Study on Soil Infiltration Capability and Its Impact Factors of Different Land-use Types in Purple Soil Region

Soil infiltration capability is the hot spot topic of soil erosion studies and soil physical and chemical properties have great influence on it. A new infiltration method point- source infiltration method was used to precisely evaluate the infiltration capability in different purple soil land- use types. And correlation analysis on soil physical and chemical properties and soil infiltration capability of different land- use types was performed. Results showed that:( i) there is a large difference among soil physical and chemical properties in different land- use types,soil water content,non- capillary porosity,capillary porosity,content of > 0. 25 mm aggregates and organic matter content in the top soil are greater than those in the subsoil;( ii) soil infiltration capability showed differences among different land- use types. Land use showed great effects,in general,the order of decrease on initial infiltration rate and average infiltration rate was: woodland slope > slope farmland >grassland,the order of decrease on steady infiltration rate was: slope farmland > woodland > grassland and the time reaching stable state was:slope farmland > woodland > grassland;( iii) correlation analysis showed that there was a significantly positive correlation between initial infiltration rate and wet sieve MWD value and structural damage rate,and it had a significantly negative correlation with capillary porosity;( iv)steady infiltration rate and non- capillary porosity showed the significantly positive correlation,and it had a significantly negative correlation with the soil bulk density;( v) the average infiltration rate and non- capillary porosity and structural damage rate showed a positive correlation and the correlation coefficient was large and there was a negative correlation between average infiltration rate and soil bulk density and capillary porosity,and the absolute value of correlation coefficient was relatively large. The results of this study can provide the theoretical basis for soil infiltration study in purple soil area.

Fast Sentiment Analysis Algorithm Based on Double Model Fusion

Nowadays,as the number of textual data is exponentially increasing,sentiment analysis has become one of the most significant tasks in natural language processing(NLP)with increasing attention.Traditional Chinese sentiment analysis algorithms cannot make full use of the order information in context and are inefficient in sentiment inference.In this paper,we systematically reviewed the classic and representative works in sentiment analysis and proposed a simple but efficient optimization.First of all,FastText was trained to get the basic classification model,which can generate pre-trained word vectors as a by-product.Secondly,Bidirectional Long Short-Term Memory Network(Bi-LSTM)utilizes the generated word vectors for training and then merges with FastText to make comprehensive sentiment analysis.By combining FastText and Bi-LSTM,we have developed a new fast sentiment analysis,called FAST-BiLSTM,which consistently achieves a balance between performance and speed.In particular,experimental results based on the real datasets demonstrate that our algorithm can effectively judge sentiments of users’comments,and is superior to the traditional algorithm in time efficiency,accuracy,recall and F1 criteria.