检索结果-内蒙古大学图书馆

Enhanced permeability prediction in porous media using particle swarm optimization with multi-source integration

Artificial Intelligence in Geosciences 2024年第1期5卷 282-293页

作者： Zhiping Chen Jia Zhang Daren Zhang Xiaolin Chang Wei Zhou State Key Laboratory of Water Resources Engineering and Management Wuhan UniversityWuhan 430072China Institute of Water Engineering Sciences Wuhan UniversityWuhan 430072China Key Laboratory of Rock Mechanics in Hydraulic Structural Engineering of Ministry of Education Wuhan UniversityWuhan 430072China

Accurately and efficiently predicting the permeability of porous media is essential for addressing a wide range of hydrogeological ***,the complexity of porous media often limits the effectiveness of individual prediction *** study introduces a novel Particle Swarm Optimization-based Permeability Integrated Prediction model(PSO-PIP),which incorporates a particle swarm optimization algorithm enhanced with dy-namic clustering and adaptive parameter tuning(KGPSO).The model integrates multi-source data from the Lattice Boltzmann Method(LBM),Pore Network Modeling(PNM),and Finite Difference Method(FDM).By assigning optimal weight coefficients to the outputs of these methods,the model minimizes deviations from actual values and enhances permeability prediction ***,the computational performances of the LBM,PNM,and FDM are comparatively analyzed on datasets consisting of sphere packings and real rock *** is observed that these methods exhibit computational biases in certain permeability *** PSOPIP model is proposed to combine the strengths of each computational approach and mitigate their *** PSO-PIP model consistently produces predictions that are highly congruent with actual permeability values across all prediction intervals,significantly enhancing prediction *** outcomes of this study provide a new tool and perspective for the comprehensive,rapid,and accurate prediction of permeability in porous media.

关键词： Porous media Particle swarm optimization algorithm multi-source data integration Permeability prediction

来源：评论

学校读者我要写书评

暂无评论

Deep Spatial Prediction via Heterogeneous multi-source Self-supervision

引用

ACM TRANSACTIONS ON SPATIAL ALGORITHMS AND SYSTEMS 2023年第3期9卷 1-26页

作者： Zhang, Minxing Yu, Dazhou Li, Yun Zhao, Liang Math & Sci Ctr Suite W401 400 Dowman Dr Atlanta GA 30322 USA

Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated

关键词： Spatial prediction spatial interpolation multi-source data integration in situ data remote sensing data error-compensation geometric representation deep learning self-supervision

来源：评论

学校读者我要写书评

暂无评论

A novel multi-source data-driven energy consumption prediction model for Venlo-type greenhouses in China

引用

SMART AGRICULTURAL TECHNOLOGY 2025年 10卷

作者： Chen, Yangda Bao, Aiqun Li, Yapeng Xiang, Yingfeng Cai, Wanlong Xia, Zhaoqiang Li, Jialei Ning, Mingyang Sun, Jing Zhang, Haixi Sun, Xianpeng Wei, Xiaoming Northwest A&F Univ Coll Hort Yangling 712100 Shaanxi Peoples R China Northwest A&F Univ Coll Informat Engn Yangling 712100 Shaanxi Peoples R China Xi An Jiao Tong Univ Sch Human Settlements & Civil Engn Xian 710049 Shaanxi Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Shaanxi Peoples R China Beijing Acad Agr & Forestry Sci Res Ctr Intelligent Equipment Beijing 100097 Peoples R China Minist Agr Key Lab Hort Engn Northwest Facil Yangling 712100 Shaanxi Peoples R China Facil Agr Engn Technol Res Ctr Shaanxi Prov Yangling 712100 Shaanxi Peoples R China

The high energy consumption characteristic of multi-span glass greenhouses significantly limits their widespread adoption. Optimizing energy strategies and implementing predictive models for energy consumption are essential for more efficient management and reduction of greenhouse operational energy costs. Existing methods rely on single-element approaches to predict energy consumption, but this reliance often results in severe performance limitations. Therefore, energy consumption prediction methods that incorporate multi-source data are necessary. To overcome the challenges concerning heterogeneity, redundancy, and interdependence among different data sources, this paper proposed a novel energy consumption method that integrates multi-source data through feature engineering and machine learning techniques, which significantly enhances the efficiency of data utilization and improves prediction accuracy. The final experimental results indicated that the proposed energy consumption prediction method demonstrates excellent performance with high prediction accuracy (R2 = 0.9388) and low computational resource consumption (runtime = 926.91s), outperforming other models. Finally, the model was interpreted using SHAP (SHapley Additive exPlanations) values, and ablation experiments were conducted to validate the effectiveness of the proposed method in greenhouse energy consumption prediction, thereby providing strong support for greenhouse management.

关键词： Greenhouse energy consumption multi-source data integration Feature engineering Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

Enhancing monthly precipitation forecasting by integrating multi-source data with machine learning models: a study in the Upper Blue Nile Basin

引用

MODELING EARTH SYSTEMS AND ENVIRONMENT 2025年第1期11卷 1-16页

作者： Mohammed, Juhar Mengiste, Yenesew Gebremichael, Mekonnen Addis Ababa Univ Addis Ababa Ethiopia Addis Ababa Sci & Technol Univ Addis Ababa Ethiopia Univ Calif Los Angeles Los Angeles CA USA

This study developed a novel framework to improve monthly precipitation forecasts by integrating multi-source data with machine-learning techniques. The framework used a blend of gauge, satellite, and reanalysis data to train the model with high-quality spatial-temporal precipitation information. Predictors such as local meteorological variables, large-scale climate indices, soil moisture data, and lagged precipitation data were used for one-month ahead precipitation forecasting. Five machine learning algorithms, including Artificial Neural Networks (ANN), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGboost), and Random Forest (RF), are evaluated in the framework for their forecasting performance across five monitoring stations in the upper Blue Nile basin. The results demonstrate that the novel forecasting framework integrating multi-source data with machine learning techniques significantly improved the monthly precipitation forecasts. All models exhibited higher R2, closer agreement with observed data measured by Wilmot's index (d), and lower MAE and RMSE values. During testing phase, the models recorded 0.64-0.87 R 2, 0.62-2.95 RMSE, 0.18-2.42 MAE and 0.7-0.85 d values across stations. Among the models evaluated in the framework ANN, SVM, and KNN consistently showcased better performance both in the training and testing phases, with ANN exhibiting the most promising results overall. However, Extreme Gradient Boosting and Random Forests exhibited comparatively weaker performance across stations. Additionally, the models' performance under different climate categories (dry, normal, and wet months) was also explored. The models excel during normal and dry months, but, during wet months their performance diminishes relatively. Furthermore, the proposed framework forecast skills compared with NCEP and ECMWF global precipitation prediction and showed a better performance. Overall, the findings highlight the potential of the deve

关键词： multi-source data integration Machine learning models Monthly precipitation forecasting Global precipitation predictions Upper Blue Nile Basin

来源：评论

学校读者我要写书评

暂无评论

Evaluating inequality divides in urban development intensity between the Global North and South

引用

LAND USE POLICY 2024年 145卷

作者： Chen, Liangkan Chen, Mingxing Zhang, Xiaoping Xian, Yue Chinese Acad Sci Inst Geog Sci & Nat Resources Res Beijing Peoples R China Chinese Acad Sci Key Lab Reg Sustainable Dev Modeling Beijing Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing Peoples R China

As the significance of cities worldwide with regard to human activities increases, Urban Development Intensity (UDI) becomes an increasingly critical factor for achieving Sustainable Development Goal (SDG) Target 11.3 and serves as a scientific foundation for establishing urban land development guidelines. However, the existing literature lacks systematic quantification of fine-scale UDI on the global scale. In this study, we propose a comprehensive framework for evaluating UDI globally, utilizing multi-source surveys to compare spatial variations between the Global North and South. We created structured grided UDI layers at a 1-km resolution covering urban areas worldwide, considering various aspects of urban development on land surface characterized by three-dimensional (3D) building metrics, population density, nighttime lights, and transport constructions. By employing composite models and the inequality index, we assessed UDI disparities across 6986 cities and metropolitan areas globally to investigate variations in UDI levels and heterogeneity among the Global North-South regions, inter-city, and intra-city contexts. Furthermore, the bivariate local Moran's I statistic and kmedoid algorithm were utilized to identify spatial and pattern clusters of UDI among global cities. Our findings revealed diverse spatial distribution of multi-source UDI differences globally, with urban areas in the Global North generally exhibiting higher and more equitable intensity than that exhibited by urban areas in the Global South, where the intensity tends to be lower at the urban peripheries and highly concentrated in city centers. Recognizing the disparities and clustering patterns of UDI levels of global cities underscore the importance of promoting urban equalization to ensure containment and drive improvement in UDI towards diverse models under local urban circumstances for effective implementation of sustainable urbanization development across cities both in the Global North

关键词： Urban development intensity multi-source data integration Global North-South Regional differences Intra-city inequality Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Enhanced Crop Yield Forecasting Using Deep Reinforcement Learning and multi-source Remote Sensing data

引用

Remote Sensing in Earth Systems Sciences 2024年第4期7卷 426-442页

作者： Chavan, Yogita Rahulsing Swamikan, Brinthakumari Gupta, Megha Varun Bobade, Sunil Malhan, Anu Department of Computer Engineering New Horizon Institute of Technology and Management Thane India Department of Artificial Intelligence and Data Science New Horizon Institute of Technology and Management Thane India

Accurate crop yield predictions are essential for agricultural planning and food security. Traditional methods relying on historical data are enhanced by modern techniques using satellite imagery, weather data, and soil conditions. This study presents an advanced crop yield forecasting model integrating deep reinforcement learning and multi-source remote sensing data. The Hybrid Reinforcement-Supervised Learning (HRSL) model combines reinforcement learning and supervised learning for enhanced classification and decision-making. Machine learning and artificial intelligence techniques analyze historical yield data and current season variables, improving prediction accuracy. Preprocessing steps like imputation, normalization, and atmospheric correction ensure robust datasets. Feature extraction with cascaded artificial neural networks (CANN) automates the learning of complex data relationships. Implemented using Python, this methodology achieves an accuracy of 97.8%. The proposed model demonstrates superior performance in yield prediction, evaluated through rigorous accuracy, precision, and training efficiency metrics. Integrating multi-source data with advanced machine learning models offers significant benefits for precision agriculture and food security. Future work will expand these techniques to broader applications and continuously improve predictive models with evolving data and computational capabilities. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Crop yield forecasting Deep reinforcement learning Food security Machine learning multi-source data integration Precision agriculture Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Sustainability prioritization of sewage sludge to energy scenarios with hybrid-data consideration: a fuzzy decision-making framework based on full consistency method and fusion ranking model

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2021年第5期28卷 5548-5565页

作者： Tang, Chengli Xu, Di Chen, Nicheng Chongqing Chem Ind Vocat Coll Dept Chem Engn Chongqing 401220 Peoples R China Chongqing Univ Sci Technol Sch Chem & Chem Engn Chongqing 401331 Peoples R China

This work proposed a novel mathematical framework for the sustainability assessment of sewage sludge to energy (SStE) scenarios, by resorting to fuzzy multi-criteria decision-making (MCMD) methods. In which, an evaluation system including twelve criteria from four dimensions was introduced, while the fuzzy triangular number (TFN) was used to address the hybrid-data issue in the decision-making. More importantly, four fuzzy MCDM methods were used to make the following methodological contributions: (1) the fuzzy full consistency method (FUCOM) was extended into uncertain conditions to determine the weights easily and reliably, which preserves the consistency in ambiguous, subjective judgments;(2) a novel TFN-based fusion ranking model was developed by aggregating three fuzzy MCDM approaches, which not only takes the hybrid data as input information for decision-making (by combining the TFN) but also promotes the confidence in final prioritization (by reconciling different sequences). Four illustrative SStE scenarios were studied to test the feasibility of the model. Besides, the effectiveness and advantages of the model were verified by results comparison and discussion.

关键词： Sustainable sludge treatment Decision support system multi-criteria analysis multi-source data integration Uncertainty

来源：评论

学校读者我要写书评

暂无评论

An unsupervised embedding harmonization system for privacy-preserving data mining in healthcare

引用

IISE TRANSACTIONS ON HEALTHCARE SYSTEMS ENGINEERING 2024年第1期14卷 1-17页

作者： Li, Mai Lin, Ying Chen, Hua Aparasu, Rajender R. Univ Houston Ind Engn Houston TX 77204 USA Univ Houston Dept Pharmaceut Hlth Outcomes & Policy Houston TX USA

Sharing data across hospitals for disease modeling is challenging due to concerns over patient privacy and the lack of an efficient privacy-preserving data mining framework. Contextual embedding models, which encode medical events into vector representations while preserving the contextual dependencies between events, have shown promise in privacy-preserving data mining without requiring original data disclosure. However, the medical event representations learned from multiple data sources lie in different embedding spaces and cannot be directly integrated. Existing embedding harmonization algorithms require a list of common medical events between different data sources and use them as corresponding pairs for transformation, known as the supervised harmonization method. However, common medical events can be difficult to collect in clinical practice. To promote data mining across hospitals, we developed a novel unsupervised embedding harmonization system that introduces an unsupervised harmonization algorithm to align contextual embeddings without the need for corresponding pairs. The proposed framework also considered different contextual embedding techniques, including Word2Vec and Med2Vec, to explore the robustness of the proposed unsupervised harmonization algorithm. The proposed framework was evaluated using medical events extracted from the Medical Information Mart for Intensive Care III database. By integrating the embeddings from multiple sources, the proposed framework can achieve better disease prediction accuracy and medical event clustering compared to models built on a single data source. The proposed unsupervised harmonization method, which achieves similar performance to the supervised harmonization model under different contextual embedding techniques, holds great promise for predictive modeling and event clustering in healthcare.

关键词： multi-source data integration contextual embedding unsupervised harmonization privacy-preserving data mining

来源：评论

学校读者我要写书评

暂无评论

Spectroscopic and sensory characterization of Brazilian Coffea canephora terroir and botanical varieties produced in the Amazon and Espirito Santo implementing multi-block approaches

引用

JOURNAL OF FOOD COMPOSITION AND ANALYSIS 2024年 133卷

作者： Baqueta, Michel Rocha Marini, Federico Teixeira, Alexsandro Lara Goulart, Bruno Henrique Fermino Pilau, Eduardo Jorge Valderrama, Patricia Pallone, Juliana Azevedo Lima State Univ Campinas Unicamp Sch Food Engn Dept Food Sci & Nutr Campinas SP Brazil Univ Roma La Sapienza Dept Chem Piazzale Aldo Moro 5 I-00185 Rome Italy Empresa Brasileira Pesquisa Agr EMBRAPA Rondonia Porto Velho RO Brazil State Univ Maringa UEM Chem Dept BR-87020900 Maringa PR Brazil Univ Tecnol Fed Parana UTFPR Campo Mourao PR Brazil

Specialty Brazilian Canephora coffees are produced in the Amazon by indigenous and non-indigenous people and in Espirito Santo. Their distinctive quality, origin, and varietal were verified by integrated analytical techniques to understand better their chemical and sensory aspects and protect their origin and traceability. In this context, chemometric multi-block approaches represent a holistic way to integrate the multi-source data and then extract their complementary information. The samples were analyzed by near-infrared (NIR) spectroscopy on portable and benchtop instruments, ultraviolet-visible (UV-Vis) spectroscopy, mass spectrometry, and sensory analysis. Each piece of relevant information was interpreted before being integrated through exploratory data analysis and predictive modelling by multi-block methods. Although subtle, ComDim analysis showed a tendency to separate the indigenous and non-indigenous, and Espirito Santo coffees. Pre-processing ensembles with ROSA calibration (PROSAC) discriminated the three coffees with mean correct classification rate of 91.1 % in the test, using benchtop NIR with 1st derivative, mass spectrometry water spectra with Pareto scaling, and autoscaled sensory data. Sequential and orthogonalized partial least square-linear discriminant analysis (SO-PLS-LDA) performed better than PROSAC, showing 94.2 % of recognition in the test, using benchtop NIR with standard normal variate, mass spectrometry organic spectra with Pareto scaling, and portable NIR with 2nd derivative. Integrating complementary information from different blocks also improves classification accuracy compared to analyzing individual matrices.

关键词： Brazilian Canephora coffee Chemometrics data fusion multi-block data analysis multi-source data integration

来源：评论

学校读者我要写书评

暂无评论

The Adaptability Assessment and Online Decision-Making for Strategy of Stability Control Systems Involving multiple Types of Security and Stability Issues 4th

The Adaptability Assessment and Online Decision-Making for S...

引用

4th International Forum on Smart Grid Protection and Control (Purple Mountain Forum)

作者： Ruan, Jingjing Xu, Wei NARI Grp Corp State Grid Elect Power Res Inst Nanjing 211106 Peoples R China

ISBN: (纸本)9789811397790;9789811397783

Affected by artificial experiences and coverage of typical operating situations, the strategy of stability control system faces huge mismatch risk. It is difficult to effectively deal with complex and serious faults, such as multiple faults or successive faults. The method of adaptability assessment and online decision-making for strategy of stability Control Systems is proposed to involve multiple types of security and stability issues. Operating status of stability control devices is obtained to correct RTU data and improve the accuracy of operating conditions. Structural modeling is realized for strategy of stability control system to identify the on-duty strategy. Then, static security, transient security and dynamic stability analysis will be performed according to the on-duty strategy. A coordinated stability control strategy is constructed for the design of UHVDC and new energy characteristics to deal with the potential security and stability problems of power grid under large-scale DC transmission of new energy. When the control amount of strategy is insufficient or mismatched, the online decision-making of the preventive control considering the fluctuation characteristics of new energy power is realized by AC/DC coordinated control means. The proposed method is proved to be fast and effective through the analysis of a practical power grid example.

关键词： Security and stability control equipment multi-source data integration Generalized modeling Online diagnosis Preventive control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：