模型支撑数据集包含以下内容：GA-DBN模型代码、模型参数数据集、193组8个堤防渗漏影响因子、GA-DBN模型训练结果，以及阳新干堤防的73组5个堤防影响因子。其中案例数据和训练集数据包括对应的水位高度差/m、覆盖层厚度/m、渗透系数、孔隙比、压缩系数和是否发生管涌六种。\n
数据集结合了模型实现与训练结果，为堤防渗漏预测提供了全面的支持。通过包含堤防渗漏影响因子和相应的训练数据，该数据集可用于分析不同因子对堤防渗漏的影响，并为堤防渗漏风险评估与预测模型的优化提供有力依据。", "ds_source": "
该数据集中的GA-DBN模型基于Python开发，包含模型代码和参数数据集。193组8个堤防渗漏影响因子和阳新干堤防的73组5个堤防影响因子来源于相应的实际数据集，这些数据集经过整理和标准化处理，为模型训练与预测提供了可靠的输入数据。这些数据支持堤防渗漏风险评估、预测分析及模型优化，具有较高的实用价值。", "ds_process_way": "
数据加工过程首先进行模型调参和数据归一化处理。在调参阶段，通过调整GA-DBN模型的超参数（如学习率、层数等）来优化模型性能，确保训练结果的准确性。\n
在数据归一化阶段，所有影响因子数据通过标准化或归一化方法进行处理，以消除不同数据量纲带来的偏差，确保各因素在同一尺度下进行比较和训练。经过这些预处理步骤，数据集为GA-DBN模型的训练和预测提供了更加一致和稳定的输入，有助于提高模型的准确性和泛化能力。", "ds_quality": "
该数据集经过严格处理，确保了数据的完整性和一致性。在GA-DBN模型的训练和验证过程中，模型达到了100%的准确率、召回率、精度和F1分数，表明数据集具有极高的质量。这些优异的性能指标不仅验证了数据的准确性和可靠性，还表明该数据集能够有效支持堤防渗漏预测的实际应用，具备较高的实用价值。模型的优秀表现进一步证明了数据在处理堤防渗漏风险分析中的有效性和准确性。", "ds_acq_start_time": null, "ds_acq_end_time": null, "ds_acq_place": "巢湖流域", "ds_acq_lon_east": 115.67, "ds_acq_lat_south": 29.92, "ds_acq_lon_west": 115.42, "ds_acq_lat_north": 30.02, "ds_acq_alt_low": null, "ds_acq_alt_high": null, "ds_share_type": "login-access", "ds_total_size": 58423, "ds_files_count": 6, "ds_format": "*.xlxs,*.py", "ds_space_res": null, "ds_time_res": "", "ds_coordinate": "无", "ds_projection": "", "ds_thumbnail": "8cef7d97-757f-4c30-8d66-962e8216b8a7.png", "ds_thumb_from": 0, "ds_ref_way": "", "paper_ref_way": "", "ds_ref_instruction": "", "ds_from_station": null, "organization_id": "37eb642a-c117-47e4-a677-07ecffb4b8b7", "ds_serv_man": "李红星", "ds_serv_phone": "0931-4967592", "ds_serv_mail": "ncdc@lzb.ac.cn", "doi_value": "", "subject_codes": [ "170.50" ], "quality_level": 3, "publish_time": "2025-03-27 21:15:40", "last_updated": "2025-06-30 11:40:13", "protected": false, "protected_to": null, "lang": "zh", "cstr": "11738.11.NCDC.NHRI.DB6790.2025", "i18n": { "en": { "title": "GA-DBN model support dataset", "ds_format": "*.xlxs,*.py", "ds_source": "
The GA-DBN model in this dataset is developed based on Python and contains the model code and parameter datasets. 193 groups of 8 levee leakage impact factors and 73 groups of 5 levee impact factors of Yangxin dry dyke defenses are derived from the corresponding actual datasets, which are sorted out and standardized to provide reliable inputs for model training and prediction. Data. These data are of high practical value to support the risk assessment, prediction analysis and model optimization of levee leakage.", "ds_quality": "
The dataset was rigorously processed to ensure data integrity and consistency. During the training and validation of the GA-DBN model, the model achieved 100% accuracy, recall, precision and F1 score, indicating that the dataset is of extremely high quality. These excellent performance metrics not only validate the accuracy and reliability of the data, but also indicate that the dataset can effectively support the practical application of embankment leakage prediction with high practical value. The excellent performance of the model further proves the effectiveness and accuracy of the data in dealing with embankment leakage risk analysis.", "ds_ref_way": "", "ds_abstract": "
The model support dataset contains the following: the GA-DBN model code, the model parameter dataset, 193 groups of 8 levee leakage impact factors, the GA-DBN model training results, and 73 groups of 5 levee impact factors for Yangxin dry dike defense. Among them, the case data and training set data include six corresponding water level height difference/m, cover layer thickness/m, permeability coefficient, pore ratio, compression coefficient, and whether pipe surge occurs.\n
The dataset combines the model implementation and training results to provide comprehensive support for embankment leakage prediction. By including the levee leakage influencing factors and the corresponding training data, the dataset can be used to analyze the influence of different factors on levee leakage and provide a strong basis for the optimization of levee leakage risk assessment and prediction models.
", "ds_time_res": "", "ds_acq_place": "Chaohu lake basin", "ds_space_res": "", "ds_projection": "", "ds_process_way": "The data processing process starts with model tuning and data normalization. In the tuning stage, the model performance is optimized by adjusting the hyperparameters (e.g., learning rate, number of layers, etc.) of the GA-DBN model to ensure the accuracy of the training results.\n
In the data normalization stage, all the influence factor data are processed by standardization or normalization methods to eliminate the bias caused by different data scales and ensure that the factors are compared and trained at the same scale. After these preprocessing steps, the dataset provides more consistent and stable inputs for the training and prediction of the GA-DBN model, which helps to improve the accuracy and generalization ability of the model.", "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": [ "堤防渗漏", "机器学习" ], "ds_subject_tags": [ "地质学" ], "ds_class_tags": [], "ds_locus_tags": [ "中国", "长江下游" ], "ds_time_tags": [], "ds_contributors": [ { "true_name": "鲁明贵", "email": "1907993011@qq.com", "work_for": "南京工业大学", "country": "中国" } ], "ds_meta_authors": [ { "true_name": "周彦章", "email": "yzzhou@nhri.cn", "work_for": "南京水利科学研究院", "country": "中国" } ], "ds_managers": [ { "true_name": "鲁明贵", "email": "1907993011@qq.com", "work_for": "南京工业大学", "country": "中国" } ], "category": "其他" }