China’s Land Cover Fraction Change during 2001–2015 Based on Remote Sensed Data Fusion between MCD12 and CCI-LC

Analysis and simulation of the driving mechanism and ecological effects of land cover change in the Weihe River basin, China

Land cover change (LCC) is both a consequence and a cause of global environmental change. This paper attempts to construct a framework to reveal the driving mechanism and ecological effects of different ecological factors under LCC and to explore the ecological characteristics of future LCC. A rule-mining framework based on a land expansion analysis strategy (LEAS) in the patch-generating land use simulation (PLUS) model was used to analyze the drivers of LCC. Neighborhood analysis and ecological effect index were used to investigate multiple ecological effects of LCC. Remote sensing-based ecological indices (RSEI) and the PLUS and stepwise regression model were introduced to explore and predict the integrated ecological effect of LCC. Focusing on the Weihe River basin, study's main drivers of LCC were precipitation, temperature, elevation, population, water table depth, proximity to governments and motorways, GDP, and topsoil organic carbon were the main drivers of LCC. Change directionality were similar for the effects of greenness and biomass formation but opposite for summertime and wintertime temperature. In addition, the conversion of land cover types to cropland had the most significant integrated ecological effect, followed by forest, grassland-shrubland, and other types. The RSEI is predicted to rise to 0.77 in 2030, and the areas where the ecological quality grade will improve and decrease are concentrated on the east and west sides of Ziwuling Mountain, respectively. The findings of this study have practical significance for land management and ecological protection.

Spatiotemporal heterogeneity correction in land ecosystem services and its value assessment: a case study of the Loess Plateau of China

The considerable variation in structures and functions of different ecosystems leads to highly variable ecosystem service values (ESVs). Consequently, the accurate quantification of ESVs can better assess and reflect impacts of land use and cover changes (LUCC) on ecosystem services. In the land use simulations of this study, a CA-Markov model was chosen and nine factors affecting land use change were evaluated, followed by the construction of a multi-criteria evaluation method to simulate land use scenarios between 2025 and 2030 on the Loess Plateau. Six key ecological indicators (economy, water production, net primary plant productivity, habitat quality, accessibility, and soil conservation) were used to correct for spatiotemporal heterogeneity within the terrestrial ESV equivalent weight table for China to obtain an ESV equivalent weight factor table that is applicable to the Loess Plateau. Using the newly corrected table, ESVs for the Loess Plateau region were estimated between 1995 and 2030, and the impacts of LUCC on ESVs were analyzed. The Kappa values for the 2015 land use simulation results were 0.80 and 0.83, which were greater than 0.75, indicating that the CA-Markov model simulations were accurate. Throughout the study period, the largest increases in land use type area were for built-up areas and forest lands, with built-up areas primarily derived from conversions of cultivated lands and grasslands, and forest land increases primarily coming from conversion of grasslands. ESVs increased overall by 933.97 × 10⁸ yuan and 312.86 × 10⁸ yuan from 1995 to 2018 and 2018 to 2030, respectively. The three largest contributors to ecosystem services among land use types were moderate grasses, shrublands, and dense grasslands. In conclusion, ESVs for the Loess Plateau steadily increased year by year from 1995 to 2030, indicating that ecological restoration projects played major roles in improving the stability and sustainability of the region's ecosystems.

Land cover change in global drylands: A review

As a sensitive region, identifying land cover change in drylands is critical to understanding global environmental change. However, the current findings related to land cover change in drylands are not uniform due to differences in data and methods among studies. We compared and judged the spatial and temporal characteristics, driving forces, and ecological effects by identifying the main findings of land cover change in drylands at global and regional scales (especially in China) to strengthen the overall understanding of land cover change in drylands. Four main points were obtained. First, while most studies found that drylands were experiencing vegetation greening, some evidence showed decreases in vegetation and large increases in bare land due to inconsistencies in the datasets and the study phases. Second, the dominant factors affecting land cover change in drylands are precipitation, agricultural activities, and urban expansion. Third, the impact of land cover change on the water cycle, especially the impact of afforestation on water resources in drylands, is of great concern. Finally, drylands experience severe land degradation and require dataset matching (classification standards, resolution, etc.) to quantify the impact of human activities on land cover.

The urgent need to develop a new grassland map in China: based on the consistency and accuracy of ten land cover products

Grasslands are the most dominant terrestrial ecosystem in China, but few national grassland maps have been generated. The grassland resource map produced in the 1980s is widely used as background data, but it has not been updated for almost 40 years. Therefore, a reliable map depicting the current spatial distribution of grasslands across the country is urgently needed. In this study, we evaluated the grassland consistency and accuracy of ten land cover datasets (GLC2000, GlobCover, CCI-LC, MCD12Q1, CLUD, GlobeLand30, GLC-FCS30, CGLS-LC100, CLCD, and FROM-GLC) for 2000, 2010, and 2020 based on extensive fieldwork. We concluded that the area of these ten grassland products ranges from 107.80×10⁴ to 332.46×10⁴ km², with CLCD and MCD12Q1 having the highest area consistency. The spatial and sample consistency is highest in the regions of east-central Inner Mongolia, the Qinghai-Tibet Plateau and northern Xinjiang, while the distribution of southern grasslands is scattered and differs considerably among the ten products. MCD12Q1 is significantly more accurate than the other nine products, with an overall accuracy (OA) reaching 77.51% and a kappa coefficient of 0.51; CLCD is slightly less accurate than MCD12Q1 (OA=73.02%, kappa coefficient=0.45) and is more conducive to the fine monitoring and management of grassland because of its 30-meter resolution. The highest accuracy of grassland was found in the Inner Mongolia-Ningxia region and Qinghai-Tibet Plateau, while the accuracy was worst in the southeastern region. In the future grassland mapping, cartographers should improve the accuracy of the grassland distribution in South China and regions where grassland is confused with forest, cropland and bare land. We specify the availability of valuable data in existing land cover datasets for China's grasslands and call for researchers and the government to actively produce a new generation of grassland maps.

Identifying Urban Wetlands through Remote Sensing Scene Classification Using Deep Learning: A Case Study of Shenzhen, China

Urban wetlands provide cities with unique and valuable ecosystem services but are under great degradation pressure. Correctly identifying urban wetlands from remote sensing images is fundamental for developing appropriate management and protection plans. To overcome the semantic limitations of traditional pixel-level urban wetland classification techniques, we proposed an urban wetland identification framework based on an advanced scene-level classification scheme. First, the Sentinel-2 high-resolution multispectral image of Shenzhen was segmented into 320 m × 320 m square patches to generate sample datasets for classification. Next, twelve typical convolutional neural network (CNN) models were transformed for the comparison experiments. Finally, the model with the best performance was used to classify the wetland scenes in Shenzhen, and pattern and composition analyses were also implemented in the classification results. We found that the DenseNet121 model performed best in classifying urban wetland scenes, with overall accuracy (OA) and kappa values reaching 0.89 and 0.86, respectively. The analysis results revealed that the wetland scene in Shenzhen is generally balanced in the east–west direction. Among the wetland scenes, coastal open waters accounted for a relatively high proportion and showed an obvious southward pattern. The remaining swamp, marsh, tidal flat, and pond areas were scattered, accounting for only 4.64% of the total area of Shenzhen. For scattered and dynamic urban wetlands, we are the first to achieve scene-level classification with satisfactory results, thus providing a clearer and easier-to-understand reference for management and protection, which is of great significance for promoting harmony between humanity and ecosystems in cities.

China's ecosystem service value in 1992-2018: Pattern and anthropogenic driving factors detection using Bayesian spatiotemporal hierarchy model

Maintaining ecosystem services (ESs) and reducing ecosystem degradation are important goals for achieving sustainable development. However, under the influence of various anthropogenic factors, the total ecosystem service value (ESV) of China continues to decline, and the detailed processes involved in this decline are unclear. In this paper, a new long-term annual land cover dataset (the Climate Change Initiative Land Cover or CCI-LC dataset) with a spatial resolution of 300 m was employed to estimate the ESV of China, and Bayesian spatiotemporal hierarchy models were built to examine the detailed patterns and anthropogenic driving factors. From 1992 to 2018, the total ESV of China fluctuated and decreased from 3265.3 to 3253.29 billion US$ at an average rate of 0.55 billion US$ per year. Furthermore, the model revealed the spatiotemporal variations in the ESV pattern, and simultaneously detected the influences of 9 variables related to economic factors, population, infrastructure, energy, agriculture and ecological restoration, providing a convenient and effective method for ESV spatiotemporal analysis. The results enrich our understanding of the detailed spatiotemporal variation and anthropogenic driving factors underlying the declining ESV in China. These findings have substantial guiding implications for adjusting ecological regulation policies.