A5100449436- Groundwater flow and contamination studies
- CO2 Sequestration and Geologic Interactions
- Radioactive element chemistry and processing
- Soil and Unsaturated Flow
- Groundwater and Isotope Geochemistry
- Neural Networks and Applications
- Enhanced Oil Recovery Techniques
- Hydrology and Watershed Management Studies
- Hydraulic Fracturing and Reservoir Analysis
- Water resources management and optimization
- Rock Mechanics and Modeling
- Geophysical and Geoelectrical Methods
- Hydrological Forecasting Using AI
- Methane Hydrates and Related Phenomena
- Machine Learning and ELM
- Brain Tumor Detection and Classification
- Heavy metals in environment
- Seismic Imaging and Inversion Techniques
- Flood Risk Assessment and Management
- Adsorption and biosorption for pollutant removal
- Fault Detection and Control Systems
- Advanced Data Processing Techniques
- Irrigation Practices and Water Management
- Advanced Mathematical Modeling in Engineering
- Hydrocarbon exploration and reservoir analysis
Jilin University
2018-2025
Zhejiang Academy of Social Sciences
2025
Shanxi Normal University
2024
Shandong Academy of Sciences
2023
Qilu University of Technology
2023
Jilin Medical University
2020-2021
Lanzhou University of Technology
2021
Jiangsu University
2019
University of Jinan
2018
Jinan University
2018
Chemical reaction simulations are considerably used to quantitatively assess the long-term geologic carbon sequestration (GCS), such as CO2 capacity estimations, leakage pathway analyses, enhanced oil recovery (EOR) efficiency studies, and risk assessments of sealing formations (caprocks), wellbores, overlying underground water resources. All these require a deep understanding -associated chemical reactions. To ensure long-term, safe in intended formations, modeling is only way plausibly...
CO2 dissolution in water at different temperature and pressure conditions is of essential interest for various environmental, geochemical, thermodynamic related problems. The topic special studies geological sequestration brine-bearing aquifers. In this Article, four powerful machine learning (ML) techniques—Radial Basis Function Neural Network (RBFNN), Multilayer Perceptron (MLP), Least-Squares Support Vector Machine (LSSVM), Gene Expression Programming (GEP)—are implemented to develop...
Abstract The stochastic models and deep‐learning are the two most commonly used methods for subsurface sedimentary structures identification. results from typically involve uncertainty due to their nature. For models, sufficient structure samples necessary training, but they practically difficult obtain. This study develops an inversion framework combine strength of these overcome limitations. model is first adopted generate required by integrating available observations. Then trained...
Plutonium (Pu) in the subsurface environment can transport different oxidation states as an aqueous solute or colloidal particles. The behavior of Pu is affected by relative abundances these species and be difficult to predict when they simultaneously exist. This study investigates concurrent intrinsic colloids, Pu(IV)(aq) Pu(V-VI)(aq) through a combination controlled experiments semi-analytical dual-porosity modeling. were conducted fractured granite at high low flow rates elucidate...
Abstract Parameter estimation for reactive transport models (RTMs) is important in improving their predictive capacity accurately simulating subsurface hydrogeochemical processes. This paper introduces a deep learning approach called the tandem neural network architecture (TNNA), which consists of forward and reverse to estimate input parameters RTMs. The TNNA has limitation that approximation error from often results biased inversion results. To solve this problem, we proposed enhance using...
Abstract. Prediction of groundwater level is immense importance and challenges coastal aquifer management with rapidly increasing climatic change. With the development artificial intelligence, data-driven models have been widely adopted in hydrological process management. However, due to limitation network framework construction, they are mostly produce only 1 time step advance. Here, temporal convolutional (TCN) based on long short-term memory (LSTM) were developed predict levels different...
Deep geological disposal is a widely accepted approach for safe management and long-term of high-level radioactive waste (HLW). However, high uncertainty associated with subsurface properties fractured rocks significant obstacle to practical safety assessment HLW disposal. In this study, we develop an integrated statistical framework quantification radionuclide migration related the HLW. We employ response surface methodology Monte Carlo simulations in granite perform global sensitivity...
Abstract Groundwater monitoring networks are direct sources of information for revealing subsurface system dynamic processes. However, designing such is difficult due to uncertainties in the spatial heterogeneity aquifer parameters as permeability ( k ). This study combines deep learning and theory with an optimization framework address network design problems heterogeneous systems. The first employs a generative adversarial parameterize distribution using low‐dimensional latent...
This study explores the spatial distribution of food services and their colocation with surrounding complementary services. It investigates these issues within Guangdong–Hong Kong–Macao Greater Bay Area (GBA), utilizing point-of-interest (POI) data, kernel density, HDBSCAN clustering algorithm, quotients. The findings are as follows: (1) this research reveals a significant agglomeration near Pearl River, notable clusters across administrative boundaries; (2) Guangzhou, Shenzhen, Foshan,...