Fingerprinting complex mixed oil spills at refineries: Source identification, quantitative source apportionment, and biodegradation assessment.

Chemical fingerprinting is well-established for source identification of marine oil spill, however cases for contaminated industrial sites are much more complicated. This study applied an integrated framework (combining source identification, source apportionment, and biodegradation assessment) for a forensic investigation of a 50,000 m Light Non-Aqueous Phase Liquid (LNAPL) plume. Comprehensive analysis of 28 samples (16 floating oils, 10 petroleum products, 2 crude oils) revealed four distinct oil mixtures within the LNAPL plume, each comprising varying proportions of reformulated gasoline, catalytic cracking diesel, straight-run diesel, and crude oil.

A depression detection approach leveraging transfer learning with single-channel EEG.

Major depressive disorder (MDD) is a widespread mental disorder that affects health. Many methods combining electroencephalography (EEG) with machine learning or deep learning have been proposed to objectively distinguish between MDD and healthy individuals. However, most current methods detect depression based on multichannel EEG signals, which constrains its application in daily life.

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study.

Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and overfitting, it also uniquely suffers from over-smoothing, information squashing, and so on, which limits their potential power for encoding the high-order neighbor structure in large-scale graphs. Although numerous efforts are proposed to address these limitations, such as various forms of skip connections, graph normalization, and random dropping, it is difficult to disentangle the advantages brought by a deep GNN architecture from those "tricks" necessary to train such an architecture.

Microwave-assisted synthesis of defective CaAgTiCoO with high photoelectrocatalytic activity for organic pollutant removal from water.

CaTiO is considered to be one of the most promising catalysts for the degradation of organic pollutants, but its application is limited by the wide band gap and low catalytic activity. Element doping is an effective strategy to solve these problems. Herein, a novel CaTiO co-doped with Ag and Co (CaAgTiCoO) was synthesized by combining co-precipitation and the microwave hydrothermal method for the first time.