Land Cover Dataset Research Articles

Impact of armed conflict on land use and land cover changes in global border areas

AbstractNational borderlands as the spatial carrier and forefront for exerting geopolinomical influence and implementing geopolinomical strategy, most have the same or similar eco‐geographical structure characteristics, such as land cover. However, there are different development trends in different national relationships (e.g., cooperation and conflict), and land use and land cover changes (LUCC), especially in apparent in border areas. In general, armed conflict in border areas is accompanied by severe, immediate and long‐lasting LUCC‐like forest loss. Here, by means of geospatial analysis, the Uppsala Conflict Data Program and Climate Change Initiative Land Cover dataset were used to investigate the linkages between the armed conflict and LUCC or the patterns and processes of LUCC before, during and after armed conflict around the globe in borderlands from 1992 to 2020. The main and key insights are: (1) nearly 50% of global armed conflict has occurred and re‐occurred in these borderlands since 1992, leading to about 16.5% of LUCC globally; (2) the impact of armed conflict on LUUC is hysteretic, based on the intensity of conflict, especially in borderlands; (3) the transfer rate of land use is high during the conflict and tends to be stable in the post‐conflict period; (4) the absolute amount of armed conflict damage to forest land is large, but the changes rate of impervious surfaces is far more than the former, nearly 18 times greater. These findings improve the understanding of the impact of armed conflict on LUCC, in border areas. This study could provide a proxy and benchmark for exploring the cause‐effect and impact‐response between geopolinomical relations and the borderlands LUCC.

Natural climate solutions in Indonesia: wetlands are the key to achieve Indonesia’s national climate commitment

Indonesia offers a dramatic opportunity to contribute to tackling climate change by deploying natural climate solutions (NCS), increasing carbon sequestration and storage through the protection, improved management, and restoration of drylands, peatlands, and mangrove ecosystems. Here, we estimate Indonesia’s NCS mitigation opportunity for the first time using national datasets. We calculated the maximum NCS mitigation potential extent using datasets of annual national land cover, peat soil, and critical lands. We collated a national emissions factor database for each pathway, calculated from a meta-analysis, recent publications from our team, and available literature. The maximum NCS mitigation potential in 2030 is 1.3 ± 0.04 GtCO2e yr−1, based on the historical baseline period from 2009–2019. This maximum NCS potential is double Indonesia’s nationally determined contribution (NDC) target from the forestry and other land use sector. Of this potential opportunity, 77% comes from wetland ecosystems. Peatlands have the largest NCS mitigation potential (960 ± 15.4 MtCO2e yr−1 or 71.5 MgCO2e ha−1 yr−1) among all other ecosystems. Mangroves provide a smaller total potential (41.1 ± 1.4 MtCO2e yr−1) but have a much higher mitigation density (12.2 MgCO2e ha−1 yr−1) compared to dryland ecosystems (2.9 MgCO2e ha−1 yr−1). Therefore, protecting, managing, and restoring Indonesia’s wetlands is key to achieving the country’s emissions reduction target by 2030. The results of this study can be used to inform conservation programs and national climate policy to prioritize wetlands and other land sector initiatives to fulfill Indonesia’s NDC by 2030, while simultaneously providing additional co-benefits and contributing to COVID-19 recovery and economic sustainability.

Global‐Scale Shifts in Rooting Depths Due To Anthropocene Land Cover Changes Pose Unexamined Consequences for Critical Zone Functioning

AbstractRooting depth is an ecosystem trait that determines the extent of soil development and carbon (C) and water cycling. Recent hypotheses propose that human‐induced changes to Earth's biogeochemical cycles propagate deeply into Earth's subsurface due to rooting depth changes from agricultural and climate‐induced land cover changes. Yet, the lack of a global‐scale quantification of rooting depth responses to human activity limits knowledge of hydrosphere‐atmosphere‐lithosphere feedbacks in the Anthropocene. Here we use land cover data sets to demonstrate that root depth distributions are changing globally as a consequence of agricultural expansion truncating depths above which 99% of root biomass occurs (D99) by ∼60 cm, and woody encroachment linked to anthropogenic climate change extending D99 in other regions by ∼38 cm. The net result of these two opposing drivers is a global reduction of D99 by 5%, or ∼8 cm, representing a loss of ∼11,600 km3 of rooted volume. Projected land cover scenarios in 2100 suggest additional future D99 shallowing of up to 30 cm, generating further losses of rooted volume of ∼43,500 km3, values exceeding root losses experienced to date and suggesting that the pace of root shallowing will quicken in the coming century. Losses of Earth's deepest roots—soil‐forming agents—suggest unanticipated changes in fluxes of water, solutes, and C. Two important messages emerge from our analyses: dynamic, human‐modified root distributions should be incorporated into earth systems models, and a significant gap in deep root research inhibits accurate projections of future root distributions and their biogeochemical consequences.

Urban green space and albedo impacts on surface temperature across seven United States cities

Extreme heat represents a growing threat to public health, especially across the densely populated, developed landscape of cities. Climate adaptation strategies that aim to manage urban microclimates through purposeful design can reduce the heat exposure of urban populations, however, it is unclear how the temperature impacts of urban green space and albedo vary across cities and background climate. This study quantifies the sensitivity of surface temperature to landcover characteristics tied to two widely used climate adaptation strategies, urban greening and albedo manipulation (e.g. white roofs), by combining long-term remote sensing observations of land surface temperature, albedo, and moisture with high-resolution landcover datasets in a spatial regression analysis at the census block scale across seven United States cities. We find tree cover to have an average cooling impact of −0.089 K per % cover, which is approximately four times stronger than the average grass cover cooling impact of −0.021 K per % cover. Variability in the magnitude of grass cover cooling impacts was primarily a function of vegetation moisture content, with the Land Surface Water Index (LSWI) explaining 89 % of the variability in grass cover cooling impacts across cities. Variability in tree cover cooling impacts was primarily a function of sunlight and vegetation moisture content, with solar irradiance and LSWI explaining 97 % of the cooling variability across cities. Albedo cooling impacts were consistent across cities with an average cooling impact of −0.187 K per increase of 0.01. While these interventions are broadly effective across cities, there are critical regional trade-offs between vegetation cooling efficiency, irrigation requirements, and the temporal duration and evolution of the cooling benefits. In warm, arid cities, high albedo surfaces offer multifaceted benefits such as cooling and water conservation, whereas temperate, mesic cities likely benefit from a combination of strategies, with greening efforts targeting highly paved neighborhoods.

The Impact of Land Cover on Selected Water Quality Parameters in Polish Lowland Streams during the Non-Vegetative Period

The search for the best landscape predictors explaining the spatial variability of stream water chemistry is one of the most important and recent research issues. Thus, in the current study, relationships between land cover indices and selected water quality parameters were evaluated regarding the example of 54 lowland temperate streams located in central Poland. From November 2021 to March 2022, water samples were collected in the monthly timescale, and the concentrations of NH4+, NO3−, and NO2−, as well as electrical conductivity, were correlated with the percentage of land cover types calculated for total catchment area, buffer zones, cut buffer zones, and radius. For such computing, Corine Land Cover 2018 and Sentinel 2 Global Land Cover datasets were used. In the case of both datasets, results indicate significant dependence of NO3−, and NO2− concentrations, as well as EC values on cover metrics. Overall, agricultural lands favored higher concentrations of NO3− and NO2−, whereas mainly coniferous forests reduced nitrogen pollution. Significant correlations were not documented in the case of NH4+ ions, the concentrations of which could be linked to point sources from municipal activity. Correlation performance was slightly better in the case of the S2GLC dataset, while the best spatial scales were generally seen for wider buffer zones (250 and 500 m) and total catchment area. The study provided spatially extensive insight into the impact of land cover predictors at different scales on nitrogen compounds in a lowland landscape.

Deploying the Total Operating Characteristic to Assess the Relationship between Land Cover Change and Land Surface Temperature in Abeokuta South, Nigeria

Urbanization affects land cover and a region’s prevailing land surface temperature (LST). As a result, understanding the effects of urbanization on LST and land cover change is critical for effectively planning, managing, and monitoring urban development and undesired LST change. This paper, therefore, examines the relationship between the change in four land cover categories and LST during 1987–2004 and 2004–2021. Our approach uses the Total Operating Characteristic (TOC) to study the relationship between LST change and the losses and gains in four land cover categories: infrastructure, vegetation, water, and bare land in Abeokuta South, Nigeria. We derived the land cover and LST dataset from satellite imagery at time points 1987, 2004, and 2021. Our results show that most of the vegetation in the study area transitions to bare land and infrastructure during both time intervals, while most of the bare areas transition to infrastructure and vegetation. Furthermore, the TOC analysis shows vegetation loss, gain in infrastructure, and bare land occurs more intensively at segments between increased thresholds of LST values during both time intervals. Conversely, vegetation gain, infrastructure, and bare land loss occur more intensely at segments between decreased LST values. The methods discussed herein can reveal important insights and stimulate the needed conversation concerning the effective planning, managing, and monitoring of urban development and undesired LST change.

Discretization of the Urban and Non-Urban Shape: Unsupervised Machine Learning Techniques for Territorial Planning

One of the goals of the scientific community is to equip the discipline of spatial planning with efficient tools to handle huge amounts of data. In this sense, unsupervised machine learning techniques (UMLT) can help overcome this obstacle to further the study of spatial dynamics. New machine-learning-based technologies make it possible to simulate the development of urban spatial dynamics and how they may interact with ecosystem services provided by nature. Modeling information derived from various land cover datasets, satellite earth observation and open resources such as Volunteered Geographic Information (VGI) represent a key structural step for geospatial support for land use planning. Sustainability is certainly one of the paradigms on which planning and the study of past, present and future spatial dynamics must be based. Topics such as Urban Ecosystem Services have assumed such importance that they have become a prerogative on which to guide the administration in the difficult process of transformation, taking place not only in the urban context, but also in the peri-urban one. In this paper, we present an approach aimed at analyzing the performance of clustering methods to define a standardized system for spatial planning analysis and the study of associated dynamics. The methodology built ad hoc in this research was tested in the spatial context of the city of L’Aquila (Abruzzo, Italy) to identify the urbanized and non-urbanized area with a standardized and automatic method.

A Land Cover Background-Adaptive Framework for Large-Scale Road Extraction

Background: Road network data are crucial in various applications, such as emergency response, urban planning, and transportation management. The recent application of deep neural networks has significantly boosted the efficiency and accuracy of road network extraction based on remote sensing data. However, most existing methods for road extraction were designed at local or regional scales. Automatic extraction of large-scale road datasets from satellite images remains challenging due to the complex background around the roads, especially the complicated land cover types. To tackle this issue, this paper proposes a land cover background-adaptive framework for large-scale road extraction. Method: A large number of sample image blocks (6820) are selected from six different countries of a wide region as the dataset. OpenStreetMap (OSM) is automatically converted to the ground truth of networks, and Esri 2020 Land Cover Dataset is taken as the background land cover information. A fuzzy C-means clustering algorithm is first applied to cluster the sample images according to the proportion of certain land use types that obviously negatively affect road extraction performance. Then, the specific model is trained on the images clustered as abundant with that certain land use type, while a general model is trained based on the rest of the images. Finally, the road extraction results obtained by those general and specific modes are combined. Results: The dataset selection and algorithm implementation were conducted on the cloud-based geoinformation platform Google Earth Engine (GEE) and Google Colaboratory. Experimental results showed that the proposed framework achieved stronger adaptivity on large-scale road extraction in both visual and statistical analysis. The C-means clustering algorithm applied in this study outperformed other hard clustering algorithms. Significance: The promising potential of the proposed background-adaptive network was demonstrated in the automatic extraction of large-scale road networks from satellite images as well as other object detection tasks. This search demonstrated a new paradigm for the study of large-scale remote sensing applications based on deep neural networks.

Global spatial distribution of vegetation and 20-years dynamic changes

Global spatial distribution of vegetation is determined jointly by climate, monsoon, ocean current and human activities. In recent decades, surface vegetation changes caused by global warming, extreme climate events and intensified human activities need a further understood. In this paper, we adopted available MODIS land cover dataset (MCD12Q1) to investigate the spatial distribution feature of global vegetation sand dynamics during the past 20 years. Results show that: (1) the spatial distribution pattern of global vegetation formed by the long-term ecosystem evolution exhibits stable with less variation in both latitude and vertical dimensions. Generally, the percent of forest, shrubland, grass and cropland respectively are 15.27%, 9.39%, 39.46% and 8.91% of surface covers, with a distinct land cover transition trend from rainforest at equator region to moss and lichen at the north and south pole. (2) In the past 20 years, the global forest land decreased by 3.0×105 km2, with an average annual decrease of 1.255%, open shrubs experienced slight fluctuations in 2001-2017 and increased sharply by 1.6×105 km2 in 2017-2018. And the grassland, croplands and cropland/natural vegetation mosaics had different degrees of growth rate, with an average annual dynamic increase of 0.021%, 0.019% and 0.502%, respectively. (3) There are about 4.2×106 km2 of forest changed into grassland in West Siberia and the Amazon, and 2.5×106 km2 of grassland into shrubs, as well as 1.9×106 km2 of grassland vegetation into farmland, and 9.4×104 km2 of forest into shrubs.

A Hybrid Classification of Imbalanced Hyperspectral Images Using ADASYN and Enhanced Deep Subsampled Multi-Grained Cascaded Forest

Hyperspectral image (HSI) analysis generally suffers from issues such as high dimensionality, imbalanced sample sets for different classes, and the choice of classifiers for artificially balanced datasets. The existing conventional data imbalance removal techniques and forest classifiers lack a more efficient approach to dealing with the aforementioned issues. In this study, we propose a novel hybrid methodology ADASYN-enhanced subsampled multi-grained cascade forest (ADA-Es-gcForest) which comprises four folds: First, we extracted the most discriminative global spectral features by reducing the vast dimensions, i.e., the redundant bands using principal component analysis (PCA). Second, we applied the subsampling-based adaptive synthetic minority oversampling method (ADASYN) to augment and balance the dataset. Third, we used the subsampled multi-grained scanning (Mg-sc) to extract the minute local spatial–spectral features by adaptively creating windows of various sizes. Here, we used two different forests—a random forest (RF) and a complete random forest (CRF)—to generate the input joint-feature vectors of different dimensions. Finally, for classification, we used the enhanced deep cascaded forest (CF) that improvised in the dimension reduction of the feature vectors and increased the connectivity of the information exchange between the forests at the different levels, which elevated the classifier model’s accuracy in predicting the exact class labels. Furthermore, the experiments were accomplished by collecting the three most appropriate, publicly available his landcover datasets—the Indian Pines (IP), Salinas Valley (SV), and Pavia University (PU). The proposed method achieved 91.47%, 98.76%, and 94.19% average accuracy scores for IP, SV, and PU datasets. The validity of the proposed methodology was testified against the contemporary state-of-the-art eminent tree-based ensembled methods, namely, RF, rotation forest (RoF), bagging, AdaBoost, extreme gradient boost, and deep multi-grained cascade forest (DgcForest), by simulating it numerically. Our proposed model achieved correspondingly higher accuracies than those classifiers taken for comparison for all the HS datasets.

Geospatial application on mapping groundwater recharge zones in Makutupora basin, Tanzania

Management of groundwater systems is indispensable to countries that depend on groundwater as the primary source of community water supply (e.g. Dodoma, Tanzania). Urbanization and industrialization lead to groundwater over-pumping and reduced recharge zones in the basin. This study used Remote Sensing and geospatial datasets to determine the groundwater recharge zones (GWRZ) followed by sensitivity analysis to identify the influence of geologic and hydrologic factors on the variation of the GWRZ in the case of the Makutupora basin, Tanzania. The implementation of weighted overlay analysis aimed to determine the GWRZ using different thematic maps created from land use land cover (LULC), drainage density, lithology, lineament density, rainfall, slope and soil datasets. The analytical hierarchy process (AHP) and multi-influencing factor (MIF) are the multi-criteria decision analysis (MCDA) implemented to assign weights to the selected influencing factors. Either, the map removal method was implemented for the sensitivity analysis. Pumping wells were overlaid to validate the GWRZ map determined. The overlay of seven thematic maps resulted in the GWRZ map being categorized as good (35.79% for AHP and 21.68% for MIF), moderate (40.98% for AHP and 58.39% for MIF) and poor (23.22% for AHP and 19.95% for MIF). Good recharge potential areas lie in an area characterized by thick forest, high lineament and water bodies around the northwestern and central-eastern side of the basin. Validation of GWRZ indicated that 33.33% for AHP and 30% for MIF are in good GWRZ, 41.6% for AHP and 28% for MIF are in moderate GWRZ and 25% for AHP and 42% for MIF are in poor GWRZ. The sensitivity analysis revealed the high effect of GWRZ on the removal of the LULC, lithology and lineament thematic layer in both AHP and MIF-generated GWRZ maps. This implies that the expansion of settlements is not considering recharge zone protection. Lineaments are also a very important factor governing groundwater recharge which needs to be protected. The result displays that urbanization dramatically reduced the potential area for groundwater recharge. Protecting the potential recharge zone from any activity that reduces the recharge is vital for the sustainability of groundwater.

CatLC: Catalonia Multiresolution Land Cover Dataset

The availability of large annotated image datasets represented one of the tipping points in the progress of object recognition in the realm of natural images, but other important visual spaces are still lacking this asset. In the case of remote sensing, only a few richly annotated datasets covering small areas are available. In this paper, we present the Catalonia Multiresolution Land Cover Dataset (CatLC), a remote sensing dataset corresponding to a mid-size geographical area which has been carefully annotated with a large variety of land cover classes. The dataset includes pre-processed images from the Cartographic and Geological Institute of Catalonia (ICGC) (https://www.icgc.cat/en/Downloads) and the European Space Agency (ESA) (https://scihub.copernicus.eu) catalogs, captured from both aircraft and satellites. Detailed topographic layers inferred from other sensors are also included. CatLC is a multiresolution, multimodal, multitemporal dataset, that can be readily used by the machine learning community to explore new classification techniques for land cover mapping in different scenarios such as area estimation in forest inventories, hydrologic studies involving microclimatic variables or geologic hazards identification and assessment. Moreover, remote sensing data present some specific characteristics that are not shared by natural images and that have been seldom explored. In this vein, CatLC dataset aims to engage with computer vision experts interested in remote sensing and also stimulate new research and development in the field of machine learning.

Detection of land use / cover changes of the KOSH region over a period of 14 years using the South African National Land Cover datasets for 2000 and 2014

Simple algebraic change detection techniques viz. image difference and image ratio were applied to the South African national land use / cover (NLC) datasets of years 2000 and 2014, prepared in grid format covering the Klerksdorp–Orkney–Stilfontein–Hartebeestfontein (KOSH) region in order to assess land use/land cover changes. Both the 2000 and 2014 NLC datasets were generated from Landsat images using different classification schemes and the code values & attributes of the land cover classes of the two datasets were different/not comparable. In order to make these datasets comparable for change detection, the NLC2000 dataset was examined in ArcView GIS by superimposing it onto the NLC2014 dataset and similarities and differences were identified. For each cover type of the NLC2000 dataset, comparable cover type of the 2014 dataset was identified by making a query to the NLC2000 dataset and after viewing the spatial distributions of selected units in respect of the NLC2014 dataset. Suitable code values of NLC2014 dataset were identified for the NLC2000 dataset and it was later reclassified. The land use / cover change detection study reveals that increase in areas were observed for the cover types: Cultivated common fields (low), Cultivated common fields (med), Mines 2 semi-bare, Wetlands, Urban commercial and Plantations/woodlots mature. The Grassland, Thicket/dense bush, Urban residential (dense trees/bush), Mines 1 bare, and Cultivated common pivots (high) showed a decrease in places. During the 14 years, Grassland had decreased from 2,132.47 km2 (77.35% of the total area) to 1,629.78 km2 (59.11% of the total area) owing to landscape transformation to other land covers (e.g. Cultivated common fields and Urban residential) due to human activities. The percentage increase in areas observed for the Cultivated common fields (low and medium) were 8.21% and 2.96% while the Mines 2 semi-bare, Wetlands, Urban commercial, Plantations/woodlots mature showed increases of 0.67%, 0.32%, 0.28% and 0.23% respectively. The area of Thicket/dense bush decreased from 108.15 km2 to 56.71 km2 (change of 1.87%). Maps of land use/land cover changes and statistics obtained for the changed areas are very useful for identifying various changes occurring in different classes and for monitoring land use dynamics.

The South African land cover change detection derived from 2013_2014 and 2017_2018 land cover products

The appetite for up-to-date information about the earth’s surface is ever increasing, as such information provides a basis for a large number of applications. These include the earth’s resource detection and evaluation, land cover and land use change monitoring together with other vast environmental studies such as climate change assessment. Due to the advantages of repetitive data acquisition, the synoptic view, together with the varied spatial resolution it provides, and its available historically achieved dataset, remote sensing earth observation has become the major preferred data source for various earth studies. This study assesses land cover change detection of the land cover products (2013_2014 and 2017_2018) derived from earth observation.There are vast number of change detection methodologies and techniques with some still emerging. This study embarked on post classification change detection methodology which entailed morphological and spectral filtering techniques. The 10 land cover classes that were assessed for change detection are: natural wooded land, shrubland, grassland, waterbodies, wetlands, barren lands, cultivated, built-up, planted forest together with mines and quarries. The change detection accuracy result was 74.97%. Through the likelihood analysis, the likelihood for change to occur (e.g. cultivated to grassland) and unlikelihood of change to occur (e.g. built-up to planted forest), resulted in 72.2% areas of potential realistic change.The change detection results, further depend on the quality, compatibility and accuracy of the input land cover datasets. The application of different ancillary data together with different modelling techniques for land cover classification also affect the true reflectance of land cover change detection. Therefore extra caution should be exercised when analysing change detection so as to provide true and reliable changes.

A high spatial resolution soil carbon and nitrogen dataset for the northern permafrost region based on circumpolar land cover upscaling

Abstract. Soils in the northern high latitudes are a key component in the global carbon cycle; the northern permafrost region covers 22 % of the Northern Hemisphere land surface area and holds almost twice as much carbon as the atmosphere. Permafrost soil organic matter stocks represent an enormous long-term carbon sink which is in risk of switching to a net source in the future. Detailed knowledge about the quantity and the mechanisms controlling organic carbon storage is of utmost importance for our understanding of potential impacts of and feedbacks on climate change. Here we present a geospatial dataset of physical and chemical soil properties calculated from 651 soil pedons encompassing more than 6500 samples from 16 different study areas across the northern permafrost region. The aim of our dataset is to provide a basis to describe spatial patterns in soil properties, including quantifying carbon and nitrogen stocks. There is a particular need for spatially distributed datasets of soil properties, including vertical and horizontal distribution patterns, for modeling at local, regional, or global scales. This paper presents this dataset, describes in detail soil sampling; laboratory analysis, and derived soil geochemical parameters; calculations; and data clustering. Moreover, we use this dataset to estimate soil organic carbon and total nitrogen storage estimates in soils in the northern circumpolar permafrost region (17.9×106 km2) using the European Space Agency's (ESA's) Climate Change Initiative (CCI) global land cover dataset at 300 m pixel resolution. We estimate organic carbon and total nitrogen stocks on a circumpolar scale (excluding Tibet) for the 0–100 and 0–300 cm soil depth to be 380 and 813 Pg for carbon, and 21 and 55 Pg for nitrogen, respectively. Our organic carbon estimates agree with previous studies, with most recent estimates of 1000 Pg (−170 to +186 Pg) to 300 cm depth. Two separate datasets are freely available on the Bolin Centre Database repository (https://doi.org/10.17043/palmtag-2022-pedon-1, Palmtag et al., 2022a; and https://doi.org/10.17043/palmtag-2022-spatial-1, Palmtag et al., 2002b).

Hyperspectral Image Classification Based on Novel Hybridization of Spatial-Spectral-Superpixelwise Principal Component Analysis and Dense 2D-3D Convolutional Neural Network Fusion Architecture

We propose a hybridized technique named Spatial-Spectral-Superpixelwise PCA-based Dense 2D-3D CNN Fusion Architecture (3SPCA-D-2D-3D-CNN), that deals with the detailed and complex study of dimensionality reduction and classification of Hyperspectal images (HSI). Our work is 2-fold: At first (1), 3SPCA is applied on raw HSI that adopts superpixels-based local reconstruction to filter the images, whereas PCA-based supplementary global features acquire the relevant and low-dimensional local features. Every HSI pixel is reconstituted by the pixels of its closest neighbors in the same superpixel block to reduce noise and improve spatial information. Next, PCA is conducted on every zone and the full HSI to get local and global features. The local-global and spatial-spectral properties are then concatenated. Secondly (2), the D-2D-3D-CNN fusion architecture is made up of three 3D convolution blocks, two 2D convolution blocks with varied kernel sizes and filters, and four fully connected (FC) dense layers, totaling nine distinguishing and information-enriched features. These features can generate precise class labels and apply them to the appropriate landcovers. The proposed method has been applied to three publicly available HSI landcover datasets, the Indian Pines, the Salinas Valley, and the Pavia University. It achieved respectively 98.33%, 99.99%, and 98.73% average accuracy scores. Due to its improved Feature Extraction capacity from a limited number of training samples and its classification performance with fewer epochs, this method outperforms other relevant state-of-the-art CNN-based methods.

Temporal and spatial differentiation characteristics of ecosystem service values based on the ecogeographical division of China: a case study in the Yellow River Basin, China.

The identification of spatiotemporal changes in ecosystem service values (ESVs) and their drivers is the basis for ecosystem service administration and decision-making. This research focuses on the Yellow River Basin (YRB). With a multitemporal land use and land cover (LULC) dataset (1995-2018), the equivalence coefficient method with spatiotemporal dynamic correction and exploratory spatial data analysis methods were used to evaluate ESV changes due to LULC changes and their spatial characteristics. The contributions of the ESV driving factors and their mutual effects were also investigated via geographic detectors. The results revealed that (1) the land use structure of the YRB, mainly grassland and cultivated land, was stable from 1995 to 2018. However, the transition between land use types was dramatic, including urban expansion accompanied by losses of farmland, grassland, and unused land; increased forestland; and significant increases in water bodies and wetland areas. (2) During the study period, the overall ESV of the YRB increased, and hydrological regulation and climate regulation services dominated the change in the ESVs in the study area. The ESV exhibited obvious ecogeographical pattern differentiation and evident positive spatial autocorrelation. High values were concentrated in the southern part of the study area, including the southeastern part of the Qinghai-Tibet Plateau region and the central part of the East Asian monsoon region. Low values were concentrated in the northwestern arid zone, dominated by desert and grassland ecosystems. (3) Because of the fragility of the regional ecological background, the spatial differentiation of the ESVs in the YRB is dependent on natural factors; however, anthropogenic factors such as the degree of land use and the human activity intensity also lead to ESV differentiation. The synergistic effects of human activities, landscape pattern changes, and natural factors result in the spatial differentiation of the ESVs in the research region. Therefore, human activities affecting the ecological environment should be controlled, nature-based solutions should be advocated, patch diversity should be increased, landscape fragmentation should be reduced, LULC ecosystem service functions should be improved, and the relationship among economic, social, and ecological landscape resources should be coordinated.

Long-Term Changes of Land Use and Land Cover in the Yangtze River Basin from 1990–2020 Landsat Data

Economic development and climate change drive the land use and land cover (LULC) change globally. Annual robust maps of LULC are critical for studying climate change and land–climate interaction. However, the current existing methods for optimizing and expanding the publicly available China land cover data set (CLCD) are limited. In this article, 30-m annual LULC changes are obtained from 1990 to 2020 in the Yangtze River basin (YRB). The results show an overall accuracy rate of 82.66% and better performances on Geo-Wiki test samples when compared to similar products. Based on our 30-m annual LULC data set, the drastic LULC changes are found in YRB over a 30-year period, where impervious surface area more than tripled, cropland area decreased by 6.12%, and water area decreased by 6.09%. In addition, through the geographically and temporally weighted regression method, a fitting model with a goodness of fit of 0.91 well reveals that human activity plays a driving role in the LULC change of YRB.

From cropland to cropped field: A robust algorithm for national-scale mapping by fusing time series of Sentinel-1 and Sentinel-2

• Automatic method developed for mapping actively cropped fields without regional adjustments. • Combined use of Sentinel-1 and Sentinel-2 increases mapping accuracy. • High performances in correctly labelling sparse crops and separating grass from cropped fields. • The first 20-m national-scale map of cropped fields and abandoned cropland generated in China. • Around 77% cropland are cropped with field crops in China at national scale. Detailed and updated maps of actively cropped fields on a national scale are vital for global food security. Unfortunately, this information is not provided in existing land cover datasets, especially lacking in smallholder farmer systems. Mapping national-scale cropped fields remains challenging due to the spectral confusion with abandoned vegetated land, and their high heterogeneity over large areas. This study proposed a large-area mapping framework for automatically identifying actively cropped fields by fusing Vegetation-Soil-Pigment indices and Synthetic-aperture radar (SAR) time-series images (VSPS). Three temporal indicators were proposed and highlighted cropped fields by consistently higher values due to cropping activities. The proposed VSPS algorithm was exploited for national-scale mapping in China without regional adjustments using Sentinel-2 and Sentinel-1 images. Agriculture in China illustrated great heterogeneity and has experienced tremendous changes such as non-grain orientation and cropland abandonment. Yet, little is known about the locations and extents of cropped fields cultivated with field crops on a national scale. Here, we produced the first national-scale 20 m updated map of cropped and fallow/abandoned land in China and found that 77 % of national cropland (151.23 million hectares) was actively cropped in 2020. We found that fallow/abandoned cropland in mountainous and hilly regions were far more than we expected, which was significantly underestimated by the commonly applied VImax-based approach based on the MODIS images. The VSPS method illustrates robust generalization capabilities, which obtained an overall accuracy of 94 % based on 4,934 widely spread reference sites. The proposed mapping framework is capable of detecting cropped fields with a full consideration of a high diversity of cropping systems and complexity of fallow/abandoned cropland. The processing codes on Google Earth Engine were provided and hoped to stimulate operational agricultural mapping on cropped fields with finer resolution from the national to the global scale.

Evaluation of MODIS, Climate Change Initiative, and CORINE Land Cover Products Based on a Ground Truth Dataset in a Mediterranean Landscape

Land cover can reflect global environmental changes if their associated transitions are quantitatively and correctly analysed, thus helping to assess the drivers and impacts of climate change and other applied research studies. It is highly important to acquire accurate spatial land cover information to perform multidisciplinary analyses. This work aims at estimating the accuracy of three widely used land cover products, the Moderate Resolution Imaging Spectroradiometer (MODIS) land cover product (MCD12Q1), the European Space Agency Climate Change Initiative land cover (ESA-CCI-LC), and the EU CORINE land cover (CLC), all for the reference year of 2018, by comparing them against a fine resolution land cover dataset created for this study with combined ground surveys and high-resolution Large Scale Orthophotography (LSO 25/2015). Initially, the four datasets had their land cover classes harmonized and all were resampled to the same spatial resolution. The accuracy metrics used to conduct the comparisons were Overall Accuracy, Producer’s Accuracy, User’s Accuracy, and the Kappa Coefficient. Comparisons with the reference dataset revealed an underestimation of the forested areas class in all three compared products. Further analysis showed that the accuracy metrics were reasonably high for the broad classes (forest vs. non-forest), with an overall accuracy exceeding 70% in all examined products. On the contrary, in the detailed classification (total land cover mapping), the comparison of the reference dataset with the three land cover products highlighted specific weaknesses in the classification results of the three products, showing that CLC depicted more precisely the landscape characteristics than the two other products, since it demonstrated the highest overall accuracy (37.47%), while MODIS and ESA-CCI-LC revealed a percentage that did not exceed 22%.