Soil organic matter (SOM) is a major indicator of soil fertility and nutrients. In this study, a soil organic matter measuring method based on an artificial olfactory system (AOS) was designed. An array composed of 10 identical gas sensors controlled at different temperatures was used to collect soil gases. From the response curve of each sensor, four features were extracted (maximum value, mean differential coefficient value, response area value, and the transient value at the 20th second). Then, soil organic matter regression prediction models were built based on back-propagation neural network (BPNN), support vector regression (SVR), and partial least squares regression (PLSR). The prediction performance of each model was evaluated using the coefficient of determination (R²), root-mean-square error (RMSE), and the ratio of performance to deviation (RPD). It was found that the R² values between prediction (from BPNN, SVR, and PLSR) and observation were 0.880, 0.895, and 0.808. RMSEs were 14.916, 14.094, and 18.890, and RPDs were 2.837, 3.003, and 2.240, respectively. SVR had higher prediction ability than BPNN and PLSR and can be used to accurately predict organic matter contents. Thus, our findings offer brand new methods for predicting SOM.

Intelligent sowing depth regulation system based on Flex sensor and Mamdani fuzzy model for a no-till planter

Design of bionic mole forelimb intelligent row cleaners

Conservation agriculture is an important measure promoting sustainable agriculture in northeast China. Coulters in the conservation agriculture system are used to cut the excessive residue in strips, loosen soils, and create good seedbeds. Information on the performance of coulters worked in a field with or without corn residue coverage is lacking in the literature. In this study, five coulters were tested in two field conditions at three working velocities to compare their performance. The five coulters were four types of fluted coulters (8 W, 13 W, 18 W, and 25 W) and one notched-flat coulter (NF); the two field conditions were whole residue plots (WR) and no residue plots(NR), and the three working velocities were 8 km/h (V1), 10 km/h (V2), and 12 km/h (V3). All of the tests were tested at a tillage depth of 80 mm. The results showed that the maximum furrow width (W_f), furrow disturbance area (A), and residue coverage change (C) were significantly affected by the working velocity and coulter type, while the cutting force (F) and skid rate (S) were significantly affected by the residue coverage, working velocity, and coulter type. The NF was found to have the smallest furrow profile, residue coverage change, and cutting force, as well as the largest skid rate. Among the fluted coulters, as the wavenumber rose, the cutting force, furrow width, and furrow disturbance area all gradually decreased, while the skid rate and residue coverage change were gradually enhanced. The straw residual intensified the cutting force and reduced the skid rate, which changed by 11.6% and 20.9%, respectively. As the working velocity rose from 8 km/h to 12 km/h, the furrow width, furrow disturbance area, residue coverage change, cutting force, and skid rate increased by 26.5%, 16.5%, 44.6%, 8.2%, and 22.7%, respectively. The results reveal that the flat coulter and large-wavenumber fluted coulters (18 W and 25 W) have less cutting force and are more beneficial for cutting straw residue in residue coverage fields, while the small-wavenumber fluted coulters (8 W and 13 W) are suitable for loosening soil and constructing seedbeds. The cutting force has significant effects on the performance of cutting straw residue, loosening soils, and creating seedbeds.

An appropriate contact mechanics model and parameters are key to achieving accurate results in discrete element analyzis. This is necessary to predict the process of contact collision between the soil and maize seed during deposition. In this paper, the contact process between maize seed and soil is analyzed using the maize seed variety (Liangyu 99) and maize-sowing field soil (with three different moisture contents) as research objects. Based on this, the contact process between maize seeds and soil has been analyzed, on the basis of which a mechanical model suitable for simulating the contact process between maize seeds and soil has been explored, and the selection of parameters between heterogeneous particles (maize seed and soil particles) has been investigated. The results showed that adhesion forces have a significant effect on the collision process between seed and soil particles. While the presence of tangential adhesion force can be replaced by increasing the static and rolling friction coefficients, the normal adhesion force cannot be compensated in this way. The Edinburgh Elasto-Plastic Adhesive (EEPA) model is selected in this paper to describe the contact between seed and soil particles. The significance of the input parameters in the EEPA model is investigated using the Plackett–Burman test. The parameters between soil and seed particles are optimized using the central composite design, and the optimal parameter combinations are obtained. The relative error between the simulation and test result of the slope test for the three soil moisture contents is within 5.4%, validating the accuracy of the calibrated parameters.

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.