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.
Soil organic matter (SOM) is one of the main sources of plant nutrition and promotes plant growth and development. The content of SOM varies in different areas of the field. In this study, a method based on pyrolysis and electronic nose combined with multi-feature data fusion optimization was proposed to realize rapid, accurate and low-cost measurement of SOM content. Firstly, an electronic nose was used to collect response data from the soil pyrolysis gas, and the sensor features (10 × 6) were extracted to form the original feature space. Secondly, Pearson correlation coefficient (PCC), one-way analysis of variance (One-Way ANOVA), principal component analysis algorithm (PCA), linear discriminant analysis algorithm (LDA), and genetic algorithm-backpropagation neural network algorithm (GA-BP) were used to realize multi-feature data fusion optimization. Thirdly, the optimized feature space was used to train the PLSR models, and the predictive performance of the models were used as an indicator to evaluate different feature optimization algorithms. The results showed that the PLSR model with GA-BP for feature optimization had the best predictive performance (R2 = 0.90) and could achieve accurate quantitative prediction of SOM content. The dimensionality of the optimized feature space was reduced to 30 and there was no redundancy in the sensor array.
Soil nitrogen is an essential nutrient element for crop growth and development, and an important indicator of soil fertility characteristics. This study proposed a method based on pyrolysis and artificial olfaction to quickly and accurately determine the soil total nitrogen (STN) content. A muffle furnace was used to pyrolyze the soil samples, and ten different types of oxide semiconductor gas sensors were used to construct a sensor array to detect the soil samples' pyrolysis gas. The response curves of the sensors were tested at pyrolysis temperatures of 200°C, 300°C, 400°C, and 500°C and at pyrolysis times of 1 min, 3 min, 5 min, and 10 min to obtain the optimal pyrolysis state of the soil samples. The optimal pyrolysis temperature was 400°C, and the pyrolysis time was 3 min. The response area, maximum value, average differential coefficient, variance value, maximum gradient value, average value, and 8th-second transient value of the sensor response curve were extracted to construct an artificial olfactory feature space of 121×10×7 (121 soil samples, ten sensor numbers, seven extracted eigenvalues). Back-propagation neural network algorithm (BPNN), partial least squares regression algorithm (PLSR), and partial least squares regression combined with back-propagation neural network algorithm (PLSR-BPNN) were used to establish a prediction model of artificial olfactory feature space and STN content. Moreover, coefficient of determination (R 2 ), root mean square error (RMSE), and the ratio of performance to deviation (RPD) were used as the performance indicators of the prediction results. The test results showed that the R 2 of the PLSR, BPNN, and PLSR-BPNN models were 0.89033, 0.81185, and 0.92186, and the RMSE values were 0.24297, 0.37370, and 0.21781, and the RPD were 2.9964, 1.9482, and 3.3426, respectively. The model established by the PLSR-BPNN algorithm has the highest R 2 and RPD and the smallest RMSE, can achieve the accurate prediction of STN content, and therefore the model is rated as "excellent". The detection method in this study achieves a low-cost, rapid, and accurate determination of STN content, and provides a new reference for the measurement of STN.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.