Qiang Liu

The Leaf Area Index (LAI) serves as a vital biophysical parameter for quantifying vegetation dynamics and ecosystem functioning. While traditional LAI retrieval methods face challenges in handling nonlinear spectral-vegetation relationships, machine learning (ML) approaches offer promising alternatives through their data-driven adaptability. This study presents a comprehensive cross-site assessment of 13 ML algorithms for LAI estimation, leveraging ground observations from 98 sites worldwide. Our systematic assessment reveals three key findings: First, ensemble methods consistently outperformed other approaches, with Gradient Boosted Tree Regression (GBTR) achieving superior accuracy (R² = 0.647, RMSE = 0.899) and robustness (ΔR² < 0.05 beyond n = 69 training samples). Second, Gaussian Process Regression (GPR) illustrated exceptional stability across varying training sizes (R² = 0.607 ± 0.012), highlighting its reliability for data-limited scenarios. Third, all tested ML models substantially outperformed operational LAI products, with the GBTR model demonstrating superior explanatory power (external validation R² = 0.647) compared to MODIS; its R² value had increased by 0.489. This optimal balance of accuracy, computational efficiency, and resistance to overfitting positions GBTR as a reasonable choice for large-scale LAI mapping. These findings underscore ML’s promising potential in vegetation monitoring while highlighting the need for hybrid approaches that combine physical principles with data-driven learning to address current limitations in extreme-value estimation and ecological generalizability.

The frequency of extreme drought events is increasing, significantly impacting ecosystems worldwide. In China, the grasslands of dryland Inner Mongolia provide a vital ecological resource, highlight the urgent need to understand their response to drought in these arid regions. We investigate vegetation dynamics and soil moisture fluctuations across three grassland types—meadows, typical grasslands, and desert grasslands—utilizing solar-induced fluorescence (SIF), normalized difference vegetation index (NDVI), and soil moisture data from 2001 to 2020. By employing event coincidence analysis and the maximum coincidence rate, we quantified the grasslands’ responses to drought events. Our findings indicate a significant upward trend in SIF across all grassland types over the past two decades, while NDVI and soil moisture levels remained relatively stable. Under drought conditions, the probability of grassland degradation ranged from 40% to 60%. Notably, desert grasslands exhibited a considerably slower response rate compared to other grassland types, while meadow grasslands responded the fastest to drought; however, all grassland types displayed a response delay of 1–2 months. When soil moisture levels fell below −1.8 standard deviations (STDs), a reversal in grassland response patterns was observed, particularly in meadow grasslands, which showed a substantial increase in response probability. At soil moisture levels below −2.4 STD, this probability stabilized at approximately 90%, significantly higher than that of other grassland types. These insights provide a vital basis for understanding and mitigating drought impacts on resilient grassland ecosystems under climate change.

Climate warming hampers grassland growth, particularly in dryland regions. To preserve robust grassland growth and ensure the resilience of grassland in these arid areas, a comprehensive understanding of the interactions between vegetation and climate is imperative. However, existing studies often analyze climate–vegetation interactions using concurrent vegetation indices and meteorological data, neglecting time-lagged influences from various determinants. To address this void, we employed the random forest machine learning method to predict the grassland NDVI (Normalized Difference Vegetation Index) in Asian drylands (including five central Asia countries, the Republic of Mongolia, and Parts of China) from 2001 to 2020, incorporating time-lag influences. We evaluated the prediction model’s performance using three indexes, namely the coefficient of determination (R²), root-mean-square error (RMSE), and Mean Absolute Error (MAE). The results underscore the superiority of the model incorporating time-lag influences, demonstrating its enhanced capability to capture the grassland NDVI in Asian drylands (R² ≥ 0.915, RMSE ≤ 0.033, MAE ≤ 0.019). Conversely, the model without time-lag influences exhibited relatively poor performance, notably inferior to the time-lag-inclusive model. The latter result aligns closely with remote sensing observations and more accurately reproduces the spatial distributions of the grassland NDVI in Asian drylands. Over the study period, the grassland NDVI in Asian drylands exhibited a weak decreasing trend, primarily concentrated in the western region. Notably, key factors influencing the grassland NDVI included the average grassland NDVI in the previous month, total precipitation in the current month, and average soil moisture in the previous month. This study not only pioneers a novel approach to predicting grassland growth but also contributes valuable insights for formulating sustainable strategies to preserve the integrity of grassland ecosystems.

Amidst the escalating impacts of global warming, the occurrence and severity of compound extreme weather events have risen significantly, presenting substantial threats to both lives and property. Existing response strategies predominantly focus on individual events, often overlooking the cumulative effects rising from their inherent complexity. To address this critical gap, we conducted a thorough examination of sequential extreme precipitation–heatwave compound events (SEPHCE) in China from 1975 to 2020, utilizing data from 1929 meteorological stations. Our investigation revealed a consistent rise in the frequency and duration of SEPHCE, with a particularly notable surge since 1993. Furthermore, shorter interval events disproportionately affected the regions of southwestern and southeast coastal China. Furthermore, SEPHCE onset times exhibited advancement, and the endings were delayed, thereby intensifying the overall trend. These findings underscore the pressing need to prioritize effective planning and adaptation strategies to mitigate the impact of these compound event, while also addressing the potential exacerbation of inequality resulting from climate change.

Climate change strongly impact vegetation phenology, with considerable potential to alter land-atmosphere carbon dioxide exchange and terrestrial carbon cycle. In contrast to well-studied spring leaf-out, the timing and magnitude of autumn senescence remains poorly understood. Here, we use monthly decreases in Normalized Difference Vegetation Index satellite retrievals and their trends to surrogate the speed of autumn senescence during 1982–2018 in the Northern Hemisphere (>30°N). We find that climate warming accelerated senescence in July, but this influence usually reversed in later summer and early autumn. Interestingly, summer greening causes canopy senescence to appear later compared to an advancing trend after eliminating the greening effect. This finding suggests that summer canopy greening may counteract the intrinsic changes in autumnal leaf senescence. Our analysis of autumn vegetation behavior provides reliable guidance for developing and parameterizing land surface models that contain an interactive dynamic vegetation module for placement in coupled Earth System Models.

Vegetation productivity first increases and then decreases with temperature; and temperature corresponding to the maximum productivity is called optimal temperature (T_opt). In this study, we used satellite derived near‐infrared reflectance of vegetation (NIR_v) data to map T_opt of vegetation productivity at the spatial resolution of 0.1° on the Tibetan Plateau (TP), one of most sensitive regions in the climate system. The average T_opt of non‐forest vegetation on the TP is about 14.7°C, significantly lower than the T_opt value used in current ecosystem models. A remarkable geographical heterogeneity in T_opt is observed over the TP. Higher T_opt values generally appear in the north‐eastern TP, while the south‐western TP has relatively lower T_opt (T_opt tends to decrease by 0.41°C per 100 m increase in elevation, faster than the elevational elapse rate of growing season temperature, implying a potential CO₂ regulation of T_opt in addition to temperature acclimation. T_opt increases by 0.66°C for each 1°C of rising mean annual temperature as a result of vegetation acclimation to climate change. However, at least at the decadal scale, there is no significant change in T_opt between 2000s and 2010s, suggesting that the T_opt climate acclimation may not keep up with the warming rate. Finally, future (2091–2100) warming could be close to and even surpass T_opt on the TP under different RCP scenarios without considering potential climate acclimation. Our analyses imply that the temperature tipping point when the impact of future warming shifts from positive to negative on the TP is greatly overestimated by current vegetation models. Future research needs to include varying thermal and CO₂ acclimation effects on T_opt across different time scales in vegetation models.