In this study, novel molecular structure encoding descriptors composed of feature encoding and one‐hot encoding was developed and then convolutional autoencoder was used to denoise based on the structure of ionic liquids (ILs). It could be used to predict the CO2 solubility in ILs at different temperatures and pressures, when combined with three different machine learning algorithms (multilayer perceptron [MLP], random forest [RF], and support vector machine [SVM]). Statistics of the prediction results show that the newly proposed molecular structure‐based coding has better regression prediction performance than the conventional molecular cheminformatics descriptors. SE‐MLP model with R2 of 0.9873 and mean square error of 0.0007 has the best performance in predicting the CO2 solubility in ILs. In addition, the relationship between features and dissolved CO2 capacity was analyzed through model interpretation to retrieve physical insights for the underlying system. This work provided a new predictive tool for enriching and refining data on CO2 solubility in ILs and for solving phase equilibrium problems.
Precise point positioning (PPP) service is of great significance for BDS. The design and implementation of the service are presented. The PPP-B2b signal of the service is constructed, which is efficient multiplexed with other signal components, and achieves compatibility between two service phases. A customized message format that can augment all visible satellites of four core constellations in mainland China is proposed. The high-gain, 64-ary, low-density parity check (LDPC) coding is used, which facilitates the integrated design of the receivers. A signal quality test has revealed that the S-curve bias (SCB) of PPP-B2b does not exceed 0.0165 ns and the coherence between the code and the carrier of the signal is only 0.137 •. A performance evaluation has indicated that at its current stage, the positioning accuracy in the horizontal and vertical directions is better than 0.15 m and 0.3 m, respectively, and the convergence time does not exceed 800 s.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.