Vegetation phenology has been used in studies as an indicator of an ecosystem’s responses to climate change. Satellite remote sensing techniques can capture changes in vegetation greenness, which can be used to estimate vegetation phenology. In this study, a long-term vegetation phenology study of the Greater Khingan Mountain area in Northeastern China was performed by using the Global Inventory Modeling and Mapping Studies (GIMMS) normalized difference vegetation index version 3 (NDVI3g) dataset from the years 1982–2012. After reconstructing the NDVI time series, the start date of the growing season (SOS), the end date of the growing season (EOS) and the length of the growing season (LOS) were extracted using a dynamic threshold method. The response of the variation in phenology with climatic factors was also analyzed. The results showed that the phenology in the study area changed significantly in the three decades between 1982 and 2012, including a 12.1-day increase in the entire region’s average LOS, a 3.3-day advance in the SOS and an 8.8-day delay in the EOS. However, differences existed between the steppe, forest and agricultural regions, with the LOSs of the steppe region, forest region and agricultural region increasing by 4.40 days, 10.42 days and 1.71 days, respectively, and a later EOS seemed to more strongly affect the extension of the growing season. Additionally, temperature and precipitation were closely correlated with the phenology variations. This study provides a useful understanding of the recent change in phenology and its variability in this high-latitude study area, and this study also details the responses of several ecosystems to climate change.

Leaf area index (LAI) is a key parameter used to describe vegetation structures and is widely used in ecosystem biophysical process and vegetation productivity models. Many algorithms have been developed for the estimation of LAI based on remote sensing images. Our goal was to produce accurate and timely predictions of grassland LAI for the meadow steppes of northern China. Here, we compare the predictive power of regression approaches and hybrid geostatistical methods using Chinese Huanjing (HJ) satellite charge coupled device (CCD) data. The regression methods evaluated include partial least squares regression (PLSR), artificial neural networks (ANNs) and random forests (RFs). The two hybrid geostatistical methods were regression kriging (RK) and random forests residuals kriging (RFRK). The predictions were validated for different grassland types and different growing stages, and their performances were also examined by adding several groups of vegetation indices (VIs). The two hybrid geostatistical models (RK and RFRK) yielded the most accurate predictions (root mean squared error (RMSE) = 0.21 m²/m² and 0.23 m²/m² for RK and RFRK, respectively), followed by the RF model (RMSE = 0.27 m²/m²), which was the most accurate among the regression models. These three models also exhibited the best temporal performance across the duration of the growing season. The PLSR and ANN models were less accurate (RMSE = 0.33 m²/m² and 0.35 m²/m² for ANN and PLSR, respectively), and the PLSR model performed the worst (exhibiting varied temporal performance and unreliable prediction accuracy that was susceptible to ground conditions). By adding VIs to the predictor variables, the predictions of the PLSR and ANN models were obviously improved (RMSE improved from 0.35 m²/m² to 0.28 m²/m² for PLSR and from 0.33 m²/m² to 0.28 m²/m² for ANN); the RF and RFRK models did not generate more accurate predictions and the performance of the RK model declined (RMSE decreased from 0.21 m²/m² to 0.32 m²/m²).

Estimating forage yield and nutrient composition using hyperspectral remote sensing is a major challenge. However, there is still a lack of comprehensive research on the optimal wavelength for the analysis of various nutrients in pasture. In this research, conducted in Hailar District, Hulunber City, Inner Mongolia Autonomous Region, China, 126 sets of hyperspectral data were collected, covering a spectral range of 350 to 1800 nanometers. The primary objective was to identify key spectral bands for estimating forage dry matter yield (DMY), nitrogen content (NC), neutral detergent fiber (NDF), and acid detergent fiber (ADF) using principal component analysis (PCA), random forests (RF), and SHapley Additive exPlanations (SHAP) analysis methods, and then the RF and Extra-Trees algorithm (ERT) model was used to predict aboveground biomass (AGB) and nutrient parameters using the optimized spectral bands and vegetation indices. Our approach effectively minimizes redundancy in hyperspectral data by selectively employing crucial spectral bands, thus improving the accuracy of forage nutrient estimation. PCA identified the most variable bands at 400 nm, 520–550 nm, 670–720 nm, and 930–950 nm, reflecting their general spectral significance rather than a link to specific forage nutrients. Further analysis using RF feature importance pinpointed influential bands, predominantly within 930–940 nm and 700–730 nm. SHAP analysis confirmed critical bands for DMY (965 nm, 712 nm, and 1652 nm), NC (1390 nm and 713 nm), ADF (1390 nm and 715–725 nm), and NDF (400 nm, 983 nm, 1350 nm, and 1800 nm). The fitting accuracy for ADF estimated using RF was lower (R² = 0.58), while the fitting accuracy for other indicators was higher (R² ≥ 0.59). The performance and prediction accuracy of ERT (R² = 0.63) were noticeably superior to those of RF. In conclusion, our method effectively identifies influential bands, optimizing forage yield and quality estimation.

This study investigated the performances of the Moderate Resolution Imaging Spectroradiometer (MODIS) and GEOLAND2 Version 1 (GEOV1) Leaf Area Index (LAI) products using ground measurements and LAI reference maps over four sites in North China for 2011–2013. The Terra + Aqua MODIS and Terra MODIS LAI retrieved by the main algorithm and GEOV1 LAI within the valid range were evaluated and intercompared using LAI reference maps to assess their uncertainty and seasonal variability The results showed that GEOV1 LAI is the most similar product with the LAI reference maps (R² = 0.78 and RMSE = 0.59). The MODIS products performed well for biomes with low LAI values, but considerable uncertainty arose when the LAI was larger than 3. Terra + Aqua MODIS (R² = 0.72 and RMSE = 0.68) was slightly more accurate than Terra MODIS (R² = 0.57 and RMSE = 0.90) for producing slightly more successful observations. Both MODIS and GEOV1 products effectively followed the seasonal trajectory of the reference maps, and GEOV1 exhibited a smoother seasonal trajectory than MODIS. MODIS anomalies mainly occurred during summer and likely occurred because of surface reflectance uncertainty, shorter temporal resolutions and inconsistency between simulated and MODIS surface reflectances. This study suggests that further improvements of the MODIS LAI products should focus on finer algorithm inputs and improved seasonal variation modeling of MODIS observations. Future field work considering finer biome maps and better generation of LAI reference maps is still needed.