Identification of the primary pollution sources and dominant influencing factors of soil heavy metals using a random forest model optimized by genetic algorithm coupled with geodetector

Ecotoxicology and Environmental Safety, Journal Year: 2025, Volume and Issue: 290, P. 117731 - 117731

Published: Jan. 1, 2025

Language: Английский

---

Novel Groundwater Quality Index (GWQI) model: A Reliable Approach for the Assessment of Groundwater

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104265 - 104265

Published: Feb. 1, 2025

Language: Английский

---

Machine learning-based Monte Carlo hyperparameter optimization for THMs prediction in urban water distribution networks

Journal of Water Process Engineering, Journal Year: 2025, Volume and Issue: 73, P. 107683 - 107683

Published: April 14, 2025

Language: Английский

---

Interpretable LAI Fine Inversion of Maize by Fusing Satellite, UAV Multispectral, and Thermal Infrared Images

Agriculture, Journal Year: 2025, Volume and Issue: 15(3), P. 243 - 243

Published: Jan. 23, 2025

Leaf area index (LAI) serves as a crucial indicator for characterizing the growth and development process of maize. However, LAI inversion maize based on unmanned aerial vehicles (UAVs) is highly susceptible to various factors such weather conditions, light intensity, sensor performance. In contrast satellites, spectral stability UAV-based data relatively inferior, phenomenon “spectral fragmentation” prone occur during large-scale monitoring. This study was designed solve problem that UAVs difficult achieve both high spatial resolution consistency. A two-stage remote sensing fusion method integrating coarse fine proposed. The SHapley Additive exPlanations (SHAP) model introduced investigate contributions 20 features in 7 categories maize, canopy temperature extracted from thermal infrared images one them. Additionally, most suitable feature sampling window determined through multi-scale experiments. grid search used optimize hyperparameters models Gradient Boosting, XGBoost, Random Forest, their accuracy compared. results showed that, by utilizing 3 × 9 with highest contributions, whole stage Forest could reach R2 = 0.90 RMSE 0.38 m2/m2. Compared single UAV source mode, enhanced nearly 25%. jointing, tasseling, filling stages were 0.87, 0.86, 0.62, respectively. Moreover, this verified significant role inversion, providing new

Language: Английский

---

EUR Prediction for Shale Gas Wells Based on the ROA-CatBoost-AM Model

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 2156 - 2156

Published: Feb. 18, 2025

Shale gas is a critical energy resource, and estimating its ultimate recoverable reserves (EUR) key indicator for evaluating the development potential effectiveness of wells. To address challenges in accurately predicting shale EUR, this study analyzed production data from 200 wells CN block. Sixteen factors influencing EUR were considered, geological, engineering, identified using Spearman correlation analysis mutual information methods to exclude highly linearly correlated variables. An attention mechanism was introduced weight input features prior model training, enhancing interpretability feature contributions. The hyperparameters optimized Rabbit Optimization Algorithm (ROA), 10-fold cross-validation employed improve stability reliability evaluation, mitigating overfitting bias. performance four machine learning models compared, optimal selected. results indicated that ROA-CatBoost-AM exhibited superior both fitting accuracy prediction effectiveness. This subsequently applied identifying primary controlling productivity, providing effective guidance practices. dominant forecasts determined by offer valuable references optimizing block strategies.

Language: Английский

---

Inferring Water Quality in the Songhua River Basin Using Random Forest Regression Based on Satellite Imagery and Geoinformation

Hydrology, Journal Year: 2025, Volume and Issue: 12(3), P. 61 - 61

Published: March 17, 2025

Maintaining high water quality is essential not only for human survival but also social and ecological safety. In recent years, due to the influence of activities natural factors, has significantly deteriorated, effective monitoring urgently needed. Traditional requires substantial financial investment, whereas remote sensing random forest model reduces operational costs achieves a paradigm shift from discrete sampling points spatially continuous surveillance. The was adopted establish inversion three parameters (conductivity, total nitrogen (TN), phosphorus (TP)) during growing period (May September) 2020 2022 in Songhua River Basin (SRB), using Landsat 8 imagery China’s national section data. Model verification shows that R2 conductivity 0.67, followed by TN at 0.52 TP 0.47. results revealed downstream SRB (212.72 μS/cm) higher than upstream (161.62 μS/cm), with concentrations exhibiting similar increasing pattern. This study significant improving conservation health SRB.

Language: Английский

---

Geospatial Exploration of Drinking Water Quality in the Coastal Region of Bangladesh: A Case Study from Paikgacha, Khulna

Environmental Forensics, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 20

Published: April 21, 2025

Language: Английский

---

The pivotal and transformative role of artificial intelligence in advanced multidimensional modeling and optimization of complex cefixime separation processes using 3-hydroxyphenol-formaldehyde nanostructures: A multi-layered analytical approach

Microchemical Journal, Journal Year: 2025, Volume and Issue: unknown, P. 113817 - 113817

Published: April 1, 2025

Language: Английский

---

A review of machine learning and internet-of-things on the water quality assessment: methods, applications and future trends

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 105182 - 105182

Published: May 1, 2025

Language: Английский

---