Xiaogang Ma

Fine-tune the stable diffusion model using mindat data to generate mineral images from textual descriptions of attribute combinations

Quanli Fu, Xiang Que, Xiaogang Ma, Mingjie Lin et autres

Abstract Mindat (mindat.org) is a comprehensive mineral database that serves as a valuable resource for mineral data, encompassing a vast collection of textural descriptions and images from around the world. While the OpenMindat project accelerates knowledge discoveries in mineralogy, numerous relationships between …

Self-Calibrating Dense Displacement Fields for Reliable Co-Registration of Large Optical Satellite Imagery

Shoukun Sun, Zhe Wang, Sanaz Salati, Jiyin Zhang et autres

Co-registration underlies nearly every multi-temporal and multi-sensor use of optical satellite imagery, and operational products still carry documented offsets well above the fraction-of-a-pixel scale at which change detection, time series, and data fusion degrade. Real image pairs differ along several axes at …

A hybrid validation framework for LLM-enhanced open data service: the mindat API as a use case

Jiyin Zhang, Weilin Chen, Chenhao Li, Xiaogang Ma

Abstract Large Language Models (LLMs) enable natural language interfaces for data retrieval, but their tendency to hallucinate hinders their adoption in scientific applications that require high accuracy. Unlike deterministic traditional APIs (Application Programming Interface), LLMs introduce inherent uncertainty, posing critical challenges for …

us (code pays fourni par la source)

Developing New Amphibole Thermobarometers to Constrain High P‐T Hydration Processes of Basic‐Ultrabasic Rocks

Wenbo Xu, Weilin Chen, Shubham Choudhary, Shijie Li et autres

Abstract Amphibole compositions record high‐pressure‐temperature ( P‐T ) hydration processes during magmatism and metamorphism in the deep Earth. However, amphibole thermobarometers calibrated for basic–ultrabasic systems are scarce. To address this issue, we compiled Ca‐amphibole data from published equilibrium experiments and used machine‐learning …

cn, us, in (code pays fourni par la source)

GGBondSAGE: A Framework for Three-Dimensional Characterization of Subsurface Stratigraphic Structures Using GraphSAGE

Qiyu Chen, Jiale Guo, Hongfeng Fang, Dajie Chen et autres

cn, Rwanda, us (code pays fourni par la source)

Knowledge-Guided Neuro–Symbolic Modeling for Mineral Prospectivity Mapping: A Case Study of Porphyry Cu–Mo Systems in Boise County, Idaho

Weilin Chen, Jiyin Zhang, Chenhao Li, Xiaogang Ma

Abstract Mineral prospectivity mapping increasingly relies on machine learning to integrate geochemical and geological information, yet purely data-driven models often perform unreliably under sparse sampling, strong class imbalance, and complex geological controls, while traditional knowledge-driven approaches remain difficult to formalize and scale. …

us (code pays fourni par la source)

Three-Dimensional Stratigraphic Modeling via Adaptive Search Strategy-Based Multiple-Point Geostatistical Simulation

Hongfeng Fang, Gang Liu, Zhesi Cui, Xiaogang Ma et autres

cn, Rwanda, us (code pays fourni par la source)

Cross-Scale U-Net: A Deep Transfer Learning Framework for Automated High-Resolution Urban Land Cover Mapping

Zhe Wang, Chao Fan, Shoukun Sun, Felix Haifeng Liao et autres

Accurate and scalable urban land cover mapping is critical for sustainable urban planning and environmental management. While deep learning models offer powerful tools for this task, their performance is often constrained by the need for vast, manually labeled datasets, which are costly …

us, cn (code pays fourni par la source)

An LLM-based multi-agent system for geoscience legacy document processing, knowledge extraction and quality control

Jiyin Zhang, Weilin Chen, Chenhao Li, Xiaogang Ma

Knowledge extraction from unstructured Earth Science documents into standardized knowledge bases is a complex task that used to be heavily reliant on manual curation and domain expertise. As an effort to automate this process, we proposed a modularized multi-agent system framework, Adaptive …

us (code pays fourni par la source)

Influence of speed and direction on coincident anticipation of tennis ball landing: an ERP study within an ecological validity framework

Xiaogang Ma, Bing Shi

To address the ecological validity limitations inherent in traditional Coincident-Anticipation Timing (CAT) research relying on simplified paradigms, this study investigated the dynamic influence of speed and direction on timing judgments using a first-person perspective tennis ball landing video paradigm combined with electroencephalography …

cn (code pays fourni par la source)

Muscle activation color information facilitates visual perception in action observation and motor imagery

Xiaogang Ma, Bing Zhi Shi

This eye-tracking study investigates how simulated muscle activation color visualization shapes visual perception during Action Observation and Motor Imagery (AO + MI) for motor skill learning. In a mixed-design experiment ( N = 40), we manipulated visual cues (with/without muscle colors) and …

cn (code pays fourni par la source)

An Intelligent Ensemble Learning Framework for Visibility and CAVOK Prediction to Support Logistics Operations

Omar Alghushairy, Raed Alsini, Ahmed Alamri, Saud Yonbawi et autres

The supply chain operation is fully dependent on weather conditions due to the damage that produce may face during bad weather or accidents that may occur because of cloud cover, especially in Saudi Arabia, which experiences frequent cloud cover throughout the year. …