Land Cover Map Research Articles

Textural indices of aerial images reveal urban landscapes temporal dynamics and their effects on plants and birds

Landscape temporal dynamics are a crucial concern in ecology to understand current biodiversity. But historical environmental data are often not easily available. This study assesses for the first time the potential of historical orthophotographs to describe past landscape conditions and determine the temporal lag between landscape changes and biotic communities responses.This method utilizes Gray level Co-occurrence Matrix (GLCM) texture indices computed from black and white orthophotographs to construct continuous metrics of landscape composition. Metrics were first developed using present-day data, i.e. 2015, and calibrated with categorical land cover maps of the Strasbourg Eurometropolis, France. Subsequently, these metrics were applied to historical orthophotographs from 1966, 1976, 1986, and 2000. Plant and bird data from research and citizen science programs were used to estimate the time delay in which these communities respond to evolutions in built areas and high vegetation.Obtained texture-based models reveal that built areas exhibit high contrast and homogeneity, depicted through a linear relation, and that high vegetation display low pixel brightness and high brightness diversity, better described via a nonlinear model. We successfully applied those findings to historical orthophotographs, and revealed dependencies on landscape composition up to 50 years ago for plants and up to 30 years ago for birds, with the time lag and the influence of built and high vegetation areas depending on the selected biodiversity indices.These results demonstrate the utility of archive black and white orthophotographs' texture indices for describing urban landscapes over the past five decades, making them valuable tools for ecological research. These indices are more accessible than categorical data like land cover maps for past years. They have the potential to greatly benefit future studies investigating time lags in landscape ecology, simplifying access to historical landscape features and contributing to sustainable urban planning efforts.

An encoder–decoder network for land cover classification using a fusion of aerial images and photogrammetric point clouds

Land cover information is becoming more important in urban planning, change detection, and management. The fusion of point clouds and images increases the accuracy of land use classification by utilising the advantages of both modalities. Similar structures such as buildings and roads, low and high vegetation, and impervious and bare regions are not too much discriminative. Models fail to discriminate these classes leading to misclassifications, false detections, and unreliable land cover maps. Therefore, this research proposes the fusion of dense point clouds and multi-spectral images based on a dual-stream deep convolutional model by adding vegetation and elevation information to spectral information. To fuse both modalities' features, a dual-stream deep neural network based on Deeplabv3+ architecture is implemented. In addition, the Xception (Extreme Inception) model is considered as a backbone and feature extractor. The model performance is evaluated with F1-Score and Overall Accuracy. 93.4% Overall Accuracy and F1-Score are achieved after adding height and vegetation information to the model. Results indicate improvements in all indexes, meaning that data fusion with the proposed model outperforms the existing state-of-the-art models.

Variability of Extreme Climate Events and Prediction of Land Cover Change and Future Climate Change Effects on the Streamflow in Southeast Queensland, Australia

The severity and frequency of extremes are changing; thus, it is becoming necessary to evaluate the impacts of land cover changes and urbanisation along with climate change. A framework of the Generalised Extreme Value (GEV) method, Google Earth Engine (GEE), and land cover patterns’ classification including Random Forest (RF) and Support Vector Machine (SVM) can be useful for streamflow impact analysis. For this study, we developed a unique framework consisting of a hydrological model in line with the Process-informed Nonstationary Extreme Value Analysis (ProNEVA) GEV model and an ensemble of General Circulation Models (GCMs), mapping land cover patterns using classification methods within the GEE platform. We applied these methods in Southeast Queensland (SEQ) to analyse the maximum instantaneous floods in non-stationary catchment conditions, considering the physical system in terms of cause and effect. Independent variables (DEM, population, slope, roads, and distance from roads) and an integrated RF, SVM methodology were utilised as spatial maps to predict their influences on land cover changes for the near and far future. The results indicated that physical factors significantly influence the layout of landscapes. First, the values of projected evapotranspiration and rainfall were extracted from the multi-model ensemble to investigate the eight GCMs under two climate change scenarios (RCP4.5 and RCP8.5). The AWBM hydrological model was calibrated with daily streamflow and applied to generate historical runoff for 1990–2010. Runoff was projected under two scenarios for eight GCMs and by incorporating the percentage of each land cover into the hydrological model for two horizons (2020–2065 and 2066–2085). Following that, the ProNEVA model was used to calculate the frequency and magnitude of runoff extremes across the parameter space. The maximum peak flood differences under the RCP4.5 and RCP8.5 scenarios were 16.90% and 15.18%, respectively. The outcomes of this study suggested that neglecting the non-stationary assumption in flood frequency can lead to underestimating the amounts that can lead to more risks for the related hydraulic structures. This framework is adaptable to various geographical regions to estimate extreme conditions, offering valuable insights for infrastructure design, planning, risk assessment, and the sustainable management of future water resources in the context of long-term water management plans.

A multi-attention residual integrated network with enhanced fireworks algorithm for remote sensing image classification

This research examines a multi-attention residual integrated network with an enhanced fireworks algorithm for remote sensing image classification. Remote sensing (RS) picture classification is important for land cover mapping, environmental monitoring, and urban planning. Remote sensing image classification is important in earth observation since the military and commercial sectors have focused on it. Due to RS data's high complexity and limited labelled examples, classifying RS pictures is difficult. Deep Learning (DL) techniques have made great strides in RS image categorization, expanding this field's potential. This research introduces Multi-Attention Residual Integrated Network with Enhanced Fireworks Algorithm (MAR-EFA) to improve hyper spectral image identification. MARIN-EFA improves feature fusion and removes unneeded features to overcome technique constraints. The suggested method weights features using different attention models. These characteristics are then carefully extracted and integrated using a residual network. Final contextual semantic integration on deeply fused features is done with a Bi-LSTM network. Our population-based Enhanced Fireworks Algorithm (EFA) is inspired by fireworks' explosive performance and optimises MARIN parameters. Attention techniques and an improved optimisation algorithm improve performance over current systems. Numerous Eurosat dataset studies were assessed using various performance indicators. The simulation results show that MARIN-EFA outperforms current methods. The suggested technique shows promise for improving RS picture classification and allowing more accurate and reliable data categorization.

Spatiotemporal assessment of the nexus between urban sprawl and land surface temperature as microclimatic effect: implications for urban planning.

Rapid urbanisation has led to significant environmental and climatic changes worldwide, especially in urban heat islands where increased land surface temperature (LST) poses a major challenge to sustainable urban living. In the city of Abha in southwestern Saudi Arabia, a region experiencing rapid urban growth, the impact of such expansion on LST and the resulting microclimatic changes are still poorly understood. This study aims to explore the dynamics of urban sprawl and its direct impact on LST to provide important insights for urban planning and climate change mitigation strategies. Using the random forest (RF) algorithm optimised for land use and land cover (LULC) mapping, LULC models were derived that had an overall accuracy of 87.70%, 86.27% and 93.53% for 1990, 2000 and 2020, respectively. The mono-window algorithm facilitated the derivation of LST, while Markovian transition matrices and spatial linear regression models assessed LULC dynamics and LST trends. Notably, built-up areas grew from 69.40 km2 in 1990 to 338.74 km2 in 2020, while LST in urban areas showed a pronounced warming trend, with temperatures increasing from an average of 43.71°C in 1990 to 50.46°C in 2020. Six landscape fragmentation indices were then calculated for urban areas over three decades. The results show that the Largest Patch Index (LPI) increases from 22.78 in 1990 to 65.24 in 2020, and the number of patches (NP) escalates from 2,531 in 1990 to an impressive 10,710 in 2020. Further regression analyses highlighted the morphological changes in the cities and attributed almost 97% of the LST variability to these urban patch dynamics. In addition, water bodies showed a cooling trend with a temperature decrease from 33.76°C in 2000 to 29.69°C in 2020, suggesting an anthropogenic influence. The conclusion emphasises the urgent need for sustainable urban planning to counteract the warming trends associated with urban sprawl and promote climate resilience.

Enhancing water balance assessment in urban areas through high-resolution land cover mapping: Case study of Debrecen, Hungary

Land cover (LC) mapping in urban areas is one of the core applications in remote sensing (RS), and it plays an important role in modern urban planning and management. In order to support up-to-date simplified water balance calculation, LC modelling needs to be developed for precise and high-resolution operations to monitor rapidly expanding urban areas. This study provides a spatial decision support tool for urban water balance calculations considering hydrological parameters at pixel scale. The study is aimed to create a high-resolution LC map for more precise water balance calculations to identify and link the most important parameters, such as crop coefficient, for estimating crop evapotranspiration, runoff coefficients, and infiltration rate. Meteorological data from 2016 to 2019 were involved in evapotranspiration estimation. The study site is Debrecen, a city in northeast Hungary with a population of about 200,000. By integrating Landsat 8 imagery, Google Earth (GE), and Corine Land Cover (CLC), a LC map of 30 m resolution was created with 81.2 % overall accuracy (OA) and a coefficient of kappa greater than 0.78. For the classification of Landsat 8, seven classes were assigned (forests, sealed surfaces, areas with crop cover, grassland, semi-sealed surfaces, bare ground and surface water bodies). Classification results were validated by 101 ground truth samples using other satellite images and aerial photographs. Water balance parameters (i.e. surface runoff, infiltration and evapotranspiration) were then defined and calculated at a pixel scale and for larger areas. The technique developed in this study can also be utilized in other urban areas.

Land cover mapping of mixed classes using 2D CNN with multi-frequency SAR data

Synthetic aperture radar (SAR) data obtained at multiple frequencies and polarizations offers valuable complementary information for classifying mixed classes that exhibit similar backscattering response. Although deep learning-based convolutional neural networks (CNNs) effectively extract features from multi-frequency SAR data, the arbitrary ordering of SAR features may hinder optimal convolution of the best feature sub-space for a specific class and underutilize available multi-frequency data. To address this, a novel CNN transforming SAR feature-space from 1-D to 2-D and employing varied dilation-rate convolutions is introduced. This transformation maximizes unique and localized feature combinations, efficiently utilizing the available feature sub-spaces and extracting discriminative features for accurate classifications, addressing the challenge of arbitrary band neighborhoods. Utilizing dual-polarization SAR data from ALOS-2 PALSAR-2 and Sentinel-1 sensors, the proposed CNN achieves an average f-score of 0.97 and a kappa coefficient of 0.97, an improvement of 11 %, 7 % and 3 % in OA compared to the 1-D, 2-D and 3-D CNN classifiers, without feature transformation. The classifier's generalization ability is evaluated using ground truth knowledge of various heterogeneous classes, and the proposed CNN classifier outperforms others in terms of accuracy metrics and generalization ability.

CRformer: Multi-modal data fusion to reconstruct cloud-free optical imagery

Cloud contamination is a common problem in Earth observation that hinders various remote sensing applications. To address this problem, recent studies have employed deep neural networks and multi-modal data fusion to reconstruct cloud-free optical imagery. However, this task faces many challenges, such as: (1) the scarcity of suitable multi-modal datasets; (2) the ineffective use of feature correlations; and (3) the limited applicability of existing models. To overcome these challenges, this study proposes a novel solution that fuses high-spatial SAR and low-spatial optical data to reconstruct high-quality cloud-free multi-spectral optical products. First, a curated benchmark dataset, named SMILE-CR, is created with a realistic cloud simulation strategy. The SMILE-CR serves as a global and multi-modal cloud removal dataset for the Landsat-8 sensor, with Sentinel-1 and MODIS data as additional supplementary data. Second, a Transformer-based cloud removal network, abbreviated as CRformer, is developed with two novel modules: multi-head dense and sparse attention and multi-scale gated-dconv feed-forward network. The CRformer achieves global attention while suppressing the weak correlations and enhancing the multi-scale cloud features by filtering out invalid features. The performance of the proposed method is evaluated through extensive experiments. The results show that the CRformer surpasses the state-of-the-art cloud removal methods with significant improvements in both quantitative and qualitative metrics. The fusion of MODIS and Sentinel-1 data is shown to be effective and necessary in reconstructing Landsat-8 observations. Moreover, the CRformer model can be readily applied to reconstruct time-series cloud-free Landsat-8 products in Wuhan city, which can improve the average accuracy of land cover mapping by over 3%.

Nature-Based Solutions vs. Human-Induced Approaches for Alpine Grassland Ecosystem: “Climate-Help” Overwhelms “Human Act” to Promote Ecological Restoration in the Three-River-Source Region of Qinghai–Tibet Plateau

How climate change and human activities drive the evolution of the regional environment and where the quality of ecosystems improve or decline over time have become widespread concerns. In this study, we took the Three-River-Source (TRS) region of the Qinghai–Tibet Plateau as a case, aiming to identify and quantify the contribution of the natural and anthropogenic factors to the ecosystem changes over the past years from 1980 to 2018 using the methods of remote sensing and spatial statistical analysis. Based on the land cover map interpreted by reference to satellite remote sensing imagery data, we defined the Ecological Restoration Area Proportion (ERAP) as the bare land patch decrement to indicate the ecologically restored quantity in space. Assembling the restoration project information, we digitalized and vectorized the ecological Restoration Intensity (RI) including the spatial range and temporal duration. Combining the ERAP and the net primary productivity (NPP), which indicates the quantity and quality of ecosystems, respectively, the ecological asset Index (EAI) was developed and calculated. Having integrated the datasets of the vegetation monitoring, climatic factors, geographical factors, and human activities, we performed multi-variable analysis of the attribution of how the change in the EAI, the NPP, and the EAI have been affected by these factors together. The NPP of the middle and eastern parts of the TRS region has improved the most, as the average growth rate of NPP reached approximately 2.5 kg C/m2/10a. Due to such dynamic pattern, we found that human-induced re-vegetation has made limited contributions in our multi-regression model as the variance explained by the RI merely amounts to 4.4% to 8.8%, while the changes were mostly dependent on the regional temperature and the precipitation which contributed over 45% to the ecological restoration on average. It was summarized that “climate-help” overwhelms “human act” in such alpine grassland ecosystem. The regression results for the different aspects of the ERAP and NPP demonstrated that the ecological restoration project helped most in regard to ecosystem quality improvement rather than the restored ecosystem quantity. Our study has developed a comprehensive assessment methodology that can be reused to account for more ecological asset. The case is an example of an alpine ecosystem in which the success of ecological restoration needs favorable climatic conditions as supporting evidence for the nature-based solution.

Application of the domain adaptation method using a phenological classification framework for the land-cover classification of North Korea

Efforts to achieve carbon neutrality are global, encompassing a wide range of factors. For the estimation of greenhouse gas emissions from the agriculture, forestry, and other land use (AFOLU) sector, the Intergovernmental Panel on Climate Change has proposed an advanced method that requires Approach 3, the highest level of suggested method, of activity data. Accordingly, we propose a phenological classification framework (PCF) that can perform land-cover classification by training the climatic repeatability of the annual cycle using a U-Net deep learning model. Additionally, the domain adaptation (DA) method can be applied to classify areas with insufficient data. We applied these methods to classify North Korea (i.e., using South Korean data), with an accuracy of 81.31%; overall this effort culminated in the simultaneous classification of the Korean Peninsula. Domain distribution comparison showed that the results for the two regions were similar. The PCF and DA methods proposed in this study allow for annual production of a land-cover map and change matrix, regardless of the presence or absence of data. The application of these methods is expected to provide a scientific basis for policy decisions that can facilitate the global attainment of carbon neutrality.

Comparison and Validation of Multiple Medium- and High-Resolution Land Cover Products in Southwest China

The rapid advancement of remote sensing technology has given rise to numerous global- and regional-scale medium- to high-resolution land cover (LC) datasets, making significant contributions to the exploration of worldwide environmental shifts and the sustainable governance of natural resources. Nonetheless, owing to the inherent uncertainties embedded within remote sensing imagery, LC datasets inevitably exhibit inaccuracies. In this study, a local accuracy assessment of LC datasets in Southwest China was conducted. The datasets utilized in our analysis include ESA WorldCover, CLCD, Esri Land Cover, CRLC, FROM-GLC10, GLC_FCS30, GlobeLand30, and SinoLC-1. This study employed a sampling approach that combines proportional allocation and stratified random sampling (SRS) to gather sample points and compute confusion matrices to validate eight LC products. The local accuracy of the eight LC maps differs significantly from the overall accuracy provided by the original authors in Southwest China. ESA WorldCover and CLCD demonstrate higher local accuracy than other products in Southwest China, with their overall accuracy (OA) values being 87.1% and 85.48%, respectively. Simultaneously, we computed the area for each LC map based on categories, quantifying uncertainty through the reporting of confidence intervals for both accuracy and area parameters. This study aims to validate and compare eight LC datasets and assess precision and area of diverse spatial resolution datasets for mapping and monitoring across Southwest China.

Resolving heterogeneous fluxes from tundra halves the growing season carbon budget

Abstract. Landscapes are often assumed to be homogeneous when interpreting eddy covariance fluxes, which can lead to biases when gap-filling and scaling up observations to determine regional carbon budgets. Tundra ecosystems are heterogeneous at multiple scales. Plant functional types, soil moisture, thaw depth, and microtopography, for example, vary across the landscape and influence net ecosystem exchange (NEE) of carbon dioxide (CO2) and methane (CH4) fluxes. With warming temperatures, Arctic ecosystems are changing from a net sink to a net source of carbon to the atmosphere in some locations, but the Arctic's carbon balance remains highly uncertain. In this study we report results from growing season NEE and CH4 fluxes from an eddy covariance tower in the Yukon–Kuskokwim Delta in Alaska. We used footprint models and Bayesian Markov chain Monte Carlo (MCMC) methods to unmix eddy covariance observations into constituent land-cover fluxes based on high-resolution land-cover maps of the region. We compared three types of footprint models and used two land-cover maps with varying complexity to determine the effects of these choices on derived ecosystem fluxes. We used artificially created gaps of withheld observations to compare gap-filling performance using our derived land-cover-specific fluxes and traditional gap-filling methods that assume homogeneous landscapes. We also compared resulting regional carbon budgets when scaling up observations using heterogeneous and homogeneous approaches. Traditional gap-filling methods performed worse at predicting artificially withheld gaps in NEE than those that accounted for heterogeneous landscapes, while there were only slight differences between footprint models and land-cover maps. We identified and quantified hot spots of carbon fluxes in the landscape (e.g., late growing season emissions from wetlands and small ponds). We resolved distinct seasonality in tundra growing season NEE fluxes. Scaling while assuming a homogeneous landscape overestimated the growing season CO2 sink by a factor of 2 and underestimated CH4 emissions by a factor of 2 when compared to scaling with any method that accounts for landscape heterogeneity. We show how Bayesian MCMC, analytical footprint models, and high-resolution land-cover maps can be leveraged to derive detailed land-cover carbon fluxes from eddy covariance time series. These results demonstrate the importance of landscape heterogeneity when scaling carbon emissions across the Arctic.

An integrated hierarchical classification and machine learning approach for mapping land use and land cover in complex social-ecological systems

Mapping land use and land cover (LULC) using remote sensing is fundamental to environmental monitoring, spatial planning and characterising drivers of change in landscapes. We develop a new, general and versatile approach for mapping LULC in landscapes with relatively gradual transition between LULC categories such as African savannas. The approach integrates a well-tested hierarchical classification system with the computationally efficient random forest (RF) classifier and produces detailed, accurate and consistent classification of structural vegetation heterogeneity and density and anthropogenic land use. We use Landsat 8 OLI imagery to illustrate this approach for the Extended Greater Masai Mara Ecosystem (EGMME) in southwestern Kenya. We stratified the landscape into eight relatively homogeneous zones, systematically inspected the imagery and randomly allocated 1,697 training sites, 556 of which were ground-truthed, proportionately to the area of each zone. We directly assessed the accuracy of the visually classified image. Accuracy was high and averaged 88.1% (80.5%–91.7%) across all the zones and 89.1% (50%–100%) across all the classes. We applied the RF classifier to randomly selected samples from the original training dataset, separately for each zone and the EGMME. We evaluated the overall and class-specific accuracy and computational efficiency using the Out-of-Bag (OOB) error. Overall accuracy (79.3%–97.4%) varied across zones but was higher whereas the class-specific accuracy (25.4%–98.1%) was lower than that for the EGMME (80.2%). The hierarchical classifier identified 35 LULC classes which we aggregated into 18 intermediate mosaics and further into five more general categories. The open grassed shrubland (21.8%), sparse shrubbed grassland (10.4%) and small-scale cultivation (13.3%) dominated at the detailed level, grassed shrubland (31.9%) and shrubbed grassland (28.9%) at the intermediate level, and grassland (35.7%), shrubland (35.3%) and woodland (12.5%) at the general level. Our granular LULC map for the EGMME is sufficiently accurate for important practical purposes such as land use spatial planning, habitat suitability assessment and temporal change detection. The extensive ground-truthing data, sample site photos and classified maps can contribute to wider validation efforts at regional to global scales.

Exploring optimal integration schemes for Sentinel-1 SAR and Sentinel-2 multispectral data in land cover mapping across different atmospheric conditions

Integrating remote sensing data, such as Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 multispectral data, can provide valuable insights for this task. However, in tropical regions, such as Yogyakarta, Indonesia, atmospheric interference from cloud cover and haze can result in spectral confusion and decreased usability of multispectral data, leading to reduced classifier accuracy. This study investigates the impact of integrating Sentinel-1 SAR and Sentinel-2 multispectral data and their derivatives on land cover mapping in part of Yogyakarta under hazy and clear atmospheric conditions. This study employed four Schemes: (1) using only SAR data and its derivatives, (2) using only multispectral data and its derivatives, (3) combining SAR, multispectral, and their derivatives, and (4) combining SAR, multispectral, and their derivatives with feature selection using Recursive Feature Elimination. The XGBoost classification algorithm tuned using Bayesian optimization was used for classification, and the accuracy and efficiency (processing time) of each Scheme were evaluated. The results showed that integrating SAR data and optical data with clear and hazy condition increased the accuracy by 4 % (clear) to 14.58 % (hazy). The integration of SAR and optical data had the highest accuracy (79.58% on hazy imagery and 84.58% on clear imagery) but longer processing time. However, the feature selection conducted in decreased model complexity and processing time, with a reduction in processing time of 78.74% on hazy imagery and 49.89% as compared to utilizing the full SAR and optical data variables. Lastly, the McNemar test concluded the significance of integrating SAR data for mapping land cover, especially with hazy optical data.

Radiometric landscape: a new conceptual framework and operational approach for landscape characterisation and mapping

ABSTRACT Landscape mapping has the potential to address some of the most pressing research issues of our time, including climate change, sustainable development, and human well-being. In this paper, we propose an original method that lays the foundations for landscape mapping and overcomes some of the major limitations of existing biophysical methods. Based on the assumption that the primary components of the landscape can be extracted directly from the radiometric information of satellite image time series, this paper presents a new approach to landscape characterization and mapping based solely on remote sensing data. The approach relies on a conceptual model, which links the description, characteristics, structure and functions of the landscape to a set of Remote Sensing-based Essential Landscape Variables (RS-ELVs). The RS-ELVs are then processed according to geographic object-based image analysis (GEOBIA) approach to produce a radiometric landscape map. The model and the remote sensing data processing chain are tested on a case study in central Madagascar (about 13 000 km2) composed of contrasting landscapes resulting from different climatic conditions and agricultural practices. The RS-ELVs are extracted from MODIS image time series for the temporal and spectral variables, and from MODIS and Sentinel-2 images for the texture variables. The parameterization of the segmentation and clustering algorithms is determined by statistical optimization. The final result is a radiometric landscape map in six classes. The landscape classes are then characterized using an independent set of remote sensing variables, a global land cover map and ground observations. The approach successfully identifies and delineates the gradient and major landscape types of the complex region of central Madagascar, confirming our initial hypothesis. The production of such radiometric landscape maps opens the way for integrated territorial development, including the planning and protection of the living environment and human well-being, and the implementation of sectoral policies.

GLC_FCS30D: the first global 30 m land-cover dynamics monitoring product with a fine classification system for the period from 1985 to 2022 generated using dense-time-series Landsat imagery and the continuous change-detection method

Abstract. Land-cover change has been identified as an important cause or driving force of global climate change and is a significant research topic. Over the past few decades, global land-cover mapping has progressed; however, long-time-series global land-cover-change monitoring data are still sparse, especially those at 30 m resolution. In this study, we describe GLC_FCS30D, a novel global 30 m land-cover dynamics monitoring dataset containing 35 land-cover subcategories and covering the period 1985–2022 in 26 time steps (maps were updated every 5 years before 2000 and annually after 2000). GLC_FCS30D has been developed using continuous change detection and all available Landsat imagery based on the Google Earth Engine platform. Specifically, we first take advantage of the continuous change-detection model and the full time series of Landsat observations to capture the time points of changed pixels and identify the temporally stable areas. Then, we apply a spatiotemporal refinement method to derive the globally distributed and high-confidence training samples from these temporally stable areas. Next, local adaptive classification models are used to update the land-cover information for the changed pixels, and a temporal-consistency optimization algorithm is adopted to improve their temporal stability and suppress some false changes. Further, the GLC_FCS30D product is validated using 84 526 globally distributed validation samples from 2020. It achieves an overall accuracy of 80.88 % (±0.27 %) for the basic classification system (10 major land-cover types) and 73.04 % (±0.30 %) for the LCCS (Land Cover Classification System) level-1 validation system (17 LCCS land-cover types). Meanwhile, two third-party time-series datasets used for validation from the United States and Europe Union are also collected for analyzing accuracy variations, and the results show that GLC_FCS30D offers significant stability in terms of variation across the accuracy time series and achieves mean accuracies of 79.50 % (±0.50 %) and 81.91 % (±0.09 %) over the two regions. Lastly, we draw conclusions about the global land-cover-change information from the GLC_FCS30D dataset; namely, that forest and cropland variations have dominated global land-cover change over past 37 years, the net loss of forests reached about 2.5 million km2, and the net gain in cropland area is approximately 1.3 million km2. Therefore, the novel dataset GLC_FCS30D is an accurate land-cover-dynamics time-series monitoring product that benefits from its diverse classification system, high spatial resolution, and long time span (1985–2022); thus, it will effectively support global climate change research and promote sustainable development analysis. The GLC_FCS30D dataset is available via https://doi.org/10.5281/zenodo.8239305 (Liu et al., 2023).

Time-first approach for land cover mapping using big Earth observation data time-series in a data cube – a case study from the Lake Geneva region (Switzerland)

ABSTRACT Accurate, consistent, and high-resolution Land Use & Cover (LUC) information is fundamental for effectively monitoring landscape dynamics and better apprehending drivers, pressures, state, and impacts on land systems. Nevertheless, the availability of such national products with high thematic accuracy is still limited and consequently researchers and policymakers are constrained to work with data that do not necessarily reflect on-the-ground realities impending to correctly capture details of landscape features as well as limiting the identification and quantification of drivers and rate of change. Hereafter, we took advantage of the Switzerland’s official LUC statistical sampling survey and dense time-series of Sentinel-2 data, combining them with Machine and Deep Learning methods to produce an accurate and high spatial resolution land cover map over the Lake Geneva region. Findings suggest that time-first approach is a valuable alternative to space-first approaches, accounting for the intra-annual variability of classes, hence improving classification performances. Results demonstrate that Deep Learning methods outperform more traditional Machine Learning ones such as Random Forest, providing more accurate predictions with lower uncertainty. The produced land cover map has a high accuracy, an improved spatial resolution, while at the same time preserving the statistical significance (i.e. class proportion) of the official national dataset. This work paves the way towards the objective to produce a yearly high resolution land cover map of Switzerland and potentially implement a continuous land change monitoring capability. However further work is required to properly address challenges such as the need for increased temporal resolution for LUC information or the quality of training samples.

Delineation of Vulnerable Areas Affected by the Eruption of Mount Agung, Bali

Vulnerability is a condition of a community or society that causes the inability to face the threat of disaster. Geographic information systems (GIS) have become essential tools in evaluating natural hazards and risks which is an aspect to define vulnerability of the volcano eruption-affected area. Based on activity of volcano, it is necessary to delineate the vulnerability of areas affected by the eruption of Mount Agung by integrating the Mount Agung Area Network Map and Geological Map with physical vulnerability data and social vulnerability. This research using processing methods and spatial analysis of Geographic Information Systems (GIS) and remote sensing methods. Geographic Information System (GIS) is used to create vulnerability maps using scoring, weighting, and overlay methods. The data used for making the vulnerability map include administrative boundaries, DEM (Digital Elevation Model), secondary data from the BPS 2020 Karangasem Regencyt in Figures, geological maps, settlement data and land cover maps. The results based on these data show the number of areas affected by the eruption of Mount Agung, the data states that the data area with low vulnerability has an area of 0.001490 Ha. Medium vulnerability data has an eruption affected area of 47.024493897 Ha. While the high vulnerability has an affected area of 36.878843877 Ha. Differences in the level of vulnerability are influenced by social vulnerability, physical vulnerability, and environmental vulnerability.Keywords: Delineation, Eruption, GIS, Mount Agung, Vulnerability

Fine-resolution land cover mapping over large and mountainous areas for Lāna‘i, Hawaii using posterior probabilities, and expert knowledge

ABSTRACT The task of accurately mapping species-specific vegetation cover in remote and topographically complex regions like those found in Hawaiʻi presents unique challenges. This study leverages a machine learning approach to accurately classify vegetation into fine species-specific classes across the island of Lāna‘i, Hawaii, offering a novel methodology for tackling such challenges. Utilizing high-resolution WordView-2 satellite imagery, a neural network classifier and a custom lidar-based geometric correction, we introduced two new approaches to refine our high-resolution land cover classifications. This included the implementation of prior-based adjustments to class posterior probabilities to enhance land cover classification accuracy. Moreover, we developed mixed hierarchical classification maps that use class posterior probabilities to identify, at the pixel level, the finest land cover class that meets a user-defined confidence threshold. The resulting high-resolution land cover map for Lāna‘i captures the rich diversity and distribution of native and invasive plant species with high overall accuracy, generally exceeding 95%, based on independent ground control data. The capacity to produce wall-to-wall species-level vegetation maps provides a new window into monitoring vegetation dynamics on Lāna‘i and similarly remote and topographically complex regions, and contributes to our broader understanding of ecosystem responses to invasive species, climatic changes, and land management practices such as erosion and sediment control planning. Our approach offers a blueprint for similar efforts in other complex and remote ecosystems.

A GIS-based approach to determine the priority area for rainwater harvest in Kupang

Kupang, a pivotal economic and administrative hub in Nusa Tenggara Timur, Indonesia, faces recurring droughts resulting in crop failures, food insecurity, and health problems. Addressing this water crisis entails rainwater harvesting as a potential solution. This study establishes a comprehensive framework for prioritizing rainwater harvesting areas in Kupang. Using the weighted overlay method and open-source GIS software, our approach involves three stages: identifying drought and flood priority zones, defining suitability indicators, and quantifying the potential of rainwater harvesting systems. By leveraging climatological, geological, and hydrological information, we determine priority areas for drought and flood management. Our analysis of rainwater harvesting suitability integrates climatological information, land use and land cover mapping, runoff potential assessment, and water use index. Quantification of rainwater harvesting system requirements hinges on rooftop area and population data. The entire wards in Kupang are classified as high priorities for drought mitigation. Therefore, rainwater harvesting is a viable strategy for all wards. The most prioritized and in-demand wards, Oesapa, Sikumana, Lasiana, and Liliba, have the potential to install a minimum of 12,000 rainwater harvesting systems, each with a 1500-liter volume barrel.