Integration of remote sensing and geophysical data to enhance lithological mapping utilizing the Random Forest classifier: a case study from Komopa, Papua Province, Indonesia


  • Hary Nugroho Doctoral Program of Geodesy and Geomatics Engineering, Faculty of Earth Sciences and Technology, Institut Teknologi Bandung
  • Ketut Wikantika Geodesy and Geomatics Engineering Study Program, Faculty of Earth Sciences and Technology, Institut Teknologi Bandung
  • Satria Bijaksana Geophysical Engineering Study Program, Faculty of Mining and Petroleum Engineering, Institut Teknologi Bandung
  • Asep Saepuloh Geological Engineering Study Program, Faculty of Earth Sciences and Technology, Institut Teknologi Bandung



airborne geophysical data, lithological mapping, machine learning, random forest, remote sensing


Lithological information is important in mineral resource exploration, geological observations, mine planning or degradation vulnerability assessment. Currently, lithology mapping can be performed in a fast, inexpensive, and easy way using remote sensing data and machine learning. Remote sensing techniques have become a valuable and promising tool for mapping lithological units and searching for minerals. Typically, the integration of remote sensing data with geophysical data provides a better diagnosis to lithological units than single-source mapping methodologies. Accordingly, this study used a combination of remote sensing and airborne geophysical data utilizing the Random Forest algorithm with small training samples to enhance lithology mapping in Komopa, Papua Province, Indonesia. Geophysical data consisting of magnetic, electromagnetic, and radiometric were added one by one gradually to the remote sensing data, which includes Sentinel 2A, ALOS PALSAR, and DEM (digital elevation model) to compare the accuracy of the classification results from each dataset. The results showed that the model that combined remote sensing data and the three types of geophysical data produced the best classification, with an overall accuracy of 0.81, precision of 0.66, recall of 0.47, and F1 score of 0.52. This fused data can increase the accuracy of the classification results by 8% overall accuracy, 6% precision, 11% recall, and 13% F1 score when compared to the model that only used remote sensing data.

Author Biography

Hary Nugroho, Doctoral Program of Geodesy and Geomatics Engineering, Faculty of Earth Sciences and Technology, Institut Teknologi Bandung

Program Studi Teknik Geodesi, Fakultas Teknik Sipil dan Perencanaan


Abraham, J.D. and Cannia, J.C. 2011. Airborne Electromagnetic Surveys for 3d Geological Mapping. Three-Dimensional Geological Mapping: Workshop Extended Abstracts. Minneapolis, Minnesota.

Ansari, A.H. and Alamdar, K. 2009. Reduction to the pole of magnetic anomalies using an analytic signal. World Applied Sciences Journal 7(4):405-409.

Anwar, M.N. 2012. Complexity Measurement for Dealing with Class Imbalance Problems in Classification Modelling. A thesis submitted in the fulfilment of the requirement for the degree of Doctor of Philosophy at Massey University, New Zealand.

Asniar, A., Maulidevi, N.U. and Surendro, K. 2022. SMOTE-LOF for noise identification in imbalanced data classification. Journal of King Saud University-Computer and Information Sciences 34(6):3413-3423, doi:10.1016/j.jksuci.2021.01.014.

Bachri, I., Hakdaoui, M., Raji, M., Benbouziane, A. and Mhamdi, H.S. 2022. Identification of lithology using Sentinel-2A through an ensemble of machine learning algorithms. International Journal of Applied Geospatial Research 13(1):1-17, doi:10.4018/ijagr.297524.

Bannari, A., El-Battay, A., Saquaque, A. and Miri, A. 2016. PALSAR-FBS L-HH mode and Landsat-TM data fusion for geological mapping. Advances in Remote Sensing 05(04):246-268, doi:10.4236/ars.2016.54020.

Barella, V.H., Garcia, L.P.F., de Souto, M.C.P., Lorena, A.C. and de Carvalho, A.C.P.L.F. 2021. Assessing the data complexity of imbalanced datasets. Information Sciences 553:83-109, doi:10.1016/j.ins.2020.12.006.

Bhattacharya, S., Carr, T.R., and Pal, M. 2016. Comparison of supervised and unsupervised approaches for mudstone lithofacies classification: Case studies from the Bakken and Mahantango-Marcellus Shale, USA. Journal of Natural Gas Science and Engineering 33:1119-1133, doi:10.1016/j.jngse.2016.04.055.

Bogner, C., Seo, B. and Rohner, D. 2018. Classification of rare land cover types: Distinguishing annual and perennial crops in an agricultural catchment in South Korea. PLoS ONE 13(1):1-22, doi:10.1371/journal. pone.0190476.

Brownlee, J. 2020. Imbalanced Classification with Python: Choose Better Metrics, Balance Skewed Classes, and Apply Cost-Sensitive Learning (v1.2). Machine Learning Mastery. Retrieved from

Chinkaka, E. 2019. Intergating Worldview-3, ASTER and Aeromagnetic Data for Lineament Structural Interpretation and Tectonic Evolution of The Haib Area, Namibia. University of Twente.

Cracknell, M.J. and Reading, A.M. 2014. Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Computers and Geosciences 63:22-33, doi:10.1016/ j.cageo.2013.10.008.

Deng, C., Pan, H., Fang, S. and Konaté, A.A. 2017. Support vector machine as an alternative method for lithology classification of crystalline rocks. Journal of Geophysics and Engineering 14(2):1-9, doi:10.1088/1742-2140/aa5b5b.

Doveton, J.H. 2018. Mathematical Minerals: A History of Petrophysical Petrography. In: Daya-Sagar, B., Cheng, Q. and Agterberg, F. (eds.), Handbook of Mathematical Geosciences. Springer Cham, doi:10.1007/978-3-319-78999-6_24.

Duan, L., Sheng, H., Yuan, H., Zhou, Q. and Li, Z. 2021. Land use conversion and lithology impacts soil aggregate stability in subtropical China. Geoderma 389(January):114953, doi:10.1016/j.geoderma.2021.114953.

Dumais, M.-A. 2014. Reprocessing and compilation of radiometrics data from Finnmark and northern Troms. NGU Report 2014.015.

Emond, A.M. 2021. Uses for Geophysical Data | Alaska Division of Geological and Geophysical Surveys. Retrieved March 14, 2022, from

Engelbrecht, J. 2016. Fully polarimetric ALOS PALSAR data to aid geological mapping in densely vegetated areas. In 35th International Geological Congress, 27 August - 4 September 2016 (pp. 1-3). Cape Town, South Africa. Retrieved from

European Space Agency. 2019. Sentinel 2A. Retrieved December 10, 2019, from types/level-2a.

Fernández, A., García, S., Galar, M. and Prati, R.C. 2018. Learning from Imbalanced Data Sets. Springer Nature Switzerland, doi:10.1007/978-3-319-98074-4.

GeoSci. 2018. Electromagnetic Data Processing. Retrieved February 6, 2022, from

Geospatial Information Agency-Republic of Indonesia. 2018. DEMNAS Seamless Digital Elevation Model (DEM) dan Batimetri Nasional. Retrieved March 20, 2019, from

Ghosh, T., Hazra, S. and Das, A.K. 2022. Potential of ALOS-2 PALSAR-2 StripMap Data for lithofacies identification and geological lineament mapping in vegetated fold-thrust belt of Nagaland, India. Advances in Space Research 69(4):1840-1862, doi:10.1016/j.asr.2021.09.007.

Gosain, A. and Sardana, S. 2017. Handling Class Imbalance Problem using Oversampling Techniques: A Review. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 79–85), doi:10.1109/ICACCI.2017.8125820.

Grebby, S., Cunningham, D., Tansey, K. and Naden, J. 2014. The impact of vegetation on lithological mapping using airborne multispectral data: a case study for the North Troodos Region, Cyprus. Remote Sensing 6:10860-10887, doi:10.3390/rs61110860.

Haldar, S.K. 2018. Exploration Geochemistry. In: Mineral Exploration (Second Edi). Elsevier, doi:10.1016/C2017-0-00902-3.

Harahap, B.H. 2012. Tectonostratigraphy of the Southern Part of Papua and Arafura Sea, Eastern Indonesia. Indonesian Journal of Geology 7(3):167-187.

Harris, J.R. and Grunsky, E.C. 2015. Predictive lithological mapping of Canada’s North using Random Forest classification applied to geophysical and geochemical data. Computers and Geosciences 80(July):9-25, doi:10.1016/j.cageo.2015.03.013.

Hoens, T.R. and Chawla, N.V. 2013. Imbalanced datasets: from sampling to classifiers. In: He, H. and Ma, Y. (eds.), Imbalanced Learning: Foundations, Algorithms, and Applications (First Ed.). John Wiley and Sons, Inc., doi:10.1002/9781118646106.ch3.

Holloway, E. and Cowie, S. 2019. Mine planning and the crucial role of geology. SEG Discovery 118:16-27, doi:10.5382/geo-and-mining-04.

Hosch, W.L. 2022. Gossan. Retrieved October 22, 2022, from

IAEA Nuclear Energy Series. 2013. Advances in Airborne and Ground Geophysical Methods for Uranium Exploration. Retrieved from

Jellouli, A., Harti, A., El, Adiri, Z., Bachaoui, E.M. and Ghmari, A.El. 2019. Application of Remote Sensing Data in Lithological Discrimination of Kerdous Inlier in the Anti Atlas Belt of Morocco. International Journal on Informatics Visualization 2(2):227-232.

Juba, B. and Le, H.S. 2019. Precision-recall versus accuracy and the role of large data sets. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 33(01) (pp. 4039–4048), doi:10.1609/aaai.v33i01.33014039.

Kääb, A., Winsvold, S.H., Altena, B., Nuth, C., Nagler, T. and Wuite, J. 2016. Glacier Remote Sensing Using Sentinel-2. Part I : Radiometric and Geometric Performance, and Application to Ice Velocity. Remote Sensing 8(598):24, doi:10.3390/rs8070598.

Karlhede, A. 2020. Tackling imbalanced data in Random Forest to predict free-to-fee transitions of a subscription. KTH Royal Institute of Technology.

King, H.M. 2022. Magnetite and Lodestone, The primary ore of iron, a mineral used in heavy media separation, and a recorder of Earth magnetism. Retrieved October 21, 2022, from

Krawczyk, B. 2016. Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence 5(4):221-232, doi:10.1007/s13748-016-0094-0.

Kuhn, S., Cracknell, M.J. and Reading, A.M. 2016. Lithological mapping via Random Forests: Information Entropy as a proxy for inaccuracy Lithological mapping via Random Forests : Information Entropy as a proxy for inaccuracy. ASEG Extended Abstracts 1:1-4, doi:10.1071/ASEG2016ab196.

Kuhn, S., Cracknell, M.J. and Reading, A.M. 2018. Case history lithologic mapping using random forests applied to geophysical and remote-sensing data: A demonstration study from the Eastern Goldfields of Australia. Geophysics 83(4), doi:10.1190/geo2017-0590.1.

Kuhn, S., Cracknell, M.J. and Reading, A.M. 2019. Lithological mapping in the Central African Copper Belt using Random Forests and clustering: Strategies for optimised results. Ore Geology Reviews 112(103015), doi:10.1016/j.oregeorev.2019.103015.

Kuhn, S., Cracknell, M.J., Reading, A.M. and Sykora, S. 2020. Case History Identification of intrusive lithologies in volcanic terrains in British Columbia by machine learning using random forests: The value of using a soft classifier. Geophysics 85(6), doi:10.1190/geo2019-0461.1.

Kurnianto, F.A., Nurdin, E.A. and Yushardi. 2020. Analysis of stratigraphy and lithology in forming gold minerals in East Java with digital elevation model and medium format photo. IOP Conference Series: Earth and Environmental Science 485(1), doi:10.1088/1755-1315/485/1/012145.

L3Harris Geospatial Solution. 2020. Vegetation Suppression. Retrieved August 1, 2020, from

Liang, H., Chen, H., Guo, J., Bai, J. and Jiang, Y. 2022. Research on lithology identification method based on mechanical specific energy principle and machine learning theory. Expert Systems with Applications 189:116-142, doi:10.1016/j.eswa.2021.116142.

Liang, S., Sun, S. and Lu, H. 2021. Application of airborne electromagnetics and magnetics for mineral exploration in the Baishiquan–Hongliujing area, northwest China. Remote Sensing 13(5):1-16, doi:10.3390/rs13050903.

Luque, A., Carrasco, A., Martín, A. and de las Heras, A. 2019. The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition 91:216-231, doi:10.1016/j.patcog.2019.02.023.

Makienko, D., Seleznev, I. and Safonov, I. 2020. The effect of the imbalanced training dataset on the quality of classification of lithotypes via whole core photos. In: Fursov, V., Goshin, Y. and Kudryashov, D. (eds.), The VI International Conference Information Technology and Nanotechnology (pp. 132–136). Samara, Russia: CEUR-WS.

Mariita, N.O. 2007. The Magnetic Method. In Short Course II on Surface Exploration for Geothermal Resources (pp. 1–8). Lake Naivasha, Kenya: UNU-GTP and KenGen, doi:10.1201/b19255-6.

Merembayev, T., Kurmangaliyev, D., Bekbauov, B. and Amanbek, Y. 2021. A comparison of machine learning algorithms in predicting lithofacies: case studies from Norway and Kazakhstan. Energies 14:1-16, doi:10.3390/en14071896.

Mine Serve International. 2000. Geological Map Scale of 1:25.000, 2nd Edition. Komopa, Papua, Indonesia.

Mohamed, A. and Deep, M.Al. 2021. Depth to the bottom of the magnetic layer, crustal thickness, and heat flow in Africa: Inferences from gravity and magnetic data. Journal of African Earth Sciences 179(104204), doi:10.1016/j.jafrearsci.2021.104204.

Myburgh, G. and van Niekerk, A. 2014. Impact of training set size on object-based land cover classification: a comparison of three classifiers. International Journal of Applied Geospatial Research 5(3):49-67, doi:10.4018/ijagr.2014070104

NASA. 2013. Shuttle Radar Topography Mission (SRTM), doi:10.5069/G9445JDF.

Noorhalim, N., Ali, A. and Shamsuddin, S.M. 2019. Handling imbalanced ratio for class imbalance problem using SMOTE. Proceedings of the Third International Conference on Computing, Mathematics and Statistics (iCMS2017) (pp. 19–30). Springer Nature Singapore, doi:10.1007/978-981-13-7279-7.

Ottinger, M. and Kuenzer, C. 2020. Spaceborne L-band synthetic aperture radar data for geoscientific analyses in coastal land applications: a review. Remote Sensing 12(14):1-36, doi:10.3390/rs12142228.

Pal, M.K. and Porwal, A. 2016. Vegetation suppression for unveiling of surface lithology from Hyperspectral images using linear spectral unmixing approach. International Geoscience and Remote Sensing Symposium 7046-7049, doi:10.1109/IGARSS.2016.7730837.

Pandarinath, K., Shankar, R., Santoyo, E., Shetty, S.B., García-Soto, A.Y. and Gonzalez-Partida, E. 2019. A rock magnetic fingerprint of hydrothermal alteration in volcanic rocks - An example from the Los Azufres Geothermal Field, Mexico. Journal of South American Earth Sciences 91(29):260-271, doi:10.1016/j.jsames.2019.02.018.

Polvimoltham, P. and Sinapiromsaran, K. 2021. Mass ratio variance majority undersampling and minority oversampling technique for class imbalance. Frontiers in Artificial Intelligence and Applications 340:152-161, doi:10.3233/FAIA210186.

Ranjbar, H., Shahriari, H. and Honarmand, M. 2004. Integration of ASTER and airborne geophysical data for exploration of copper mineralization. a case study of Sar Cheshmeh Area. Proceedings of 20th congress, International Society for Photogrammetry and Remote Sensing, Istanbul (pp. 12-13). Istanbul: ISPRS.

Ren, Q., Cheng, H. and Han, H. 2017. Research on machine learning framework based on random forest algorithm. AIP Conference Proceedings Vol. 1820, pp. 1-7, doi:10.1063/1.4977376.

Rezaeezade, A., Perin, G. and Picek, S. 2022. To overfit, or not to overfit: improving the performance of deep learning-based SCA. In: Batina, L. and Daemen, J. (rds.), Progress in Cryptology-AFRICACRYPT 2022 (pp. 397-421). Springer, Cham, doi:10.1007/978-3-031-17433-917.

Salako, A.O. and Adepelumi, A.A. 2016. Evaluation of hydraulic conductivity of subsoil using electrical resistivity and ground penetrating radar data: example from Southwestern Nigeria. International Journal of Geo-Engineering 7(1), doi:10.1186/s40703-016-0018-7.

Salgado, C.M., Azevedo, C., Proen, H. and Vieira, S.M. 2016. Noise versus outliers. In: Secondary Analysis of Electronic Health Records (pp. 163–183). Springer, Cham, doi:10.1007/978-3-319-43742-2.

Scikitlearn. 2020. Sklearn.ensemble Random Forest Classifier. Retrieved January 20, 2020, from generated/sklearn.ensemble.RandomForestClassifier.html.

Shebl, A., Abdellatif, M., Hissen, M., Ibrahim Abdelaziz, M. and Csámer, Ã. 2021. Lithological mapping enhancement by integrating Sentinel 2 and gamma-ray data utilizing support vector machine: A case study from Egypt. International Journal of Applied Earth Observation and Geoinformation 105(November), doi:10.1016/j.jag.2021.102619.

Shebl, A., Kusky, T. and Csámer, Ã. 2022. Advanced land imager superiority in lithological classification utilizing machine learning algorithms. Arabian Journal of Geosciences 1-13, doi:10.1007/s12517-022-09948-w.

Slavinski, H., Morris, B., Ugalde, H., Spicer, B., Skulski, T. and Rogers, N. 2010. Integration of lithological, geophysical, and remote sensing information: A basis for remote predictive geological mapping of the Baie Verte Peninsula, Newfoundland. Canadian Journal of Remote Sensing 36(2):99-118, doi:10.5589/m10-031.

Sun, Y., Wong, A.K.C. and Kamel, M.S. 2009. Classification of imbalanced data: a review. International Journal of Pattern Recognition and Artificial Intelligence 23(4):687-719, doi:10.1142/S0218001409007326.

Van Gorsel, J.T. 2018. New Guinea (incl. PNG). In: Bibliography of the Geology of Indonesia and Surrounding Areas (7.0, pp. 0-261). Retrieved from

Weiss, G.M. 2004. Mining with rarity: a unifying framework. ACM SIGKDD Explorations Newsletter 6(1):7-19, doi:10.1145/1007730.1007734.

Welsink, A. 2020. Comparing Classification of Ghana’s Complex Agroforestry Land Cover by a Random Forest and a Convolutional Neural Network with a Small Training Set. Wageningen University.

Wemegah, D.D., Preko, K., Noye, R.M., Boadi, B., Menyeh, A., Danuor, S.K. and Amenyoh, T. 2015. Geophysical interpretation of possible gold mineralization zones in Kyerano, South-Western Ghana using aeromagnetic and radiometric datasets. Journal of Geoscience and Envrionment Protection 3(June):67-82, doi:10.4236/gep.2015.34008.

Wenhua, W., Zhuwen, W., Ruiyi, H., Fanghui, X., Xinghua, Q. and Yitong, C. 2021. Lithology classification of volcanic rocks based on conventional logging data of machine learning: A case study of the eastern depression of Liaohe oil field. Open Geosciences 13:1245-1258, doi:10.1515/geo-2020-0300.

Xie, Y., Zhu, C., Zhou, W., Li, Z., Liu, X. and Tu, M. 2018. Evaluation of machine learning methods for formation lithology identification: A comparison of tuning processes and model performances. Journal of Petroleum Science and Engineering 160:182-193, doi:10.1016/j.petrol.2017.10.028.

Yoon, H. 2021. Finding unexpected test accuracy by cross validation in machine learning. International Journal of Computer Science and Network Security 21(12):549-555.

Yu, L., Porwal, A., Holden, E.J. and Dentith, M.C. 2011. Suppression of vegetation in multispectral remote sensing images. International Journal of Remote Sensing 32(22):7343-7357, doi:10.1080/01431161.2010.523726.

Zhang, H., Jia, P., Zhang, X. and Wang, Z. 2017. The application of airborne geophysics data for rapid regional geological mapping in northwestern Angola. Sains Malaysiana 46(11):2109-2118, doi:10.17576/jsm-2017-4611-11.

Zhou, K., Zhang, J., Ren, Y., Huang, Z. and Zhao, L. 2020. A gradient boosting decision tree algorithm combining synthetic minority oversampling technique for lithology identification. Geophysics 85(4):WA147-WA158, doi:10.1190/geo2019-0429.1.

Zhu, M.I.N., Xia, J., Jin, X., Yan, M., Cai, G., Yan, J. and Ning, G. 2018. Class weights random forest algorithm for processing class imbalanced medical data. IEEE Access 3536(c), doi:10.1109/ACCESS.2018.2789428.








How to Cite

Nugroho, H., Wikantika, K., Bijaksana, S., & Saepuloh, A. (2023). Integration of remote sensing and geophysical data to enhance lithological mapping utilizing the Random Forest classifier: a case study from Komopa, Papua Province, Indonesia. Journal of Degraded and Mining Lands Management, 10(3), 4417–4432.



Research Article