Geochemical characterization of oceanic basalts using Artificial Neural Network
© Das and Iyer; licensee BioMed Central Ltd. 2009
Received: 6 June 2009
Accepted: 23 December 2009
Published: 23 December 2009
The geochemical discriminate diagrams help to distinguish the volcanics recovered from different tectonic settings but these diagrams tend to group the ocean floor basalts (OFB) under one class i.e., as mid-oceanic ridge basalts (MORB). Hence, a method is specifically needed to identify the OFB as normal (N-MORB), enriched (E-MORB) and ocean island basalts (OIB).
We have applied Artificial Neural Network (ANN) technique as a supervised Learning Vector Quantisation (LVQ) to identify the inherent geochemical signatures present in the Central Indian Ocean Basin (CIOB) basalts. A range of N-MORB, E-MORB and OIB dataset was used for training and testing of the network. Although the identification of the characters as N-MORB, E-MORB and OIB is completely dependent upon the training data set for the LVQ, but to a significant extent this method is found to be successful in identifying the characters within the CIOB basalts. The study helped to geochemically delineate the CIOB basalts as N-MORB with perceptible imprints of E-MORB and OIB characteristics in the form of moderately enriched rare earth and incompatible elements. Apart from the fact that the magmatic processes are difficult to be deciphered, the architecture performs satisfactorily.
Several discrimination diagrams have been proposed to classify the ocean floor basalts (OFB) into ocean island basalts (OIB), mid-oceanic ridge basalts (MORB), and island arc basalts (IAB) that are recovered from different tectonic settings. These diagrams are constructed by considering a variety of oxides and/or their ratios, for instance the triangular diagrams of Ti/100 - Zr - Y.3 by Pearce & Cann , Hf/3 - Th - Ta by Wood et al. , TiO2 - MnO - P2O5 × 100 by Mullen  and 2Nb -Zr/4 -Y by Meschede . The model based geochemical studies classify the MORB into three types such as normal - , enriched or plume - and transitional MORB (i.e., N- MORB, E or P-MORB and T-MORB, respectively) or as OIB [5–7]. The discrimination diagrams provide a broad picture of the type of basalts but it is difficult to determine the basic characters that are involved in the geochemical classification of OFB based solely on the above mentioned elements and oxides. Recently, Sheth  considered several log-ratio and discriminant-analysis based diagrams to evaluate and classify the basalts into OIB, island arc basalts (IAB) and MORB. The suggested discriminate diagrams helped to distinguish the volcanics recovered from different tectonic settings but group the OFB under one class i.e., as MORB. Hence, a method is needed to specifically identify the OFB as N-MORB, E/P-MORB and OIB.
Therefore, other than through conventional discrimination plots, a methodology is explored for an improved technique to characterise and evaluate the various basaltic characters in a geochemical dataset. We found that a hybrid Artificial Neural Network (ANN) architecture, also known as Learning Vector Quantisation (LVQ) which is a supervised network, could better help to characterise the OFB. As a supervised method, LVQ uses known target output classifications for each input pattern of the form. Some instances where LVQ architecture has being extensively used are for pattern recognition and seafloor classification  and characterisation of the seafloor sediments . In this communication we use the LVQ approach in order to determine the inherent geochemical characters and to classify the Central Indian Ocean Basin (CIOB) basalts.
Learning Vector Quantisation (LVQ) Architecture
An ANN is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this pattern is the novel structure which is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process. Learning in biological systems involves adjustments to the synaptic connections that exist between the neurons. This is true of ANNs as well.
where θk is the weight of CVs.
'Learning' means modifying the value of CVs in accordance with adapting rules  and therefore, changing the position of a CV in the input space. Since class boundaries are built piecewise - linear segments of the mid-planes between CVs of neighboring classes - these are adjusted during the learning process. The tessellation (a tessellation or tiling) of the plane is a collection of figures that fills the plane with no overlaps and no gaps) induced by the set of CVs is optimal if all data within one cell indeed belong to the same class. Classification after learning is based on a presented sample's vicinity to the CVs. The classifier assigns the same class label i.e., the label of the cell's prototype (the CV nearest to the sample) to all the samples that fall into the same tessellation.
where the sign depends on whether the datum sample is correctly classified (+) or misclassified (-). The learning rate α(t) ∈ [0, 1] decreases monotonically with time. For different picks of data samples from our training set, this procedure is repeated iteratively until a convergence occurs. Kohonen12 also presents optimized learning-rate LVQ, where the learning-rate is individually optimized for each codebook. The learning function (α) for LVQ1[10–12] uses small values and was optimized to: for right (0.1/t0.1) and wrong (0.1/t0.06) classifications. During the training and testing of LVQ1, the randomly generated weight matrix was tuned for a particular character in the data set. The LVQ1 network learns all the possible variations for a particular data set and in order to obtain the optimum iteration, we continuously changed the number of iteration steps from a small number to a large one with continuous observation of classification of the data. It was noticed that irrespective of the number of neurons, 30 iterations were optimum for classifying the CIOB basalts.
The basic LVQ algorithm i.e., LVQ1 rewards correct classifications by moving the CV towards a presented input vector, whereas incorrect classifications are punished by moving the CV in an opposite direction. The magnitudes of these weight adjustments are controlled by a learning rate  which can be lowered over time so as to acquire finer movements in a later learning phase. Improved versions of LVQ1 are Kohonen's OLVQ1 (with different learning rates for each CV in order to obtain a faster convergence) and LVQ2, LVQ2.1 and LVQ3. Since LVQ1 tends to push CVs away from decision surfaces, it can be expected to search for a better approximation by adjustments of two CVs belonging to adjacent classes. Therefore, in LVQ2 adaptation occurs only in regions with a few cases of mis-classification in order to achieve finer and better class boundaries. While LVQ2 allows adaptation for correctly classifying CVs, LVQ3 leads to an even more weight adjusting operations due to less restrictive adaptation rules.
The accuracy of classification and, therefore generalization and the speed of learning depends on several factors. Generally, the developer of a LVQ has to prepare a learning schedule and a plan as to which LVQ-algorithm(s) - LVQ1, OLVQ, LVQ2.1 etc. - should be used with values for the main parametres during the different training phases. Also, the number of CVs for each class must be decided in order to reach an high classification accuracy and generalization while avoiding under- or over-fitting of the CVs. Additionally, the rules for stopping the learning process as well as the initialization method (e.g., random values, values of randomly selected samples) determine the results.
In this study we have implemented the LVQ1 network to classify the CIOB basalts without placing emphasis on the geographical locations of the samples. The LVQ1 algorithm is such that if the class levels of the input and closest matching reconstruction vectors are the same, then the weights are moved closer to the input vector. Conversely, a mismatch between the two causes the weight to move away from the input vector. This concept is termed as "reward-punishment". Randomly generated weight matrix is used as an initial weight distribution for LVQ1. The weight update equations are implemented on the winning neuron for each input vector presented, with alternate testing and training throughout the dataset. The weight updating takes place following the above equation #3.
The LVQ1 was used as a single layer for classification of the CIOB basalts and thirty five samples were used to train the network with every sample containing twenty one variables. The LVQ1 testing was carried out on known and classified basalt data set [13–21] so as to optimize the weight matrix and to store the characters of the training data. Optimization is a basic step that helps the network to classify the unknown basalt data.
Time taken by the computer to identify the basalt characters while using different number of output neurons.
Time lapsed (sec) →
Use of LVQ to Classify Oceanic Basalts
As stated earlier, based on geochemical data the OFB have been classified as N-, E/P- or T-MORB or OIB. Recently, Lacassie et al.  have used self organizing map (SOM) based ANN to classify the volcanic rocks. But it is difficult to determine the inherent geochemical characters of the samples with respect to N-MORB, E/P-MORB and OIB, until and unless the network has pre-defined parametres to separate the geochemical characters of the data. Therefore, an attempt is made to introduce the LVQ method for classification and to unravel discrete geochemical traits of the OFB by using certain characteristic elemental concentration of these basalts. In order to classify the OFB we considered one major oxide (K2O), seven trace (Sc, Rb, Sr, Y, Zr, Nb and Ba,), six rare earth elements (REE) (La, Ce, Nd, Sm, Eu, and Yb) and seven elemental ratios (Zr/Nb, Y/Nb, Ba/Nb, Zr/Y, Sm/Nd, La/Yb and Ce/Y). A reason for utilizing the above mentioned elements and their ratios is because these carry the geochemical signatures of the individual OFB type i.e., N-MORB, E/P-MORB and OIB . A criterion that we considered while selecting the samples for training and testing, was that the data should not be solely from one sampled site in the CIOB.
The representative MORB values used in this study
To help identify the involved characters in the data set, filters were designed using the optimized and final weight-matrix of the CVs. The filters are similar to the testing part of the LVQ1 architecture. While passing through the filters the network identifies the individual characters of the unknown data and this recognition is dependent upon the available characters of the basalts in the form of CVs in the weight-matrix.
Classification Of Unknown Basalt Data
Sampling in the CIOB recovered a variety of rocks such as basalts, ferrobasalts, spilites and pumice clasts . Basalts occur as pillows, large outcrops and as fragments. Compositionally, the basalts are Normal-MORB (N-MORB) similar to those from the Mid-Atlantic Ridge and East Pacific Rise . Ferrobasalts, recovered near topographic highs and high amplitude magnetic zones, consist of plagioclase (predominant), sometimes olivine and frequently small euhedral magnetite and hematite grains . Spilites, occurring near the Indrani fracture zone (79°E), show fine to medium grains of albitic plagioclase, clinopyroxene and olivine while epidote, hematite, chlorite and ore minerals form minor constituents. Pumices encompass a large field and are trachyandesite to rhyodacite in composition .
The CIOB basalts show considerable ranges in concentrations of the incompatible elements (e.g., Zr = 63-228 Xppm; Nb = 0.95-5 ppm; Ba = ~15-78 ppm; La = ~3-16 ppm) [27, 28]. The incompatible elements (Ba, Zr, Nb, REE) with bulk distribution coefficients less than 1 (D<<1), show systematic enrichments with decreasing MgO where as the incompatible elements Sr and Sc (D ≥ 1), exhibit a scattered distribution. This could be accounted by the fractionation of olivine ± clinopyroxene and is also supported by the CaO/Al2O3 ratio of the samples.
Characterisation of the CIOB basalts in terms of inherent character as N-MORB, E/P-MORB and OIB using LVQ (ANN architecture) technique.
57% of the basalts are typical N-MORB
20% of the basalts have both N-MORB and E/P-MORB characters
11% of the basalts show a combination of N-MORB and OIB signatures
12% of the basalts have a mixed nature of N-MORB, E/P-MORB and OIB.
Thus, the CIOB basalts are largely N-MORB but in terms of certain elemental concentrations a few basalts have characteristics of the three basic groups of the OFB. This indicates the inhomogeneity of the source region together with variable melting of the source.
It is well recognized that the geochemical study of basalts together with discrimination plots of selective elements and their ratios could help to identify the basic volcanics vis-è-vis their tectonic settings. The purpose of this work however, was to highlight the development of a suitable real-time program to help classify the oceanic basalts on the basis of their discrete geochemical characters which may not be fully revealed in the classical discrimination diagrams. In this respect, the need of soft computational techniques (like ANN) is useful and faster.
The present study indicates that the supervised LVQ1 architecture performs satisfactorily to identify the geochemical characters in the data and the possibility of mis-characterization is minimal. Further work could help to refine the model by a possible reduction in the number of variables that are needed for the classification scheme.
The data were collected under the "Surveys for Polymetallic Nodules" project funded by Department of Ocean Development, New Delhi. We thank our Director for permission to communicate this paper. PD acknowledges the CSIR New Delhi, for financial assistance in the form of a Research Fellowship. PD is thankful to Dr. B. Chakraborty for providing an opportunity to learn the ANN and LVQ techniques. We acknowledge the reviewers for their suggestions that helped to improve the manuscript. This is NIO's contribution No. 4666
- Pearce JA, Cann JR: Tectonic setting of basic volcanic rocks determined using trace element analysis. Earth and Planetary Science Letters. 1973, 19: 290-300. 10.1016/0012-821X(73)90129-5.View ArticleGoogle Scholar
- Wood DA, Joron JL, Treuil M: A re-appraisal of the use of trace elements to classify and discriminate between magma series erupted in different tectonic settings. Earth and Planetary Science Letters. 1979, 45: 326-336. 10.1016/0012-821X(79)90133-X.View ArticleGoogle Scholar
- Mullen ED: MnO/TiO2: a minor element discriminant for basaltic rocks of oceanic environments and its implications for petrogenesis. Earth and Planetary Science Letters. 1983, 62: 53-62. 10.1016/0012-821X(83)90070-5.View ArticleGoogle Scholar
- Meschede M: A method of discriminating between different types of mid-ocean ridge basalts and continental tholeiites with the Nb - Zr - Y diagram. Chemical Geology. 1986, 56: 207-218. 10.1016/0009-2541(86)90004-5.View ArticleGoogle Scholar
- Schilling J-G, Zajac M, Evans R, Johnston T, White W, Devine JD, Kingsley R: Petrologic and geochemical variations along the Mid-Atlantic Ridge from 27°N to 73°N. American Journal of Science. 1983, 283: 510-586.View ArticleGoogle Scholar
- Sun SS, Nesbitt RW, Sharaskin AY: Geochemical characteristics of mid-ocean ridge basalts. Earth and Planetary Science Letters. 1979, 44: 119-138. 10.1016/0012-821X(79)90013-X.View ArticleGoogle Scholar
- Wilson M: Igneous petrogenesis. 1989, Chapman and Hall, London, 466-View ArticleGoogle Scholar
- Sheth H: Do major oxide tectonic discrimination diagrams work? Evaluating new log-ratio and discriminant-analysis-based diagrams with Indian Ocean mafic volcanics and Asian ophiolites. Terra Nova. 2008, 20: 229-236. 10.1111/j.1365-3121.2008.00811.x.View ArticleGoogle Scholar
- Chakraborty B, Kodagali VN, Baracho J: Seafloor classification using multi-beam echo sounding angular backscatter data: a real time approach employing hybrid neural network architecture. IEEE Journal of Ocean Engineering. 2003, 28: 121-128. 10.1109/JOE.2002.808211.View ArticleGoogle Scholar
- Chakraborty B, Mahale B, de Sousa C, Das P: Seafloor classification using echo-waveforms: a method employing hybrid neural network architecture. IEEE Geosciences and Remote Sensing Letters. 2004, 3: 196-200. 10.1109/LGRS.2004.831206.View ArticleGoogle Scholar
- Kohonen T: Self-Organising Map. Proceeding IEEE. 1990, 78: 1464-1480. 10.1109/5.58325.View ArticleGoogle Scholar
- Kohonen T: Self-Organizing maps. Berlin, Germany: Springer-Verlag. 2001, 245-261.Google Scholar
- Dickey JS, Frey FA, Hart SR, Watson EB, Thompson G: Geochemistry and petrology of dredged basalts from the Bouvet triple junction, South Atlantic. Geochimica et Cosmochimica Acta. 1977, 41: 1105-1118. 10.1016/0016-7037(77)90105-3.View ArticleGoogle Scholar
- Langmuir CH, Bender JF, Bence AE, Hanson GN, Taylor SR: Petrogenesis of basalts from the Famous area: Mid-Atlantic Ridge. Earth and Planetary Science Letters. 1977, 36: 133-156. 10.1016/0012-821X(77)90194-7.View ArticleGoogle Scholar
- Humphris SE, Thompson G: Geochemistry of rare earth elements in basalts from the Walvis Ridge: implication for its origin and evolution. Earth and Planetary Science Letters. 1983, 66: 223-242. 10.1016/0012-821X(83)90138-3.View ArticleGoogle Scholar
- le Roex AP: Source regions of mid-ocean ridge basalts: evidence for enrichment processes. Edited by: Menzies MA, Hawkesworth CJ. 1987, Mantle metasomatism, Academic Press, London, 389-419.Google Scholar
- le Roex AP, Dick HJB, Watkins RT: Petrogenesis of anomalous MORB from the Southwest Indian ridge: 11°53' E to 14° 38' E. Contribution Mineralogy and Petrology. 1992, 110: 253-268. 10.1007/BF00310742.View ArticleGoogle Scholar
- Grove TL, Kinzler RJ, Bryan WB: Fractionation of mid-ocean ridge basalts (MORB). Mantle flow and melt generation at mid-ocean ridges. Geophysical Monographs American Geophysical Union. Edited by: Morgan JP, Blackman DK, Sinton JM. 1992, 71: 281-310.View ArticleGoogle Scholar
- Halliday AN, Lee DC, Tommasini S, Davies RG, Paslick CR, Fitton JG, James ED: Incompatible trace elements in OIB and MORB and source enrichment in the sub-oceanic mantle. Earth and Planetary Science Letters. 1995, 133: 379-395. 10.1016/0012-821X(95)00097-V.View ArticleGoogle Scholar
- le Roux PJ, le Roex AP, Schilling J-G, Shimizu N, Perkins WW, Pearce NJG: Mantle heterogeneity beneath the southern Mid-Atlantic Ridge: trace element evidence for contamination of ambient asthenospheric mantle. Earth and Planetary Science Letters. 2002, 203: 479-498. 10.1016/S0012-821X(02)00832-4.View ArticleGoogle Scholar
- Raos AS, Crawford AJ: Basalts from the Efate Island group, central section of the Vanuatu arc, SW Pacific: geochemistry and petrogenesis. Journal of Volcanology and Geothermal Research. 2004, 134: 35-66. 10.1016/j.jvolgeores.2003.12.004.View ArticleGoogle Scholar
- Lacassie JP, del Solar JR, Roser B, Francisco HF: Visualization of volcanic rock geochemical data and classification with artificial neural networks. Mathematical Geology. 2006, 38: 697-710. 10.1007/s11004-006-9042-z.View ArticleGoogle Scholar
- Mukhopadhyay R, Iyer SD, Ghosh AK: The Indian Ocean nodule field: petrotectonic evolution and ferromanganese deposits. Earth-Science Reviews. 2002, 60: 67-130. 10.1016/S0012-8252(02)00078-8.View ArticleGoogle Scholar
- Mukhopadhyay R, Batiza R, Iyer SD: Petrology of seamounts in the Central Indian Ocean Basin: evidence of near axis origin. Geo-Marine Letters. 1995, 65: 343-352.Google Scholar
- Iyer SD, Mukhopadhyay R, Popko DC: Ferrobasalts from the Central Indian Ocean Basin. Geo-Marine Letters. 1999, 18: 297-304. 10.1007/s003670050083.View ArticleGoogle Scholar
- Iyer SD, Sudhakar M: A new report on the occurrence of zeolitites in the abyssal depths of the Central Indian Basin. Sedimentary Geology. 1993, 84: 169-178. 10.1016/0037-0738(93)90053-8.View ArticleGoogle Scholar
- Das P, Iyer SD: An investigation of basalts from the Central Indian Ocean Basin. 17th Annual V. M. Goldschmidt Conference Cologne, Germany August 2007. Geochimica et Cosmochimica Acta. 2007, 71 (15): A202-Google Scholar
- Das P: Morphotectonic evolution and petrochemistry of Central Indian Ocean Floor. PhD thesis. 2008, Jadavpur Univ. Kolkata, IndiaGoogle Scholar
- Mahoney JJ, Jones WB, Frey FA, Salters VJM, Pyle DG, Davies HL: Geochemical characteristics of lavas from Broken Ridge, the Naturaliste Plateau and southernmost Kerguelen Plateau: Cretaceous plateau volcanism in the southeast Indian Ocean. Chemical Geology. 1995, 120: 315-345. 10.1016/0009-2541(94)00144-W.View ArticleGoogle Scholar
- Weis D, Frey FA: Role of Kerguelen plume in generating the eastern Indian Ocean seafloor. Journal of Geophysical Research. 1996, 101: 13831-13849. 10.1029/96JB00410.View ArticleGoogle Scholar
- Sun SS, McDonough : Chemical and isotopic systematics of oceanic basalts: implications for mantle composition and processes. Magmatism in the ocean basins. Edited by: Saunders AD, Norry M. 1989, Geol Soc London Spec Publ, 42: 313-345.Google Scholar
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.