The leaf area index (LAI) is not only an important parameter for monitoring crop growth, but also an important input parameter for crop yield prediction models and hydrological and climatic models. Several studies have recently been conducted to estimate crop LAI using unmanned aerial vehicle (UAV) multispectral and hyperspectral data. However, there are few studies on estimating the LAI of winter wheat using unmanned aerial vehicle (UAV) RGB images. In this study, we estimated the LAI of winter wheat at the jointing stage on simple farmland in Xinjiang, China, using parameters derived from UAV RGB images. According to gray correlation analysis, UAV RGB-image parameters such as the Visible Atmospherically Resistant Index (VARI), the Red Green Blue Vegetation Index (RGBVI), the Digital Number (DN) of Blue Channel (B) and the Green Leaf Algorithm (GLA) were selected to develop models for estimating the LAI of winter wheat. The results showed that it is feasible to use UAV RGB images for inverting and mapping the LAI of winter wheat at the jointing stage on the field scale, and the partial least squares regression (PLSR) model based on the VARI, RGBVI, B and GLA had the best prediction accuracy (R² = 0.776, root mean square error (RMSE) = 0.468, residual prediction deviation (RPD) = 1.838) among all the regression models. To conclude, UAV RGB images not only have great potential in estimating the LAI of winter wheat, but also can provide more reliable and accurate data for precision agriculture management.

The accurate estimation of leaf chlorophyll content (LCC) is a significant foundation in assessing litchi photosynthetic activity and possible nutrient status. Hyperspectral remote sensing data have been widely used in agricultural quantitative monitoring research for the non-destructive assessment of LCC. Variable selection approaches are crucial for analyzing high-dimensional datasets due to the high danger of overfitting, time-intensiveness, or substantial computational requirements. In this study, the performance of five machine learning regression algorithms (MLRAs) was investigated based on the hyperspectral fractional order derivative (FOD) reflection of 298 leaves together with the variable combination population analysis (VCPA)-genetic algorithm (GA) hybrid strategy in estimating the LCC of Litchi. The results showed that the correlation coefficient (r) between the 0.8-order derivative spectrum and LCC had the highest correlation coefficients (r = 0.9179, p < 0.01). The VCPA-GA hybrid strategy fully utilizes VCPA and GA while compensating for their limitations based on a large number of variables. Moreover, the model was developed using the selected 14 sensitive bands from 0.8-order hyperspectral reflectance data with the lowest root mean square error in prediction (RMSEP = 5.04 $\mathsf{\mu }\mathrm{g}·{\mathrm{cm}}^{-2}$). Compared with the five MLRAs, validation results confirmed that the ridge regression (RR) algorithm derived from the 0.2 order was the most effective for estimating the LCC with the coefficient of determination (R² = 0.88), mean absolute error (MAE = 3.40$\mathsf{\mu }\mathrm{g}·{\mathrm{cm}}^{-2}$), root mean square error (RMSE = 4.23$\mathsf{\mu }\mathrm{g}·{\mathrm{cm}}^{-2}$), and ratio of performance to inter-quartile distance (RPIQ = 3.59). This study indicates that a hybrid variable selection strategy (VCPA-GA) and MLRAs are very effective in retrieving the LCC through hyperspectral reflectance at the leaf scale. The proposed methods could further provide some scientific basis for the hyperspectral remote sensing band setting of different platforms, such as an unmanned aerial vehicle (UAV) and satellite.

Chlorophyll is an essential pigment for photosynthesis in tea plants, and fluctuations in its content directly impact the growth and developmental processes of tea trees, thereby influencing the final quality of the tea. Therefore, achieving rapid and non-destructive real-time monitoring of leaf chlorophyll content (LCC) is beneficial for precise management in tea plantations. In this study, derivative transformations were first applied to preprocess the tea hyperspectral data, followed by the use of the Stable Competitive Adaptive Reweighted Sampling (SCARS) algorithm for feature variable selection. Finally, multiple individual machine learning models and stacking models were constructed to estimate tea LCC based on hyperspectral data, with a particular emphasis on analyzing how the selection of base models and meta-models affects the predictive performance of the stacking models. The results indicate that derivative processing enhances the sensitivity of hyperspectral data to tea LCC; furthermore, compared with individual machine learning models, the stacking models demonstrate superior predictive accuracy and generalization ability. Among the 17 constructed stacking configurations, when the meta-model is fixed, the predictive performance of the stacking model improves continuously with an increase in the number and accuracy of the base models and with a decrease in the structural similarity among the selected base models. Therefore, when constructing stacking models, the base model combination should comprise various models with minimal structural similarity while ensuring robust predictive performance, and the meta-model should be chosen as a simple linear or nonlinear model.

Leaf area index (LAI) is an important parameter for monitoring crop growth, and an important input parameter for crop yield prediction model, hydrological and climatic models. LAI can be used in field crop growth monitoring and verification of remote sensing products. Therefore, accurate, rapid and large-scale estimation of LAI is not only conducive to better monitoring crops, but also conducive to its application in modeling, crop management and precision agriculture. Remote sensing technique has become a promising method to detect and monitor the crop LAI due to its many advantages. In this paper, Banjiequan Village, Wumachang Township, Qitai County, Xinjiang, China was selected as the study area. In order to rapidly and extensively retrieve LAI of winter wheat using domestic remote sensing images, 17 common vegetation indices were extracted from the GF-1/2 images, which was synchronized with field sampling, and observation at intervals of 20 m in the east-west direction and 30 m in the north-south direction in a 130 m × 420 m block. A total of 78 sampling points were taken from a small area of 4 rows × 50 cm. Sampling width was measured by tape ruler and coordinates of sampling points were given by GPS. Based on the vegetation indices extracted from GF-1/2 image and LAI data measured at erecting stage, jointing stage and flowering stage, we established univariate (linear, exponential, power, quadratic polynomials) and multivariate (partial least squares regression, PLSR) empirical models for inversion of winter wheat LAI, and validated them. The correlation coefficients of LAI with MSR (modified simple ratio), GNDVI (green normalized difference vegetation index), EVI (enhanced vegetation index) extracted from the erecting, jointing and flowering stages of GF-1 were the maximum, which were 0.708, 0.671, and 0.743, respectively, indicating that the correlation between these vegetation indices and LAI of winter wheat was significant. The univariate model R² based on MSR_GF-1, NDVI_GF-2 (normalized difference vegetation index), GNDVI_GF-1 at jointing stage and EVI_GF-1 at flowering stage were all greater than 0.7. Compared with different image data at the same growth stage, the quadratic polynomial model based on NDVI_GF-2 and PLSR model based on NDVI_GF-2, MSR_GF-2, and SAVI_GF-2 (soil-adjusted vegetation index) were more precise than those based on GF-1, with R² of 0.768 and 0.809 respectively. Compared with the models with the same data (GF-1) at different growth stages, the quadratic polynomial model based on GNDVI_GF-1 at jointing stage and the PLSR model based on EVI_GF-1, GSR_GF-1 (green simple ratio) and NDVI_GF-1 at flowering stage had the maximum value of R², which was 0.783. The RMSE of the PLSR model was smaller than that of the quadratic polynomial model, indicating the stability of the multivariate model was better than univariate model. Analyzing the LAI distribution maps inverted from different growth stages, it was found that the LAI inversion values basically coincided with the measured LAI values. The above results show that the domestic high-resolution remote sensing image has certain application value in crop physiological parameter inversion, and provides some references for related researches in the future.