Estimation of the canopy water content (CWC) is extremely important for irrigation management decisions. Machine learning and hyperspectral imaging technology have provided a potentially useful tool for precise measurement of plant water content. The tools, however, are hampered by feature selection as well as an advanced model in itself. Therefore, this study aims to propose an efficient prediction model and compare three feature selection methods including vegetation indices (VI), model-based features (MF), and principal component analysis (PCA). The selected features were applied with a back-propagation neural network (BPNN), random forest (RF), and partial least square regression (PLSR) for training the samples with minimal loss on a cross-validation set. The hyperspectral images were collected from rice crops grown under different water stress levels. A total of 128 images were used to evaluate our proposed methods. The results indicated that the integration of PCA and MF methods can provide a more robust feature selection for the proposed prediction model. The three bands of 1467, 1456, and 1106 nm were the supreme variants of CWC forecasting. These features were combined with an optimized BPNN model and significantly improved the foretelling accuracy. The accuracy and correlation coefficient of the advanced BPNN-PCA-MF model are close to 1 with an RMSE of 0.252. Thus, this study positively contributes to plant water content prediction researchers and policymakers so that well in advance and effective steps can be taken for precision irrigation.

The presence of pests is one of the main problems in crop production, and obtaining reliable statistics of pest infestation is essential for pest management. Detection of pests should be automated because human monitoring of pests is time-consuming and error-prone. Aphids are among the most destructive pests in greenhouses and they reproduce quickly. Automatic detection of aphid nymphs on leaves (especially on the lower surface) using image analysis is a challenging problem due to color similarity and complicated background. In this study, we propose a method for segmentation and counting of aphid nymphs on leaves using convolutional neural networks. Digital images of pakchoi leaves at different aphid infestation stages were obtained, and corresponding pixel-level binary mask annotated. In the test, segmentation results by the proposed method achieved high overlap with annotation by human experts (Dice coefficient of 0.8207). Automatic counting based on segmentation showed high precision (0.9563) and recall (0.9650). The correlation between aphid nymph count by the proposed method and manual counting was high (R² = 0.99). The proposed method is generic and can be applied for other species of pests.

Striped stem-borer (SSB) infestation is one of the most serious sources of damage to rice growth. A rapid and non-destructive method of early SSB detection is essential for rice-growth protection. In this study, hyperspectral imaging combined with chemometrics was used to detect early SSB infestation in rice and identify the degree of infestation (DI). Visible/near-infrared hyperspectral images (in the spectral range of 380 nm to 1030 nm) were taken of the healthy rice plants and infested rice plants by SSB for 2, 4, 6, 8 and 10 days. A total of 17 characteristic wavelengths were selected from the spectral data extracted from the hyperspectral images by the successive projection algorithm (SPA). Principal component analysis (PCA) was applied to the hyperspectral images, and 16 textural features based on the gray-level co-occurrence matrix (GLCM) were extracted from the first two principal component (PC) images. A back-propagation neural network (BPNN) was used to establish infestation degree evaluation models based on full spectra, characteristic wavelengths, textural features and features fusion, respectively. BPNN models based on a fusion of characteristic wavelengths and textural features achieved the best performance, with classification accuracy of calibration and prediction sets over 95%. The accuracy of each infestation degree was satisfactory, and the accuracy of rice samples infested for 2 days was slightly low. In all, this study indicated the feasibility of hyperspectral imaging techniques to detect early SSB infestation and identify degrees of infestation.