Search

Agricultural nitrous oxide (N2O) emission accounts for a non-trivial fraction of global greenhouse gas (GHG) budget. To date, estimating N2O fluxes from cropland remains a challenging task because the related microbial processes (e.g., nitrification and denitrification) are controlled by complex interactions among climate, soil, plant and human activities. Existing approaches such as process-based (PB) models have well-known limitations due to insufficient representations of the processes or uncertainties of model parameters, and due to leverage recent advances in machine learning (ML) a new method is needed to unlock the "black box"to overcome its limitations such as low interpretability, out-of-sample failure and massive data demand. In this study, we developed a first-of-its-kind knowledge-guided machine learning model for agroecosystems (KGML-ag) by incorporating biogeophysical and chemical domain knowledge from an advanced PB model, ecosys, and tested it by comparing simulating daily N2O fluxes with real observed data from mesocosm experiments. The gated recurrent unit (GRU) was used as the basis to build the model structure. To optimize the model performance, we have investigated a range of ideas, including (1) using initial values of intermediate variables (IMVs) instead of time series as model input to reduce data demand; (2) building hierarchical structures to explicitly estimate IMVs for further N2O prediction; (3) using multi-task learning to balance the simultaneous training on multiple variables; and (4) pre-training with millions of synthetic data generated from ecosys and fine-tuning with mesocosm observations. Six other pure ML models were developed using the same mesocosm data to serve as the benchmark for the KGML-ag model. Results show that KGML-ag did an excellent job in reproducing the mesocosm N2O fluxes (overall r2Combining double low line0.81, and RMSECombining double low line3.6g€¯mgNm-2d-1 from cross validation). Importantly, KGML-ag always outperforms the PB model and ML models in predicting N2O fluxes, especially for complex temporal dynamics and emission peaks. Besides, KGML-ag goes beyond the pure ML models by providing more interpretable predictions as well as pinpointing desired new knowledge and data to further empower the current KGML-ag. We believe the KGML-ag development in this study will stimulate a new body of research on interpretable ML for biogeochemistry and other related geoscience processes.

This study explored the moderating role of social support between learning self-efficacy and learned helplessness in higher vocational students in Henan Province, People's Republic of China. The Learning Self-Efficacy Scale, Social Support Scale, and Learned Helplessness Scale were adopted to conduct questionnaire surveys, which involved 1,067 students in five Chinese higher vocational colleges. A hierarchical regression model was used to analyze the role of social support in moderating the relationship between learning self-efficacy and learned helplessness. This study observed that learning self-efficacy had a negative effect on learned helplessness and that social support played a moderating role between learning self-efficacy and learned helplessness in the students.

BACKGROUND The quality of rapeseed and the degree of heavy metal pollution are directly related to human health. Monitoring the content of toxic elements such as As, Sb, Cd, and Tl in rapeseed is helpful for early monitoring of raw materials for edible oil production. OBJECTIVES To avoid the cumbersome pretreatment of strong acid digestion, quickly determine the accurate content of volatile toxic elements such as As, Sb, Cd, and Tl in rapeseed, and to solve the challenge of pretreatment due to the heavy fat content of grains, oils, and foods. METHODS A suspension-emulsion synergistic sample preparation technique was used to investigate conditions affecting suspension-emulsion, and a homogeneous and stable slurry-emulsion solution (SES) system was prepared. In the electrothermal vaporizer (ETV) with high sampling efficiency, the temperature-programmed parameters and the dosage of improver palladium nitrate were all optimized. SES was directly injected, and inductively coupled plasma-mass spectrometry (ICP-MS) was used to determine As, Sb, Cd and Tl. RESULTS The overall reproducibility (relative standard deviation, RSD) of the suspension-emulsion sampling-ETV-ICP-MS detection method were 10.1%, 8.8%, 8.9% and 6.4% [c=0.5% (m/V), n=5] for As, Sb, Cd and Tl, respectively. Under the optimum conditions, the limits of detection (3σ) were 40.0ng/L, 20.0ng/L, 50.0ng/L and 10.0ng/L for As, Sb, Cd and Tl, respectively. Accordingly, the limits of detection for the original solid samples were 8.0ng/g, 4.0ng/g, 10.0ng/g and 2.0ng/g for As, Sb, Cd and Tl, respectively. The contents of As, Sb, Cd and Tl in tested rapeseed samples were 50.4-90.5ng/g, 28.0-59.9ng/g, 51.3-69.1ng/g and 91.3-216.6ng/g, respectively. CONCLUSIONS The suspension-emulsion synergistic treatment of rapeseed with high oil content is simple, fast, and cost efficient. It utilizes the advantages of ETV sampling and promotes the application of ETV-ICP-MS solid sampling analysis.

Air pollution is one of the greatest environmental risks to health, with 99% of the world's population living where the World Health Organization's air quality guidelines were not met. In addition to the respiratory and cardiovascular systems, the brain is another potential target of air pollution. Population- and experiment-based studies have shown that air pollution may affect mental health through direct or indirect biological pathways. The evidence for mental hazards associated with air pollution has been well documented. However, previous reviews mainly focused on epidemiological associations of air pollution with some specific mental disorders or possible biological mechanisms. A systematic review is absent for early effect biomarkers for characterizing mental health hazards associated with ambient air pollution, which can be used for early warning of related mental disorders and identifying susceptible populations at high risk. This review summarizes possible biomarkers involved in oxidative stress, inflammation, and epigenetic changes linking air pollution and mental disorders, as well as genetic susceptibility biomarkers. These biomarkers may provide a better understanding of air pollution's adverse effects on mental disorders and provide future research direction in this arena. [ABSTRACT FROM AUTHOR]