Monitoring the dynamics of vegetation growth and its response to climate change is important to understand the mechanisms underlying ecosystem behaviors. This study investigated the relationship between vegetation growth and climate change during the growing seasons on the Loess Plateau in China by analyzing the normalized difference vegetation index (NDVI) derived from the Land Long Term Data Record dataset from 1982 to 2011. Results showed that growing-season NDVI had increased at an annual rate of 0.0028, particularly in the semi-arid and semi-humid regions. By contrast, the NDVI first increased from 1982 to 1994 (0.0013 year⁻¹, P < 0.05) and then decreased from 1994 to 2011 (0.0016 year⁻¹, P < 0.05) in the arid region. Temperature had a positive effect on NDVI in most periods within and across seasons in the semi-humid region but had no significant effect in the arid region. Precipitation had a positive effect on NDVI in the arid region in summer and in the semi-arid region in autumn. Summer precipitation was important for autumn vegetation growth in the arid region, whereas summer temperature increased autumn vegetation growth in the semi-arid and semi-humid regions. Further analyses supported the lag-time effects of climate change on vegetation growth on the Loess Plateau. Precipitation shifts had 15- to 18-month time lag effects on vegetation growth in the three climate regions. Vegetation NDVI had a 17-month lag response to temperature in the semi-arid region. Human activities should not be neglected in analyzing the relationship between vegetation growth and climate change on the Loess Plateau.

Leaf chlorophyll content (LCC) is one of the most important factors affecting photosynthetic capacity and nitrogen status, both of which influence crop harvest. However, the development of rapid and nondestructive methods for leaf chlorophyll estimation is a topic of much interest. Hence, this study explored the use of the machine learning approach to enhance the estimation of leaf chlorophyll from spectral reflectance data. The objective of this study was to evaluate four different approaches for estimating the LCC of apple tree leaves at five growth stages (the 1st, 2nd, 3rd, 4th and 5th growth stages): (1) univariate linear regression (ULR); (2) multivariate linear regression (MLR); (3) support vector regression (SVR); and (4) random forest (RF) regression. Samples were collected from the leaves on the eastern, western, southern and northern sides of apple trees five times (1st, 2nd, 3rd, 4th and 5th growth stages) over three consecutive years (2016–2018), and experiments were conducted in 10–20-year-old apple tree orchards. Correlation analysis results showed that LCC and ST, LCC and vegetation indices (VIs), and LCC and three edge parameters (TEP) had high correlations with the first-order differential spectrum (FODS) (0.86), leaf chlorophyll index (LCI) (0.87), and (SD_r − SD_b)/ (SD_r + SD_b) (0.88) at the 3rd, 3rd, and 4th growth stages, respectively. The prediction models of different growth stages were relatively good. The MLR and SVR models in the LCC assessment of different growth stages only reached the highest R² values of 0.79 and 0.82, and the lowest RMSEs were 2.27 and 2.02, respectively. However, the RF model evaluation was significantly better than above models. The R² value was greater than 0.94 and RMSE was less than 1.37 at different growth stages. The prediction accuracy of the 1st growth stage (R² = 0.96, RMSE = 0.95) was best with the RF model. This result could provide a theoretical basis for orchard management. In the future, more models based on machine learning techniques should be developed using the growth information and physiological parameters of orchards that provide technical support for intelligent orchard management.

Leaf nitrogen concentration (LNC) is an important indicator for accurate diagnosis and quantitative evaluation of plant growth status. The objective was to apply a discrete wavelet transform (DWT) analysis in winter wheat for the estimation of LNC based on visible and near-infrared (400–1350 nm) canopy reflectance spectra. In this paper, in situ LNC data and ground-based hyperspectral canopy reflectance was measured over three years at different sites during the tillering, jointing, booting and filling stages of winter wheat. The DWT analysis was conducted on canopy original spectrum, log-transformed spectrum, first derivative spectrum and continuum removal spectrum, respectively, to obtain approximation coefficients, detail coefficients and energy values to characterize canopy spectra. The quantitative relationships between LNC and characteristic parameters were investigated and compared with models established by sensitive band reflectance and typical spectral indices. The results showed combining log-transformed spectrum and a sym8 wavelet function with partial least squares regression (PLS) based on the approximation coefficients at decomposition level 4 most accurately predicted LNC. This approach could explain 11% more variability in LNC than the best spectral index mSR₇₀₅ alone, and was more stable in estimating LNC than models based on random forest regression (RF). The results indicated that narrowband reflectance spectroscopy (450–1350 nm) combined with DWT analysis and PLS regression was a promising method for rapid and nondestructive estimation of LNC for winter wheat across a range in growth stages.

Soil is the largest carbon reservoir on the terrestrial surface. Soil organic carbon (SOC) not only regulates global climate change, but also indicates soil fertility level in croplands. SOC prediction based on remote sensing images has generated great interest in the research field of digital soil mapping. The short revisiting time and wide spectral bands available from Sentinel-2A (S2A) remote sensing data can provide a useful data resource for soil property prediction. However, dense soil surface coverage reduces the direct relationship between soil properties and S2A spectral reflectance such that it is difficult to achieve a successful SOC prediction model. Observations of bare cropland in autumn provide the possibility to establish accurate SOC retrieval models using the S2A super-spectral reflectance. Therefore, in this study, we collected 225 topsoil samples from bare cropland in autumn and measured the SOC content. We also obtained S2A spectral images of the western Guanzhong Plain, China. We established four SOC prediction models, including random forest (RF), support vector machine (SVM), partial least-squares regression (PLSR), and artificial neural network (ANN) based on 15 variables retrieved from the S2A images, and compared the prediction accuracy using RMSE (root mean square error), R² (coefficient of determination), and RPD (ratio of performance to deviation). Based on the optimal model, the spatial distribution of SOC was mapped and analyzed. The results indicated that the inversion model with the RF algorithm achieved the highest accuracy, with an R² of 0.8581, RPD of 2.1313, and RMSE of 1.07. The variables retrieved from the shortwave infrared (SWIR) bands (B11 and B12) usually had higher variable importance, except for the ANN model. SOC content mapped with the RF model gradually decreased with increasing distance from the Wei river, and values were higher in the west than in the east. These results matched the SOC distribution based on measurements at the sample sites. This research provides evidence that soil properties such as SOC can be retrieved and spatially mapped based on S2A images that are obtained from bare cropland in autumn.

The performance of three machine learning methods (support vector regression, random forests and artificial neural network) for estimating the LAI of paddy rice was evaluated in this study. Traditional univariate regression models involving narrowband NDVI with optimized band combinations as well as linear multivariate calibration partial least squares regression models were also evaluated for comparison. A four year field-collected dataset was used to test the robustness of LAI estimation models against temporal variation. The partial least squares regression and three machine learning methods were built on the raw hyperspectral reflectance and the first derivative separately. Two different rules were used to determine the models’ key parameters. The results showed that the combination of the red edge and NIR bands (766 nm and 830 nm) as well as the combination of SWIR bands (1114 nm and 1190 nm) were optimal for producing the narrowband NDVI. The models built on the first derivative spectra yielded more accurate results than the corresponding models built on the raw spectra. Properly selected model parameters resulted in comparable accuracy and robustness with the empirical optimal parameter and significantly reduced the model complexity. The machine learning methods were more accurate and robust than the VI methods and partial least squares regression. When validating the calibrated models against the standalone validation dataset, the VI method yielded a validation RMSE value of 1.17 for NDVI_(766,830) and 1.01 for NDVI_(1114,1190), while the best models for the partial least squares, support vector machine and artificial neural network methods yielded validation RMSE values of 0.84, 0.82, 0.67 and 0.84, respectively. The RF models built on the first derivative spectra with mtry = 10 showed the highest potential for estimating the LAI of paddy rice.