Land Cover Dataset Research Articles

Comparing NISAR (Using Sentinel-1), USDA/NASS CDL, and Ground Truth Crop/Non-Crop Areas in an Urban Agricultural Region.

A general limitation in assessing the accuracy of land cover mapping is the availability of ground truth data. At sites where ground truth is not available, potentially inaccurate proxy datasets are used for sub-field-scale resolution investigations at large spatial scales, i.e., in the Contiguous United States. The USDA/NASS Cropland Data Layer (CDL) is a popular agricultural land cover dataset due to its high accuracy (>80%), resolution (30 m), and inclusions of many land cover and crop types. However, because the CDL is derived from satellite imagery and has resulting uncertainties, comparisons to available in situ data are necessary for verifying classification performance. This study compares the cropland mapping accuracies (crop/non-crop) of an optical approach (CDL) and the radar-based crop area (CA) approach used for the upcoming NASA-ISRO Synthetic Aperture Radar (NISAR) L- and S-band mission but using Sentinel-1 C-band data. CDL and CA performance are compared to ground truth data that includes 54 agricultural production and research fields located at USDA's Beltsville Agricultural Research Center (BARC) in Maryland, USA. We also evaluate non-crop mapping accuracy using twenty-six built-up and thirteen forest sites at BARC. The results show that the CDL and CA have a good pixel-wise agreement with one another (87%). However, the CA is notably more accurate compared to ground truth data than the CDL. The 2017-2021 mean accuracies for the CDL and CA, respectively, are 77% and 96% for crop, 100% and 94% for built-up, and 100% and 100% for forest, yielding an overall accuracy of 86% for the CDL and 96% for CA. This difference mainly stems from the CDL under-detecting crop cover at BARC, especially in 2017 and 2018. We also note that annual accuracy levels varied less for the CA (91-98%) than for the CDL (79-93%). This study demonstrates that a computationally inexpensive radar-based cropland mapping approach can also give accurate results over complex landscapes with accuracies similar to or better than optical approaches.

Land cover dataset of the China Central-Asia West-Asia Economic Corridor from 1993 to 2018

Land Cover (LC) maps offer vital knowledge for various studies, ranging from sustainable development to climate change. The China Central-Asia West-Asia Economic Corridor region, as a core component of the Belt and Road initiative program, has been experiencing some of the most severe LC change tragedies, such as the Aral Sea crisis and Lake Urmia shrinkage, in recent decades. Therefore, there is a high demand for producing a fine-resolution, spatially-explicit, and long-term LC dataset for this region. However, except China, such dataset for the rest of the region (Kyrgyzstan, Turkmenistan, Kazakhstan, Uzbekistan, Tajikistan, Turkey, and Iran) is currently lacking. Here, we constructed a historical set of six 30-m resolution LC maps between 1993 and 2018 at 5-year time intervals for the seven countries where nearly 200,000 Landsat scenes were classified into nine LC types within Google Earth Engine cloud computing platform. The generated LC maps displayed high accuracies. This publicly available dataset has the potential to be broadly applied in environmental policy and management.

Land Cover Change Detection Based on Lenet-5 by Using Very-High-Resolution Remote Sensing Images

On the basis of remote sensing images, land cover change detection (LCCD) has gained popularity. Even though several techniques have been promoted lately, their effectiveness and usability still need to be improved. To assist urban sustainable development, evaluate natural disasters, and analyze the environment, very high-resolution (VHR) remote sensing images can be used to detect land cover change. Planning professionals can evaluate changes in land cover using remote sensing and geographic information systems, which have a reputation for excellence. A fully convolutional two-stream architecture is used in this paper to first extract highly representative deep features from bi-temporal images. After that, a Lenet5 is given the deep features to segment the land changes and detect changes. With the help of Faster-RCNN the land change classes are classified. We implement the proposed model in Python and conduct experiments on the land cover dataset. The outcomes of the experiments demonstrate that the proposed method outperformed previous deep learning algorithms, achieving the best accuracy, precision, recall, and F1-score.

Assessing effect of best management practices in unmonitored watersheds using the coupled SWAT-BiLSTM approach

In order to enhance the simulation of BMPs (Best Management Practices) reduction effects in unmonitored watersheds, in this study, we combined the physically-based hydrological model Soil & Water Assessment Tool (SWAT) and the data-driven model Bi-directional Long Short-Term Memory (Bi-LSTM), using the very-high-resolution (VHR) Land Use and Land Cover (LULC) dataset SinoLC-1 as data input, to evaluate the feasibility of constructing a water environment model for the Ba-River Basin (BRB) in central China and improving streamflow prediction performance. In the SWAT-BiLSTM model, we calibrated the top five SWAT parameters sorted by P-Value, allowing SWAT to act as a transfer function to convert meteorological data into base flow and storm flow, serving as the data input for the Bi-LSTM model. This optimization improved the Bi-LSTM's learning process for the relationship between the target and explanatory variables. The daily streamflow prediction results showed that the hybrid model had 9 regions rated as "Very good," 2 as "Good," 2 as "Satisfactory," and 1 as "Unsatisfactory" among the 14 regions. The model achieved an NSE of 0.86, R2 of 0.85, and PBIAS of −2.71% for the overall daily streamflow prediction performance during the verification period of the BRB. This indicates that the hybrid model has high predictive accuracy and no significant systematic bias, providing a sound hydrodynamic environment for water quality simulation. The simulation results of different BMPs scenarios showed that in the scenarios with only one BMP measure, stubble mulch had the best reduction effect, with average reductions of 17.83% for TN and 36.17% for TP. In the scenarios with a combination of multiple BMP measures, the combination of stubble mulch, soil testing and formula fertilization, and vegetative filter strip performed the best, achieving average reductions of 42.71% for TN and 50.40% for TP. The hybrid model provides a novel approach to simulate BMPs' reduction effects in regions without measured hydrological data and has the potential for wide application in BMP-related decision-making.

A novel method for identification of disturbance from surface coal mining using all available Landsat data in the GEE platform

Coal mining has contributed to a solid and stable global economy. Surface mining and underground mining are the principal methods for extraction of coal worldwide and given the developments in mining technology and equipment, these methods are increasingly generating more and more coal. Surface mining is also a subject that cannot be overlooked in the context of sustainable development because amongst human activities it causes comparatively strong land disturbance. Much of the damage and assessment of land and ecosystems from surface mining occurs at the site, and at the regional scale; hence access to the mining data is limited. Moreover, it is difficult for remote sensing to extract information on larger-scale areas with high precision. As a consequence, a frequency index of open coal mining can be created by merging the vast high-resolution images acquired by Landsat sensors with the spectral properties of open coal scraped from the overburden layer. Such indices and morphological principles can be used to develop strategies for quickly identifying the open coal boundaries in a vast area without mine-related information. In addition, LandTrendr may be used to reconstruct the spatial and temporal processes of surface disturbance and remediation caused by regional surface coal mining to identify surface mining disturbance and reclamation. Seven typical mining locations worldwide were selected to test and confirm the proposed method's practicality and robustness, including delivering accurate findings based on randomly testing sample points and comparing the mature data outputs. The results showed that: (1) the overall accuracy of the open coal areas identified by the OCFI (Open Coal Frequency Index) was over 85 % (range 0.85–0.96). In all study areas, the accuracy of recognizing disturbance and reclamation events was greater than 76 %. (2) The surface mining disturbed 3046.42 km2 of land and 1487.39 km2 was reclaimed in the seven mining areas investigated between 1986 and 2018, resulting in a reclamation rate of 48.82 %. The proposed method is more accurate and faster in identifying open coal locations than the current commonly used land cover datasets based on comparisons with other data products. The approach can extract surface coal mining in the absence of mining data and offer precise boundary data for mining research, which can be extremely useful for extending mining operations.

High-resolution land cover classification: cost-effective approach for extraction of reliable training data from existing land cover datasets

ABSTRACT There has been a significant increase in the availability of global high-resolution land cover (HRLC) datasets due to growing demand and favorable technological advancements. However, this has brought forth the challenge of collecting reference data with a high level of detail for global extents. While photo-interpretation is considered optimal for collecting quality training data for global HRLC mapping, some producers of existing HRLCs use less trustworthy sources, such as existing land cover at a lower resolution, to reduce costs. This work proposes a methodology to extract the most accurate parts of existing HRLCs in response to the challenge of providing reliable reference data at a low cost. The methodology combines existing HRLCs by intersection, and the output represents a Map Of Land Cover Agreement (MOLCA) that can be utilized for selecting training samples. MOLCA's effectiveness was demonstrated through HRLC map production in Africa, in which it generated 48,000 samples. The best classification test had an overall accuracy of 78%. This level of accuracy is comparable to or better than the accuracy of existing HRLCs obtained from more expensive sources of training data, such as photo-interpretation, highlighting the cost-effectiveness and reliability potential of the developed methodology in supporting global HRLC production.

Study on the Characteristics and Influencing Factors of Land Use Changes in the Metropolitan Fringe Area: The Case of Shenzhen Metropolitan Area in China

With the development of the regional economy, the metropolitan area has gradually shifted from the rapid development stage of concentrating on the central city to the stage of coordinated and integrated regional development. This trend has brought new development opportunities to the metropolitan fringe area; however, due to the differences in resource endowment and the complex relationship between different levels of government, the metropolitan fringe area inevitably has contradictions and imbalances in economic and social development. There has been extensive research on land use and urban governance in the metropolitan area, but less attention has been paid to the metropolitan fringe area, and it is difficult to quantitatively characterize the complex interactions between various forces in this area. This paper summarizes the spatial pattern and spatiotemporal characteristics of construction land use in the fringe area of Shenzhen metropolitan area based on the 30 m resolution land cover dataset from 2000 to 2020, and analyzes the driving factors affecting the changes of construction land use through logistic regression. The results show that the overall land use in the study area is shifting from cropland and forest land to urban and rural construction land. With different stages of development, the rate of land change varies greatly from one period to another. Three factors, population density, lighting index and distance to highway, have a significant correlation with the changes in built-up land across the region, while the boundary effects of administrative boundaries show some variation in the impact of urban land expansion at different economic levels. Finally, we put forward that reducing the negative impact of administrative divisions on the integration of resources in different cities is important for realizing the synergistic development of the Shenzhen metropolitan area.

High-resolution land use and land cover dataset for regional climate modelling: historical and future changes in Europe

Abstract. Anthropogenic land use and land cover change (LULCC) is a major driver of environmental changes. The biophysical impacts of these changes on the regional climate in Europe are currently being extensively investigated within the World Climate Research Program (WCRP) Coordinated Downscaling Experiment (CORDEX) Flagship Pilot Study (FPS) Land Use and Climate Across Scales (LUCAS) using an ensemble of different regional climate models (RCMs) coupled with diverse land surface models (LSMs). In order to investigate the impact of realistic LULCC on past and future climates, high-resolution datasets with observed LULCC and projected future LULCC scenarios are required as input for the RCM–LSM simulations. To account for these needs, we generated the LUCAS Land Use and land Cover change (LUC) dataset version 1.1 at 0.1∘ resolution for Europe with annual LULC maps from 1950 to 2100 (https://doi.org/10.26050/WDCC/LUC_hist_EU_v1.1, Hoffmann et al., 2022b, https://doi.org/10.26050/WDCC/LUC_future_EU_v1.1, Hoffmann et al., 2022a), which is tailored to use in state-of-the-art RCMs. The plant functional type (PFT) distribution for the year 2015 (i.e. the Modelling human LAND surface Modifications and its feedbacks on local and regional cliMATE – LANDMATE – PFT dataset) is derived from the European Space Agency Climate Change Initiative Land Cover (ESA-CCI LC) dataset. Details on the conversion method, cross-walking procedure, and evaluation of the LANDMATE PFT dataset are given in the companion paper by Reinhart et al. (2022b). Subsequently, we applied the land use change information from the Land-Use Harmonization 2 (LUH2) dataset, provided at 0.25∘ resolution as input for Coupled Modelling Intercomparison Project Phase 6 (CMIP6) experiments, to derive LULC distributions at high spatial resolution and at annual time steps from 1950 to 2100. In order to convert land use and land management change information from LUH2 into changes in the PFT distribution, we developed a land use translator (LUT) specific to the needs of RCMs. The annual PFT maps for Europe for the period 1950 to 2015 are derived from the historical LUH2 dataset by applying the LUT backward from 2015 to 1950. Historical changes in the forest type changes are considered using an additional European forest species dataset. The historical changes in the PFT distribution of LUCAS LUC follow closely the land use changes given by LUH2 but differ in some regions compared to other annual LULCC datasets. From 2016 onward, annual PFT maps for future land use change scenarios based on LUH2 are derived for different shared socioeconomic pathway (SSP) and representative concentration pathway (RCP) combinations used in the framework of CMIP6. The resulting LULCC maps can be applied as land use forcing to the new generation of RCM simulations for downscaling of CMIP6 results. The newly developed LUT is transferable to other CORDEX regions worldwide.

CO2 emissions in the Amazon: are bottom-up estimates from land use and cover datasets consistent with top-down estimates based on atmospheric measurements?

Amazon forests are the largest forests in the tropics and play a fundamental role for regional and global ecosystem service provision. However, they are under threat primarily from deforestation. Amazonia's carbon balance trend reflects the condition of its forests. There are different approaches to estimate large-scale carbon balances, including top-down (e.g., CO2 atmospheric measurements combined with atmospheric transport information) and bottom-up (e.g., land use and cover change (LUCC) data based on remote sensing methods). It is important to understand their similarities and differences. Here we provide bottom-up LUCC estimates and determine to what extent they are consistent with recent top-down flux estimates during 2010 to 2018 for the Brazilian Amazon. We combine LUCC datasets resulting in annual LUCC maps from 2010 to 2018 with emissions and removals for each LUCC, and compare the resulting CO2 estimates with top-down estimates based on atmospheric measurements. We take into account forest carbon stock maps for estimating loss processes, and carbon uptake of regenerating and mature forests. In the bottom-up approach total CO2 emissions (2010 to 2018), deforestation and degradation are the largest contributing processes accounting for 58% (4.3 PgCO2) and 37% (2.7 PgCO2) respectively. Looking at the total carbon uptake, primary forests play a dominant role accounting for 79% (−5.9 PgCO2) and secondary forest growth for 17% (−1.2 PgCO2). Overall, according to our bottom-up estimates the Brazilian Amazon is a carbon sink until 2014 and a source from 2015 to 2018. In contrast according to the top-down approach the Brazilian Amazon is a source during the entire period. Both approaches estimate largest emissions in 2016. During the period where flux signs are the same (2015–2018) top-down estimates are approximately 3 times larger in 2015–2016 than bottom-up estimates while in 2017–2018 there is closer agreement. There is some agreement between the approaches–notably that the Brazilian Amazon has been a source during 2015–2018 however there are also disagreements. Generally, emissions estimated by the bottom-up approach tend to be lower. Understanding the differences will help improve both approaches and our understanding of the Amazon carbon cycle under human pressure and climate change.

Does compact city shape matter to residents' happiness?

This paper investigates the impact of city shape variation on residents' happiness in Chinese cities. We first measure the city shape index of Chinese cities between 2000 and 2015 using matched data from the European Space Agency Global Land Cover dataset and the Chinese administrative map to delineate the changes in city shape in China's urbanization. Then we use a reduced-form estimation strategy to examine the causality between city shape variation and urban residents' happiness using our city shape dataset and the microsurvey data of CHIP (Chinese Household Income Project). We find that city shape exerts a negative influence on the happiness of urban residents. Such an effect is more pronounced in large cities. However, well-developed public transportation infrastructure can mitigate the negative impact of a non-compact city shape. Turning to the mechanism, commute time to the workplace and amenities is the main channel through which city shape works. We find that bad shape significantly increases the commute time between residential, workplace, and commercial amenities and therefore makes urban residents unhappy.

Thirty-meter map of young forest age in China

Abstract. Young forest age mapping at a fine spatial resolution is important for increasing the accuracy of estimating land–atmosphere carbon fluxes and guiding forest management practices. In recent decades, China has actively conducted afforestation and forest protection projects, thereby laying the foundation for the realization of carbon neutrality. However, very few studies have been conducted which map the ages of young forests for the whole of China at a fine spatial resolution. In this research, a continuous change detection and classification (CCDC)-based method suitable for large-scale forest age mapping is proposed and used to estimate young forest ages across China in 2020 at a spatial resolution of 30 m. First, a 10 m spatial-resolution land cover dataset (WorldCover2020) from the European Space Agency (ESA) was used to determine the forest cover areas in 2020. Then, the CCDC algorithm was used to identify stand-replacing disturbances to determine the stand age based on 436 967 Landsat tiles across China from 1990 to 2020. A validation sample set composed of multiple land use and land cover (LULC) products was used to calculate the overall accuracy (OA) of the 2020 young forest age (1–31-year) map of China, and the OA was 90.28 %. The reliability and applicability of the proposed CCDC-based forest age mapping method were validated by comparing the forest age map with Hansen's forest change dataset, Max Planck Institute for Biogeochemistry (MPI-BGC) 1 km global forest age datasets, and field measurements. The CCDC-based method has strong application potential in real-time mapping of the age of young forests at the global scale. The produced forest age map provides a basic dataset for research on the forest carbon cycle and forest ecosystem services as well as important guidance for government departments, such as the National Forestry and Grassland Administration and the National Development and Reform Commission in China. Data presented in this study is available at https://doi.org/10.6084/m9.figshare.21627023.v7 (Xiao, 2022).

Map of Land Cover Agreement: Ensambling Existing Datasets for Large-Scale Training Data Provision

Land cover information plays a critical role in supporting sustainable development and informed decision-making. Recent advancements in satellite data accessibility, computing power, and satellite technologies have boosted large-extent high-resolution land cover mapping. However, retrieving a sufficient amount of reliable training data for the production of such land cover maps is typically a demanding task, especially using modern deep learning classification techniques that require larger training sample sizes compared to traditional machine learning methods. In view of the above, this study developed a new benchmark dataset called the Map of Land Cover Agreement (MOLCA). MOLCA was created by integrating multiple existing high-resolution land cover datasets through a consensus-based approach. Covering Sub-Saharan Africa, the Amazon, and Siberia, this dataset encompasses approximately 117 billion 10m pixels across three macro-regions. The MOLCA legend aligns with most of the global high-resolution datasets and consists of nine distinct land cover classes. Noteworthy advantages of MOLCA include a higher number of pixels as well as coverage for typically underrepresented regions in terms of training data availability. With an estimated overall accuracy of 96%, MOLCA holds great potential as a valuable resource for the production of future high-resolution land cover maps.

How the land use/cover changes and environmental factors at different scales affect lake water quality in arid and semi-arid regions

The quantitative relationship between land use/cover change (LUCC) within basins, lake water environmental factors, and water quality has long been a popular research area. In this study, we investigated three typical basins (Ulansuhai Basin, Daihai Basin, and Dalinor Basin) in arid and semi-arid areas of China. The assessment was based on the China Land Cover Dataset (CLCD), which was used to calculate the land use dynamic degree index and Markov transfer matrix. Moreover, an econometric analysis model and a hybrid evolutionary algorithm (HEA) model were used to explore the quantitative relationship between LUCC and environmental factors on the lake water quality. The results showed that the LUCC of the three lake basins was dominated by cultivated land and grassland over the past 20 years. In all of the basins, grassland and water area were converted into cultivated land, water area decreased to varying degrees, and impervious surface area increased continuously. Moreover, the concentration of TN and TP were generally proportional to chemical oxygen demand concentration (COD), biochemical oxygen demand concentration (BOD5), and dissolved oxygen concentration (DO), but inversely proportional to water depth and transparency; the relationship between Nutrient concentration and pH was usually related to the ecological threshold. On the basin scale, the grassland and forestland played positive roles in improving water quality, while cultivated land and impervious surface were the main factors contributing to water pollution. Overall, this study provides a scientific theoretical basis for the rational utilization of land resources, improvement of lake water quality, and ecological protection of typical lake basins in arid and semi-arid regions.

Exploring Switzerland’s Land Cover Change Dynamics Using a National Statistical Survey

Timely and reliable Land Use and Cover change information is crucial to efficiently mitigate the negative impact of environmental changes. Switzerland has the ambitious objective of being a sustainable country while remaining an attractive business location with a high level of well-being. However, this aspiration is hampered by increasing pressures that are significantly impacting the environment and putting serious demands on land. In the present study, we used the national Land Cover (LC) dataset, named ArealStatistik, produced by the Federal Statistical Office, to explore the spatiotemporal patterns of Land Cover in Switzerland, providing a comprehensive assessment of land cover change at the national scale. Results indicate that, in general, Switzerland has undergone small, spatially dispersed, dynamic, and gradual change trends, with high rates of transition between low growing Brush Vegetation and forest LC classes in recent years. These pixel-level trends are more important in the lower altitude plateau and Jura regions, while greater changes in the spatial configuration of LC are observed in the alpine regions. However, findings also suggest that identifying drivers and understanding the rate of change are limited by the spatial resolution and temporal update frequency of the ArealStatistik. The ability to understand these drivers would benefit from a high-resolution annual LC dataset. Such a data product can be produced using the ArealStatistik together with dense satellite data time-series and Machine/Deep Learning techniques.

Investigation of the Microenvironment, Land Cover Characteristics, and Social Vulnerability of Heat-Vulnerable Bus Stops in Knoxville, Tennessee

The urban heat island is a climate, public health, and environmental justice issue. Sustainable urban infrastructure needs improvements in public transport to protect citizens’ health from the urban heat island. This case study investigates the local microenvironment and social vulnerability of heat-vulnerable bus stops in Knoxville, Tennessee, using publicly available data from a variety of sources. These included ground and satellite measurements of heat and humidity from the Knoxville Heat Mapping Campaign, characteristics of land surface from the National Land Cover Dataset 2019 of the United States Geological Survey, and the 2018 Social Vulnerability Index from the U.S. Centers for Disease Control and Prevention. A geographic information system and a principal component analysis were used to identify social vulnerability in areas where the bus stops are located. The results show that most heat-vulnerable bus stops are poor microenvironments without trees and shelters. The hottest bus stops are concentrated in the highly developed and densely populated areas of West Knoxville and downtown Knoxville and in South, North, Northeast, and Northwest Knoxville, which are relatively high vulnerability clustered and have poor public infrastructure. The findings provide the foundation for mitigation strategies to better prepare local communities for climate change by identifying public transportation areas negatively impacted by the urban heat island.

Dealing with the uncertainty of technical changes in the CORINE Land Cover dataset: The Portuguese approach

Land Use and Land Cover (LULC) datasets are widely used across disciplines, with many users demanding more and better information. Understanding the uncertainties and errors associated to the main LULC datasets is a required step to facilitate their correct use, as well as to identify what could be improved in the future production of these products. CORINE Land Cover is probably the most well-known and used LULC dataset in Europe, especially valuable for the rich time-series that it provides. Despite being produced through a change mapping first approach, which tries to avoid technical errors and uncertainties in the temporal analysis of LULC changes, the Copernicus Land Monitoring Service distributes status layers of CORINE (CSL), which are not valid for change analysis because of their associated errors and uncertainties. The CORINE layers of changes (CHA) remove a lot of these issues, but do not meet the needs of many users. In Portugal, the national authority in charge of producing CORINE, the DGT, has implemented a backdating approach to produce consistent CSL layers that allow change analysis with low levels of uncertainty. Throughout this paper, we evaluate the changes that can be analyzed through all available CORINE layers in Portugal: Copernicus CSL layers; the national DGT CSL layers; and CHA layers. To this end, we aim to assess what type of changes can be studied through each type of layer, their associated sources of uncertainty and the relevance and utility of the Portuguese backdating approach to produce a consistent time-series of LULC maps. The results prove how the Portuguese CORINE layers distributed by the Copernicus Land Monitoring Service contain important sources of uncertainty, which however have been removed through the national backdating methodology. This methodology can be therefore exported for the production of CORINE in other European countries.

Spatiotemporal Features of the Surface Urban Heat Island of Bacău City (Romania) during the Warm Season and Local Trends of LST Imposed by Land Use Changes during the Last 20 Years

Using MODIS and Landsat LST images, the present paper advances a series of results on the characteristics of the surface heat island (SUHI) of Bacău City (Romania) during the warm season (April to September) for a period of 20 years (2001–2020). At the same time, given their higher temporal resolution and their availability for both day and night, MODIS LST was used to understand the spatial features of the SUHI in relation to land use. In this way, a total of 946 MODIS Terra and 483 Landsat satellite images were used to outline the main LST characteristics of the days with clear sky in this middle-sized city in northeast Romania. In order to analyze MODIS LST changes in relation to land use changes in the period 2001–2018, we used the standardized CORINE Land Cover datasets. With the help of the Rodionov test, we were able to determine the geometry and intensity of the SUHI. During the day, the spatial extension of the SUHI reaches its maximum level and is delimited by the isotherm of 31.0 °C, which is 1.5–2.0 °C warmer than the neighboring non-urban areas. During the night, the SUHI has a more regulated spatial extension around the central area of the city, delimited by the 15.5 °C isotherm with LST values that are 1.0–1.5 °C warmer than the surrounding non-urban areas. Additionally, from a methodological point of view, we highlight that resampled MODIS and Landsat images at a spatial resolution of 500 m can be used with confidence to understand the detailed spatial features of the SUHI. The results of this study could help the elaboration of future policies meant to mitigate the effects of urbanization on the SUHI in an era of increasing air temperatures during summer.

Cryptic tolerant fish species and their potential effect on index of biotic integrity (IBI) scores

Indices such as the Index of Biotic Integrity (IBI) are often used by management agencies to estimate the abstract property of stream health. These indices are usually predicated on the belief that certain fish species are tolerant to environmental perturbation while others are sensitive. Species are usually designated as either tolerant or sensitive in these analyses based on inherent ecological or taxonomic characteristics. However, previous literature has shown that certain species from ecological or taxonomic “sensitive” groups experience increased abundance in degraded streams. We term such species “cryptic tolerants”. Using a stream fish assemblage dataset of 433 unique sample locations across the state of Alabama and the National Landcover Dataset, our objectives were to 1) identify the most common cryptic tolerant species, 2) investigate how cryptic tolerant species might inflate indices of stream health, and 3) compare an alternative measure of stream health in which species are statistically defined rather than defined using the traditional trait-based approach. We identified cryptic tolerants using Nonmetric Multidimensional Scaling in six ecoregions. A series of regressions revealed that the proportion of cryptic tolerant species decreased in response to an increasing proportion of forested land in catchments while the proportion of true sensitives increased in all ecoregions except for the Cumberland Plateau. An index that simply used the percentage of statistically defined, non-tolerant species generally had lower p-values and higher r2 values than IBI scores when both were regressed against percentage of forest in catchment. However, both indices had low degrees of correlation with expected disturbance, indicating a univariate index may be inadequate to characterize stream health. Our results highlight a potential issue with applying the IBI to diverse southeastern systems in the United States, which may be alleviated by designating species sensitivity based on empirical response to disturbance rather than taxonomic or ecological characteristics.

A multi-data approach to evaluate progress towards land degradation neutrality in Central Asia

Central Asia hosts one of the largest continuous grassland areas on our planet, that is of vital importance for food security, biodiversity and carbon sequestration. However, this region is also subjected to some of the most intense land degradation processes, related to large scale land use change and climate change.To combat land degradation and pursue sustainable land management the concept of land degradation neutrality (LDN) has been proposed. LDN assessments are recommended to be based on global data in regions that lack sufficient regional data such as Central Asia. However, it remains unclear how the selection of datasets influences the estimated extent of land degradation. We followed the LDN framework and first calculated changes to three LDN indicators: land productivity, land cover, and Soil Organic Carbon (SOC). We then evaluated the impact of using different regional and global land cover data on the extent of land degradation in the region. Finally, we calculated a regionally specific integrated indicator on soil quality that we used to assess the “like-for-like” principle which enables counterbalancing losses and gains.Our results indicate that particularly the selection of land cover data has a significant impact on the overall assessment of degradation state. The extent of land between 2000 and 2019 varies considerably depending on the data and ranges between 15 and 34 % of the whole Central Asian region. Our findings reveal that the area of degraded land on high quality soils is twice as high as the area of high quality soils where the land condition has improved (12 % versus 6 %). In areas with low soil quality, 13 % was subject to degradation, and 10 % improved.Whilst the degradation extent varies according to the selected land cover datasets, our results demonstrates that Central Asia is undergoing land degradation affecting high quality soils. Sensitivity analysis of multiple datasets can reduce the risk of misjudgement in degradation extent assessments, especially in regions with mosaic ecosystems, such as grasslands.

Land cover mapping via crowdsourced multi-directional views: The more directional views, the better

In the last decades, a number of crowdsourced land cover datasets have been developed, owning to their great potential to provide human-centric ground observations. In this study, we investigated the GLOBE Observer Land Cover program by assessing the efficacy of its multi-directional data-collecting protocol. Specifically, we explored data characteristics by presenting its unique data sampling protocol, data sample distributions, and similarity across multi-directional views. We developed an end-to-end classification framework that links user-uploaded multi-directional views with their user-provided land cover labels and investigated classification performance with different levels of viewing involvement, using various popular deep learning architectures, under different image fusion strategies. Our study provides empirical evidence that multi-directional views benefit land cover classification. We observe that classification performance improved across four selected deep learning architectures when more directional views were involved. The classification scenario with EfficentNet, the involvement of quadruple views, and the late fusion strategy led to an improvement of 0.084 in the weighted F1 score (from 0.628 to 0.712) compared to the one with single view. We encourage crowdsourced observing and monitoring programs to adopt multi-directional view sampling protocols and call for the development of robust information on fusion strategies that harness the potential of multi-directional views.