-
摘要: 在研究富鈷結殼高產區地形特征基礎上，以富鈷結殼站點地理坐標為中心，獲得了一平方公里的海拔高度數值矩陣作為地形特征。使用卷積神經網絡的分析方法對數值矩陣進行訓練，學習坡度和平整度等區域特征，將富鈷結殼站點地形和其他海底地形進行區分。依據訓練后獲得的模型，對富鈷結殼高產區進行預測，取得了較好的預測效果，結合其他因素的影響，可以提高結殼靶區選取的精準度。Abstract: Cobalt-rich crusted deposits are found all over the world’s oceans, and their distribution is closely related to the submarine topography. The determination of crusting area is the basic work for the exploration and mining of these deposits. Many factors affect the accumulation of crusts, and topography is a crucial factor. Mineralization forecast requires comprehensive consideration of geological background and experts’ views and opinions, the prior knowledge of prospectors is the biggest factor affecting the results. In the course of ocean research, especially with the rapid development of space information technology, a huge amount of ocean data that cover about 70% of the total surface area have been accumulated rapidly; how to extract valuable information from large, fast, complex, and multisource data has become a hot topic in current ocean research. Machine learning- and deep learning-related research methods can read feature signs from mineral data to obtain existing mineral knowledge to further serve mine prediction work. Based on the study of terrain features of cobalt-rich crust in high-producing areas, the numerical matrix of altitude of 1 km2 ocean surface was obtained, with the geographical coordinates of cobalt-rich crust sites as the center. Using the analysis method of convolutional neural network, the numerical matrix is trained to learn regional features such as slope and flatness and to distinguish the cobalt-rich crust–crust site topography from other submarine topography. According to the training model, the high-producing cobalt-rich crusting area was predicted and better forecasting value is obtained. Meanwhile, the accuracy of the selection of crusting target area was improved by combining the influence of other factors.
-
圖 7 VGGNet 16（5×5，Max-pooling）損失曲線（a）和準確率（b）
Figure 7. VGGNet 16 (5×5, Max-pooling) loss (a) and accuracy (b)
圖 8 VGGNet 16（5×5，Mean-pooling）損失曲線（a）和準確率（b）
Figure 8. VGGNet 16 (5×5, Mean-pooling) loss (a) and accuracy (b)
表 1 地形坡度統計
Table 1. Topographic slope statistics
Slope/(°) Ratio/% <8 21.43 8–12 66.38 >12 21.43 
下載: 導出CSV
表 2 實驗結果
Table 2. Results of experiments
Method Accuracy Conv-3 (5×5) 0.8226 VGGNet 16 (3×3, Max-pooling) 0.7987 VGGNet 16 (5×5, Max-pooling) 0.8158 VGGNet 16 (5×5, Mean-pooling) 0.8346 VGGNet (7×7) Nonconvergence
下載: 導出CSV
259luxu-164<th id="5nh9l"></th> <strike id="5nh9l"></strike> <th id="5nh9l"><noframes id="5nh9l"><th id="5nh9l"></th> <strike id="5nh9l"></strike> <th id="5nh9l"><noframes id="5nh9l"> <th id="5nh9l"></th> <strike id="5nh9l"><noframes id="5nh9l"><span id="5nh9l"></span> <span id="5nh9l"><noframes id="5nh9l"><span id="5nh9l"></span> <strike id="5nh9l"><noframes id="5nh9l"><strike id="5nh9l"></strike> <span id="5nh9l"><noframes id="5nh9l"> <span id="5nh9l"><noframes id="5nh9l"> <span id="5nh9l"></span> <span id="5nh9l"><video id="5nh9l"></video></span> <th id="5nh9l"><noframes id="5nh9l"><th id="5nh9l"></th> -
參考文獻
[1] Pan J H, Liu S Q, Yang Y, et al. Types, distribution and occurrence of Co-rich crusts in the Western Pacific. Miner Deposit, 2002, 21(Suppl): 44潘家華, 劉淑琴, 楊憶, 等. 西太平洋富鈷結殼的類型、分布與產狀. 礦床地質, 2002, 21(增刊): 44 [2] Morley N H, Burton J D, Tankere S P C, et al. Distribution and behaviour of some dissolved trace metals in the western Mediterranean Sea. Deep Sea Res Part Ⅱ, 1997, 44(3-4): 675 doi: 10.1016/S0967-0645(96)00098-7 [3] Wang X H, Zhou L P, Wang Y M. Paleoenvironmental implications of high-density records in Co-rich seamount crusts from the Pacific Ocean. Sci China Ser D-Earth Sci, 2008, 51(10): 1460 doi: 10.1007/s11430-008-0092-6 [4] Halbach P, Puteanus D. The influence of the carbonate dissolution rate on the growth and composition of Co-rich ferromanganese crusts from Central Pacific seamount areas. Earth Planet Sci Lett, 1984, 68(1): 73 doi: 10.1016/0012-821X(84)90141-9 [5] Zhang W Y, Zhang F Y, Zhu K C. Fractal research on seamount topography in the West Pacific Ocean. Geoscience, 2009, 23(6): 1138 doi: 10.3969/j.issn.1000-8527.2009.06.020章偉艷, 張富元, 朱克超. 西太平洋海域海山地形分形特征研究. 現代地質, 2009, 23(6):1138 doi: 10.3969/j.issn.1000-8527.2009.06.020 [6] Liu Y G, He G W, Yao H Q, et al. Global distribution characteristics of seafloor cobalt-rich encrustation resources. Miner Deposit, 2013, 32(6): 1275 doi: 10.3969/j.issn.0258-7106.2013.06.013劉永剛, 何高文, 姚會強, 等. 世界海底富鈷結殼資源分布特征. 礦床地質, 2013, 32(6):1275 doi: 10.3969/j.issn.0258-7106.2013.06.013 [7] Cheng Y S. Study of Evaluation of Co-rich Ferromanganese Crust Resources on Seamounts in Northwest Pacific Ocean[Dissertation]. Qingdao: Ocean University of China, 2014程永壽. 西北太平洋海山富鈷結殼資源評價和礦區圈定[學位論文]. 青島: 中國海洋大學, 2014 [8] Hubel D H, Wiesel T N. Receptive fields of single neurones in the cat's striate cortex. J Physiol, 1959, 148(3): 574 doi: 10.1113/jphysiol.1959.sp006308 [9] Zhou F Y, Jin L P, Dong J. Review of convolutional neural network. Chin J Comput, 2017, 40(6): 1229 doi: 10.11897/SP.J.1016.2017.01229周飛燕, 金林鵬, 董軍. 卷積神經網絡研究綜述. 計算機學報, 2017, 40(6):1229 doi: 10.11897/SP.J.1016.2017.01229 [10] Yuan F, Zhang M M, Li X H, et al. Prospectivity modeling: from two-dimension to three-dimension. Acta Petrol Sin, 2019, 35(12): 3863 doi: 10.18654/1000-0569/2019.12.18袁峰, 張明明, 李曉暉, 等. 成礦預測: 從二維到三維. 巖石學報, 2019, 35(12):3863 doi: 10.18654/1000-0569/2019.12.18 [11] Liu Q Q, Meng Q. Geochemical survey of metallogenic area (zone) and some problems are discussed. Geol Explor, 1981(11): 59劉泉清, 孟奇. 成礦區(帶)地球化學普查及若干問題的探討. 地質與勘探, 1981(11):59 [12] Yang H S, Liu Y L, Wang P. Mathematical geology of gold deposits in south Gansu and north Sichuan regions—a prognostic neomethod study. Geol Geochem, 1998(1): 86楊恒書, 劉玉玲, 王萍. 川北甘南地區金礦數學地質預測新方法研究. 地質地球化學, 1998(1):86 [13] Zhang B L. The new theory and technology of "geochemical three field anomalies mutually constrain each other" to predict the location of hidden resources has been applied to quickly select the target area for prospecting, and remarkable results have been achieved. Gold Sci Technol, 2004, 12(5): 48 doi: 10.3969/j.issn.1005-2518.2004.05.017張寶林. 應用“地物化三場異常互相約束”的隱伏資源定位預測新理論和新技術快速優選找礦靶區取得顯著效果. 黃金科學技術, 2004, 12(5):48 doi: 10.3969/j.issn.1005-2518.2004.05.017 [14] Zhang Q H, Pu K X, Luo H Y. Application of comprehensive methods in prospecting target of polymetallic ore. Miner Explor, 2019, 10(4): 929 doi: 10.3969/j.issn.1674-7801.2019.04.027張慶華, 蒲開興, 羅洪遠. 綜合方法在多金屬找礦靶區預測中的應用. 礦產勘查, 2019, 10(4):929 doi: 10.3969/j.issn.1674-7801.2019.04.027 [15] Ye S S, Zhou D D, Wang S C. Integrated mineral information forecasting system//Proceedings of the 7th National Conference on Mathematical Geology and Geoscience Information. Kunming, 2005: 59葉水盛, 周東岱, 王世稱. 綜合信息礦產預測系統//第七屆全國數學地質與地學信息學術會議. 昆明, 2005: 59 [16] Li X Z. Development of an Expert System for Statistical Prediction of Medium and Large Scale Deposits[Dissertation]. Wuhan: China University of Geosciences, 2004李新中. 中、大比例尺礦床統計預測專家系統的研制[學位論文]. 武漢: 中國地質大學, 2004 [17] Xu S T, Zhou Y Z. Artificial intelligence identification of ore minerals under microscope based on deep learning algorithm. Acta Petrol Sin, 2018, 34(11): 3244徐述騰, 周永章. 基于深度學習的鏡下礦石礦物的智能識別實驗研究. 巖石學報, 2018, 34(11):3244 [18] Liu Y P, Zhu L X, Zhou Y Z. Application of convolutional neural network in prospecting prediction of ore deposits: taking the Zhaojikou Pb?Zn ore deposit in Anhui Province as a case. Acta Petrol Sin, 2018, 34(11): 3217劉艷鵬, 朱立新, 周永章. 卷積神經網絡在礦床找礦預測中的應用— —以安徽省兆吉口鉛鋅礦床為例. 石油學報, 2018, 34(11):3217 [19] Xiao Z, Luo B, Liu Y M. Research on prospecting of ductile shear zone in mining area based on deep learning. World Nonferrous Met, 2019(21): 46 doi: 10.3969/j.issn.1002-5065.2019.21.028肖壯, 羅彬, 劉友明. 基于深度學習的礦區韌性剪切帶找礦研究. 世界有色金屬, 2019(21):46 doi: 10.3969/j.issn.1002-5065.2019.21.028 [20] Ma W L. Study on Relation between Seamounts Type and Crusts Mineralization[Dissertation]. Hangzhou: Zhejiang University, 2006馬維林. 海山類型與結殼成礦的關系研究[學位論文]. 杭州: 浙江大學, 2006 [21] Wei Z Q, He G W, Deng X G, et al. The progress in the study and survey of oceanic cobalt-rich crust resources. Geol China, 2017, 44(3): 460韋振權, 何高文, 鄧希光, 等. 大洋富鈷結殼資源調查與研究進展. 中國地質, 2017, 44(3):460 [22] Jiao D F, Jin X L, Chu F Y, et al. Formation conditions and control factors of thick Co-rich ferromanganese crusts. Miner Deposits, 2007, 26(3): 296 doi: 10.3969/j.issn.0258-7106.2007.03.006矯東風, 金翔龍, 初鳳友, 等. 厚結殼的形成條件及控制因素分析. 礦床地質, 2007, 26(3):296 doi: 10.3969/j.issn.0258-7106.2007.03.006 [23] Yan S J, Du D W, Song Q L, et al. Synergy Creg estimation of cobalt-rich crusts and spatial distribution of regional elements in Magellan Seamounts. Acta Mineral Sin, 2013(Suppl 2): 674閆仕娟, 杜德文, 宋慶磊, 等. 麥哲倫海山富鈷結殼及區域要素空間分布的協同克里格估計. 礦物學報, 2013(增刊 2): 674 [24] Chu F Y, Sun G S, Li X M, et al. The growth habit and controlling factors of the cobalt-rich crusts in Seamount of the Central Pacific. J Jilin Univ Earth Sci Ed, 2005, 35(3): 320初鳳友, 孫國勝, 李曉敏, 等. 中太平洋海山富鈷結殼生長習性及控制因素. 吉林大學學報: 地球科學版, 2005, 35(3):320 [25] Wang S, Yang K J. An image scaling algorithm based on bilinear interpolation with VC++. Tech Autom Appl, 2008, 27(7): 44 doi: 10.3969/j.issn.1003-7241.2008.07.014王森, 楊克儉. 基于雙線性插值的圖像縮放算法的研究與實現. 自動化技術與應用, 2008, 27(7):44 doi: 10.3969/j.issn.1003-7241.2008.07.014 [26] Zhang Q Q, Liu Y, Pan J L, et al. Continuous speech recognition by convolutional neural networks. Chin J Eng, 2015, 37(9): 1212張晴晴, 劉勇, 潘接林, 等. 基于卷積神經網絡的連續語音識別. 工程科學學報, 2015, 37(9):1212 [27] Xie Z H, Jiang P, Yu X H, et al. Hyperspectral face recognition system based on VGGNet and multi-band recurrent network. J Comput Appl, 2019, 39(2): 388 doi: 10.11772/j.issn.1001-9081.2018081788謝志華, 江鵬, 余新河, 等. 基于VGGNet和多譜帶循環網絡的高光譜人臉識別系統. 計算機應用, 2019, 39(2):388 doi: 10.11772/j.issn.1001-9081.2018081788 -
點擊查看大圖
圖(8) / 表(2)
計量
- 文章訪問數: 1775
- HTML全文瀏覽量: 780
- PDF下載量: 100
- 被引次數: 0
