The application of a deep learning algorithm (DL) can more accurately predict the initial flowering period of Platycladus orientalis (L.) Franco. In this research, we applied DL to establish a nationwide long-term prediction model of the initial flowering period of P. orientalis and analyzed the contribution rate of meteorological factors via Shapely Additive Explanation (SHAP). Based on the daily meteorological data of major meteorological stations in China from 1963–2015 and the observation of initial flowering data from 23 phenological stations, we established prediction models by using recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU). The mean absolute error (MAE), mean absolute percentage error (MAPE), and coefficient of determination (R2) were used as training effect indicators to evaluate the prediction accuracy. The simulation results show that the three models are applicable to the prediction of the initial flowering of P. orientalis nationwide in China, with the average accuracy of the GRU being the highest, followed by LSTM and the RNN, which is significantly higher than the prediction accuracy of the regression model based on accumulated air temperature. In the interpretability analysis, the factor contribution rates of the three models are similar, the 46 temperature type factors have the highest contribution rate with 58.6% of temperature factors’ contribution rate being higher than 0 and average contribution rate being 5.48 × 10−4, and the stability of the contribution rate of the factors related to the daily minimum temperature factor has obvious fluctuations with an average standard deviation of 8.57 × 10−3, which might be related to the plants being sensitive to low temperature stress. The GRU model can accurately predict the change rule of the initial flowering, with an average accuracy greater than 98%, and the simulation effect is the best, indicating that the potential application of the GRU model is the prediction of initial flowering.
With the development of science and technology, science and technology policies are increasing year by year. Science and technology policies are literature existing in the form of texts, which are characterized by rigorous structure, clear hierarchy, and standard language. Mining template information from policies can optimize data templates and improve the efficiency of recommending data to users. This paper proposes a joint entity relation extraction model based on capsule networks and part-of-speech weighting. In order to learn more feature information from word vector, capsule network based on bidirectional gated cyclic unit is used to replace the traditional convolutional neural network. In view of the phenomenon of imperfect semantic expression of word vector, part-of-speech features are added to enrich text information. Meanwhile, in order to solve the weight distribution problem of word features and part-of-speech features, an artificial fish swarm algorithm is proposed to optimize the two feature weights by iterative optimization, and the effectiveness of the proposed model is proved by experiments.
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.