The status of insecticide resistance levels is important for applying suitable pest management approaches. The present study investigated the insecticide resistance of Plutella xylostella (Linnaeus) (Lepidoptera: Plutellidae) populations from five major cruciferous growing areas in Taiwan. The surveyed locations were distributed from central to southern Taiwan and included Taichung, Changhua, Yunlin, Chiayi, and Kaohsiung. High levels of resistance to spinosad, indoxacarb, metaflumizone, and chlorantraniliprole were recorded among the surveyed populations except in Taichung. The resistance ratios ranged from 2.376 to 1,236-fold for spinosad and 24.63–1,511-fold for indoxacarb. Similarly, those for metaflumizone and chlorantraniliprole, were 2.563–76.21- and 4.457–683.0-fold, respectively. However, Bacillus thuringiensis subsp. aizawai, Bacillus thuringiensis subsp. kurstaki, emamectin benzoate, and diafenthiuron were still relatively effective against most field populations of P. xylostella. After approximately 10 generations of being maintained in the laboratory without exposure to insecticides, the resistance ratios of the Kaohsiung and Changhua populations declined to approximately 1.4–10-fold, and insecticides with control failure likelihood also began to show a negligible risk of control failure. Although spinosad, indoxacarb, metaflumizone, and chlorantraniliprole have lost their effectiveness in most field populations of P. xylostella in Taiwan, their effectiveness may be recovered in the absence of insecticide-selection pressure for approximately 10 generations. Therefore, we suggest that a constant survey of insecticide resistance and well-designed insecticide rotation based on the survey results are necessary for the effective control and insecticide resistance management of P. xylostella.

The detection of rice leaf folder (RLF) infestation usually depends on manual monitoring, and early infestations cannot be detected visually. To improve detection accuracy and reduce human error, we use push-broom hyperspectral sensors to scan rice images and use machine learning and deep neural learning methods to detect RLF-infested rice leaves. Different from traditional image processing methods, hyperspectral imaging data analysis is based on pixel-based classification and target recognition. Since the spectral information itself is a feature and can be considered a vector, deep learning neural networks do not need to use convolutional neural networks to extract features. To correctly detect the spectral image of rice leaves infested by RLF, we use the constrained energy minimization (CEM) method to suppress the background noise of the spectral image. A band selection method was utilized to reduce the computational energy consumption of using the full-band process, and six bands were selected as candidate bands. The following method is the band expansion process (BEP) method, which is utilized to expand the vector length to improve the problem of compressed spectral information for band selection. We use CEM and deep neural networks to detect defects in the spectral images of infected rice leaves and compare the performance of each in the full frequency band, frequency band selection, and frequency BEP. A total of 339 hyperspectral images were collected in this study; the results showed that six bands were sufficient for detecting early infestations of RLF, with a detection accuracy of 98% and a Dice similarity coefficient of 0.8, which provides advantages of commercialization of this field.