Journal of Earth Sciences, Geology and Geospatial Research

(Annual (One issue per year))

Ling Zeng is an Associate Professor at Chengdu University of Technology, China. She received her Ph.D. in Geosciences from China University of Geosciences (Beijing) in 2014. Before joining Chengdu University of Technology, she worked as a postdoctoral researcher and visiting scholar at Nanyang Technological University, Singapore.

Her research focuses on geostatistics, spatial and spatiotemporal modeling, machine learning and deep learning applications in geosciences, environmental pollution assessment, remote sensing, soil heavy metal mapping, AI-assisted geological data analysis, and time series prediction. In particular, she has developed strong expertise in deep-learning-based time series forecasting and data-driven modeling for meteorological and environmental applications, including PM2.5 forecasting, ozone prediction, air quality assessment, and the interpretation of meteorological and gaseous pollutant factors.

Dr. Zeng has published extensively on soil heavy metal interpolation, environmental risk assessment, remote sensing-based geological identification, geological image analysis, and atmospheric pollution modeling. Her recent work integrates statistical diagnostics, machine learning, deep learning, SHAP-based interpretability, temporal fusion transformers, and hybrid spatiotemporal models to improve the prediction and explanation of complex environmental processes.

She has also contributed to applied research through several patents, including methods for pollution evaluation, soil heavy metal prediction, and rock and mineral identification using artificial intelligence. She is the sole author of UNetGE Software V1.0 and has co-authored academic books on geoscience data analysis and geostatistics in the AI era.

Her work bridges geoscience, artificial intelligence, statistics, environmental science, and meteorological data analytics, aiming to support more accurate environmental assessment, pollution forecasting, geological interpretation, and sustainable resource and air quality management.

• Geostatistics
• Spatial and spatiotemporal modeling
• Machine learning and deep learning in geosciences
• Environmental pollution assessment
• Remote sensing applications
• Soil heavy metal mapping
• AI-assisted geological data analysis
• Time series prediction

• Geostatistics
• Spatial data analysis
• Geoscientific big data
• Artificial Intelligence in geosciences
• Environmental risk assessment
• Soil heavy metal contamination assessment
• Remote sensing and GIS
• Deep learning applications in Earth sciences
• Air pollution prediction (PM2.5 and Ozone)
• Kriging and spatial interpolation methods
• Environmental monitoring and modeling

2026    Variogram-distance Graph Attention Kriging: An Innovative Hybrid Approach for Improving Soil Heavy Metals Interpolation
2026    Comparative Study of Four Hybrid Spatiotemporal Models for Daily PM2.5 Prediction in the Chengdu–Chongqing Region
2026    Interpretable Daily MDA8 Ozone Forecasting Framework Based on Temporal Fusion Transformer and SHAP Analysis
2025    XGBoost-assisted Co-Kriging Method for Pollution Assessment (Patent)
2024    Geoscience Data Probability and Statistical Analysis (Book)
2022    Source Apportionment of Heavy Metal Contamination in Urban–Agricultural–Aquacultural Soils near the Bohai Bay Coast Using Land-Use Classification and Google Satellite Tracing
2020    Identifying Emeishan Basalt by Supervised Learning with Landsat-5 and ASTER Data
2019    Remote Sensing and Geostatistical Applications in Geological Data Analysis (listed among earlier works in her research profile)