Estimating and mapping tailings properties of the largest iron cluster in China for resource potential and reuse: A new perspective from interpretable CNN model and proposed spectral index based on hyperspectral satellite imagery

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2025, Номер 139, С. 104512 - 104512

Опубликована: Апрель 7, 2025

Язык: Английский

---

Evaluation of machine learning models for accurate prediction of heavy metals in coal mining region soils in Bangladesh

Environmental Geochemistry and Health, Год журнала: 2025, Номер 47(5)

Опубликована: Апрель 23, 2025

Язык: Английский

---

Unraveling soil salinity on potentially toxic element accumulation in coastal Phragmites australis: A novel integration of multivariate and interpretable machine-learning models

Marine Pollution Bulletin, Год журнала: 2025, Номер 217, С. 118072 - 118072

Опубликована: Май 5, 2025

Язык: Английский

---

Heterocyclic aromatic compounds in Lake Ontario sediments: Spatiotemporal distribution and new approaches to fingerprinting

The Science of The Total Environment, Год журнала: 2025, Номер 986, С. 179802 - 179802

Опубликована: Май 30, 2025

Язык: Английский

---

Spatial patterns and mechanism of the impact of soil salinity on potentially toxic elements in coastal areas

The Science of The Total Environment, Год журнала: 2024, Номер 951, С. 175802 - 175802

Опубликована: Авг. 26, 2024

Язык: Английский

---

Comprehensive Perspective on Contamination Identification, Source Apportionment, and Ecological Risk Assessment of Heavy Metals in Paddy Soils of a Tropical Island

Agronomy, Год журнала: 2024, Номер 14(8), С. 1777 - 1777

Опубликована: Авг. 13, 2024

The closed-loop material and energy cycles of islands increase the susceptibility their internal ecosystem components to heavy metal accumulation transfer. However, limited research on island scale hinders our understanding environmental geochemistry in this unique environment. This study focused assessing a tropical island’s ecological risk by investigating contamination potential sources. results revealed elevated cadmium nickel concentrations 0.44–1.31% soil samples, particularly coastal plains developed areas. Using absolute principal component score-multiple linear regression (APCS-MLR) model assisted GIS mapping, we identified three sources: geological factors, agricultural activities, traffic emissions. Network analysis indicated direct exposure risks vegetation microorganisms contaminated (0.4611 0.7687, respectively), with posing highest risk, followed Zn, Cd, Pb, Cu, Cr transferring across trophic levels. These findings provide crucial insights for mitigating associated metals controlling priority pollutants sources environments.

Язык: Английский

---

An Interpretable Model for Salinity Inversion Assessment of the South Bank of the Yellow River Based on Optuna Hyperparameter Optimization and XGBoost

Agronomy, Год журнала: 2024, Номер 15(1), С. 18 - 18

Опубликована: Дек. 26, 2024

Soil salinization is a serious land degradation phenomenon, posing severe threat to regional agricultural resource utilization and sustainable development. It has been mainstream trend use machine-learning methods achieve monitoring of large-scale salinized soil quickly. However, machine learning model training requires many samples hyper-parameter optimization lacks solvability. To compare the performance different models, this study conducted sampling experiment on saline soils along south bank Yellow River in Dalate Banner. The lasted two years (2022 2023) during spring bare period, collecting 304 samples. salinity was estimated with multi-source remote sensing satellite data by combining extreme gradient boosting (XGBoost), Optuna optimization, Shapley addition (SHAP) interpretable model. Correlation analysis continuous variable projection were employed identify key inversion factors. regression effects partial least squares (PLSR), geographically weighted (GWR), long short-term memory networks (LSTM), (XGBoost) compared. optimal selected estimate area from 2019 2023. results showed that XGBoost fitted optimally, test set had high R2 (0.76) ratio deviation (2.05), estimation consistent measured values. SHAP revealed index topographic factors primary Notably, same factor influenced varying estimates at locations. 2023 65% 44%, respectively, overall decreased. From viewpoint spatial distribution, degree gradually increasing north, it most side near River. This great significance for quantitative irrigated River, prevention control salinization, development agriculture.

Язык: Английский

---

Digital Mapping and Scenario Prediction of Soil Salinity in Coastal Lands Based on Multi-Source Data Combined with Machine Learning Algorithms

Опубликована: Янв. 1, 2024

Soil salinization is a major soil degradation process threatening ecosystems and posing great challenge to sustainable agriculture food security worldwide. This study aimed evaluate the potential of state-of-the-art machine learning algorithms in salinity (EC1: 5) mapping. Further, we predicted distribution patterns under different future scenarios Yellow River Delta. A geodatabase comprising 201 samples 19 conditioning factors was used compare predictive performance ordinary kriging, inverse distance weighting regression, random forest, CatBoost models. The model exhibited highest with both training (MAE=0.383, RMSE = 0.601) testing datasets (MAE=0.403, 0.670). Among explanatory factors, Na2O most important for predicting EC1:5, followed by normalized difference vegetation index organic carbon. EC1:5 predictions suggested that Delta region faces severe salinization, particularly coastal zones. three increases carbon content (1, 2, 3 g/kg), 2 g/kg scenario resulted best improvement effect on saline-alkali soils > ds/m. Our results provide valuable insights policymakers improve land quality plan regional agricultural development.

Язык: Английский

---

Understanding the risks of peri-urbanization to food systems to help establish sustainable agriculture near cities

Environmental Impact Assessment Review, Год журнала: 2024, Номер 112, С. 107777 - 107777

Опубликована: Дек. 13, 2024

Язык: Английский

---