A granitic pegmatite information extraction method based on improved U-Net
LI Wanyue1,2(), LOU Debo1(), WANG Chenghui1, LIU Huan1, ZHANG Changqing1, FAN Yinglin3, DU Xiaochuan1,2
1. MLR Key Laboratory of Metallogeny and Mineral Assessment, Institute of Mineral Resources, Chinese Academy of Geological Sciences, Beijing 100037, China 2. School of Earth Science and Resource, China University of Geosciences (Beijing), Beijing 100083, China 3. General Prospecting Institute of China National Administration of Coal Geology, Beijing 100039, China
Identifying granitic pegmatite-type lithium deposits based on remote sensing technology is a significant method for lithium ore prospecting. To enhance the information extraction accuracy of the deep learning-based semantic segmentation method for granitic pegmatites, this study improved the classic U-Net network. A batch normalization module was added to the convolutional layer of the encoder part, with the ReLU activation function replaced by the ReLU6 activation function. Simultaneously, a composite loss function was constructed to improve operational efficiency and reduce the precision loss in the training process. The domestic GF-2 images of a granitic pegmatite-type lithium deposit were employed to create a dataset for experiments. The results show that the improved U-Net model effectively identified the information on granitic pegmatites in the study area covered by GF-2 images. Compared to the original U-Net network, U-Net model based on VGG backbone network, U-Net model based on MobileNetV3 backbone network, and conventional random forest model, the improved U-Net model has its average intersection over union increased by 14.69, 0.95, 5.08, and 35.34 percentage points, respectively. Moreover, its F1-score increased by 18.38, 1.02, 5.7, and 54.59 percentage points, respectively. Hence, the improved U-Net model achieves the high-precision automatic extraction of ore-bearing granitic pegmatite information from remote sensing images in areas with low vegetation coverage.
李婉悦, 娄德波, 王成辉, 刘欢, 张长青, 范莹琳, 杜晓川. 基于改进U-Net网络的花岗伟晶岩信息提取方法[J]. 自然资源遥感, 2024, 36(2): 89-96.
LI Wanyue, LOU Debo, WANG Chenghui, LIU Huan, ZHANG Changqing, FAN Yinglin, DU Xiaochuan. A granitic pegmatite information extraction method based on improved U-Net. Remote Sensing for Natural Resources, 2024, 36(2): 89-96.
Hu X J, Li H. Research progress and prospect of granitic pegmatite-type lithium deposits[J]. The Chinese Journal of Nonferrous Metals, 2021, 31(11):3468-3488.
Wang D H. Study on critical mineral resources:Significance of research,determination of types,attributes of resources,progress of prospecting,problems of utilization,and direction of exploitation[J]. Acta Geologica Sinica, 2019, 93(6):1189-1209.
Lou D B, Wang D H, Li W Y, et al. Progress of prospecting prediction research for granitic pegmatite-type lithium deposits at home and abroad[J]. Mineral Deposits, 2022, 41(5):975-988.
Chen Y J, Xue L Z, Wang X L, et al. Progress in geological study of pegmatite-type lithium deposits in the world[J]. Acta Geologica Sinica, 2021, 95(10):2971-2995.
Jiang Q, Dai J J, Wang D H, et al. Application of optical remote sensing to identifying granite pegmatite lithium deposits[J]. Mineral Deposits, 2021, 40(4):793-804.
[7]
Cardoso-Fernandes J, Teodoro A C, Lima A. Remote sensing data in lithium (Li) exploration:A new approach for the detection of Li-bearing pegmatites[J]. International Journal of Applied Earth Observation and Geoinformation, 2019, 76:10-25.
Jin M S, Gao Y B, Li K, et al. Remote sensing prospecting method for pegmatite type rare metal deposit:Taking Dahongliutan area in western Kunlun for example[J]. Northwestern Geology, 2019, 52(4):222-231.
Pan M, Tang Y, Xiao R Q, et al. The discovery of the superlarge Li ore vein X03 in the Jiajika ore district[J]. Acta Geologica Sichuan, 2016, 36(3):422-425,430.
Yao F J, Xu X W, Yang J M, et al. A technology for identifying Li-Be pegmatite using ASTER remote sensing data in granite of Gobi shallow-covered area:A case study of recognition and prediction of Li-Be pegmatite in Jingerquan,Xinjiang[J]. Mineral Deposits, 2020, 39(4):686-696.
Du X C, Lou D B, Xu L G, et al. Extraction of granitic pegmatite based on GF-2 image and random forest algorithm[J/OL]. Remote Sensing for Natural Resources, 2023(2023-01-18). https://kns.cnki.net/kcms/detail/10.1759.P.20230117.1030.007.html.
[12]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]// 3rd International Conference on Learning Representations,ICLR 2015-Conference Track Proceedings, 2015.
[13]
Howard A G, Zhu M, Chen B, et al. MobileNets:Efficient convolutional neural networks for mobile vision applications[EB/OL]. arXiv, 2017. http://arxiv.org/abs/1704.04861.pdf.
[14]
Sandler M, Howard A, Zhu M, et al. Inverted residuals and linear bottlenecks:Mobile networks for classification, detection and segmentation[EB/OL]. arXiv, 2018. http://arxiv.org/abs/1704.04861.pdf.
[15]
Howard A, Sandler M, Chen B, et al. Searching for MobileNetV3[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV).Seoul,Korea (South).IEEE, 2019:1314-1324.
[16]
Ronneberger O, Fischer P, Brox T. U-net:Convolutional networks for biomedical image segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2015:234-241.
Wang H Y. Research on extracting pegmatite dike information of remote sensing image based on depth semantic segmentation[D]. Beijing: China University of Geosciences>(Beijing), 2021.
Wang B Z, Han J, Xie X L, et al. Discovery of the indosinian(beryl-bearing) spodumene pegmatitic dike swarm in the Chakaibeishan area in the northeastern margin of the Tibetan Plateau:Implications for Li-Be mineralization[J]. Geotectonica et Metallogenia, 2020, 44(1):69-79.
Kong H L, Zhang J W, Jin M S, et al. Progress of pegmatite lithiumberyllium and other key metal mineral exploration in northern Qaidam margin of Qinghai Province[C]// Proceedings of the First National Mineral Exploration Conference.Hefei, 2021:819-822.
Sun W W, Yang G, Chen C, et al. Development status and literature analysis of China’s earth observation remote sensing satellites[J]. Journal of Remote Sensing, 2020, 24(5):479-510.
[21]
Ioffe S, Szegedy C. Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]// Proceedings of the 32nd International Conference on International Conference on Machine Learning,2015,Lille,France.ACM, 2015:448-456.
2024, Vol. 36 
), 娄德波1(
