Marine geological data mining system development and its application in seamount age prediction
-
摘要:
利用数据挖掘技术分析海洋地质调查数据,以获取其中隐藏信息,对推进海洋地质数据的科学高效利用具有重要意义。在模块化设计原则下,利用Python语言开发海洋地质数据挖掘相关的核心功能,利用WinForm搭建人机交互界面,并通过参数交互的方式实现了界面和后台功能间的互动。基于综合地质地球物理资料,利用软件预测了太平洋海山年龄。预测结果精度高于利用传统克里金插值方法所得结果的精度。应用结果表明,所开发软件的数据预处理、指标分析、综合评价等功能具有很好的实用性。
Abstract:Using data mining technology to find hidden information in the marine exploration data is important for increasing the marine data using efficiently. The core functions of marine geological data mining system (MGDMS) was developed in the Python, the graphical user interface (GUI) was designed in the WinForm, and finally the interaction between GUI and the core functions was realized via parameter transformation and transference. Based on the geological and geophysical data, the ages of seamount in the Pacific are predicted using the MGDMS, and the predicted ages are more precise than those of conventional Kriging method. Our case study result indicates that the functions of data preprocessing, index analysis, and overall evaluation with the MGDMS are suitable for marine geophysical data mining.
-
Key words:
- marine geology /
- data mining /
- system development /
- seamount age
-
表 1 用于太平洋海山年龄预测的基础数据源
Table 1. Data sources for the Pacific seamount age prediction
表 2 与海山年龄相关地球物理数据的MIV绝对值
Table 2. The absolute mean impact values of the seamount-age related geophysical observables
地球物理观测值 数据类型 处理方法 |MIV|/Ma 洋壳年龄 网格 提取 9.23 重力异常 网格 提取 3.50 海山高度 网格 提取 1.42 沉积层厚度 网格 提取 1.08 磁异常 网格 提取 0.82 海底热流 地点 内插 0.21 表 3 克里金插值算法、BP和GA-BP算法预测精度对比
Table 3. Comparison in prediction accuracy among the Kriging, BP, and GA-BP algorithms
预测模型 RMSE/Ma R² 克里金 27.54 0.60 BP模型 20.35 0.74 GA-BP模型 9.69 0.93 -
[1] LI W L,GAO S Y,HAN C H,et al. A brief analysis on data mining for deep-sea mineral resources based on big data[J]. Procedia Computer Science,2019,154:699-705. doi: 10.1016/j.procs.2019.06.109
[2] 杜艳玲. 混合云存储环境下海洋大数据的布局及迁移算法研究[D]. 上海: 上海海洋大学, 2014.
[3] JIANG K,JIANG X. Technological development of ocean mineral resources exploitation[J]. Nonferrous Metals Engineering,2011,1(1):3-8.
[4] HE G,DENG X,YANG S. Geological characteristics of polymetallic nodules in the central Indian Ocean and comparison with those from CC Zone in the eastern Pacific[J]. Marine Geology Quaternary Geology,2011,31(2):21-30. doi: 10.3724/SP.J.1140.2011.02021
[5] HAND D J. Principles of data mining[J]. Drug safety,2007,30(7):621-622. doi: 10.2165/00002018-200730070-00010
[6] ZONGXI Y,JINRONG T,PING Z. Earth science research in US Geological Survey under the big data revolution[J]. Geological Bulletin of China,2013,32(9):1337-1343.
[7] DUNHAM M H. Data mining: Introductory and advanced topics[M]. Pearson Education India, 2006.
[8] SHARMA P,SHARMA S. Past Present & Future of Data Mining[J]. IITM Journal of Information Technology,2018:42.
[9] LI C,YAN W,XIAO K,et al. Analysis and application mode of geological big data[J]. Journal of Geology,2015,39(3):352-357.
[10] LI J. Predictive modelling using random forest and its hybrid methods with geostatistical techniques in marine environmental geosciences[M]//The Proceedings of the Eleventh Australasian Data Mining Conference, 2013.
[11] OBELCZ J, XU K, BENTLEY S J, et al. Sneaky submarine landslides, and how to quantify them: a case study from the Mississippi River Delta front contrasting geophysical and machine learning techniques[C]//AGU Fall Meeting Abstracts, 2017: NH44B-03.
[12] SHENG J,SUN J,BAI Y,et al. Evaluation of hydrocarbon potential using fuzzy AHP-based grey relational analysis:a case study in the Laoshan Uplift,South Yellow Sea,China[J]. Journal of Geophysics Engineering,2020,17(1):189-202. doi: 10.1093/jge/gxz107
[13] 刘兰法. 海洋天然气水合物三维地质建模研究[D]. 青岛: 中国石油大学(华东), 2014.
[14] 李连伟,许明明,刘展,等. 天然气水合物数据挖掘服务组件的设计与实现[J]. 计算机应用与软件,2016,33(10):32-36. doi: 10.3969/j.issn.1000-386x.2016.10.008
[15] 郑文棠. 岭澳核电三期高边坡三维地形可视化[C]//岩石力学与工程的创新和实践: 第十一次全国岩石力学与工程学术大会, 2010: 5.
[16] DOMBI G W,NANDI P,SAXE J M,et al. Prediction of rib fracture injury outcome by an artificial neural network[J]. Journal of Trauma,1995,39(5):915-921. doi: 10.1097/00005373-199511000-00016
[17] JIANG J L,SU X,ZHANG H,et al. A novel approach to active compounds identification based on support vector regression model and mean impact value[J]. Chemical Biology & Drug Design,2013,81(5):650-657.
[18] LI H,ZHONG Z,LI L,et al. A cascaded QSAR model for efficient prediction of overall power conversion efficiency of all-organic dye-sensitized solar cells[J]. Journal of Computational Chemistry,2015,36(14):1036-1046. doi: 10.1002/jcc.23886
[19] ZHENG J,LAN Q,ZHANG X,et al. Prediction of MRI RF exposure for implantable plate devices using artificial neural network[J]. IEEE Transactions on Electromagnetic Compatibility,2020,62(3):673-681. doi: 10.1109/TEMC.2019.2916837
[20] RUMMEL R J. Applied factor analysis[M]. Northwestern University Press, 1988.
[21] 郭晓伟. 基于深度学习的车型识别算法与DSP平台实现[D]. 长沙: 国防科学技术大学, 2016.
[22] 李静. 煤矿震动波CT反演探测技术的优化与应用[D]. 徐州: 中国矿业大学, 2017.
[23] RUMELHART D E,HINTON G E,WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature,1986,323(6088):533-536. doi: 10.1038/323533a0
[24] DING S,SU C,YU J. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review,2011,36(2):153-162. doi: 10.1007/s10462-011-9208-z
[25] BOOKER L B,GOLDBERG D E,HOLLAND J H. Classifier systems and genetic algorithms[J]. Artificial Intelligence,1989,40(1-3):235-282. doi: 10.1016/0004-3702(89)90050-7
[26] TARDUNO J A,GEE J. Large-scale motin between Pacific and Atlantic hotspots[J]. Nature,1995,378(6556):477-480. doi: 10.1038/378477a0
[27] 朱本铎,吕文超,张伙带. 中西太平洋海山年龄及其地质意义[J]. 矿床地质,2014:1151-1152. doi: 10.3969/j.issn.0258-7106.2014.06.002
[28] TARDUNO J A,DUNCAN R A,SCHOLL D W,et al. The Emperor Seamounts:southward motion of the Hawaiian Hotspot Plume in earth's mantle[J]. Science,2003,301(5636):1064. doi: 10.1126/science.1086442
[29] WATTS A B,SANDWELL D T,SMITH W H F,et al. Global gravity,bathymetry,and the distribution of submarine volcanism through space and time[J]. Journal of Geophysical Research:Solid Earth,2006,111:B08408.
[30] FAGGION O,PINNA E,SAVELLI C,et al. Geomagnetism and age study of Tyrrhenian seamounts[J]. Geophysical Journal International,1995,123(3):915-930. doi: 10.1111/j.1365-246X.1995.tb06898.x
[31] CANDE S C,KENT D V. Ultrahigh resolution marine magnetic anomaly profiles:A record of continuous paleointensity variations?[J]. Journal of Geophysical Research Solid Earth,1992,97(B11):15075-15083. doi: 10.1029/92JB01090
[32] SETON M,MVLLER R D,ZAHIROVIC S,et al. A Global data set of present-day oceanic crustal age and seafloor spreading parameters[J]. Geochemistry,Geophysics,Geosystems,2020,21(10):e2020GC009214.
[33] VOLKER D,GEERSEN J,CONTRERAS-REYES E,et al. Sedimentary fill of the Chile Trench (32–46°S):volumetric distribution and causal factors[J]. Journal of the Geological Society,2013,170(5):723. doi: 10.1144/jgs2012-119
[34] CLAGUE D A,DALRYMPLE G B. Cretaceous K‐Ar ages of volcanic rocks from the Musicians Seamounts and the Hawaiian Ridge[J]. Geophysical Research Letters,2013,2(7):305-308.
[35] HARRIS R N,FISHER A T,CHAPMAN D S. Fluid flow through seamounts and implications for global mass fluxes[J]. Geology,2004,32(8):725-728. doi: 10.1130/G20387.1
[36] SANDWELL D T,MUELLER R D,SMITH W H F,et al. New global marine gravity model from CryoSat-2 and Jason-1 reveals buried tectonic structure[J]. Science,2014,346(6205):65-7. doi: 10.1126/science.1258213
[37] MAUS S,BARCKHAUSEN U,BERKENBOSCH H,et al. EMAG2:a 2–arc min resolution earth magnetic anomaly grid compiled from satellite,airborne,and marine magnetic measurements[J]. Geochemistry Geophysics Geosystems,2009,10(8):Q08005.
[38] MVLLER R D. Age,spreading rates,and spreading asymmetry of the world's ocean crust[J]. Geochemistry Geophysics Geosystems,2008,9(4):Q04006.
[39] STRAUME E O,GAINA C,MEDVEDEV S,et al. GlobSed:updated total sediment thickness in the World's Oceans[J]. Geochemistry Geophysics Geosystems,2019,20(4):1756-1772. doi: 10.1029/2018GC008115
[40] AMANTE C. ETOPO1 1 Arc-Minute Global Relief Model: procedures, data sources and analysis[EB/OL]. http://www.ngdc.noaa.gov/mgg/global/global.html, 2009.
[41] CLOUARD V,BONNEVILLE A. Ages of seamounts,islands,and plateaus on the Pacific plate[J]. Geological Society of America Bulletin,2005:388.
[42] YESSON C,CLARK M R,TAYLOR M L,et al. The global distribution of seamounts based on 30 arc seconds bathymetry data[J]. Deep Sea Research Part I Oceanographic Research Papers,2011,58(4):442-453. doi: 10.1016/j.dsr.2011.02.004
[43] LEE H B,OH J K,PARK C K,et al. Geophysical and sedimentological characteristics of Lomilik Seamount,West Pacific[J]. Ocean & Polar Research,2004,26(2):207-218.
[44] CARBOTTE S M,DIXON J M,FARRAR E,et al. Geological and geophysical characteristics of the Tuzo Wilson Seamounts:implications for plate geometry in the vicinity of the Pacific – North America – Explorer triple junction[J]. Canadian Journal of Earth ences,1989,26(11):2365-2384. doi: 10.1139/e89-202
[45] KIM C H. Magnetic characteristics of TA19-1 and TA19-2 Seamounts in the Lau Basin,the South Western Pacific[J]. Economic and Environmental Geology,2014,47(4):395-404. doi: 10.9719/EEG.2014.47.4.395