A hybrid physics–data-driven predictive framework for early warning and risk assessment of soil heavy metal pollution using complex networks

How effective are physics-informed neural networks compared to machine learning in predicting groundwater flow in complex heterogeneous aquifers?

A hybrid model for agricultural pollution load forecasting by integrating meteorological data and soil properties: an XGBoost-LSTM approach

Accurate forecasting of agricultural non-point source pollution is pivotal for sustainable land management and environmental risk mitigation. However, the complex interplay between meteorological factors and heterogeneous soil properties introduces significant temporal and spatial variability into pollutant load estima...

Next-Generation Approaches for Predicting Soil Heavy Metal Contamination: Insights from Geospatial and AI-Based Methods

Contamination of soil with heavy metals poses a serious risk to ecosystems, agriculture, and human health. The spatial and temporal constraints limit the use of traditional techniques of predicting contamination, such as soil sampling and geochemical mapping. New developments in geospatial methods and artificial intell...

Physically aligned forest fire risk prediction: A deep learning framework coupling fuel and climate multivariate factors

Existing forest fire risk prediction methods often focus on single-element analysis, which makes it difficult to effectively capture the underlying mechanisms of the “fuel-climate” interaction. This paper proposes a physically aligned prediction framework named FWI-MSNet. Using 18 years of synchronized observation data...

Towards physics-consistent machine learning models: A geomechanics-based artificial neural network for high-cyclic soil response

It is proposed to design a Geomechanics-based Artificial Neural Network (GANN) that bypasses the need for calibration parameters and instead uses common soil descriptors, ensuring that the predicted strain evolution remains consistent with soil mechanics principles.

Physics-Informed Neural Networks for One-Dimensional Groundwater Contaminant Transport: A Synthetic Numerical Study of Prediction and Parameter Inversion

This study developed a physics-informed neural network (PINN) surrogate model for a one-dimensional synthetic groundwater contaminant-transport problem with adsorption, using Crank–Nicolson numerical solutions as the reference data. The effects of observation density and noise on predictive accuracy, training uncertain...