSO)事件。
本文主要研究内容如下：
(1)分析了神经网络的拓扑结构算法，提出选用最小均方误差法确定网络的拓扑结构。研究探讨了适合于本研究的网络算法流程。
(2)基于神经网络技术，对地球自转速率变化分别进行了单独、联合和实时快速预报。a)结果证实了神经网络具有良好的非线性预报能力；b)大气是日长变化主要的激发源，联合大气角动量序列作日长变化预报，结果表明，预报精度得到显著的提高，特别是对于时间跨度较大的预报；c)实时快速预报具有重要的科学意义和实际应用价值，本文首次在网络的预报过程中引入美国环境预报中心(NCEP)全球分析与预报系统的X_3实时预报序列，结果表明，本工作所作的联合实时预报是成功的。
(3)基于神经网络技术，对极移分别进行了单独和联合预报。联合预报和单独预报相比，对于时间跨度为1-7日的预报，联合预报的精度略低于单独预报；但从8—40日，联合预报的精度均明显高于单独预报。由于大气仅是极移的主要激发源之一，海洋和地下水等激发源由于资料的原因目前尚未计及，所以，综合考虑大气、海洋和地下水等激发因素对极移进行联合预报，值得作深入的研究和探讨。
(4) 2006年6月起，西太平洋海表水温的异常变化(SSTA)已连续4个月超过0.5℃，极有可能演化成为新的ENSO事件。我们利用最新的SSTA观测资料，应用神经网络技术，对此次ENSO事件进行试验预报。本文根据CPC每月发布的最新观测数据，在2006年9月至2007年4月期间，对赤道太平洋Nino_(3.4)海区的SSTA进行神经网络的非线性预报，每次都预报12个月的SSTA值。通过与CPC网站发布的预报结果相比较，我们的结果接近于所有动力学模型和统计学模型的平均值。这表明我们的预报具有一定的可靠性和参考价值。
Prediction of the variations of the Earth's variable rotation is of great scientificand practical importance. However, due to the complicated time-variablecharacteristics of the Earth's variable rotation, it's usually difficult to obtainsatisfied predictions by conventional linear time series analysis methods. This studyemploys the non-linear artificial neural networks (ANN) to predict the variations ofthe Earth's rotation.
As the solid Earth and its surrounding fluid layers form an approximately closedynamic system, changes of atmospheric or oceanic angular momentum will resultin variations in the solid Earth's rotation, based on the law of conversation ofangular momentum. The high-accuracy Earth rotation observations and researcheson global atmospheric models reveal that the axial atmospheric angular momentum(AAM)χ_3 correlates strongly with the LOD changes and the equatorial AAM 2χ_1andχ_2 correlate with the polar motion excitation. Thus, when the AAM series isincorporated into the prediction of the Earth's variable rotation, it will add aphysical constraint to the prediction. The present study focuses on incorporating theAAM series into the prediction of the Earth's variable rotation to improveaccuracies of the ERP predictions by ANN. In addition, the technology is alsoapplied to predict the E1 Nino/Southern Oscillation (ENSO) event.
The main research work of this thesis can be summarized as follows:
(1) The algorithms of determining the topology of an ANN is analyzed, and theRoot Mean Squared Error (RMSE) is chosen as the criterion to determine thetopology of the network. The network algorithm flow that is suitable for our work is investigated.
(2) Based on the ANN technique, the variations of the Earth's rotational rate (i.e.,length of day, LOD) are predicted in three ways, i.e., using LODR only, using bothLODR and AAM data, and real-time rapid approach, respectively, a) The resultsshow that ANN has effective non-linear prediction ability, b) As the atmosphere isthe main excitation source of the LOD change, the accuracies of predictions aresignificantly improved after introducing the AAM into the LOD prediction,especially for the long prediction intervals, c) Real-time rapid prediction is of greatscientific and practical importance. In this thesis we introduce the operationalprediction series ofχ_3, which is from National Centers for EnvironmentalPrediction (NCEP), to the prediction set of ANN model for the first time. Theresults show that our work about real-time rapid prediction is successful.
(3) Based on the ANN technique, the polar motion (PM) are predicted in twoways, i.e., using PM only and using both PM and AAM data. The results show thatfor 1 to 7 days forward prediction, the accuracy is not improved after introducingthe AAM data, but for 8 to 40 days forward prediction the accuracy is significantlyimproved after introducing the AAM data. Because the ocean and the ground waterare also the polar motion excitation sources except for the atmosphere, it awaitsfurther investigations for incorporating the atmosphere, oceans and ground waterinto the polar motion prediction.
(4) Since June of 2006, the sea surface temperature anomaly (SSTA) of the westPacific has exceeded 0.5℃for 4 continuous months, it maybe evolve into a newENSO event. We apply the up-t0-date SSTA data to predict this event by AAN. Wepredict the SSTA of Nino_(3.4) sea area, based on the monthly data released by theClimate Prediction Center (CPC) of NECP. We conducted 8 predictions fromSeptember, 2006 to April, 2007. Every prediction was made 12 months forward.We compare our results with those of CPC. Our work is closer to the average of alldynamical and statistical models. This demonstrates that our prediction has certainreliability and reference values.
引文
1. Ahmed Khalid Eldaw. Long range forecasting of the nine river flow using large scale oceanic atmospheric forcings [PH.D thesis]. Colorado, USA: Colorado State University, 2001.
2. Akyilmaz O, Kutterer H. Prediction of Earth rotation parameters by fuzzy inference systems. Journal of Geodesy. 2004, 78: 82-93.
3. Anshelevich VV, Amirikian BR, Lukashin AV, et al. On the ability of neural networks to perform generalization by induction. Biological Cybernetics. 1989, 61: 125-128.
4. Barnes RTH., Hide R, White AA and Wilson CA. Atmospheric angular momentum fluctuation, length-of-day changes and polar motion. Proc. R. Soc. Lond., Ser. A. 1983, 387: 31-73.
5. Blum EK, Li LK. Approximation theory and feedforward networks. Neural Networks. 1991, 4(4): 511-515.
6. Bodri L, Cermak V. Prediction of surface air temperature by neural network example based on three-year temperature monitoring at Sporilov station. Stud. Geophys. Geod. 2003, 47: 173-184.
7. Chao BF. Predictability of the Earth's polar motion. Bull Geod. 1984, 59: 81-93.
8. Chao BF. On the excitation of the Earth's polar motion. Geophysical Research Letters. 1985, 12(8): 526-529.
9. Chao BF. Length of day variations caused by El Nino-Southern Oscillation and Quasi-Biennial Oscillation. Science, 1989, 243: 923.
10. Chen JL, Wilson CR, Hu XG, et al. Oceanic effects on polar motion determined from an ocean model and satellite altimetry: 1993-2001. Journal of Geophysical Research-Solid Earth. 2004, 109 (B2): Art. No. B0241.
11. Chin TM, Gross RS, Dickey JO. Modeling and forecast of the polar motion excitation functions for short-term polar motion prediction. Journal of Geodesy. 2004, 78:343-353, DOI 10.1007/s00190-004-0411-4.
12. Chin TM, Gross RS, Dickey JO. Multi-reference evaluation of uncertainty in earth orientation parameter measurements. Journal of Geodesy. 2005, 79: 24-32. DOI 10.1007/s00190-005-0439-0.
13. Dennis D. McCarthy, G'erard Petit (eds.). IERS Conventions (2003), IERS Technical Note; 32, Observatoire de Paris, Paris.
14. Dickey JO, Marcus SL, Hide R, et al. Angular momentum exchange among the solid Earth, atmosphere and oceans: A case study of the 1982-1973 El Nino event. J. Geophys. Res. 1994, 99(B12): 23921-23938.
15. Dickey JO, Marcus SL, Steppe JA, et al. The Earth's angular momentum budget on subseaeonal time scales. Science. 1992, 255: 321-324.
16. Egger D. Neuronales Netz pradiziert Erdrotation. In: Allgemeine Vermessungsnachrichten (AVN), 1992,11/12, S: 517-524.
17. Egger D, FROHLICH H.: Pradiktion von Erdrotationsdaten klassisch und neuronal, in: Allgemeine Vermessungsnachrichten (AVN) 1993, 10, S.366-375.
18. Eubanks TM. Variations in the Orientation of the Earth, in Contributions of Space Geodesy to Geodynamic: Earth Dynamics, Geodyn. Ser., edited by Smith D and Turcotte D. Washington, D.C.: AGU, 1993. 1-54.
19. Florian Seitz, Jochen Stuck, Maik Thomas. Consistent atmospheric and oceanic excitation of the Earth's free polar motion. Geophysical Journal International. 2004, 157:25-35.
20. Gross RS, Fukumori I, Menemenlis D. Atmospheric and oceanic excitation of the Earth's wobbles during 1980-2000. Journal of Geophysical Research. 2002, 108(B8), 2370, doi:10.1029/2002JB002143.
21. Gross RS, Fukumori I, Menemenlis D. Atmospheric and oceanic excitation of decadal-scale Earth orientation variations. Journal of Geophysical Research. 2005, 110, B09405, doi: 10.1029/2004JB003565.
22. Gross RS, I Fukumori D, Menemenlis, et al. Atmospheric and oceanic excitation of length-of-day variations during 1980-2000. Journal of Geophysical Research. 2004, 109, B01406., doi: 10.1029/2003JB002432.
23. Hecht-Nielson R. Kolmogorov's mapping neural network existence theorem. IEEE Conference on Neural Networks. 1987, 3: 11-14.
24. Hecht-Nielson R. Theory of the back propagation neural network. International Conference on Neural Network. Washington D C: Reading pub, 1989.
25. Henrique Steinherz Hippert, Carlos Eduardo Pedreira, Reinaldo Castro Souza. Neural Networks for Short-Term Load Forecasting: A Review and Evaluation. IEEE TRANSACTIONS ON POWER SYSTEMS. 2001, 16(1): 44-55.
26. Hippert HS, Pedreira CE. Estimating temperature profiles for short-term load forecasting: neural networks compared to linear models, IEE Proc.-Gener. Transm. Distrib. 2004, 151(4): 543-547.
27. Hopfield JJ. Neural network and physical system with emergent collective computational abilities. Proc. Natl. Acad. Sci. 1982, USA, 79: 2254-2258.
28. Hopfield JJ. Neurons with graded response have collective computational properties like those of two state neurons. Proc. Natl. Acad. Sci. 1984, USA, 81: 3088-3092.
29. Hu X, Liao X, Huang C. Data weighting and solution assessment in combination. Journal of Geodesy. 1999, 73 (8): 391-397.
30. Huang CL, Dehant V, Liao XH. The explicit scalar equations of infinitesimal elastic-gravitational motion in the rotating, slightly elliptical fluid outer core of the Earth. Geophysical Journal International. 2004,157 (2): 831-837.
31. Huang CL, Liao XH. Comment on 'Representation of the elastic-gravitational excitation of a spherical Earth model by generalized spherical harmonics' by Phinney & Burridge. Geophysical Journal International. 2003, 155 (2): 669-678.
32. Huang W, Lippmann R P. Comparisons between neural net and conventional classifiers. IEEE first Int.Conf. Neural Networks. San Diego, 1987 : 741-746.
33. Hopfner J. Interannual variations in length of day and atmospheric angular momentum with respect to ENSO cycles. Scientific Technical Report, No.: STR99/07, presented at the 22nd General Assembly International Union of Geodesy and Geophysics Birmingham, UK, 18-30 July 1999.
34. Jacek MZ. Introduction to Artificial Neural Systems. New York: West Pub Company, 1992.
35. Jolanta Nastula, David A Salstein, Barbara Kot aczek. Time Variable Atmospheric and Oceanic Signals in Excitation Functions of Polar Motion. IERS Technical Note, No.30.
36. Kalarus M, Schuh H, Kosek W, et al. The application of artificial neural networks and autoregressive techniques for Earth Orientation Parameters prediction. EGU, Vienna, Austria, 24-29 April 2005.
37. Kalarus M, Kosek W. Prediction of Earth Orientation Parameters by artificial neural networks. Earth Rotation and Satellite Geodesy from Astrometry to GNSS, Warsaw, 18-19 September 2003.
38. Kosek W, McCarthy DD, Luzum BJ. Possible improvement of Earth orientation forecast using autocovariance prediction procedures. Journal of Geodesy. 1998, 72: 189-199.
39. Kung SY, Hwang JN. An algebraic projecting analysis for optimal hidden unit size and learning rate in backpropagation learning. Proceedings of IEEE International Conference on Neural Networks. San Diego, 1988,1- 262-270.
40. Lambeck K. The Earth's Variable Rotation. New York: Cambridge University Press, 1980.
41. Liao DC, Greiner-Mai H. A new ALOD series in monthly intervals (1892.0-1997.0) and its comparison with other geophysical result. Journal of Geodesy. 1999, 73 (9): 466-477.
42. Liao DC, Liao XH. New evidence for possible impact of solar activity on long-term fluctuation of the earth rotation. Chinese Science Bulletin. 2001, 46 (11): 905-908.
43. Liao DC, Liao XH, Zhou YH. Contribution of oceanic and atmospheric excitations to the Chandler wobble. Chinese Journal of Geophysical-Chinese Edition. 2003, 46 (4): 455-461.
44. Liao DC, Liao XH, Zhou YH. Oceanic and atmospheric excitation of the Chandler wobble. Geophysical Journal International. 2003, 152 (1): 215-227.
45. Liao DC, Liao XH, Zhou YH. Statistical property of the Chandler wobble excitation function. Chinese Science Bulletin. 2004, 49 (22): 2348-2353.
46. Liao DC, Zhou YH. Chandler wobble period and Q derived by wavelet transform. Chinese Journal of Astronomy and Astrophysics. 2004, 4 (3): 247-257.
47. Liao DC, Liao XH, Zhou YH, et al. Hydrological, atmospheric and oceanic excitations of the Chandler wobble. Chinese Astronomy and Astrophysics. 2004, 28 (2): 212-221.
48. Liao X, Zhang K, Chang Y. On boundary-layer convection in a rotating fluid layer. Journal of Fluid Mechanics. 2006, 549: 375-384.
49. Liao XH, Zhang KK. On the convective excitation of torsional oscillations in rotating systems. Astrophysical Journal. 2006, 638 (2): L113-L116 Part 2.
50. Liao X, Zhang K, Chang Y. Nonlinear torsional oscillations in rotating systems. Physical Review Letters. 2007, 98 (9): Art. No.094501.
51. Lippmann R P. An Introduction to Computing with Neural Nets. IEEE ASSP Magazine. 1987: 4-22.
52. Luzum BJ, Ray JR, Carter MS, et al. Recent improvements to IERS Bulletin A Combination and Prediction. GPS Solution. 2001, 4(3): 33-40.
53. Ma LH, Liao DC, Han YB. Atmospheric and oceanic excitations to LOD change on quasi-biennial time scales. Chinese Journal of Astronomy and Astrophysics. 2006, 6 (6): 759-768.
54. Magali RG Meireles, Paulo EM Almeida, Marcelo Godoy Simoes, A comprehensive Review for Industrial Applicability of Artificial Neural Networks. IEEE transactions on industrial electronics. 2003, 50(3): 585-601.
55. Malkin, Skurikhina. On prediction of EOP. Comm IAA, 1991, 93.
56. Malkin Z. On Estimation of Real Accuracy of EOP Prediction. In: Dick S, McCarthy D, Luzum B(eds) Polar Motion: Historical and Scientific Problems, IAU Coll. 187, Cagliari, Italy, Sep 27-30, 1999. ASP, San Francisco 208: 505-510.
57. McCarthy, Luzum. Prediction of Earth Orientation. Bull Geod. 1991, 65: 18-22.
58. McCarthy DD, Petit G. IERS Convension (2003). IERS Technical Note 32. Paris : Observatoire de Paris, 2003.
59. Moorthi S, Pan HL, Caplan P. Changes to the 2001 NCEP operational MRF/AVN global analysis/forecast system. NWS Technical Procedures Bulletin, 2001, 484:1-14.
60. Munk WH, MacDonald GJF. The Rotation of the Earth—A Geophysical Discussion. New York: Cambridge University Press. 1960.
61. Ojo AK, Games GK. Selecting ANN Models for Geoidal Undulation Prediction. In: Proceedings of the 2003 International Conference on Artificial Intelligence. Las Vegas: CSREA Press,2003.Vol 1, 191-192.
62. Ojo AK, James GK. Artificial Neural Networks for Geoidal Undulation Prediction. International Conference on Artificial Intelligence, 2003.
63. Peter J. Huber. Modeling the length of day and extrapolating the rotation of the Earth. Journal of Geodesy. 2006, 80(6): 283-303, DOI 10.1007/s00190-006-0067-3.
64. Robert Scott Weigel. Prediction and modeling of magnetospheric substorms [PH.D thesis]. Austin, USA: The University of Texas at Aystin, 2000.
65. Salstein D A, Kann D M, Miller A J, et al. The sub-bureau for atmospheric angular momentum of the international earth rotation service: a meteorological data center with geodetic applications. Bull. Am. Meteor. Soc.1993,74: 67-80.
66. Schuh H, Ulrich M, Egger D, et al. Prediction of Earth orientation parameters by artificial neural networks. Journal of Geodesy. 2002, 76: 247-258.
67. Schuh H, Kosek W, et al. First results of the earth orientation parameters prediction comparison campaign, EGU, Vienna, Austria, 2-7 April 2006.
68. Thomas Toniazzo, Adam A Scaife. The influence of ENSO on winter North Atlantic climate. Geophysical Research Letters. 2006, 33, L24704, doi: 10.1029/2006GL027881,.
69. Thomas J Johnson, Brian J Luzum, Jim R Ray. Improved near-term Earth rotation predictions using atmospheric angular momentum analysis and forecasts. Journal of Geodynamics. 2005, 39: 209-221.
70. Wieland A, Leighton R. Geometric analysis of neural network capabilities. IEEE First International conference on Neural Networks. 1987, 3: 385-392.
71. Wooden WH, Johnson TJ. "Rapid Service/Prediction Centre," IERS Annual Report 2002. 2003,46-53.
72. Yan HM, Zhong M, Zhu YZ, et al. Nontidal oceanic contribution to length-of-day changes estimated from two ocean models during 1992-2001. Journal of Geophysical Research -Solid Earth. 2006, 111 (B2): Art. No. B0410.
73. Yu N, Zheng D, Wu H. Contribution of new AAM data source to ALOD excitation. Journal of Geodesy. 1999, 73: 385-390.
74. Zheng DW, Song GX, Luo SF. El Nino prediction. Nature. 1990, 348:119.
75. Zheng DW, Chao BF, Zhou YH, et al. Improvement of edge effect of the wavelet time-frequency spectrum: application to the length-of-day series. Journal of Geodesy. 2000, 74: 249-254.
76. Zheng DW, Ding XL, Zhou YH, et al. Premonitory phenomenon of El Nino event reflected in the observations of LOD and sea level. Chinese Science Bulletin. 2000, 45(24): 2231-2235.
77. Zheng DW, Zhou YH, Liao XH. Interannual variation in the length of day and ENSO events in 1982-1983 and 1997-1997. Science in China (Series A). 2001, 44(1): 128-137.
78. Zheng DW, Ding XL, Zhou YH, et al. Earth rotation and ENSO events: combined excitation of interannual LOD variations by multiscale atmospheric oscillations. Global and Planetary Change. 2003, 36 (1-2): 89-97.
79. Zhou YH, Zheng DW, Zhao M, et al. Interannual polar motion with relation to the North Atlantic Oscillation. Global and Planetary Change. 1998, 18: 79-84.
80. Zhou YH, Zheng DW, Yu NH, et al. Excitation of annual polar motion by atmosphere and ocean. Chinese Science Bulletin. 2000, 45 (2): 139-142.
81. Zhou YH, Wu HQ, Yu NH. Excitation of seasonal polar motion by atmospheric and oceanic angular momentums. Progress in Natural Science. 2000, 10(12): 931-936.
82. Zhou YH, Zheng DW, Liao XH. Wavelet analysis of interannual LOD, AAM, and ENSO: 1997-98 El Nino and 1998-99 La Nina signals. Journal of Geodesy. 2001, 75: 164-168.
83. Zhou YH, Zheng DW, Yu NH, et al. Movement of Earth rotation and activities of atmosphere and ocean. Chinese Science Bulletin. 2001, 46(11): 881-888.
84. Zhou YH, Yan XH, Ding XL, et al. Excitation of non-atmospheric polar motion by the migration of the Pacific Warm Pool. Journal of Geodesy. 2004, 78:109-113. DOI 10. 1007/s00190-004-0380-7.
85. Zhou YH, Chen JL, Liao XH, et al. Oceanic excitations on polar motion: a cross comparison among models. Geophysical Journal International. 2005, 162, 390-398, doi: 10.1111/j. 1365-246X.2005.02694.x.
86. Zhou YH, Salstein DA, Chen JL. Revised atmospheric excitation function series related to Earth's variable rotation under consideration of surface topography. Journal of Geophysical Research. 2006, 111, D 12108, doi: 10.1029/2005JD006608.
87. Zhong M, Zhu YZ, Gao BX, et al. Atmospheric, hydrological and oceanic comprehensive contributions to seasonal polar wobble of Earth Rotation. Science in China Series A-Mathematics Physics Astronomy. 2002, 45 (12): 1620-1627.
88. Zhong M, Yan HM, Zhu YZ, et al. Atmospheric angular momentum fluctuations and their excitations of earth rotation variations at seasonal scale. Chinese Astronomy and Astrophysics. 2002, 26 (3): 363-371.
89. Zhong M, Yan HM, Zhu YZ. The investigation of atmospheric angular momentum as a contributor to polar wobble and length of day change with AMIP Ⅱ GCM data. Advance in Atmospheric Science. 2002, 19 (2): 287-296.
90. Zhong M, Naito I, Kitoh A. Atmospheric, hydrological, and ocean current contributions to Earth's annual wobble and length-of-day signals based on output from a climate model. Journal of Geophysical Research -Solid Earth. 2003, 108 (B1): Art. No. 2057.
91. Zhong M, Yan HM, Wu XP, et al. Non-tidal oceanic contribution to polar wobble estimated from two oceanic assimilation data sets. Journal of Geodynamics. 2006, 41 (1-3): 147-154.
92. Zhu SY. Prediction of polar motion. Bull Geod, 1982, 56:258-273.
93．丁月蓉，郑大伟。天文测量数据的处理方法。南京：南京大学出版社，1990。
94．付英，曾敏，李兴源。隐含层人工神经网络电压安全评估的影响。电力系统自动化。1996，20(11)：13-16。
95．高大启。有教师的线性基本函数前向三层神经网络结构研究。计算机学报。1998，21(1)：80-86。
96．顾晖。地球自转和大气角动量“50天”波动的特征。上海：中国科学院上海天文台，硕士学位论文，1991。
97．郭俊义。地球物理学基础。北京：测绘出版社，2001。
98．胡守仁，余少波，戴葵。神经网络导论。湖南：国防科技大学出版社，1993。
99．金龙。神经网络气象预报建模理论方法与应用。北京：气象出版社，2004。
100．焦李成。神经网络系统理论。西安：西安电子科技大学出版社，1996。
101．蒋伟进。非线性混沌时序的神经网络预测与控制算法研究。计算机应用与软件。21(4)：81-83。
102．雷正伟，徐章遂，米东等。神经网络的预测性能的优化分析。计算机测量与控制。2004，12(1)：15-20。
103．廖德春，廖新浩。全球陆地水储量对地球自转变化的激发作用。天文学报。2000，41(4)：373～383。
104．廖德春，周永宏，廖新浩。天文观测已检测到2002年的弱El Nino事件。科学通报。2003，48(11)：1135-1138．
105．廖德春，廖新浩，周永宏。海洋和大气对Chandler摆动激发的贡献。地球物理学报。2003，46(4)：455-461。
106．廖德春，廖新浩，周永宏。Chandler摆动激发函数的统计特性。科学通报。2004，49(22)：2284-2289。
107．李晓燕，翟盘茂。ENSO事件指数与指标研究。气象学报。2000，58(1)：102-109。
108．马利华。地球自转速率的季节性变化和准两年振荡。北京：中国科学院国家天文台，博士学位论文，2006。
109．裴玉龙，王晓宁。基于BP神经网络的交通影响预测模型。哈尔滨工业大学学报。36(8)：1034-1037。
110．戚德虎，康继昌。BP神经网络设计。计算机工程与设计。1998，2：48-50．
111．汪家道，孔宪梅等。节点自删除神经网络及其在磨粒识别中的应用。清华大学学报(自然科学版)。1998，38(4)：42-46。
112．王文剑。一种输入驱动的BP网络高效学习算法。系统工程理论与实践。2000，20：99-101。
113．谢伯全。大气对地球定向参数(EOP)的高频激发。上海：中国科学院上海天文台，硕士学位论文，1994。
114．叶叔华，黄碱。天文地球动力学。山东：山东科学技术出版社，2000。
115．应行仁。三层神经网络隐单元与样本记忆的关系。模式识别与人工智能。1990，3(1)：29-34。
116．虞南华，郑大伟。地球自转及其和地球物理现象的联系：Ⅱ地极运动。地球物理学进展。1996，11(3)：70-81。
117．虞南华，郑大伟。大气角动量资料源的变化对研究日长变化激发的贡献。天文学报。1998，39(2)：122-130。
118．虞南华，郑大伟。大气对地球自转季节性变化的贡献。天文学报。2000，41(2)：148-152。
119．虞南华。大气、海洋对地球自转变化的影响。上海：中国科学院上海天文台，博士学位论文，1998。
120．袁曾任。人工神经元网络及其应用。北京：清华大学出版社，1999。
121．郑大伟，虞南华。地球自转及其和地球物理现象的联系：Ⅰ日长变化。地球物理学进展。1996，11(2)：81-104。
122．郑大伟，丁晓利，周永宏等。ELNino事件的前兆现象在日长格海平面观测中的反映。科学通报。2000，45(23)：2572-2576。
123．郑大伟，周永宏，廖新浩等。日长年际变化与1982-1983年和1997-1998年ENSO事件。中国科学(A辑)。2000，30(10)：946-953。
124．赵铭。天体测量学导论。北京：中国科学技术出版社，2006。
125．周永宏，郑大伟。日长年际变化、El Nino／南方涛动和大气准两年振荡的小波分析。天文学报。1997，38(2)：209-214。
126．周永宏，郑大伟，虞南华。大气和海洋对周年极移的激发。科学通报。1999，44(15)：1605-1608。
127．周永宏，郑大伟，虞南华等。地球自转运动与大气、海洋活动。科学通报。2000，45(24)：2588-2597。
128．周永宏，郑大伟，廖新浩。日长变化、大气角动量和ENSO：1997～1998厄尔尼诺和1998～1999拉尼娜信号。测绘学报。2001，30(4)：288-292。
129．周永宏。地球自转和地震活动关系的分析与研究。上海：中国科学院上海天文台，硕士学位论文，1993。
130．周永宏。气象涛动对地球自转变化激发的分析与研究。上海：中国科学院上海天文台，博士学位论文，1997。
131．曾文，张训械等。利用人工神经网络建立我国南海地区电离层模式。地球物理学报。1999，42(5)：581-589。
132．张训械，胡雄，吕级三。地球无线电掩星观测及其在航天技术中的应用。导弹与航天运载技术。2004，5：1-8。
133．张烈平，周德俭，牛秦洲。基于BP神经网络的预测建模系统的研究与实现。计算机仿真。2004，21(9)：48-50。
134．翟盘茂。国内外ENSO监测和预测技术分析。浙江气象。2003，24(2)：1-6。
2. Akyilmaz O, Kutterer H. Prediction of Earth rotation parameters by fuzzy inference systems. Journal of Geodesy. 2004, 78: 82-93.
3. Anshelevich VV, Amirikian BR, Lukashin AV, et al. On the ability of neural networks to perform generalization by induction. Biological Cybernetics. 1989, 61: 125-128.
4. Barnes RTH., Hide R, White AA and Wilson CA. Atmospheric angular momentum fluctuation, length-of-day changes and polar motion. Proc. R. Soc. Lond., Ser. A. 1983, 387: 31-73.
5. Blum EK, Li LK. Approximation theory and feedforward networks. Neural Networks. 1991, 4(4): 511-515.
6. Bodri L, Cermak V. Prediction of surface air temperature by neural network example based on three-year temperature monitoring at Sporilov station. Stud. Geophys. Geod. 2003, 47: 173-184.
7. Chao BF. Predictability of the Earth's polar motion. Bull Geod. 1984, 59: 81-93.
8. Chao BF. On the excitation of the Earth's polar motion. Geophysical Research Letters. 1985, 12(8): 526-529.
9. Chao BF. Length of day variations caused by El Nino-Southern Oscillation and Quasi-Biennial Oscillation. Science, 1989, 243: 923.
10. Chen JL, Wilson CR, Hu XG, et al. Oceanic effects on polar motion determined from an ocean model and satellite altimetry: 1993-2001. Journal of Geophysical Research-Solid Earth. 2004, 109 (B2): Art. No. B0241.
11. Chin TM, Gross RS, Dickey JO. Modeling and forecast of the polar motion excitation functions for short-term polar motion prediction. Journal of Geodesy. 2004, 78:343-353, DOI 10.1007/s00190-004-0411-4.
12. Chin TM, Gross RS, Dickey JO. Multi-reference evaluation of uncertainty in earth orientation parameter measurements. Journal of Geodesy. 2005, 79: 24-32. DOI 10.1007/s00190-005-0439-0.
13. Dennis D. McCarthy, G'erard Petit (eds.). IERS Conventions (2003), IERS Technical Note; 32, Observatoire de Paris, Paris.
14. Dickey JO, Marcus SL, Hide R, et al. Angular momentum exchange among the solid Earth, atmosphere and oceans: A case study of the 1982-1973 El Nino event. J. Geophys. Res. 1994, 99(B12): 23921-23938.
15. Dickey JO, Marcus SL, Steppe JA, et al. The Earth's angular momentum budget on subseaeonal time scales. Science. 1992, 255: 321-324.
16. Egger D. Neuronales Netz pradiziert Erdrotation. In: Allgemeine Vermessungsnachrichten (AVN), 1992,11/12, S: 517-524.
17. Egger D, FROHLICH H.: Pradiktion von Erdrotationsdaten klassisch und neuronal, in: Allgemeine Vermessungsnachrichten (AVN) 1993, 10, S.366-375.
18. Eubanks TM. Variations in the Orientation of the Earth, in Contributions of Space Geodesy to Geodynamic: Earth Dynamics, Geodyn. Ser., edited by Smith D and Turcotte D. Washington, D.C.: AGU, 1993. 1-54.
19. Florian Seitz, Jochen Stuck, Maik Thomas. Consistent atmospheric and oceanic excitation of the Earth's free polar motion. Geophysical Journal International. 2004, 157:25-35.
20. Gross RS, Fukumori I, Menemenlis D. Atmospheric and oceanic excitation of the Earth's wobbles during 1980-2000. Journal of Geophysical Research. 2002, 108(B8), 2370, doi:10.1029/2002JB002143.
21. Gross RS, Fukumori I, Menemenlis D. Atmospheric and oceanic excitation of decadal-scale Earth orientation variations. Journal of Geophysical Research. 2005, 110, B09405, doi: 10.1029/2004JB003565.
22. Gross RS, I Fukumori D, Menemenlis, et al. Atmospheric and oceanic excitation of length-of-day variations during 1980-2000. Journal of Geophysical Research. 2004, 109, B01406., doi: 10.1029/2003JB002432.
23. Hecht-Nielson R. Kolmogorov's mapping neural network existence theorem. IEEE Conference on Neural Networks. 1987, 3: 11-14.
24. Hecht-Nielson R. Theory of the back propagation neural network. International Conference on Neural Network. Washington D C: Reading pub, 1989.
25. Henrique Steinherz Hippert, Carlos Eduardo Pedreira, Reinaldo Castro Souza. Neural Networks for Short-Term Load Forecasting: A Review and Evaluation. IEEE TRANSACTIONS ON POWER SYSTEMS. 2001, 16(1): 44-55.
26. Hippert HS, Pedreira CE. Estimating temperature profiles for short-term load forecasting: neural networks compared to linear models, IEE Proc.-Gener. Transm. Distrib. 2004, 151(4): 543-547.
27. Hopfield JJ. Neural network and physical system with emergent collective computational abilities. Proc. Natl. Acad. Sci. 1982, USA, 79: 2254-2258.
28. Hopfield JJ. Neurons with graded response have collective computational properties like those of two state neurons. Proc. Natl. Acad. Sci. 1984, USA, 81: 3088-3092.
29. Hu X, Liao X, Huang C. Data weighting and solution assessment in combination. Journal of Geodesy. 1999, 73 (8): 391-397.
30. Huang CL, Dehant V, Liao XH. The explicit scalar equations of infinitesimal elastic-gravitational motion in the rotating, slightly elliptical fluid outer core of the Earth. Geophysical Journal International. 2004,157 (2): 831-837.
31. Huang CL, Liao XH. Comment on 'Representation of the elastic-gravitational excitation of a spherical Earth model by generalized spherical harmonics' by Phinney & Burridge. Geophysical Journal International. 2003, 155 (2): 669-678.
32. Huang W, Lippmann R P. Comparisons between neural net and conventional classifiers. IEEE first Int.Conf. Neural Networks. San Diego, 1987 : 741-746.
33. Hopfner J. Interannual variations in length of day and atmospheric angular momentum with respect to ENSO cycles. Scientific Technical Report, No.: STR99/07, presented at the 22nd General Assembly International Union of Geodesy and Geophysics Birmingham, UK, 18-30 July 1999.
34. Jacek MZ. Introduction to Artificial Neural Systems. New York: West Pub Company, 1992.
35. Jolanta Nastula, David A Salstein, Barbara Kot aczek. Time Variable Atmospheric and Oceanic Signals in Excitation Functions of Polar Motion. IERS Technical Note, No.30.
36. Kalarus M, Schuh H, Kosek W, et al. The application of artificial neural networks and autoregressive techniques for Earth Orientation Parameters prediction. EGU, Vienna, Austria, 24-29 April 2005.
37. Kalarus M, Kosek W. Prediction of Earth Orientation Parameters by artificial neural networks. Earth Rotation and Satellite Geodesy from Astrometry to GNSS, Warsaw, 18-19 September 2003.
38. Kosek W, McCarthy DD, Luzum BJ. Possible improvement of Earth orientation forecast using autocovariance prediction procedures. Journal of Geodesy. 1998, 72: 189-199.
39. Kung SY, Hwang JN. An algebraic projecting analysis for optimal hidden unit size and learning rate in backpropagation learning. Proceedings of IEEE International Conference on Neural Networks. San Diego, 1988,1- 262-270.
40. Lambeck K. The Earth's Variable Rotation. New York: Cambridge University Press, 1980.
41. Liao DC, Greiner-Mai H. A new ALOD series in monthly intervals (1892.0-1997.0) and its comparison with other geophysical result. Journal of Geodesy. 1999, 73 (9): 466-477.
42. Liao DC, Liao XH. New evidence for possible impact of solar activity on long-term fluctuation of the earth rotation. Chinese Science Bulletin. 2001, 46 (11): 905-908.
43. Liao DC, Liao XH, Zhou YH. Contribution of oceanic and atmospheric excitations to the Chandler wobble. Chinese Journal of Geophysical-Chinese Edition. 2003, 46 (4): 455-461.
44. Liao DC, Liao XH, Zhou YH. Oceanic and atmospheric excitation of the Chandler wobble. Geophysical Journal International. 2003, 152 (1): 215-227.
45. Liao DC, Liao XH, Zhou YH. Statistical property of the Chandler wobble excitation function. Chinese Science Bulletin. 2004, 49 (22): 2348-2353.
46. Liao DC, Zhou YH. Chandler wobble period and Q derived by wavelet transform. Chinese Journal of Astronomy and Astrophysics. 2004, 4 (3): 247-257.
47. Liao DC, Liao XH, Zhou YH, et al. Hydrological, atmospheric and oceanic excitations of the Chandler wobble. Chinese Astronomy and Astrophysics. 2004, 28 (2): 212-221.
48. Liao X, Zhang K, Chang Y. On boundary-layer convection in a rotating fluid layer. Journal of Fluid Mechanics. 2006, 549: 375-384.
49. Liao XH, Zhang KK. On the convective excitation of torsional oscillations in rotating systems. Astrophysical Journal. 2006, 638 (2): L113-L116 Part 2.
50. Liao X, Zhang K, Chang Y. Nonlinear torsional oscillations in rotating systems. Physical Review Letters. 2007, 98 (9): Art. No.094501.
51. Lippmann R P. An Introduction to Computing with Neural Nets. IEEE ASSP Magazine. 1987: 4-22.
52. Luzum BJ, Ray JR, Carter MS, et al. Recent improvements to IERS Bulletin A Combination and Prediction. GPS Solution. 2001, 4(3): 33-40.
53. Ma LH, Liao DC, Han YB. Atmospheric and oceanic excitations to LOD change on quasi-biennial time scales. Chinese Journal of Astronomy and Astrophysics. 2006, 6 (6): 759-768.
54. Magali RG Meireles, Paulo EM Almeida, Marcelo Godoy Simoes, A comprehensive Review for Industrial Applicability of Artificial Neural Networks. IEEE transactions on industrial electronics. 2003, 50(3): 585-601.
55. Malkin, Skurikhina. On prediction of EOP. Comm IAA, 1991, 93.
56. Malkin Z. On Estimation of Real Accuracy of EOP Prediction. In: Dick S, McCarthy D, Luzum B(eds) Polar Motion: Historical and Scientific Problems, IAU Coll. 187, Cagliari, Italy, Sep 27-30, 1999. ASP, San Francisco 208: 505-510.
57. McCarthy, Luzum. Prediction of Earth Orientation. Bull Geod. 1991, 65: 18-22.
58. McCarthy DD, Petit G. IERS Convension (2003). IERS Technical Note 32. Paris : Observatoire de Paris, 2003.
59. Moorthi S, Pan HL, Caplan P. Changes to the 2001 NCEP operational MRF/AVN global analysis/forecast system. NWS Technical Procedures Bulletin, 2001, 484:1-14.
60. Munk WH, MacDonald GJF. The Rotation of the Earth—A Geophysical Discussion. New York: Cambridge University Press. 1960.
61. Ojo AK, Games GK. Selecting ANN Models for Geoidal Undulation Prediction. In: Proceedings of the 2003 International Conference on Artificial Intelligence. Las Vegas: CSREA Press,2003.Vol 1, 191-192.
62. Ojo AK, James GK. Artificial Neural Networks for Geoidal Undulation Prediction. International Conference on Artificial Intelligence, 2003.
63. Peter J. Huber. Modeling the length of day and extrapolating the rotation of the Earth. Journal of Geodesy. 2006, 80(6): 283-303, DOI 10.1007/s00190-006-0067-3.
64. Robert Scott Weigel. Prediction and modeling of magnetospheric substorms [PH.D thesis]. Austin, USA: The University of Texas at Aystin, 2000.
65. Salstein D A, Kann D M, Miller A J, et al. The sub-bureau for atmospheric angular momentum of the international earth rotation service: a meteorological data center with geodetic applications. Bull. Am. Meteor. Soc.1993,74: 67-80.
66. Schuh H, Ulrich M, Egger D, et al. Prediction of Earth orientation parameters by artificial neural networks. Journal of Geodesy. 2002, 76: 247-258.
67. Schuh H, Kosek W, et al. First results of the earth orientation parameters prediction comparison campaign, EGU, Vienna, Austria, 2-7 April 2006.
68. Thomas Toniazzo, Adam A Scaife. The influence of ENSO on winter North Atlantic climate. Geophysical Research Letters. 2006, 33, L24704, doi: 10.1029/2006GL027881,.
69. Thomas J Johnson, Brian J Luzum, Jim R Ray. Improved near-term Earth rotation predictions using atmospheric angular momentum analysis and forecasts. Journal of Geodynamics. 2005, 39: 209-221.
70. Wieland A, Leighton R. Geometric analysis of neural network capabilities. IEEE First International conference on Neural Networks. 1987, 3: 385-392.
71. Wooden WH, Johnson TJ. "Rapid Service/Prediction Centre," IERS Annual Report 2002. 2003,46-53.
72. Yan HM, Zhong M, Zhu YZ, et al. Nontidal oceanic contribution to length-of-day changes estimated from two ocean models during 1992-2001. Journal of Geophysical Research -Solid Earth. 2006, 111 (B2): Art. No. B0410.
73. Yu N, Zheng D, Wu H. Contribution of new AAM data source to ALOD excitation. Journal of Geodesy. 1999, 73: 385-390.
74. Zheng DW, Song GX, Luo SF. El Nino prediction. Nature. 1990, 348:119.
75. Zheng DW, Chao BF, Zhou YH, et al. Improvement of edge effect of the wavelet time-frequency spectrum: application to the length-of-day series. Journal of Geodesy. 2000, 74: 249-254.
76. Zheng DW, Ding XL, Zhou YH, et al. Premonitory phenomenon of El Nino event reflected in the observations of LOD and sea level. Chinese Science Bulletin. 2000, 45(24): 2231-2235.
77. Zheng DW, Zhou YH, Liao XH. Interannual variation in the length of day and ENSO events in 1982-1983 and 1997-1997. Science in China (Series A). 2001, 44(1): 128-137.
78. Zheng DW, Ding XL, Zhou YH, et al. Earth rotation and ENSO events: combined excitation of interannual LOD variations by multiscale atmospheric oscillations. Global and Planetary Change. 2003, 36 (1-2): 89-97.
79. Zhou YH, Zheng DW, Zhao M, et al. Interannual polar motion with relation to the North Atlantic Oscillation. Global and Planetary Change. 1998, 18: 79-84.
80. Zhou YH, Zheng DW, Yu NH, et al. Excitation of annual polar motion by atmosphere and ocean. Chinese Science Bulletin. 2000, 45 (2): 139-142.
81. Zhou YH, Wu HQ, Yu NH. Excitation of seasonal polar motion by atmospheric and oceanic angular momentums. Progress in Natural Science. 2000, 10(12): 931-936.
82. Zhou YH, Zheng DW, Liao XH. Wavelet analysis of interannual LOD, AAM, and ENSO: 1997-98 El Nino and 1998-99 La Nina signals. Journal of Geodesy. 2001, 75: 164-168.
83. Zhou YH, Zheng DW, Yu NH, et al. Movement of Earth rotation and activities of atmosphere and ocean. Chinese Science Bulletin. 2001, 46(11): 881-888.
84. Zhou YH, Yan XH, Ding XL, et al. Excitation of non-atmospheric polar motion by the migration of the Pacific Warm Pool. Journal of Geodesy. 2004, 78:109-113. DOI 10. 1007/s00190-004-0380-7.
85. Zhou YH, Chen JL, Liao XH, et al. Oceanic excitations on polar motion: a cross comparison among models. Geophysical Journal International. 2005, 162, 390-398, doi: 10.1111/j. 1365-246X.2005.02694.x.
86. Zhou YH, Salstein DA, Chen JL. Revised atmospheric excitation function series related to Earth's variable rotation under consideration of surface topography. Journal of Geophysical Research. 2006, 111, D 12108, doi: 10.1029/2005JD006608.
87. Zhong M, Zhu YZ, Gao BX, et al. Atmospheric, hydrological and oceanic comprehensive contributions to seasonal polar wobble of Earth Rotation. Science in China Series A-Mathematics Physics Astronomy. 2002, 45 (12): 1620-1627.
88. Zhong M, Yan HM, Zhu YZ, et al. Atmospheric angular momentum fluctuations and their excitations of earth rotation variations at seasonal scale. Chinese Astronomy and Astrophysics. 2002, 26 (3): 363-371.
89. Zhong M, Yan HM, Zhu YZ. The investigation of atmospheric angular momentum as a contributor to polar wobble and length of day change with AMIP Ⅱ GCM data. Advance in Atmospheric Science. 2002, 19 (2): 287-296.
90. Zhong M, Naito I, Kitoh A. Atmospheric, hydrological, and ocean current contributions to Earth's annual wobble and length-of-day signals based on output from a climate model. Journal of Geophysical Research -Solid Earth. 2003, 108 (B1): Art. No. 2057.
91. Zhong M, Yan HM, Wu XP, et al. Non-tidal oceanic contribution to polar wobble estimated from two oceanic assimilation data sets. Journal of Geodynamics. 2006, 41 (1-3): 147-154.
92. Zhu SY. Prediction of polar motion. Bull Geod, 1982, 56:258-273.
93．丁月蓉，郑大伟。天文测量数据的处理方法。南京：南京大学出版社，1990。
94．付英，曾敏，李兴源。隐含层人工神经网络电压安全评估的影响。电力系统自动化。1996，20(11)：13-16。
95．高大启。有教师的线性基本函数前向三层神经网络结构研究。计算机学报。1998，21(1)：80-86。
96．顾晖。地球自转和大气角动量“50天”波动的特征。上海：中国科学院上海天文台，硕士学位论文，1991。
97．郭俊义。地球物理学基础。北京：测绘出版社，2001。
98．胡守仁，余少波，戴葵。神经网络导论。湖南：国防科技大学出版社，1993。
99．金龙。神经网络气象预报建模理论方法与应用。北京：气象出版社，2004。
100．焦李成。神经网络系统理论。西安：西安电子科技大学出版社，1996。
101．蒋伟进。非线性混沌时序的神经网络预测与控制算法研究。计算机应用与软件。21(4)：81-83。
102．雷正伟，徐章遂，米东等。神经网络的预测性能的优化分析。计算机测量与控制。2004，12(1)：15-20。
103．廖德春，廖新浩。全球陆地水储量对地球自转变化的激发作用。天文学报。2000，41(4)：373～383。
104．廖德春，周永宏，廖新浩。天文观测已检测到2002年的弱El Nino事件。科学通报。2003，48(11)：1135-1138．
105．廖德春，廖新浩，周永宏。海洋和大气对Chandler摆动激发的贡献。地球物理学报。2003，46(4)：455-461。
106．廖德春，廖新浩，周永宏。Chandler摆动激发函数的统计特性。科学通报。2004，49(22)：2284-2289。
107．李晓燕，翟盘茂。ENSO事件指数与指标研究。气象学报。2000，58(1)：102-109。
108．马利华。地球自转速率的季节性变化和准两年振荡。北京：中国科学院国家天文台，博士学位论文，2006。
109．裴玉龙，王晓宁。基于BP神经网络的交通影响预测模型。哈尔滨工业大学学报。36(8)：1034-1037。
110．戚德虎，康继昌。BP神经网络设计。计算机工程与设计。1998，2：48-50．
111．汪家道，孔宪梅等。节点自删除神经网络及其在磨粒识别中的应用。清华大学学报(自然科学版)。1998，38(4)：42-46。
112．王文剑。一种输入驱动的BP网络高效学习算法。系统工程理论与实践。2000，20：99-101。
113．谢伯全。大气对地球定向参数(EOP)的高频激发。上海：中国科学院上海天文台，硕士学位论文，1994。
114．叶叔华，黄碱。天文地球动力学。山东：山东科学技术出版社，2000。
115．应行仁。三层神经网络隐单元与样本记忆的关系。模式识别与人工智能。1990，3(1)：29-34。
116．虞南华，郑大伟。地球自转及其和地球物理现象的联系：Ⅱ地极运动。地球物理学进展。1996，11(3)：70-81。
117．虞南华，郑大伟。大气角动量资料源的变化对研究日长变化激发的贡献。天文学报。1998，39(2)：122-130。
118．虞南华，郑大伟。大气对地球自转季节性变化的贡献。天文学报。2000，41(2)：148-152。
119．虞南华。大气、海洋对地球自转变化的影响。上海：中国科学院上海天文台，博士学位论文，1998。
120．袁曾任。人工神经元网络及其应用。北京：清华大学出版社，1999。
121．郑大伟，虞南华。地球自转及其和地球物理现象的联系：Ⅰ日长变化。地球物理学进展。1996，11(2)：81-104。
122．郑大伟，丁晓利，周永宏等。ELNino事件的前兆现象在日长格海平面观测中的反映。科学通报。2000，45(23)：2572-2576。
123．郑大伟，周永宏，廖新浩等。日长年际变化与1982-1983年和1997-1998年ENSO事件。中国科学(A辑)。2000，30(10)：946-953。
124．赵铭。天体测量学导论。北京：中国科学技术出版社，2006。
125．周永宏，郑大伟。日长年际变化、El Nino／南方涛动和大气准两年振荡的小波分析。天文学报。1997，38(2)：209-214。
126．周永宏，郑大伟，虞南华。大气和海洋对周年极移的激发。科学通报。1999，44(15)：1605-1608。
127．周永宏，郑大伟，虞南华等。地球自转运动与大气、海洋活动。科学通报。2000，45(24)：2588-2597。
128．周永宏，郑大伟，廖新浩。日长变化、大气角动量和ENSO：1997～1998厄尔尼诺和1998～1999拉尼娜信号。测绘学报。2001，30(4)：288-292。
129．周永宏。地球自转和地震活动关系的分析与研究。上海：中国科学院上海天文台，硕士学位论文，1993。
130．周永宏。气象涛动对地球自转变化激发的分析与研究。上海：中国科学院上海天文台，博士学位论文，1997。
131．曾文，张训械等。利用人工神经网络建立我国南海地区电离层模式。地球物理学报。1999，42(5)：581-589。
132．张训械，胡雄，吕级三。地球无线电掩星观测及其在航天技术中的应用。导弹与航天运载技术。2004，5：1-8。
133．张烈平，周德俭，牛秦洲。基于BP神经网络的预测建模系统的研究与实现。计算机仿真。2004，21(9)：48-50。
134．翟盘茂。国内外ENSO监测和预测技术分析。浙江气象。2003，24(2)：1-6。