Storage, patterns, and environmental controls of soil organic carbon stocks in the permafrost regions of the Northern Hemisphere.

Large stocks of soil organic carbon (SOC) accumulated in the Northern Hemisphere permafrost regions may be vulnerable to climatic warming, but global estimates of SOC distribution and magnitude in permafrost regions still have large uncertainties. Based on multiple high-resolution environmental variables and a compiled soil sample dataset (>3000 soil profiles), we used machine-learning methods to estimate the size and spatial distribution of SOC for the top 3 m soils in the Northern Hemisphere permafrost regions. We also identified key environmental predictors of SOC. The results showed that the SOC storage for the top 3 m soil was 1079 ± 174 Pg C across the Northern Hemisphere permafrost regions (20.8 × 106 km2), including 1057 ± 167 Pg C in the northern permafrost regions and 22 ± 7 Pg C in the Third Pole permafrost regions. The mean annual air temperature and NDVI are the main controlling factors for the spatial distribution of SOC stocks in the northern and the Third Pole permafrost regions. Our estimations were more accurate than the existing global SOC stock maps. The results improve our understanding of the regional and global permafrost carbon cycle and their feedback to the climate system.

Improving the estimation of alpine grassland fractional vegetation cover using optimized algorithms and multi-dimensional features.

BACKGROUND: Fractional vegetation cover (FVC) is an important basic parameter for the quantitative monitoring of the alpine grassland ecosystem on the Qinghai-Tibetan Plateau. Based on unmanned aerial vehicle (UAV) acquisition of measured data and matching it with satellite remote sensing images at the pixel scale, the proper selection of driving data and inversion algorithms can be determined and is crucial for generating high-precision alpine grassland FVC products. METHODS: This study presents estimations of alpine grassland FVC using optimized algorithms and multi-dimensional features. The multi-dimensional feature set (using original spectral bands, 22 vegetation indices, and topographical factors) was constructed from many sources of information, then the optimal feature subset was determined based on different feature selection algorithms as the driving data for optimized machine learning algorithms. Finally, the inversion accuracy, sensitivity to sample size, and computational efficiency of the four machine learning algorithms were evaluated. RESULTS: (1) The random forest (RF) algorithm (R2: 0.861, RMSE: 9.5%) performed the best for FVC inversion among the four machine learning algorithms driven by the four typical vegetation indices. (2) Compared with the four typical vegetation indices, using multi-dimensional feature sets as driving data obviously improved the FVC inversion accuracy of the four machine learning algorithms (R2 of the RF algorithm increased to 0.890). (3) Among the three variable selection algorithms (Boruta, sequential forward selection [SFS], and permutation importance-recursive feature elimination [PI-RFE]), the constructed PI-RFE feature selection algorithm had the best dimensionality reduction effect on the multi-dimensional feature set. (4) The hyper-parameter optimization of the machine learning algorithms and feature selection of the multi-dimensional feature set further improved FVC inversion accuracy (R2: 0.917 and RMSE: 7.9% in the optimized RF algorithm). CONCLUSION: This study provides a highly precise, optimized algorithm with an optimal multi-dimensional feature set for FVC inversion, which is vital for the quantitative monitoring of the ecological environment of alpine grassland.

[Influence of Land Use Change on Ecosystem Service Value Based on GEE in the Beijing-Tianjin-Hebei Region from 1998 to 2018].

In sustainable development assessment of the Beijing-Tianjin-Hebei region, the ability to dynamically estimate the value of ecosystem services is of great significance. This study considers the Beijing-Tianjin-Hebei region as the research area, based on the google earth engine (GEE); the classification and decision tree (CART) classification algorithm was adopted to supervise and classify the Landsat Thematic Mapper/Operational Land Imager (TM/OLI) images in the study area in 1998, 2003, 2008, 2013, and 2018, and land use types in these five periods were obtained. Quantitative analysis of the dynamic changes of land use in the Beijing-Tianjin-Hebei region from 1998 to 2018 was carried out. Then, the ecosystem service value (ESV) equivalent estimation method was used to quantitatively estimate the ESV in the Beijing-Tianjin-Hebei region and combine it with a 15 km×15 km scale grid to detect its temporal and spatial dynamics. The main results were as follows. ① From 1998 to 2018, the area of construction land (increased by 16.67%) and grassland (reduced by 13.73%) in the six land use types in the Beijing-Tianjin-Hebei region was the largest, and the change in the proportion of water bodies (0.2%) was the smallest. ② The total value of ESV in the Beijing-Tianjin-Hebei region experienced a short-term increase from 1998 to 2003 (an increase of 91.97×108 yuan), and continued to decrease from 2003 to 2018 (a decrease of 239.07×108 yuan), mainly related to the expansion of construction land area in the other three time periods excluding 1998 and 2003. Among the six land use types, the forest provides the highest value of ecosystem services, and the construction land and unused land provide the lowest value of ecosystem services. ③ The ESV time-space analysis based on the 15 km×15 km scale grid showed that the ESV medium area in the Beijing-Tianjin-Hebei region gradually decreased from 1998 to 2018, the ESV lower area and the higher area gradually increased, and the ESV lower-area growth rate was higher than for the higher area. ④ The revised value of the Beijing-Tianjin-Hebei region (sensitivity coefficient range 0-0.83) has good significance and reliability. In future economic development, the Beijing-Tianjin-Hebei region should rationally optimize the land use pattern and strengthen the protection of forest land, grassland, water bodies and cultivated land.