Abstract: 【Aim】 The automation and intelligence of population monitoring of the brown planthopper, Nilaparvata lugens, have not been resolved now. The aim of this study is to explore the relationship of canopy spectrum and temperature, and leaf chlorophyll content with the number of N. lugens on rice plants, and to establish a back propagation (BP) neural network to monitor the population size of N. lugens based on multi-source information fusion of hyperspectral, thermal imaging, and chlorophyll, so as to provide a new method for the development of automation and intelligence in monitoring N. lugens populations. 【Methods】 Under controlled conditions, rice was cultivated using the square plastic box, and different pairs (0, 1, 2, 3, 4, 5, 6 and 7 pairs) of female and male adults of N. lugens (female to male ratio=1∶1) were released onto rice plants at the tillering stage. Then, the number of N. lugens on rice (number of individuals per 4 hills of rice) was investigated on day 16, 27, 32, 44 and 60 post original infestation, and the spectral reflectance and temperature of rice canopy were measured using a hyperspectral spectrometer and a thermal imager, respectively. The relative content of chlorophyll in leaves was measured using a chlorophyll meter (soil and plant analyzer development, SPAD) as SPAD readings. The Pearson correlation method was used to analyze the correlations between these measured indexes and the number of N. lugens. The multivariate scattering correction was used to process the spectral reflectance data to reduce noise. The successive projection algorithm was adopted for dimensionality reduction and screening the sensitive band of hyperspectral reflectance. Using single source of spectral reflectance information and its multi-source information fusion with canopy temperature and SPAD readings as inputs, the modeling methods, the general (BPNN) and optimized BP neural networks by particle swarm optimization (PSO-BPNN) were used to establish the neural network models to monitor the population sizes of N. lugens damaging different periods. 【Results】 The reflectance from rice canopy at the near-infrared band 730-930 nm was significantly negatively correlated with the number of N. lugens damaging rice plants, and the temperature difference between rice canopy and air (TDC) and the SPAD readings of leaves were also significantly negatively correlated with the number of N. lugens. The coefficient of determination R² of the prediction set for monitoring the population size of N. lugens using the BPNN based on the noise reduction value of reflectance at the sensitive band of rice canopy screened by the successive projection algorithm could reach up to 0.504-0.892. The R² of the predication set for monitoring the number of N. lugens by the BP neural network based on multi-source information fusion of canopy reflectance, TDC, and leaf SPAD readings could reach up to 0.640-0.975. Further, on the basis of multi-source information, the BP neural network optimized by particle swarm optimization (PSO) algorithm improved the accuracy for monitoring the number of N. lugens, and the R² value of the predication set was up to 0.931-0.991. 【Conclusion】 The PSO-BP neural network method based on multi-source information fusion of rice canopy hyperspectral and thermal imaging, as well as leaf SPAD readings, has high accuracy and good effectiveness in monitoring the number of N. lugens, and is expected to be applied for automatic monitoring of N. lugens populations in paddy fields.

Key words: Nilaparvata lugens; canopy spectral reflectance, canopy temperature, chlorophyll SPAD, BP neural network, particle swarm optimization