岩性识别方法是基于机器学习分类算法，可以对测井数据和测井图进行分类和识别，有效地学习和记忆储层中岩层的特征。该方法可以比较吸附岩体、决策树、随机森林和SVM四种算法，选择出最高的岩性识别精度。为满足识别精度、效率等要求提供重要依据，对测井数据的自动解释和计算机的地层自识别具有重要意义。\n
数据内容如下：\n
ILD：Induction Logging Device；\n
SP：Spontaneous Potential；\n
CN：Neutron Logging；\n
ILM：Intermediate Logging Device；\n
GR：Gamma Ray Logging；\n
CAL：Caliper；\n
AC：Acoustic Logging；\n
DEN：Density Logging。", "ds_source": "
原始测井数据为：塔里木盆地泥盆纪东河塘组测井数据。", "ds_process_way": "
对测井数据进行集成，采用机器学习方法对岩性进行自动识别。", "ds_quality": "
数据质量良好。", "ds_acq_start_time": "2009-01-01 00:00:00", "ds_acq_end_time": "2013-12-31 00:00:00", "ds_acq_place": "塔里木盆地", "ds_acq_lon_east": 90.0, "ds_acq_lat_south": 37.0, "ds_acq_lon_west": 75.0, "ds_acq_lat_north": 42.0, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 49026988, "ds_files_count": 22, "ds_format": "Excel", "ds_space_res": "0.1-10m", "ds_time_res": "", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "ec7c79a4-b7b1-4926-916d-6f130c096a16.jpg", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "fdaf40e0-8913-40fa-927b-8786c3af0bf5", "ds_serv_man": "敏玉芳", "ds_serv_phone": "0931-4967596", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.50" ], "quality_level": 3, "publish_time": "2024-03-28 09:26:22", "last_updated": "2025-06-30 11:30:27", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.XDA14.DB6396.2024", "i18n": { "en": { "title": "Research dataset on automatic formation lithology identification based on integrated logging data (2009-2013)", "ds_format": "Excel", "ds_source": "
The original logging data are: well logging data of the Devonian Donghetang Formation in the Tarim Basin.", "ds_quality": "
Data quality is good.", "ds_ref_way": "", "ds_abstract": "
The lithology recognition method is based on a machine learning classification algorithm, which can classify and recognize logging data and logging diagrams, and effectively learn and memorize the characteristics of the rock layers in the reservoir. The method can compare four algorithms, namely adsorbed rock body, decision tree, random forest and SVM, to select the highest lithology recognition accuracy. It provides an important basis for meeting the requirements of recognition accuracy and efficiency, and is of great significance for automatic interpretation of logging data and formation self-recognition by computer.\n
The data content is as follows:\n
ILD：Induction Logging Device;\n
SP：Spontaneous Potential;\n
CN：Neutron Logging;\n
ILM：Intermediate Logging Device;\n
GR：Gamma Ray Logging;\n
CAL：Caliper;\n
AC：Acoustic Logging;\n
DEN：Density Logging.
", "ds_time_res": "", "ds_acq_place": "Tarim Basin", "ds_space_res": "0.1-10m", "ds_projection": "", "ds_process_way": "Integration of logging data and automatic lithology identification using machine learning methods.", "ds_ref_instruction": "" } }, "submit_center_id": "ncdc", "data_level": 0, "license_type": "CC BY 4.0", "doi_reg_from": "reg_local", "cstr_reg_from": "reg_local", "doi_not_reg_reason": null, "cstr_not_reg_reason": null, "is_paper_in_submitting": false, "ds_topic_tags": [ "泥盆纪东河塘组", "测井曲线", "油气测井", "塔里木盆地", "岩性识别" ], "ds_subject_tags": [ "地质学" ], "ds_class_tags": [], "ds_locus_tags": [ "塔里木盆地" ], "ds_time_tags": [ 2009, 2010, 2011, 2012, 2013 ], "ds_contributors": [ { "true_name": "陈冬", "email": "dong.chen@cup.edu.cn", "work_for": "中国石油大学（北京）石油工程学院", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "陈冬", "email": "dong.chen@cup.edu.cn", "work_for": "中国石油大学（北京）石油工程学院", "country": "中国" } ], "ds_managers": [ { "true_name": "陈冬", "email": "dong.chen@cup.edu.cn", "work_for": "中国石油大学（北京）石油工程学院", "country": "中国" } ], "category": "其他" }