In order to solve the problem of data loss in sensor data collection, this paper took the stem moisture data of plants as the object, and compared the filling value of missing data in the same data segment with different data filling methods to verify the validity and accuracy of the stem water filling data of the LSTM (Long Short-Term Memory) model. This paper compared the accuracy of missing stem water data for plants under different data filling methods to solve the problem of data loss in sensor data collection. Original stem moisture data was selected from Lagerstroemia Indica which was planted in the Haidian District of Beijing in June 2017. Part of the data which treated as missing data was manually deleted. Interpolation methods, time series statistical methods, the RNN (Recurrent Neural Network), and LSTM neural network were used to fill in the missing part and the filling results were compared with the original data. The result shows that the LSTM has more accurate performance than the RNN. The error values of the bidirectional LSTM model are the smallest among several models. The error values of the bidirectional LSTM are much lower than other methods. The MAPE (mean absolute percent error) of the bidirectional LSTM model is 1.813%. After increasing the length of the training data, the results further proved the effectiveness of the model. Further, in order to solve the problem of one-dimensional filling error accumulation, the LSTM model is used to conduct the multi-dimensional filling experiment with environmental data. After comparing the filling results of different environmental parameters, three environmental parameters of air humidity, photosynthetic active radiation, and soil temperature were selected as input. The results show that the multi-dimensional filling can greatly extend the sequence length while maintaining the accuracy, and make up for the defect that the one-dimensional filling accumulates errors with the increase of the sequence. The minimum MAPE of multidimensional filling is 1.499%. In conclusion, the data filling method based on LSTM neural network has a great advantage in filling the long-lost time series data which would provide a new idea for data filling.

This article presents a non-destructive methodology to determine the modulus of elasticity (MOE) in static bending of wood through the use of near-infrared (NIR) spectroscopy. Wood specimens were obtained from Quercus mongolica growing in Northeast of China. The NIR spectra of specimens were acquired by using a one-chip NIR fiber optic spectrometer whose spectral range was 900~1900 nm. The raw spectra of specimens were pretreated by multiplication scatter correlation and Savitzky-Golay smoothing and differentiation filter. To reduce the dimensions of data and complexity of modeling, the synergy interval partial least squares and successive projections algorithm were applied to extract the characteristic wavelengths, which had closing relevance with the MOE of wood, and five characteristic wavelengths were selected from full 117 variables of a spectrum. Taking the characteristic wavelengths as input values, partial least square regression (PLSR) and the propagation neural network (BPNN) were implemented to establish calibration models. The predictive ability of the models was estimated by the coefficient of determination (r_p) and the root mean square error of prediction (RMSEP) and in the prediction set. In comparison with the predicted results of the models, BPNN performed better results with the higher r_p of 0.91 and lower RMSEP of 0.76. The results indicate that it is feasible to accurately determine the MOE of wood by using the NIR spectroscopy technique.

Stem water content (StWC = volume of water : volume of stem) is an important physiological parameter for vascular plants. And a better understanding of StWC contributes to solving some research hotspots in forestry, such as drought resistance, cold resistance, precise irrigation, and health assessment. However, there are few noninvasive, in situ, real-time, safe, and low-cost methods for detecting StWC of woody plants. This article presents a novel sensor for noninvasive detection of in situ StWC based on standing wave ratio. Moreover, extensive experiments were conducted to analyze the performance of this sensor including sensitive distance, measuring range, influence factors, and measuring accuracy. The experimental results show that the sensitive distance of StWC sensor is approximately 53 mm in axial direction and 20 mm in radial direction with the measuring range from 0.01 to 1.00 cm³ cm^-3. The combined effects of stem EC and temperature on sensor output are significant and it is necessary to correct the error caused by the two factors. Compared with the oven-drying method, StWC sensor has higher measuring accuracy than Testo 606-2 which is a sensor for measuring wood water content and its average error is less than 0.01 cm³ cm^-3. In addition, StWC sensor performed very well on the crape myrtle with high sensitivity equal to 1022.1 mV (cm³ cm^-3)^-1 and measuring results also accorded with the diurnal dynamics of stem water content.

To address the problems in the calibration of soil water content sensors, in this study, we designed a low-cost edge electromagnetic field induction (EEMFI) sensor for soil water content measurement and proposed a normalized calibration method to eliminate the errors caused by the measurement sensor’s characteristics and improve the probe’s consistency, replaceability, and calibration efficiency. The model calibration curve-fitting coefficients of the EEMFI sensors were above 0.98, which indicated a significant correlation. The experimental results of the static and dynamic characteristics showed that the measurement range of the sensor varied from 0% to 100% saturation, measurement accuracy was within ±2%, the maximum value of the extreme difference of the stability test was 1.09%, the resolution was 0.05%, the delay time was 3.9 s, and the effective measurement diameter of the EEMFI sensor probe was 10 cm. The linear fit coefficient of determination of the results was greater than 0.99, and the maximum absolute error of the measurement results with the drying method was less than ±2%, which meets the requirements of soil water content measurement in agriculture and forestry fields. The field experiment results further showed that the EEMFI sensor can accurately respond to changes in soil water content, indicating that the EEMFI sensor is reliable.

Plant vitality is an important indicator of plant health. Previous studies have often assessed plant vitality using related physiological parameters, but few studies have examined the effects of changes in plant vitality on stem water content (StWC), which can be measured online, in real time, and nondestructively using a novel fringing impedance sensor. In the present study, the sensor calibration results showed a linear fitting relationship between the sensor output voltage and StWC, with coefficients reaching 0.96. The coefficients of correlations between StWC and four plant physiological parameters related to plant vitality (net photosynthetic rate, transpiration rate, stomatal conductance, and intercellular carbon dioxide concentration) were more than 0.8, indicating that StWC can be used to characterize plant vitality to a certain extent. A comparison between plants with normal vitality and weakened vitality showed that the self-regulation ability of plants gradually weakened as the plant vitality decreased, the diurnal mean of StWC lowered, and the diurnal range of StWC increased. In conclusion, StWC can be used as a new parameter to assess plant vitality.

In recent years, the advancement of deep learning technology has led to excellent performance in synthetic aperture radar (SAR) automatic target recognition (ATR) technology. However, due to the interference of speckle noise, the task of classifying SAR images remains challenging. To address this issue, a multi-scale local–global feature fusion network (MFN) integrating a convolution neural network (CNN) and a transformer network was proposed in this study. The proposed network comprises three branches: a CovNeXt-SimAM branch, a Swin Transformer branch, and a multi-scale feature fusion branch. The CovNeXt-SimAM branch extracts local texture detail features of the SAR images at different scales. By incorporating the SimAM attention mechanism to the CNN block, the feature extraction capability of the model was enhanced from the perspective of spatial and channel attention. Additionally, the Swin Transformer branch was employed to extract SAR image global semantic information at different scales. Finally, the multi-scale feature fusion branch was used to fuse local features and global semantic information. Moreover, to overcome the problem of poor accuracy and inefficiency of the model due to empirically determined model hyperparameters, the Bayesian hyperparameter optimization algorithm was used to determine the optimal model hyperparameters. The model proposed in this study achieved average recognition accuracies of 99.26% and 94.27% for SAR vehicle targets under standard operating conditions (SOCs) and extended operating conditions (EOCs), respectively, on the MSTAR dataset. Compared with the baseline model, the recognition accuracy has been improved by 12.74% and 25.26%, respectively. The results demonstrated that Bayes-MFN reduces the inter-class distance of the SAR images, resulting in more compact classification features and less interference from speckle noise. Compared with other mainstream models, the Bayes-MFN model exhibited the best classification performance.