Environmental Health

Interpretable QSAR models for acute oral toxicity via tuned XGBoost and hybrid data sampling techniques.

Accurate, interpretable prediction of acute oral toxicity (LD₅₀) is challenged by severe dataset imbalance and complex structure-activity relationships. This study develops a transparent QSAR framework by integrating 2D topological and 3D conformational descriptors with hybrid SMOTE-RUS resampling to classify rat oral LD₅₀ into Very Toxic vs. Not Very Toxic. Using 8,396 compounds from NICEATM-EPA ...

Copper stress responses in Scenedesmus obliquus-Bacillus subtilis Consortia: Machine Learning-Based prediction of copper removal.

Copper pollution in wastewater is an environmental issue that requires efficient and sustainable waste treatment methods. To improve the efficiency of traditional microalgal treatment of heavy metals and enable predictive assessment of treatment outcomes, this study examined the physiological behavior of Scenedesmus obliquus to copper stress and the mitigating role of a microalgae-bacteria consort...

Design and laboratory verification of an AI-driven plant protection robot with a custom communication protocol.

Traditional agricultural plant protection primarily relies on manual labor and indiscriminate chemical spraying, resulting in inefficiency, increased ...

Safe-by-redesign guidance for toxic industrial chemicals using explainable artificial intelligence: Introducing the DETOX-QSAR model.

Exploring the potential targets and mechanisms of malachite green induced lung adenocarcinoma through network toxicology and molecular docking.

Malachite green (MG), a synthetic dye, has turned into a major risk to human health, because of its toxicity of teratogenic, genotoxic, carcinogenic, ...

A multisource dataset for anomaly detection and fault prediction in urban water distribution networks.

This multi-source dataset was compiled to support research on anomaly-based leak detection in urban water distribution networks (WDNs). It contains on...

Inverting a new hydrogen map on the moon derived from Chang'E-2 gamma-ray spectrum data.

This study addresses the challenge of extracting subtle 2H characteristic γ ray ([email protected] MeV) count from the Chang'e-2 Gamma-Ray Spectrometer (CE2-GR...

Deep learning-guided discovery and engineering of binding peptides for accelerated enzymatic degradation of polyethylene terephthalate.

Enzymatic polyethylene terephthalate (PET) degradation holds promise for environmental restoration. However, limited substrate catalytic capacity hind...

ExSERA: The explainable machine learning model for skin sensitization risk assessment.

The development of new approach methodologies using machine learning offers promising alternatives to animal testing for toxicity assessment. However,...

Seasonal variations in sources and dynamics of surface water-groundwater nitrate in a plain river network area: Based on hydrochemical, dual isotope approach and feature importance interpretation.

Understanding the seasonal dynamics of nitrate pollution in interconnected surface water (SW) and groundwater (GW) systems is critical for effective n...

Machine learning-driven source apportionment and health risk assessment of multi-source groundwater pollution in highly permeable aquifers: A case study in Southwest China.

Industrial expansion releases multiple pollutants into groundwater, whose migration in highly permeable aquifers is governed by rapid flow through coa...

Sustainable Materials Design With Multi-Modal Artificial Intelligence.

The growing scarcity of critical minerals, coupled with high embodied carbon emissions and persistent pollution from material smelting, highlights the...

Integrating ensemble and contrastive learning with explainable AI for modeling eutrophication-driven algal risks.

This study develops a Composite Eutrophication Index (CEI) based on four water-quality parameters to predict river eutrophication risk, using ten quan...

Dissolved organic matter regulating the speciation and transport of potentially toxic metals in groundwater: Environmental implications and perspectives.

Groundwater, as an important freshwater resource, faces an increasingly severe problem of contamination by potential toxic metals (PTEs). Dissolved or...

Dietary nutritional strategies for circadian rhythm regulation: advances, challenges and future directions.

The escalation of urban light pollution and the trend toward a globalized lifestyle have led to a notable increase in circadian rhythm disruption (CRD...

Risk-Guided Atrial Fibrillation Screening With Artificial Intelligence-Enabled Electrocardiogram Models: A VITAL-AF Trial Analysis.

BACKGROUND: Screening for atrial fibrillation (AF) may lead to earlier detection and initiation of preventive measures. Current AF screening approache...

Interpretable machine learning reveals regional heterogeneity and key environmental drivers of BOD5 in complex river networks.

Accurate prediction of Biochemical oxygen demand (BOD5) can substantially reduce the labor-intensive monitoring required to assess organic pollution i...

A-Site Cation Functional Engineering Enables Lead-free Perovskite Photosynapse for Neuromorphic Visual Computing.

Optoelectronic synapses that directly couple light sensing with memory and computing functions offer a promising route toward energy-efficient neuromo...

Long-Term Exposure to Fine Particulate Matter and Kidney Function among Patients with Polycystic Kidney Disease.

BACKGROUND: Polycystic kidney disease (PKD) is the fourth leading cause of end-stage kidney disease. Although the condition is primarily genetic, envi...

Explanatory Machine Learning Model to Associate All-Cause Mortality with PM2.5 by Sources and Components: A Nationwide Difference-in-Differences Study.

Background: Long-term PM2.5 exposure is a major health risk, yet the heterogeneity of its chemical components and sources is often overlooked in risk ...