Multi-Feature Optimization Study of Soil Total Nitrogen Content Detection Based on Thermal Cracking and Artificial Olfactory System

To improve the accuracy of detecting soil total nitrogen (STN) content by an artificial olfactory system, this paper proposes a multi-feature optimization method for soil total nitrogen content based on an artificial olfactory system. Ten different metal–oxide semiconductor gas sensors were selected to form a sensor array to collect soil gas and generate response curves. Additionally, six features such as the response area, maximum value, average differential coefficient, standard deviation value, average value, and 15th-second transient value of each sensor response curve were extracted to construct an artificial olfactory feature space (10×6). Moreover, the relationship between feature space and soil total nitrogen content was used to establish backpropagation neural network (BPNN), extreme learning machine (ELM), and partial least squares regression (PLSR) models were used, and the coefficient of determination (R2), root mean square error (RMSE), and the ratio of performance to deviation (RPD) were selected as prediction performance indicators. The Monte Carlo cross-validation (MCCV) and K-means improved leave-one-out cross-validation (K-means LOOCV) were adopted to identify and remove abnormal samples in the feature space and establish the BPNN model, respectively. There were significant improvements before and after comparing the two rejection methods, among which the MCCV rejection method was superior, where values for R2, RMSE, and RPD were 0.75671, 0.33517, and 1.7938, respectively. After removing the abnormal samples, the soil samples were then subjected to feature-optimized dimensionality reduction using principal component analysis (PCA) and genetic algorithm-based optimization backpropagation neural network (GA-BP). The test results showed that after feature optimization the model indicators performed better than those of the unoptimized model, and the PLSR model with GA-BP for feature optimization had the best prediction effect, with an R2 value of 0.93848, RPD value of 3.5666, and RMSE value of 0.16857 in the test set. R2 and RPD values improved by 14.01% and 50.60%, respectively, compared with those before optimization, and RMSE value decreased by 45.16%, which effectively improved the accuracy of the artificial olfactory system in detecting soil total nitrogen content and could achieve more accurate quantitative prediction of soil total nitrogen content.

The balance of nitrogen forms and number of microorganisms of the nitrogen cycle in vermicomposts based on leaf litter and cow manure

The processes of nitrogen transformation in the vermiculture system by Eisenia fetida using cow manure and leaf litter (poplar with small birch addition) have been investigated. Vermicomposting was carried out for five months in half-cubic meter wooden containers. The Kjeldahl method and potentiometry determined the total nitrogen, NH4 + and NO3- content in vermicompost. The total nitrogen content in cow manure was 1.83%, in leaf litter - 0.73%. The nitrate and ammonium content in non-composted leaf litter was 351 and 7.3 mEq/kg of dry matter, respectively. The nitrate and ammonium content in non-composted cow manure was 18.2 and 22 mEq/kg, respectively. Both investigated substrates of vermicomposting did not influence total nitrogen content. In cow manure-based vermicomposting system, the ammonium amount decreased by 5.3 times, while the concentration of nitrates increased by 6.5 times. In the leaf litter-based vermicomposting system, the ammonium amount increased by 2.9 times, and the amount of the nitrate increased by 1.6 times. The Azotobacter bacteria actual activity in both vermicomposts was close to 100%. The sum of nitrogen cycle microorganisms in manure vermicompost was 2.4 times higher than in leaf litter vermicompost.

Grazing Intensity Changed The Activities of Nitrogen Assimilation Related Enzymes In Desert Steppe Plants

Background: The study on nitrogen assimilation mechanism of grazing grassland plants is of great significance to reveal the law of nutrient absorption and utilization of grassland vegetation. Methods: This study took Stipa breviflora desert steppe which was grazed for 17 years as the research object, and sampled the root system, leaf and rhizosphere soil of constructive species Stipa breviflora under the treatments of no grazing, light grazing, moderate grazing and heavy grazing during the peak growing season. The activities of enzymes related to nitrogen assimilation in roots and leaves were measured, and the related factors affecting nitrogen content were analyzed. Results: The results showed that heavy grazing significantly increased the total nitrogen content in the root system of Stipa breviflora, but decreased the total nitrogen content in the leaves, and the performance of grazing prohibition was consistent with that of heavy grazing; The activities of Nitrate reductase (NR), glutamine synthetase (GS), glutamic oxaloacetic transaminase (GOT) and glutamic pyruvate transaminase (GPT) were stronger under light or moderate grazing. Under grazing prohibition and heavy grazing, the content of proline in roots and leaves of Stipa breviflora increased significantly, especially in leaves; NR, GS, GOT and GPT were significantly correlated with total nitrogen content in roots and leaves of Stipa breviflora. Conclusions: Grazing prohibition and heavy grazing were not conducive to the nitrogen absorption and utilization of Stipa breviflora, which was closely related to the reduction of nitrate and ammonium nitrogen contents in the rhizosphere soil of Stipa breviflora by grazing. Grazing prohibition and heavy grazing affected the nitrogen content of Stipa breviflora by affecting the activities of related enzymes in the process of nitrogen assimilation of roots and leaves.