Understanding present and future impacts of drought on the terrestrial carbon budget is of great significance to the evaluation of terrestrial ecosystem disturbance and terrestrial carbon sink. Here, we evaluate the effect of vegetation net primary productivity (NPP) associated with drought through the difference between the mean NPP in the drought and normal years during a specific time period (30 years). Then, the NPP effects in different vegetation types and climatic zones under baseline stage (1981–2010) and future climate scenarios (RCP2.6, RCP4.5, and RCP8.5) is assessed. The results indicate that the negative NPP extremes are captured in most regions, except for the high‐latitude in the Northern Hemisphere. The NPP loss caused by extreme droughts in 2071–2100 is largest under RCPs, followed by the effects of severe and moderate droughts. Regionally, central United States, southern Africa, central Asia, India, Amazon tropical rainforest, and Australia are projected to experience a significant increase in negative NPP extremes and most of these regions are in arid and semi‐arid and tropical rain forest areas. In contrast, tropical Asia suffers little drought effects. For different vegetation, Evergreen Broadleaf Forest, Closed Shrubland, Open Shrubland, Croplands, and Grassland are the most affected by drought. The largest NPP loss occurs in most part of regions under RCP4.5 scenario, not RCP8.5. Climate change is projected to play the largest role in aggravating the risk of drought‐induced NPP reduction. And meanwhile, the adverse effects of drought on vegetation may be resisted through rational fertilizer utilization and land management in future.

Drought is an extremely dangerous natural hazard that causes water crises, crop yield reduction, and ecosystem fires. Researchers have developed many drought indices based on ground-based climate data and various remote sensing data. Ground-based drought indices are more accurate but limited in coverage; while the remote sensing drought indices cover larger areas but have poor accuracy. Applying data-driven models to fuse multi-source remote sensing data for reproducing composite drought index may help fill this gap and better monitor drought in terms of spatial resolution. Machine learning methods can effectively analyze the hierarchical and non-linear relationships between the independent and dependent variables, resulting in better performance compared with traditional linear regression models. In this study, seven drought impact factors from the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite sensor, Global Precipitation Measurement Mission (GPM), and Global Land Data Assimilation System (GLDAS) were used to reproduce the standard precipitation evapotranspiration index (SPEI) for Shandong province, China, from 2002 to 2020. Three machine learning methods, namely bias-corrected random forest (BRF), extreme gradient boosting (XGBoost), and support vector machines (SVM) were applied as regression models. Then, the best model was used to construct the spatial distribution of SPEI. The results show that the BRF outperforms XGBoost and SVM in SPEI estimation. The BRF model can effectively monitor drought conditions in areas without ground observation data. The BRF model provides comprehensive drought information by producing a spatial distribution of SPEI, which provides reliability for the BRF model to be applied in drought monitoring.

Accurate extraction of crop cultivated area and spatial distribution is essential for food security. Crop classification methods based on machine learning and deep learning and remotely sensed time-series data are widely utilized to detect crop planting area. However, few studies assess the effectiveness of machine learning and deep learning algorithm integrated time-series satellite data for identifying multiple crop type classification over a large-scale region. Hence, this study aims to evaluate the effectiveness of machine learning and deep learning models in crop classification and provide a framework for large-scale multiple crop type classification based on time-series of satellite data. The time-series of the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and NaE (combined NDVI and EVI) were adopted as input features, and four widely used machine learning models, including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), and their integration (Stacking) were compared to examine the performance of multiple crop types (i.e., wheat, corn, wheat-corn, early rice, and early rice-late rice) classification in the North China Plain. The performance of two types of deep learning classifiers: the One-dimensional Convolutional Neural Network (Conv1D) and Long Short-Term Memory Networks (LSTM), were also tested. The results showed that the NaE feature performed best among three input features, and the Stacking model produced the highest accuracy (77.12%) compared to other algorithms.

This study explored the applicability of Temperature Vegetation Dryness Index (TVDI) derived from MODIS (Moderate Resolution Imaging Spectroradiometer) normalized difference vegetation index (NDVI) and land surface temperature (LST) data for drought monitoring in Eurasia from April to September during 2005 - 2014. TVDI was calculated based on the vegetation index/temperature trapezoid eigenspace (VITT) in this study. The Standardized Precipitation Evapotranspiration Index in three time scales (SPEI-01, SPEI-03, SPEI-06) and the Essential Climate Variable surface soil moisture product (ECV-SM) was used to evaluate the performance of TVDI over Eurasia, and to assess the sensitivity of TVDI to different land-cover types. The records of drought events from Emergency Events Database (EM-DAT) were also used to validate TVDI. The results indicated that TVDI negatively responded to SPEIs about 77.43%, 72.01%, and 75.95% of lands respectively, of which 29.84%, 33.93%, and 25.59% were subjected significant relationships (p <; 0.05). A negative correlation between TVDI and SPEIs was detected in most land-cover types, except for evergreen broadleaf forest and deciduous needleaf forest. Similarly, TVDI was also negative correlated with ECV-SM. About 66% of the study areas show negative correlation and 33% of them were statistically significant. There is a highly negative correlation between TVDI and ECV-SM in most types of land cover. Moreover, TVDI could not reflect drought condition correctly when TVDI <; 0.40; it could only reflect long-time excessive drought condition when TVDI > 0.86. A comparison of TVDI with drought records demonstrated that the TVDI could capture drought events in study area.

Drought has devastating impacts on agriculture and other ecosystems, and its occurrence is expected to increase in the future. However, its spatiotemporal impacts on net primary productivity (NPP) in Mongolia have remained uncertain. Hence, this paper focuses on the impact of drought on NPP in Mongolia. The drought events in Mongolia during 2003–2018 were identified using the Moderate Resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index (NDVI). The Boreal Ecosystem Productivity Simulator (BEPS)-derived NPP was computed to assess changes in NPP during the 16 years, and the impacts of drought on the NPP of Mongolian terrestrial ecosystems was quantitatively analyzed. The results showed a slightly increasing trend of the growing season NPP during 2003–2018. However, a decreasing trend of NPP was observed during the six major drought events. A total of 60.55–87.75% of land in the entire country experienced drought, leading to a 75% drop in NPP. More specifically, NPP decline was prominent in severe drought areas than in mild and moderate drought areas. Moreover, this study revealed that drought had mostly affected the sparse vegetation NPP. In contrast, forest and shrubland were the least affected vegetation types.

Estimating gross primary productivity (GPP) is important for simulating the subsequent carbon cycle elements and assessing the capacity of terrestrial ecosystems to support the sustainable development of human society. Light use efficiency (LUE) models were widely used to estimate GPP due to their concise model structures. However, quantifying LUE_max (maximum light use efficiency) and representing the responses of photosynthesis to environmental factors are still subject to large uncertainties, which lead to substantial errors in GPP simulations. In this study, we developed a hybrid model based on machine learning and a LUE model for GPP estimates. This hybrid model was built by targeting LUE with a machine learning approach, namely multi-layer perceptron (MLP), and then, estimating GPP within a LUE model framework with the MLP-based LUE and other required inputs. We trained the hybrid LUE (H-LUE) model and then, compared it against two conventional LUE models, the vegetation photosynthesis model (VPM) and vegetation photosynthesis and respiration model (VPRM), regarding GPP estimation, using tower-based daily-scale observations from 180 flux sites that cover nine different plant function types (PFTs). The results revealed better performance (R² = 0.86 and RMSE = 1.79 gC m⁻² d⁻¹ on the test dataset) of the H-LUE model compared to the VPM and VPRM. Evaluations of the three models under four different extreme conditions consistently revealed better performance of the H-LUE model, indicating greater adaptability of the model to varied environments in the context of climate change. Furthermore, we also found that the H-LUE model can reasonably represent the responses of the LUE to meteorological variables. Our study revealed the reliable and robust performance of the developed hybrid LUE when simulating GPP across global biomes, providing references for developing better hybrid GPP models.