Spatial Mapping and Prediction of Groundwater Quality Using Ensemble Learning Models and SHapley Additive exPlanations with Spatial Uncertainty Analysis

Water, Год журнала: 2024, Номер 16(17), С. 2375 - 2375

Опубликована: Авг. 24, 2024

The spatial mapping and prediction of groundwater quality (GWQ) is important for sustainable management, but several research gaps remain unexplored, including the inaccuracy interpolation, limited consideration geological environment human activity effects, limitation to specific pollutants, unsystematic indicator selection. This study utilized entropy-weighted water index (EWQI), LightGBM model, pressure-state-response (PSR) framework SHapley Additive exPlanations (SHAP) analysis address above gaps. normalized importance (NI) shows that NO3− (0.208), Mg2+ (0.143), SO42− (0.110), Cr6+ (0.109) Na+ (0.095) should be prioritized as parameters remediation, skewness EWQI distribution indicates although most sampled locations have acceptable GWQ, a few areas suffer from severely poor GWQ. PSR identifies 13 indicators environments activities SMP Despite high AUROCs (0.9074, 0.8981, 0.8885, 0.9043) across four random training testing sets, it was surprising significant uncertainty observed, with Pearson correlation coefficients (PCCs) 0.5365 0.8066. We addressed this issue by using spatial-grid average probabilities maps. Additionally, population nighttime light are key indicators, while net recharge, land use cover (LULC), degree urbanization lowest importance. SHAP highlights both positive negative impacts on identifying point-source pollution main cause GWQ in area. Due field, future studies focus six aspects: multi-method assessment, quantitative relationships between comparisons various models, application selection, development methods reduce uncertainty, explainable machine learning techniques management.

Язык: Английский

---

Revealing the effects of environmental and spatio-temporal variables on changes in Japanese sardine (Sardinops melanostictus) high abundance fishing grounds based on interpretable machine learning approach

Frontiers in Marine Science, Год журнала: 2025, Номер 11

Опубликована: Янв. 13, 2025

The construction of accurate and interpretable predictive model for high abundance fishing ground is conducive to better sustainable fisheries production carbon reduction. This article used refined statistical maps visualize the spatial temporal patterns catch changes based on 2014-2021 fishery statistics Japanese sardine Sardinops melanostictus in Northwest Pacific Ocean. Three models (XGBoost, LightGBM, CatBoost) two variable importance visualization methods (model built-in (split) SHAP methods) were comparative analysis determine optimal modeling strategies. Results: 1) From 2014 2021, annual showed an overall increasing trend peaked at 220,009.063 tons 2021; total monthly increased then decreased, with a peak 76, 033.4944 (July), was mainly concentrated regions 39.5°-43°N 146.75°-155.75°E; 2) Catboost predicted than LightGBM XGBoost models, highest values accuracy F1-score, 73.8% 75.31%, respectively; 3) ranking model’s method differed significantly from that method, variables increased. Compared informs magnitude direction influence each global local levels. results research help us select construct prediction grounds Ocean, which will provide scientific basis achieve environmental economically development.

Язык: Английский

---

Meta-machine learning framework for robust short-term solar power prediction across different climatic zones

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 147, С. 110295 - 110295

Опубликована: Фев. 22, 2025

Язык: Английский

---

Advancements in natural fibre based polymeric composites: A comprehensive review on mechanical-thermal performance and sustainability aspects

Sustainable materials and technologies, Год журнала: 2025, Номер unknown, С. e01345 - e01345

Опубликована: Март 1, 2025

Язык: Английский

---

New insights into the performance of biomass carbon-based supercapacitors based on interpretable machine learning approach

Journal of Energy Storage, Год журнала: 2025, Номер 118, С. 116300 - 116300

Опубликована: Март 20, 2025

Язык: Английский

---

Advanced Integrated Fast-Charging Protocol for Lithium-Ion Batteries by Considering Degradation

ACS Sustainable Chemistry & Engineering, Год журнала: 2024, Номер 12(17), С. 6786 - 6796

Опубликована: Апрель 13, 2024

In the modern electric vehicle industry, fast charging of lithium-ion batteries is essential. Charging at a high C-rate minimizes time; however, this results in degradation due to rapid rise temperature and voltage. Therefore, we propose an advanced protocol that reflects conditions by integrating multistage constant current-constant voltage pulse protocols. The proposed was efficiently evaluated using high-fidelity battery model based on porous electrode theory. However, model-based optimal design has challenges regarding expansion space increasing number parameters lack information about conditions. A Bayesian optimization applied perform sample-efficient without first-principles incorporate variability cells into stochastic prediction model. guidelines identified naïve are used as prior knowledge improve efficiency considering degradation. As result, protocols suppress allow for minimized times compared reference (i.e., voltage) given Pareto front.

Язык: Английский

---

Computer-aided mobility solutions: Machine learning innovations to secure smart urban transportation

Sustainable Cities and Society, Год журнала: 2024, Номер 107, С. 105422 - 105422

Опубликована: Апрель 16, 2024

Язык: Английский

---

Novel natural gradient boosting-based probabilistic prediction of physical properties for polypropylene-based composite data

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 135, С. 108864 - 108864

Опубликована: Июнь 18, 2024

Язык: Английский

---

Accelerated intelligent prediction and analysis of mechanical properties of magnesium alloys based on scaled Super learner machine-learning algorithms

Mechanics of Materials, Год журнала: 2024, Номер unknown, С. 105168 - 105168

Опубликована: Сен. 1, 2024

Язык: Английский

---

Enhanced Ensemble Learning-Based Uncertainty and Sensitivity Analysis of Ventilation Rate in a Novel Radiative Cooling Building

Heliyon, Год журнала: 2024, Номер 11(1), С. e41572 - e41572

Опубликована: Дек. 31, 2024

Язык: Английский

---