Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Basic Disciplines of Agriculture submitted time 2023-08-14 Cooperative journals: 《智慧农业（中英文）》
Abstract： [Objective] Deep learning is one of the most important technologies in the field of artificial intelligence, which has sparked a research boom in academic and engineering applications. It also shows strong application potential in remote sensing retrieval of geophysical parameters. The cross-disciplinary research is just beginning, and most deep learning applications in geosciences are still "black boxes", with most applications lacking physical significance, interpretability, and universality. In order to promote the application of artificial intelligence in geosciences and agriculture and cultivate interdisciplinary talents, a paradigm theory for geophysical parameter retrieval based on artificial intelligence coupled physics and statistical methods was proposed in this research. [Methods] The construction of the retrieval paradigm theory for geophysical parameters mainly included three parts: Firstly, physical logic deduction was performed based on the physical energy balance equation, and the inversion equation system was constructed theoretically which eliminated the ill conditioned problem of insufficient equations. Then, a fuzzy statistical method was constructed based on physical deduction. Representative solutions of physical methods were obtained through physical model simulation, and other representative solutions as the training and testing database for deep learning were obtained using multi-source data. Finally, deep learning achieved the goal of coupling physical and statistical methods through the use of representative solutions from physical and statistical methods as training and testing databases. Deep learning training and testing were aimed at obtaining curves of solutions from physical and statistical methods, thereby making deep learning physically meaningful and interpretable. [Results and Discussions] The conditions for determining the formation of a universal and physically interpretable paradigm were: (1) There must be a causal relationship between input and output variables (parameters); (2) In theory, a closed system of equations (with unknowns less than or equal to the number of equations) can be constructed between input and output variables (parameters), which means that the output parameters can be uniquely determined by the input parameters. If there is a strong causal relationship between input parameters (variables) and output parameters (variables), deep learning can be directly used for inversion. If there is a weak correlation between the input and output parameters, prior knowledge needs to be added to improve the inversion accuracy of the output parameters. The MODIS thermal infrared remote sensing data were used to retrieve land surface temperature, emissivity, near surface air temperature and atmospheric water vapor content as a case to prove the theory. When there was strong correlation between output parameters (LST and LSE) and input variables (BTi), using deep learning coupled with physical and statistical methods could obtain very high accuracy. When there was a weak correlation between the output parameter (NSAT) and the input variable (BTi), adding prior knowledge (LST and LSE) could improve the inversion accuracy and stability of the output parameter (NSAT). When there was partial strong correlation (WVC and BTi), adding prior knowledge (LST and LSE) could slightly improve accuracy and stability, but the error of prior knowledge (LST and LSE) may bring uncertainty, so prior knowledge could also be omitted. According to the inversion analysis of geophysical parameters of MODIS sensor thermal infrared band, bands 27, 28, 29 and 31 were more suitable for inversion of atmospheric water vapor content, and bands 28, 29, 31 and 32 were more suitable for inversion of surface temperature, Emissivity and near surface air temperature. If someone want to achieve the highest accuracy of four parameters, it was recommended to design the instrument with five bands (27, 28, 29, 31, 32) which were most suitable. If only four thermal infrared bands were designed, bands 27, 28, 31, and 32 should be given priority consideration. From the results of land surface temperature, emissivity, near surface air temperature and atmospheric water vapor content retrieved from MODIS data using this theory, it was not only more accurate than traditional methods, but also could reduce some bands, reduce satellite load and improve satellite life. Especially, this theoretical method overcomes the influence of the MODIS official algorithm (day/night algorithm) on sudden changes in surface types and long-term lack of continuous data, which leads to unstable accuracy of the inversion product. The analysis results showed that the proposed theory and conditions are feasible, and the accuracy and applicability were better than traditional methods. The theory and judgment conditions of geophysical parameter retrieval paradigms were also applicable for target recognition such as remote sensing classification, but it needed to be interpreted from a different perspective. For example, the feature information extracted by different convolutional kernels must be able to uniquely determine the target. Under satisfying with the conditions of paradigm theory, the inversion of geophysical parameters based on artificial intelligence is the best choice. [Conclusions] The geophysical parameter retrieval paradigm theory based on artificial intelligence proposed in this study can overcome the shortcomings of traditional retrieval methods, especially remote sensing parameter retrieval, which simplify the inversion process and improve the inversion accuracy. At the same time, it can optimize the design of satellite sensors. The proposal of this theory is of milestone significance in the history of geophysical parameter retrieval.
Subjects: Agriculture, Forestry,Livestock & Aquatic Products Science >> Basic Disciplines of Agriculture submitted time 2023-05-30 Cooperative journals: 《智慧农业（中英文）》
MAO Kebiao
ZHANG Chenyang
SHI Jiancheng
WANG Xuming
GUO Zhonghua
LI Chunshu
DONG Lixin
WU Menxin
SUN Ruijing
WU Shengli
JI Dabin
JIANG Lingmei
ZHAO Tianjie
QIU Yubao
DU Yongming
XU Tongren
Abstract： Deep learning is one of the most important technologies in the field of artificial intelligence, which has sparked a research boom in academic and engineering applications. It also shows strong application potential in remote sensing retrieval of geophysical parameters. The cross-disciplinary research is just beginning, and most deep learning applications in geosciences are still "black boxes", with most applications lacking physical significance, interpretability, and universality. A paradigm theory for geophysical parameter retrieval based on artificial intelligence coupled physics and statistical methods was proposed in this research. Firstly, physical logic deduction was performed based on the physical energy balance equation, and the inversion equation system was constructed theoretically. Then, a fuzzy statistical method was constructed based on physical deduction. Representative solutions of physical methods were obtained through physical model simulation, and other representative solutions as the training and testing database for deep learning were obtained using multi-source data. Finally, the solution using deep learning was optimized. The conditions for determining the formation of a universal and physically interpretable paradigm are: (1) There must be a causal relationship between input and output variables (parameters); (2) In theory, a closed system of equations (with unknowns less than or equal to the number of equations) can be constructed between input and output variables (parameters), which means that the output parameters can be uniquely determined by the input parameters. If there is a strong causal relationship between input parameters (variables) and output parameters (variables),deep learning can be directly used for inversion. If there is a weak correlation between the input and output parameters, prior knowledge needs to be added to improve the inversion accuracy of the output parameters. Thermal infrared remote sensing data were used to retrieve land surface temperature, emissivity, near surface air temperature and atmospheric water vapor content as a case to prove the theory. The analysis results show that the proposed theory and conditions are feasible, and the accuracy and applicability are better than traditional methods. The theory and judgment conditions of geophysical parameter retrieval paradigms are also applicable for target recognition such as remote sensing classification, but it needs to be interpreted from a different perspective. For example, the feature information extracted by different convolutional kernels must be able to uniquely determine the target. Under satisfying with the conditions of paradigm theory, the inversion of geophysical parameters based on artificial intelligence is the best choice. The proposal of this theory is of milestone significance in the history of geophysical parameter retrieval.
Subjects: Astronomy >> Astrophysical processes submitted time 2022-01-14 Cooperative journals: 《天文研究与技术》
Abstract：随着空间天文卫星获取数据量越来越多，数据应用逐渐发挥了重要作用。现有的天文卫星地面系统中，数据存储方式和组织方法各异，数据量达PB级，并且数据量持续增长，无法快速查找并提取特征参数，难以满足数据应用对查询的时效性要求。本文提出了一种新的空间天文卫星数据组织方法，通过解析抽取数据中的海量特征参数，建立观测时间、空间位置与特征参数的关联，实现在统一时空下的多源数据组织；同时采用关系型数据库与非关系型数据库结合的异构存储方式，设计了海量特征参数存储管理系统。将本文方法应用于空间科学卫星大数据应用平台系统中，使用硬X射线调制望远镜卫星数据的实验结果表明，系统针对按照时间、空间条件获取数据的要求能够较好满足，相比关系型数据库数据组织方式，相同查询模式下数据检索效率明显提高；并且随着数据存储量的增加，系统具有稳定的扩展能力。
Subjects: Astronomy >> Astrophysical processes submitted time 2021-05-27 Cooperative journals: 《天文研究与技术》
Abstract：GECAM是专门针对引力波伽马暴的研究机遇而提出的中国科学院空间科学（二期）先导专项卫星任务。GECAM卫星通过数传、遥测以及北斗短报文三个通道下行触发、事例、并道、工程以及短报文等多种类型的数据，数据预处理过程需要对这些数据进行快速正确处理，以满足科学家对天文事件数据正确性和时效性的要求。本文针对GECAM卫星数据处理时效性要求高、数据连续完整、多信道数据融合处理以及触发事件数据切分等特点，对科学数据处理流程和天文警报信息处理流程进行了设计，概述了关键核心算法的思路与实现方法。卫星发射入轨后，数据预处理软件运行良好，正确性和及时性指标满足要求，为后续爱因斯坦探针（EP）卫星、中法天文卫星（SVOM）等空间天文卫星开展数据预处理工作提供了参考。
Subjects: Geosciences >> Space Physics submitted time 2017-03-10
Abstract：太阳跟踪研究的发展，向太阳跟踪器的控制系统智能化提出了更高的要求。以SOLYS Gear Drive 太阳跟踪器为仪器平台，创新性地提出利用路由器建立控制主机和太阳跟踪器在局域网内，以及局域网和互联网之间的通信,并以虚拟仪器开发软件LabVIEW为软件平台，综合调用百度地图应用程序接口API和指令脚本文件，设计了一套控制系统。实现对仪器的状态监测，指令控制，远程访问等。系统功能丰富，操作简单，界面可视化好，普遍适用性强。
Peer Review Status:
Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： In order to ensure quantum science experiments can be developed smoothly, a high data rate two-way link for Space-Ground microwave communication must be established. Via following the study on Consultative Committee for Space Data Systems (CCSDS) and taking into account the scientific requirements of microwave communication link for quantum science experiment satellite, the physical layer hardware architecture and modulation/demodulation algorithm of microwave communication link for the satellite are presented.The uplink modulation type of the microwave communication link is SRRC-OQPSK, which accord with CCSDS spectrum standard. The specification of uplink data rate is 1.024Mbps,. The downlink modulation type of the microwave communication link is SRRC-OQPSK/GMSK, and the data rate is 4Mbps. By compatible tests with several ground stations, we find that the sensitivity of carrier acquisition is superior to -100dBm, and AGC ability is greater than 43dB. Moreover, the bit error rate of actual transmission is superior to 1�0-9 as the received signal level is equal to -96 dBm. The measured results indicate that the physical layer design scheme of microwave communication link meets the requirements of space quantum science experiments.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： Multi-point synchronous magnetic field measurements can give more accurate space current density compared with the traditional single-point measurement, since multi-point measurement can eliminate the temporal change in the magnetic field. Based on the current density inversion method for multi-point magnetic field measurements, through simulation, several factors affecting space current density inversion are analyzed, such as the number of satellites, satellite formation configuration, satellite positioning precision, satellite attitude determination error, magnetic field measurement accuracy, external magnetic field intensity, external current density and so on. It is shown that 5-point measurements are better than 4-point measurements, and error in attitude determination and external magnetic field intensity are the main factors causing the error in current density inverted, while satellite formation configuration is also an important factor. According to the simulation, the maximum error in current density is less than 24% near the equator when the attitude determination error is 0.001癮nd the scale of the satellite formation is about 100km.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： By studying Rayleigh lidar data，The seasonal variations of atmospheric temperature of 35-70km in Beijing area are analyzed.The atmospheric temperature between 30-70km height range at Beijing region has obvious annual cycle variation. The highest temperature in the stratosphere appeared in June and July, which is about 270K. The lowest temperature in the middle layer 70km is also in June, July, about 200K. Take the data of October 14, 2014 as an example， Gravity wave dissipation under 50km is found，while， the gravity waves propagate upward almost without dissipation above 50km.By comparing the average potential energy density between 35-50km height range, the seasonal variation of the gravity waves activities intensity in the Beijing area was studied. The gravity waves activities over Beijing have an obvious cycle of one year.The average potential energy density in winter is , while in summer, the average potential energy density is , the gravity waves activities intensity in winter is about two times of that in summer. In addition, the profile of seasonal averaged gravity waves potential energy density are given in spring,summer,autumn and winter. The dissipation of gravity waves in different seasons and different heights is analyzed in Beijing area.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： A general design of solar neutral atom code mask imager (SONACOMI) is proposed. The instrument is designed to measure the solar energetic atom emitted from the solar flare or CME, measuring the differential energy spectrum of ENAs between 0.5MeV/u and 6MeV/u and FOV of ENAs covering . This instrument combines innovative sensor geometry, an m series coding mask modulation aperture, and a combination of high voltage deflecting plate of active and passive shielding charging particles to obtain ENAs in space flight.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： This study use the wind data from the observation of China Langfang (39°N，117°E) meteor radar during the 1 April 2012 to 31 March 2013 to investigate the features of the mesospheric and lower thermospheric mean winds within 80-100 km altitude regions. The results show that the mean zonal winds and mean meridional winds both have obviously seasonal variations. During the winter, eastward winds prevail in the MLT ranges, which is strong in mesosphere and decrease versus increasing altitude. In the summer, westward winds dominate in mesosphere, and decrease along with increasing altitude, then turn to the strong eastward in lower thermosphere. The wind evolution in the spring and autumn are the transition characters between the summer and winter. The mean meridional winds are southward in summer and northward with sometimes reversal in winter, in general. The above main seasonal variations of mean winds are captured largely by the simulation of WACCM4 model and HWM93 model. WACCM overestimates the winds, but HWM93 underestimates the winds.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： Parameterized ionosphere model TIEGCM is used as background model. Basing on the COSMIC observations, global ionospheric electron density assimilation model is established using ensemble Kalman filter. Result shows, this model can effectively assimilate observations into background model and acquire three dimensional ionospheric electron density. Compared to background, the error between analysis and observations decreases significantly. The root mean square error(RMSE) of NmF2 decreases about 60% for observations assimilated, and 20% for observations not assimilated. The RMSE of hmF2 doesn’t get improvement except for mean error. The results of simultaneous assimilation (SA) and batches assimilation (BA) are compared for this case. The time that the two methods spend in assimilation is about 6 to 7 minutes, which does not differ very much. SA needs nearly 8 GB storage while BA less than 2GB. The statistic of electron density error shows that they nearly acquire the same mean error, but the SA gets relative better improvement in RMSE above 250km.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： The problem of minimum-fuel aeroassisted orbital transfer of a high lift-to-drag ratio vehicle from Low Earth Orbit (LEO) or Geostationary Earth Orbit (GEO) to low-Earth orbit with an inclination change is considered. Assuming impulsive thrust, the trajectory design is described in detail and the aeroassisted orbital transfer is posed as a nonlinear optimal control problem. Through comparison of the double-impusive orbit transfer and aeroassisted orbit Transfer in noncoplanar orbit, we concluded the influence of altitude difference from two noncoplanar orbits and the perigee choice of the middle transtion orbit. The main problem that aeroassisted orbital transfer may face is hypersonic flight in the upper atmosphere. In the end the technology used in X-37B flight was concluded.
Peer Review Status:Awaiting Review
Subjects: Geosciences >> Space Physics submitted time 2017-01-22
Abstract： Solar proton event forecast is very important to guarantee the security of spacecrafts and astronauts. According to the short to medium term space mission, the greater than 10 MeV, 30 MeV and 60 MeV solar proton event fluences are statistically analyzed. It is found that the probability distributions of solar proton event fluences basically satisfy the log-normal distributions, and their expectations and averages are logarithmic functions of the time periods. Based on these, a short to medium term forecast model of solar proton event fluences is built, which can forecast the greater than 10 MeV, 30 MeV and 60 MeV solar proton event fluences with some given confidence levels for 1 to 365 days. So, this model is very helpful to safely carry out the space mission with less than 1 year mission period.
Peer Review Status:Awaiting Review
Hits
Hits
Downloads
Comment