Fluorescence lifetime is the main characteristic parameter of fluorescence. It is a widely used to draw fluorescence lifetime attenuation curves and to fit fluorescence lifetime parameters by using gated detection methods to identify the species of substances. However, the fluorescence attenuation of each fluorophore in a multi-component compound interferes with one another, affecting the accuracy of identification. In this paper, we propose a method to accurately identify substances by using the occurrence time of the secondary crest of the fluorescence lifetime attenuation curve based on the principle of gated detection to measure the fluorescence lifetime. Furthermore, we design a fluorescence lifetime imaging measurement system and select the same areas of interest in the images for analysis and comparison. The average lifetime of the fluorescence and the occurrence time of the secondary crest are considered as the characteristic parameters. We use five commercially available motor engine oils as the experimental samples and compare the recognition performance of different kernel functions based on a support vector machine (SVM). The radial basis kernel function presents the best performance in terms of recognition accuracy and speed. The recognition rates of the SVM model with the average fluorescence lifetime and the occurrence time of the secondary crest in the attenuation curve of the fluorescence lifetime as a feature vector are 76.24% and 74.65%, respectively. The recognition rate of the SVM model which combines them as feature vectors reaches 91.88%. The experimental results demonstrate that the occurrence time of the secondary crest in the attenuation curve of the fluorescence lifetime can be employed as the basis for substance identification in the analysis of the fluorescence characteristics of multi-component compounds, whose recognition accuracy is similar to the average fluorescence lifetime parameter. Moreover, the occurrence time of the secondary crest of the fluorescence lifetime attenuation curve can be implemented to identify multi-component compounds when it is used as a characteristic parameter.

To classify and detect the type and content of petroleum hydrocarbon contaminants in the soil surface layer, fluorescence spectrometry is commonly used. The experimental oils were selected from three common engine oils available in the market: Loxson L-CKC220 gear oil, APSIN 10W-40 engine oil and Jaguar 200 SF MA 15W-40 motorcycle oil. The fluorescence spectra of the oils were obtained using the fluorescence-induced technique, the spectral wavelengths were selected using a genetic algorithm (GA), and the detection models were constructed by combining RF (Random Forest), AdaBoost, and Gradient Enhanced Decision Tree (GBDT) regression algorithms for classification, identification, and concentration prediction analysis. The experimental results show that the average accuracy of classification and identification of gear oil, engine oil and motorcycle oil reach 83.9, 97.8, and 92.2

To investigate the effect of water stress on strawberry seedlings, a chlorophyll-fluorescence-image-acquisition system was developed. Strawberry seedlings of uniform growth were selected for grouped water-stress incubation experiments; the collected chlorophyll-fluorescence images of leaves were converted to red-green-blue (RGB), hue-saturation-value (HSV), and hue-saturation-intensity (HSI) color spaces and analyzed for water and chlorophyll contents measured at the same time for 14 consecutive days. The results indicate that the analysis and prediction of plant stress conditions can be effectively conducted using the channel components of the color-space model and the channel component ratios, which provide a reference for promoting agricultural development.

In order to investigate the effect of water stress on strawberry seedlings, a chlorophyll fluorescence acquisition system was built based on chlorophyll fluorescence imaging technology. By conducting grouped water stress incubation experiments on strawberry seedlings, the water content and chlorophyll content (SPAD) of leaves were measured at the same moment for 14 consecutive days, and the RGB, HSV and HSI color space models of true color images were converted using MATLAB software based on the collected chlorophyll fluorescence images. The experimental results showed that the leaf water content of the experimental group decreased with the increase of chlorophyll content and the correlation coefficient of the correlation model is $\mathrm{R}^{2}=0.96$ ; When channel components in color space were used to characterize the water stress condition of strawberry seedlings, the correlation between the water content of the leaves of experimental group B and the channel component I was the highest, with a modeled correlation coefficient of $\mathrm{R}^{2}=0.88$ ; the correlation between the chlorophyll content (SPAD) of the leaves of experimental group B and the channel component I was the highest, with a modeled correlation coefficient of $\mathrm{R}^{2}=0.89$ . The average relative error between the validation and prediction groups did not exceed 10 % when the water content and chlorophyll content of seedling leaves under water stress were predicted using I-channel components. In summary, the I-channel of HSI color space model can be used to characterize the water content and chlorophyll content (SPAD) of strawberry seedling leaves under water stress, thus effectively conducting the assessment of plant stress status and providing some reference value for agricultural development.

In order to solve the prediction problem of oil pollutant concentration on soil surface, oil spectral curve was obtained by laser induced fluorescence technology. Based on kurtosis, skewness and standard deviation, wavelet kurtosis was proposed as the quantitative parameter to predict the concentration of contaminated oil on soil surface. The random forest regression algorithm was used to compare and analyze three different oil products in the market. The experimental results show that the prediction accuracy of three kinds of oil concentration by random forest regression model is improved by 6.67%, 6.66% and 3.33% respectively. It provides some reference for the regression model of predicting the concentration of oil pollutants in soil surface.

Drought stress is the main factor affecting plant grown and development. Chlorophyll fluorescence was chosen as research object to study the effects of drought stress on the growth of Longjing tea seedlings crops. A chlorophyll fluorescence collection system was designed with LED, CCD and filter. Longjing tea seedling with good growth were selected for drought treatment. The tea seedlings should be dark treatment before each experiment. Using LED lamps actively induced the emission fluorescence of tea seedlings, and the images were collected in the same time period for 8 consecutive days. The chlorophyll fluorescence quenching curve was drawn through the mean gray value of the images after preprocessing with median filter. We proposed a new method for evaluating fluorescence quenching curves using slope index, named the slope fluorescence index (SFI). The range of the gray scale mean at the same time in 1-8 days is calculated, the relative errors of range were calculated over the selected time range and determining the time range of range stability. Within the time range, correlation model between each point on the curves and the stress days was established to find a point with the largest correlation coefficient R 2 . The results showed that there was the highest correlation between the SFI of fluorescence quenching curve at 327s and the days of drought stress (determinant coefficient R 2=0.94021). Slope fluorescence index (SFI) is used to evaluate chlorophyll fluorescence quenching curve, which will provide a new idea for monitoring plant growth under stress.