Screening Environmentally Benign Ionic Liquids for CO Absorption Using Representation Uncertainty-Based Machine Learning.

Screening ionic liquids (ILs) with low viscosity, low toxicity, and high CO absorption using machine learning (ML) models is crucial for mitigating global warming. However, when candidate ILs fall into the extrapolation zone of ML models, predictions may become unreliable, leading to poor decision-making. In this study, we introduce a "representation uncertainty" (RU) approach to quantify prediction uncertainty by employing four IL representations: molecular fingerprint, molecular descriptor, molecular image, and molecular graph.

[Effects of long-term localized fertilization on soil humus combining form in sheltered vegetable field].

The study showed that on a sheltered vegetable field, a long-term application of organic plus chemical fertilizers induced a higher content of loosely combined soil humus than applying chemical fertilizers alone, while there was no significant difference in firmly combined humus content among different fertilization treatments. More tightly combined humus was observed in organic fertilizer treatments than in chemical fertilizer treatments, and the highest content (11.53 g x kg(-1)) was in the treatment of organic fertilizer plus chemical NPK.