Land Cover Dataset Research Articles

Impacts of land cover changes on biogenic emission and its contribution to ozone and secondary organic aerosol in China

Abstract. The greening impacts on China from 2000 to 2017 led to an increase in vegetated areas and thus enhanced biogenic volatile organic compound (BVOC) emissions. BVOCs are regarded as important precursors for ozone (O3) and secondary organic aerosol (SOA). As a result, accurate estimation of BVOC emissions is critical to understand their impacts on air quality. In this study, the Model of Emissions of Gases and Aerosols from Nature (MEGAN) v2.1 was used to investigate the impact of different leaf area index (LAI) and land cover (LC) datasets on BVOC emissions in China in 2016, and the effects on O3 and SOA were evaluated based on the Community Multiscale Air Quality (CMAQ) modeling system. Three LAI satellite datasets of the Global LAnd Surface Satellite (GLASS), the Moderate Resolution Imaging Spectroradiometer (MODIS) MOD15A2H version 6 (MOD15), and the Copernicus Global Land Service (CGLS), as well as three LC satellite datasets of the MODIS MCD12Q1 LC products, the Copernicus Climate Change Service (C3S) LC products, and the CGLS LC products, were used in five parallel experiments (cases: C1–C5). Results show that changing LAI and LC datasets of the model input has an impact on BVOC estimations. BVOC emissions in China ranged from 25.42 to 37.39 Tg in 2016 and were mainly concentrated in central and southeastern China. Changing the LC inputs for the MEGAN model has a more significant difference in BVOC estimates than using different LAI datasets. The combination of C3S LC and GLASS LAI performs better in the CMAQ model, indicating that it is the better choice for BVOC estimations in China. The highest contribution of BVOCs to O3 and SOA can reach 12 ppb and 9.8 µg m−3, respectively. Changing the MEGAN inputs further impacts the concentrations of O3 and SOA, especially changing LC datasets. The relative difference between MCD12Q1 LC and C3S LC is over 52 % and 140 % in O3 and biogenic SOA (BSOA) in central and eastern China. The BSOA difference is mainly attributed to the isoprene SOA (ISOA), a major contributor to BSOA. The relative differences in ISOA between different cases are up to 160 % in eastern China. Therefore, our results suggest that the uncertainties in MEGAN inputs should be fully considered in future O3 and SOA simulations.

Protected area planning to conserve biodiversity in an uncertain future.

Protected areas are a key instrument for conservation. Despite this, they are vulnerable to risks associated with weak governance, land-use intensification, and climate change. We used a novel hierarchical optimization approach to identify priority areas for expanding the global protected area system that explicitly accounted for such risks while maximizing protection of all known terrestrial vertebrate species. To incorporate risk categories, we built on the minimum set problem, where the objective is to reach species distribution protection targets while accounting for 1 constraint, such as land cost or area. We expanded this approach to include multiple objectives accounting for risk in the problem formulation by treating each risk layer as a separate objective in the problem formulation. Reducing exposure to these risks required expanding the area of the global protected area system by 1.6% while still meeting conservation targets. Incorporating risks from weak governance drove the greatest changes in spatial priorities for protection, and incorporating risks from climate change required the largest increase (2.52%) in global protected area. Conserving wide-ranging species required countries with relatively strong governance to protect more land when they bordered nations with comparatively weak governance. Our results underscore the need for cross-jurisdictional coordination and demonstrate how risk can be efficiently incorporated into conservation planning. Planeación de las áreas protegidas para conservar la biodiversidad en un futuro incierto.

Fine‐scale accuracy assessment of the 2016 National Land Cover Dataset for stream‐based wildlife habitat

AbstractEfficiently and effectively identifying and assessing potential wildlife habitat and important ecological resources is essential as rapid anthropogenic land use change alters and detrimentally affects terrestrial and aquatic habitats. Accuracy assessment of remotely sensed data supports ecological planning and management decisions, and is especially important when using freely available, coarse‐resolution spatial datasets, such as the National Land Cover Dataset (NLCD). A popular dataset designed for application at larger regional to national spatial scales, the NLCD has been used in finer scale studies outside of its intended use, often without the imperative support of field‐based accuracy assessment. We ground‐truthed stratified random sampling points to assess the accuracy of the 2016 NLCD at a fine spatial scale relevant to stream‐based ecological research. Our results demonstrated an overall accuracy of <65%, less than the United States Geological Survey recommended accuracy of ≥85%. Results indicated that the NLCD may not be effective as a tool for stream‐level studies and could provide erroneous results for fine‐scale habitat assessment and planning when used as the only reference dataset. When conducting ecological research, it is important to consider the appropriate scale, resolution, and limitations of available datasets to achieve the most accurate results.

Reconstructing Long‐Term Forest Cover in China by Fusing National Forest Inventory and 20 Land Use and Land Cover Data Sets

AbstractAs an important type of terrestrial carbon sink, forests play a critical role in offsetting anthropogenic fossil fuel CO2 emissions which should help nations to achieve carbon neutrality goals worldwide. According to National Forest Inventory (NFI), China has experienced substantial increases in forest cover by benefiting from national afforestation projects initiated in the l980s. However, none of the current land use and land cover (LULC) data sets can reproduce the long‐term changes of forest cover derived from NFI in China. Here, by combining NFI and 20 LULC data sets, we developed a new method of reconstructing historical forest cover in China from 1980 to 2015 at 5‐year intervals. The new forest cover data set can accurately reproduce the historical changes of forest cover in China during this period. Validated against 3851 field survey samples covering the study period of 1985–2015, the data sets show high accuracy with overall accuracy varying from 76.9% to 99.4%. Accurate long‐term forest cover maps have great potential for use in estimating terrestrial carbon, tracking forest management, and other scientific research studies.

Relative abundance of grazing and browsing herbivores is not a direct reflection of vegetation structure: Implications for hominin paleoenvironmental reconstruction.

The diet of fossil herbivores inferred from enamel stable carbon isotopes is often used to make paleoenvironmental reconstructions. While many studies have focused on using environmental indicator taxa to make paleoenvironmental reconstructions, community-based approaches are considered to provide a more complete picture of paleolandscapes. These studies assume that the diet and relative abundance of herbivores are related to the areal extent of different vegetation types on the landscape. Here, we quantitatively test this assumption in 16 modern ecosystems in eastern and southern Africa with a wide range of woody vegetation cover. We conducted a landscape-level spatial analysis of vegetation patterns using a published land cover data set and computed landscape metrics. We compiled data on relative abundance and diet of herbivores inferred from carbon isotope studies for all large herbivores in these ecosystems. We found that despite differences in the total areal extent of different vegetation types, numerous sizable patches of each vegetation type are available in most ecosystems. However, despite variation across the ecosystems examined, grazers are typically the most abundant herbivores even in sites that have a higher proportion of forest and shrub cover. This indicates that the diet and relative abundance of herbivores is not a simple reflection of the total areal extent of vegetation types available on the landscape. The higher proportion of grazers observed in these ecosystems is a result of multiple factors including habitat heterogeneity, differences in biomass turnover rate between grasses and woody vegetation, resource partitioning, and the advantages of group living in open environments. Comparison of diet and relative abundance of herbivores in modern ecosystems to fossil herbivore assemblages shows that very different vegetation regimes can support similar herbivore assemblages. This study has significant implications for paleolandscape reconstructions and cautions against a simplistic wooded vs. grassland paleoenvironmental interpretations based on fossil herbivore assemblages.

Spatial modeling to understand the dynamics of land cover MODIS satellite data and Markov Chain

The ever-increasing economic and population growth closely relates to the change in land cover. As a region grows, the land cover shifts from forests to agriculture and further to developed areas. Such a gradual change occurs slowly; however, understanding the land cover dynamics is essential to regional planning, especially in developing regions, including Indonesia. Despite its importance, studies on land cover changes in developing regions lack a coherent dataset, as many studies are based on ad-hoc approaches, resulting in embedded uncertainties. An example is the land cover classification using LANDSAT data in many parts of the developing countries lacking consistency. As an alternative, the MODIS dataset is a relatively new dataset produced by NASA, presenting a standardized land cover dataset with a 500×500 m resolution at global coverage. Such a standardized dataset gives consistency in land cover dynamics and future projections. This study presents the potential of MODIS and its use case in understanding land cover dynamics in an urbanizing watershed, i.e., the Majalaya Watershed in West Java, Indonesia. The study presents the use of Markov Chain Analysis in understanding the tendency of changes between land cover classes. This study also indicates future research directions to enrich the topic further.

An object-based image analysis approach for comparing tree detection from satellite imagery at different scales; A case study in Sukumba Mali

This paper combines an object-based image analysis (OBIA) approach, with markov-random field based-super resolution mapping (MRF-SRM) technique to extract individual tree objects from satellite imagery. Extraction of individual trees in urban and developing cities using satellite imageries has been quite challenging and a subject of active research with many approaches to it. The study area is a part of Sukumba village located in Koutiala district, Mali. The aim is to evaluate the performance comparison of the combined MRF-SRM approach, which was demonstrated for each combination of scale factor and class separability. Due to varying contrast sensitivity, there exist a general limitation in the spatial distribution of land cover data sets derived from most coarse and fine resolution satellite imageries. A 10 m spatial resolution Sentinel-2 and 2 m spatial resolution Worldview-3 satellite images were used for the study. First, the pixel based MRF-SRM classification technique of Tolpekin and Stein, 2009 was applied on both images. Subsequently, the classified SRM thematic results were partitioned into objects (segments) using region growing segmentation algorithm as post a classification procedure. Finally, validation and comparison of the resulting tree objects was done using an object based image analysis approach to determine existential (TP), extensional (FP) and positional (PA) accuracy. For Sentinel-2 image and out of 1787 reference objects, 1214 (TP) was detected and 573 (FP) was undetected. The PA is 6.504 m out of 10 m, total detection error is 0.467 m and the final detection accuracy is 68%. Similarly, for Worldview-3 image and out of 1787 reference objects, 1772 (TP) was detected and 15 (FP) was undetected. The PA is 1.714 m out of 2 m, total detection error is 0.318 m and the final detection accuracy is 99%. The successful approach used in this study will support the capacity of monitoring agricultural change in data sparse regions and developing countries.

Comparing Global Sentinel-2 Land Cover Maps for Regional Species Distribution Modeling

Mapping the spatial and temporal dynamics of species distributions is necessary for biodiversity conservation land-use planning decisions. Recent advances in remote sensing and machine learning have allowed for high-resolution species distribution modeling that can inform landscape-level decision-making. Here we compare the performance of three popular Sentinel-2 (10-m) land cover maps, including dynamic world (DW), European land cover (ELC10), and world cover (WC), in predicting wild bee species richness over southern Norway. The proportion of grassland habitat within 250 m (derived from the land cover maps), along with temperature and distance to sandy soils, were used as predictors in both Bayesian regularized neural network and random forest models. Models using grassland habitat from DW performed best (RMSE = 2.8 ± 0.03; average ± standard deviation across models), followed by ELC10 (RMSE = 2.85 ± 0.03) and WC (RMSE = 2.87 ± 0.02). All satellite-derived maps outperformed a manually mapped Norwegian land cover dataset called AR5 (RMSE = 3.02 ± 0.02). When validating the model predictions of bee species richness against citizen science data on solitary bee occurrences using generalized linear models, we found that ELC10 performed best (AIC = 2278 ± 4), followed by WC (AIC = 2367 ± 3), and DW (AIC = 2376 ± 3). While the differences in RMSE we observed between models were small, they may be significant when such models are used to prioritize grassland patches within a landscape for conservation subsidies or management policies. Partial dependencies in our models showed that increasing the proportion of grassland habitat is positively associated with wild bee species richness, thereby justifying bee conservation schemes that aim to enhance semi-natural grassland habitat. Our results confirm the utility of satellite-derived land cover maps in supporting high-resolution species distribution modeling and suggest there is scope to monitor changes in species distributions over time given the dense time series provided by products such as DW.

Preseason crop type prediction using crop sequence boundaries

Preseason crop-type prediction has emerged as a valuable tool for agricultural use. A reliable algorithm for early crop-type prediction has many applications, including crop mapping, planted acreage prediction, crop yield prediction, disaster response, area sample design, crop survey imputation, and more. The primary source of data for preseason crop prediction in the United States is the United States Department of Agriculture National Agricultural Statistics Service’s Cropland Data Layer, which is an annual crop specific land cover data set produced using satellite imagery and administrative data. Historical crop rotations taken from the Cropland Data Layer can be used by machine learning models to predict the future crop type in any given land area. The dataset obtained from the Cropland Data Layer is large, containing hundreds of millions of pixels per state. Current approaches for predictive modeling have utilized sampling, resulting in more scalable machine learning. In this paper, the authors propose an alternative method that uses all available Cropland Data Layer data in a rapid and memory-efficient manner. The proposed method relies on a novel technique for identifying groups of pixels with homogenous cropping history. These pixel groups are summarized as polygons representing field boundaries, referred to as crop sequence boundaries. Use of these new polygons for modeling significantly reduces the computational burden of incorporating all the Cropland Data Layer data and eliminates any increased uncertainty brought on by sampling. This novel polygon-based approach competes well with existing methods in scalability and accuracy, achieving the highest overall accuracy in 23 out of 24 tests performed.

Combined use of urban Atlas and Corine land cover datasets for the implementation of an ecological network using graph theory within a multi-species approach

Ecological sustainability has recently risen to prominence in scientific research and management applications. Approaches to measuring ecological connectivity and their application to optimize ecological network (EN) design are powerful tools against landscape fragmentation and biodiversity loss.We focused on building an EN by identifying the most sensitive areas for ecological connectivity within the Reggio Calabria (Italy) metropolitan area. We also proposed a defragmentation scenario to improve the obtained EN.The CORINE Land Cover and the Urban Atlas 2018 were used to obtain a fine-scale representation of the study area. Ten terrestrial mammal species were used to model connectivity following a multi-species approach. Dispersal distance, patch size, and resistance to species movement were used to identify patches and corridors. Vegetational fractional coverage based on three years time series of Sentinel-2 red-edge normalized difference vegetation index was used to discriminate areas with higher naturalness. We used graph theory and connectivity metrics to test the EN’s robustness and identify locations for restoration in a defragmentation scenario.The obtained EN, formed by three separate components, was composed of 724 arcs and 300 nodes with an average patch area of 27.04 ha. After the defragmentation hypothesis, the EN, formed by only one component, was composed of 771 arcs and 328 nodes with an average patch area of 26.82 ha.It was possible to analyze an EN’s connectivity and evaluate the impact of a scenario intended to enhance multi-species connectivity. By comparing several connectivity metrics, we highlighted the potential of land interventions as a planning tool to enhance future ecological sustainability and biodiversity conservation.

FENet: feature enhancement network for land cover classification

ABSTRACT Extracting mask information of buildings and water areas from high resolution remote sensing images is beneficial to monitoring and management of urban development. However, due to different times, different geographical locations and different remote sensing acquisition angles, water areas and buildings will feed back different spectral information. Existing semantic segmentation methods do not pay enough attention to channel information, and the feature information extracted by downsampling is relatively abstract, which is easy to cause the loss of some details in high-resolution images under complex scenes, leading to the misjudgement of buildings and waters. To solve the existing problems, feature enhancement network (FENet) for high-resolution remote sensing image segmentation of buildings and water areas is proposed. By paying more attention to the characteristic information of the passage, the probability of misjudgement of buildings and waters can be reduced and their edge contour information can be enhanced. The self-attention feature module proposed in this paper encodes the context information and transmits it to the local features, and establishes the relationship between channels through the channel feature enhancement module to reduce the loss of channel feature information. The feature fusion module fuses feature information of different scales in space and outputs more detailed prediction images. Comparative experiments show that this model is superior to the existing classical semantic segmentation model. Compared with the existing models, the proposed method can achieve 2% improvement than PSPNet on the indicator MIoU, and the final MIoU reaches 82.85% for land cover dataset. This study demonstrates the advantages of our proposed method in land cover classification and detection.

Evaluation of Global Land Use–Land Cover Data Products in Guangxi, China

Land use–land cover (LULC) is an important feature for ecological environment research, land resource management and evaluation. Although global high-resolution LULC data sets are booming, their regional performances were still evaluated in limited regions. To demonstrate the local applicability of global LULC data products, six emerging LULC data products were evaluated and compared in Guangxi, China. The six products used are European Space Agency GlobCover (ESAGC), ESRI Land Use–Land Cover (ESRI–LULC), Finer Resolution Observation and Monitoring of Global Land Cover (FROM–GLC), the China Land Cover Dataset (CLCD), the Global Land Cover product with Fine Classification System at 30 m (GLC_FCS30) and GlobeLand30 (GLC30). Reference data were obtained from the local government statistical yearbook and high-resolution remote sensing images on Google Earth. The results showed that CLCD, ESRI–LULC and GLC30 were found to agree well with the forest reference data, with the highest correlation coefficient of 0.999. For the cropland areas, GLC30, CLCD and ESAGC agreed well with the reference data, and the highest correlation coefficient was 0.957. Combined with the comparison with the high-resolution images obtained by Google Earth, we finally concluded that ESAGC, CLCD and GLC30 can best represent the LULCs in Guangxi. Furthermore, the spatial consistency analysis showed that three or more products identified the same LULC type as high as 96.98% of the area. We suggest that majority voting might be applied to global LULC products to provide fused products with better performances on a regional or local scale to avoid the error caused by a single data product.

Contribution of Land Cover Classification Results Based on Sentinel-1 and 2 to the Accreditation of Wetland Cities

Wetland cities were proposed by the International Wetland Convention Organization for the protection of urban wetlands. Few studies have performed land cover classifications for internationally recognized wetland cities or explored what contribution the classification results can make to the establishment of additional wetland cities to date. Based on Sentinel-1 and 2 data, this study used a 10-fold random forest method to classify the land cover of the first six wetland cities recognized in China. A land cover dataset, which had a resolution of 10 m and included four wetland types, was obtained and the wetland area and protected wetland areas of the six cities were calculated. The results showed that (1) the classification accuracy of six cities was good, the overall accuracy was above 90%, and the Kappa coefficient was above 0.88. (2) Cropland or forested areas were the most common non-wetland land coverage type in wetland cities and accounted for more than 20% or 40% of the land coverages, while water was the most common wetland type and accounted for more than 2% of the land coverages. From 2015 to 2020, the built area in most cities increased, while cropland and forest decreased significantly. (3) The wetland rate was 6.68–37.56% and the wetland protection rate was 49.48–73.74% in the six wetland cities. From 2015 to 2020, the wetland rate of the six cities were relatively stable, and the wetland protection rate of inland cities (Yinchuan, Changde, Harbin and Changshu) increased significantly, while those of coastal cities (Haikou and Dongying) decreased, which might be related to the change in coastline. Therefore, we found that the wetlands in these cities were well protected. Land cover classification for wetland cities can provide a reference for using remote sensing techniques used to monitor internationally wetland cities while also supporting the creation of additional wetland cities.

Applicability of WorldCover in Wind Power Engineering: Application Research of Coupled Wake Model Based on Practical Project

This paper discusses how the incorporation of high-resolution ground coverage dataset ESA WorldCover into a wind flow field and wake simulation calculation, as well as the use of the coupled wake model for wind farm output simulation, can improve the accuracy of wind resource assessment using engineering examples. In the actual case of grid-connected wind farms in central China, SCADA wind speed data is reconstructed to the free flow wind speed in front of the wind turbine impeller using the transfer function of the nacelle, and the wind farm is modeled using OpenWind software, simulating the wind speed at the height of each wind turbine hub and each wind turbine output. The results show that when other initial data are consistent, using ESA’s high-precision land cover dataset WorldCover 10 m to make roughness lengths which improves the wind farm output simulation accuracy by 8.91%, showing that it is worth trying to apply WorldCover 10 m to the wind farm simulation design. At the same time, this case is used to compare and analyze the application of the Eddy-Viscosity wake model and the two coupled wake models based on the Eddy-Viscosity wake model. The results show that the coupled wake model will have higher accuracy than the Deep Array Eddy Viscosity wake model and it is 1.24% more accurate than the Eddy Viscosity wake model, and the ASM Eddy Viscosity wake model is 5.21% more accurate than the Eddy Viscosity wake model.

Spatial and temporal dynamics of cropland in the Sanjiang Plain from 2014 to 2020 based on annual 30 m crop data layers

AbstractThe land cover of the Sanjiang Plain has changed dramatically since the 1950s. Although previous studies have analysed its spatiotemporal dynamics at long time intervals, a near real-time and accurate representation of the interannual evolution of cropping patterns in this region is of far-reaching importance for rationally allocating agricultural resources and ensuring food security. Based on the 30 m and 10 m land cover datasets in 2015 and 2017–2019, the current study used Landsat-8 satellite data in 2014, 2016 and 2020 to identify paddy rice and dryland crops using a decision tree classification approach and constructed the annual cropland datasets of the Sanjiang Plain from 2014 to 2020. The results show that the overall classification accuracies of crop datasets exceeded 95%, and the Kappa coefficients were higher than 0.92. The average annual accuracies of users and producers were 93% and 94% for rice fields and 97% and 95% for dryland crops, respectively. During the 7 years, the total area of paddy fields and dryland crops decreased by 5% and 8%. However, with minor positive and negative variation between years. 24.2% of paddy rice and 42% of dryland crops has been cultivated under 4 years. The centres of gravity for both crops mainly aggregated in the central counties with the migration direction and magnitude varying interannually. The current study emphasizes the importance of establishing annual high-resolution crop datasets to track the detailed spatio-temporal trajectories of cropping patterns that are essential to support sustainable cropland management and agricultural development.

An improved framework for assessing the impact of different urban development strategies on land cover and ecological quality changes -A case study from Nanjing Jiangbei New Area, China

Land cover (LC) change has been highly valued by policy makers for driving the evolution of regional ecological and environmental quality. The core area of Nanjing Jiangbei New Area (NJNA) has undergone the development process from traditional urbanization to new-type urbanization (NTU), however the impacts of different urban development strategies or pathways on the change pace and direction of land cover and ecological quality are not adequately understood in a quantitative manner which is not conducive for similar regions to learn lessons from past development processes. Based on RapidEye, GF-1 and SPOT-6 images acquired in 2009, 2015 and 2021, a Modified Mask-RCNN framework was devised and implemented to create a high accuracy LC dataset first in this analysis. Then, the applicability or efficacy of the Remote Sensing Ecological Index (RSEI) model and the Regional Optimized Remote Sensing Ecological Index (RO-RSEI) model, developed from the Landsat observations was compared in characterizing the ecological quality. Finally, the attribution analysis of spatio-temporal changes in LC and their induced ecological quality evolutions was carried out in conjunction with socio-economic factors. The results showed that the overall accuracies of the LC classifications were estimated at 91.50 % (2009), 91.25 % (2015), and 92.75 % (2021), respectively. The mean values of RO-RSEI analyses were at 0.652, 0.649, and 0.656, respectively, indicating that in the past 12 years, the ecological quality first got degraded then got ameliorated along with the urbanization. The urban green spaces got restored and increased in the NTU process, and protecting the forest and cropland was also reinforced thanks to the strict enforcement of related policies. These positive changes are attributed to the popularization of ecological civilization philosophy and the escalation of social awareness of environmental protection and low carbon development. The proposed framework can provide technical reference for ecological quality monitoring under the progress of NTU.

Continuous Long Time Series Monitoring of Urban Construction Land in Supporting the SDG 11.3.1—A Case Study of Nanning, Guangxi, China

Enhancing the spatio-temporal dynamic monitoring of the construction land of emerging major cities provides the basis for understanding the effects of human activities on the earth’s ecological environment changes, which is regarded as an important way to improve human wellbeing and to achieve the UN SDGs. This paper, which uses Nanning as an example, adopts 30 m annual remote sensing land cover datasets from 1990–2021 to elaborately analyze the temporal evolution and spatial expansion of construction land and to evaluate the sustainable development level based on SDG 11.3.1. The conclusions of this paper are as follows: (1) For Nanning City, during 1990–2021, construction land area increased from 54.77 km2 to 326.33 km2—a nearly five-fold increase. Spreading expansion and finger-like expansion along roads played a leading role during the development of the construction land in Nanning. Liangqing and Yongning are the future directions of urban development. The LCRPGR of Nanning declined with one peak period around 1995, and the LCRPGR was relatively stable with a high intensity of land use. (2) For the other emerging major cities, continuous long duration data are more suitable for urban construction land monitoring compared with traditional sparse time-series monitoring. The rich information derived from continuous long duration data can help decision makers to formulate and implement more comprehensive measures. The research paradigm adopted in this study can be applied in other cities. The newly developed urban districts will have foreseeable high sustainable development risks, and urban development strategies at the international, national, and urban levels could reduce those risks and promote the realization of UN SDGs from different angles and with different intensities.

Research on land cover type classification method based on improved MaskFormer for remote sensing images.

High-resolution remote sensing images have the characteristics of wide imaging coverage, rich spectral information and unobstructed by terrain and features. All of them provide convenient conditions for people to study land cover types. However, most existing remote sensing image land cover datasets are only labeled with some remote sensing images of low elevation plain areas, which is highly different from the topography and landscape of highland mountainous areas. In this study, we construct a Qilian County grassland ecological element dataset to provide data support for highland ecological protection. To highlight the characteristics of vegetation, our dataset only includes the RGB spectrum fused with the near-infrared spectrum. We then propose a segmentation network, namely, the Shunted-MaskFormer network, by using a mask-based classification method, a multi-scale, high-efficiency feature extraction module and a data-dependent upsampling method. The extraction of grassland land types from 2 m resolution remote sensing images in Qilian County was completed, and the generalization ability of the model on a small Gaofen Image Dataset (GID) verified. Results: (1) The MIoU of the optimised network model in the Qilian grassland dataset reached 80.75%, which is 2.37% higher compared to the suboptimal results; (2) the optimized network model achieves better segmentation results even for small sample classes in data sets with unbalanced sample distribution; (3) the highest MIOU of 72.3% is achieved in the GID dataset of open remote sensing images containing five categories; (4) the size of the optimized model is only one-third of the sub-optimal model.

A Method to Improve Land Use Representation for Weather Simulations Based on High‐Resolution Data Sets—Application to Corine Land Cover Data in the WRF Model

AbstractLand cover (LC) data incorporation, for weather modeling purposes, highlights many problems. The straightforward Single Level Mode (SLM) aggregation is not adapted for high‐resolution LC maps, with a high number of classes, because it could generate false classifications. We propose a Multi‐Level Mode (MLM) aggregation method that includes a hierarchical structure. This study focuses on the Corine Land Cover (CLC) data set. Differences between MLM and SLM methods are small at the finest horizontal resolution and increase to a value of around 16% at 9‐km horizontal resolution. To further integrate CLC data into WRF (Weather Research Forecasting model), we included a dedicated table of physical parameters next to using the classical conversion toward the USGS one. To evaluate the LC impact on the modeled boundary layer, we used WRF at 1 km to simulate a 4‐day period with diurnal cycles of valley winds in the heterogeneous western pre‐Alps area. We tested three LCs (USGS, MODIS, and CLC), where CLC has two physical parameter tables and two aggregation methods. CLC performs better than other tested LCs. The CLC aggregation methods revealed limited differences between the simulated variables, although the MLM method gives better results. Since these comparisons are restricted to a single location with the same LC type, the differences between various simulations regarding atmospheric parameters probably result from horizontal advection from upwind areas where surface conditions differ. Extended time series with multiple locations and diverse meteorological conditions need to be considered to reinforce the results presented here.

Anthropogenic impacts on tidal creek sedimentation since 1900.

Land cover and use around the margins of estuaries has shifted since 1950 at many sites in North America due to development pressures from higher population densities. Small coastal watersheds are ubiquitous along estuarine margins and most of this coastal land-cover change occurred in these tidal creek watersheds. A change in land cover could modify the contribution of sediments from tidal creek watersheds to downstream areas and affect estuarine habitats that rely on sediments to persist or are adversely impacted by sediment loading. The resilience of wetlands to accelerating relative sea-level rise depends, in part, on the supply of lithogenic sediment to support accretion and maintain elevation; however, subtidal habitats such as oyster reefs and seagrass beds are stressed under conditions of high turbidity and sedimentation. Here we compare sediment accumulation rates before and after 1950 using 210Pb in 12 tidal creeks across two distinct regions in North Carolina, one region of low relief tidal-creek watersheds where land cover change since 1959 was dominated by fluctuations in forest, silviculture, and agriculture, and another region of relatively high relief tidal-creek watersheds where land-use change was dominated by increasing suburban development. At eight of the creeks, mass accumulation rates (g cm-2 y-1) measured at the outlet of the creeks increased contemporaneously with the largest shift in land cover, within the resolution of the land-cover data set (~5-years). All but two creek sites experienced a doubling or more in sediment accumulation rates (cm yr-1) after 1950 and most sites experienced sediment accumulation rates that exceeded the rate of local relative sea-level rise, suggesting that there is an excess of sediment being delivered to these tidal creeks and that they may slowly be infilling. After 1950, land cover within one creek watershed changed little, as did mass accumulation rates at the coring location, and another creek coring site did not record an increase in mass accumulation rates at the creek outlet despite a massive increase in development in the watershed that included the construction of retention ponds. These abundant tidal-creek watersheds have little relief, area, and flow, but they are impacted by changes in land cover more, in terms of percent area, than their larger riverine counterparts, and down-stream areas are highly connected to their associated watersheds. This work expands the scientific understanding of connectivity between lower coastal plain watersheds and estuaries and provides important information for coastal zone managers seeking to balance development pressures and environmental protections.