High-resolution Land Cover Research Articles

Error-reduced Digital Elevation Models and High-Resolution Land Cover Roughness in Mapping Tsunami Exposure for Low Elevation Coastal Zones

Error-reduced Digital Elevation Models and High-Resolution Land Cover Roughness in Mapping Tsunami Exposure for Low Elevation Coastal Zones

A Constantly Updated Flood Hazard Assessment Tool Using Satellite-Based High-Resolution Land Cover Dataset Within Google Earth Engine

This work aims to develop a constantly updated flood hazard assessment tool that utilizes readily available datasets derived by remote sensing techniques. It is based on the recently released global land use/land cover (LULC) dataset Dynamic World, which is readily available, covering the period from 2015 until now, as an open data source within the Google Earth Engine (GEE) platform. The tool is updated constantly following the release rate of Sentinel-2 images, i.e., every 2 to 5 days depending on the location, and provides a near-real-time detection of flooded areas. Specifically, it identifies how many times each 10 m pixel is characterized as flooded for a selected time period. To investigate the fruitfulness of the proposed tool, we provide two different applications; the first one in the Thrace region, where the flood hazard map computed with the presented herein approach was compared against the flood hazard maps developed in the frames of the EU Directive 2007/60, and we found several inconsistencies between the two approaches. The second application focuses on the Thessaly region, aiming to assess the impacts of a specific, unprecedented storm event that affected the study area in September 2023. Moreover, a new economic metric is proposed, named maximum potential economic loss, to assess the socioeconomic implications of the flooding. The innovative character of the presented methodology consists of the use of remotely sensed-based datasets, becoming available at increasing rates, for developing an operational instrument that defines and updates the flood hazard zones in real-time as required.

The trace of the trees: a historically situated geospatial assessment of deforestation in Bosawas biosphere reserve

ABSTRACT Deforestation is often framed as one of Nicaragua’s most pressing ecological challenges. Historically, the country has addressed the issue by relying on fence-and-control approaches to conservation. This is the case of Bosawas, the largest biosphere reserve in Central America. Despite advancements in remote sensing data, few spatially explicit attempts have been made to assess how this type of conservation scheme interacts with the country’s deforestation trends. This research combines two independently generated high-resolution land cover maps and agrarian census data to assess the extent of deforestation that has taken place in Bosawas from 1990 to 2022. Our findings indicate that the establishment of the biosphere reserve has proven ineffective in preventing deforestation and evidence that its current trend is closely related to the encroachment of capitalistic agrarian-based modes of production. This encroachment is rooted in a long history of state-led interventions, which has led to the gradual dissolution of local customary social orders, allowing the penetration of new ones that privilege individualistic and profit-oriented forms of land tenure and resources exploitation. Hence, conservation strategies that neglect the historical and political-economic roots of deforestation in Bosawas risk aggravating territorial conflicts and facilitating land dispossession modalities affecting mostly local inhabitants.

Reconstruction of 30 m Land Cover in the Qilian Mountains from 1980 to 1990 Based on Super-Resolution Generative Adversarial Networks

Long time series of annual land cover with fine spatio-temporal resolutions play a crucial role in studying environmental climate change, biophysical modeling, carbon cycling models, and land management. Despite a strong consistency exhibited by several publicly available medium to fine resolution global land cover datasets, significant discrepancies exist at the regional scale; moreover, only every 5/10 year land cover were available. Consequently, high-quality annual land cover datasets before 2000 are unavailable in China. In this study, we proposed a deep learning-based method by integrating multiple remote sensing data from different platforms with historical high spatial resolution land cover datasets (CNLUCC) to derive the 30 m annual land cover maps from 1980 to 1990 for Qilian Mountain. First, the super-resolution generative adversarial network models for upscaling the 5.5 km AVHRR NDVI to 250 m were established by employing the AVHRR and MODIS NDVI data with the same year as input, and the early time series AVHRR NDVI data were subsequently upscaled to 250 m through the above models. Second, the breaks for the additive seasonal and trend (BFAST) change detection algorithm was applied to the upscaled time series NDVI data to detect the change time of different land cover types. Third, the CNLUCC data in 1980 and 1990 were updated to annual land cover datasets from 1980 to 1990 and the annual mapping results provided insights into the dynamic processes of urbanization, deforestation, water bodies, and farmland from 1980 to 1990. Finally, comprehensive analysis and validation were carried out for evaluation and an overall accuracy of 77.26% for the land cover product in 1986 was achieved.

Cross-resolution land cover classification using outdated products and transformers

ABSTRACT Large-scale, high-resolution land cover classification is a prerequisite for constructing Earth system models and addressing ecological and resource issues. Advancements in satellite sensor technology have led to improvements in spatial resolution and wider coverage areas. Nevertheless, the lack of high-resolution labelled data is still a challenge, hindering the large-scale application of land cover classification methods. In this study, a Transformer-based weakly supervised method for cross-resolution land cover classification using outdated data is proposed. First, to capture long-range dependencies without overlooking the fine-grained details of objects, a U-Net-like Transformer based on a reverse difference mechanism (RDM) using dynamic sparse attention is designed. Second, an anti-noise loss calculation module based on optimal transport (OT) is proposed. The anti-noise loss calculation identifies confident areas and vague areas based on the OT matrix, which relieves the effect of noises on outdated land cover products. By introducing a weakly supervised loss with weights and using an unsupervised loss, the RDM-based U-Net-like Transformer was trained. Remote sensing images with 1 m resolutions and the corresponding ground truths of six states in the United States were used to validate the performance of the proposed method. The experiments used outdated land cover products with 30 m resolutions from 2013 as training labels and produced land cover maps with 1 m resolutions from 2017. The results showed the superiority of the proposed method over state-of-the-art methods. The code is available at https://github.com/yu-ni1989/ANLC-Former.

Leveraging machine learning and Landsat time series for high-resolution mapping of mining-induced vegetation changes in Ouagadougou, Burkina Faso

Quarries are open pit mines, where construction materials such as granite and clay are extracted from the earth's surface, leading to a major disturbance of vegetation and subsequent degradation of ecosystem services. Assessing mining-associated degradation over time remains a challenge. This paper uses a temporal series of Landsat satellite image extracted from Google Earth Engine (GEE) for monitoring mining effects on land cover around the West African city of Ouagadougou, Burkina Faso. We conducted a binary classification of quarry and non-quarry using Landsat 9 images. To account for varying quarry patterns, we applied the LandTrendr algorithm to analyze images from 1990 to 2022, mapping annual vegetation disturbance and recovery. This generated high-resolution land cover maps with over 90 % accuracy across 257 quarries (38 km²). LandTrendr identified disturbance years with 87 % accuracy and assessed recovery in abandoned quarries. Remote sensing accuracy was validated through fieldwork and analysis of historical aerial photos. Our findings revealed that major disturbances coincided with new quarrying activities, particularly during urban expansion from 2005 to 2019, with NDVI decreasing by 0.3 in active mining areas. Vegetation recovery was observed in 23 % of the abandoned quarries, with NDVI increases by 0.15 within five years post abandonment, particularly in clay quarries. The strongest recovery occurred in given up abandoned from 2015 to 2019, aligned with increased conservation efforts. Our approach offers valuable insights into mining impacts and vegetation resilience in semi-arid environments, informing sustainable urban planning and environmental management in rapidly transforming regions of West Africa.

Deciphering the effects of 2D/3D urban morphology on diurnal cooling efficiency of urban green space

Urban green spaces (UGS) have emerged as a main nature-based solution proven to effectively cool urban areas, and cooling efficiency (CE) serves as a prominent indicator for assessing the performance of UGS. Yet few studies have explored the diurnal dynamics of CE and the comprehensive effects of both 2D and 3D urban morphology on CE over a 24-h period. In this study, we employed diurnal land surface temperature (LST) data from Ecosystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) to delve into the diurnal CE of UGS within the urban core area of megacity Paris, France. Meanwhile, using high-resolution land cover data, digital height model, and explainable machine learning models, we elucidated the intricate relationship between various 2D and 3D urban morphology metrics and CE during a 24-h cycle. In summary, city-scale continuous monitoring revealed diurnal CE variations, with values ranging from 0.008 °C to 0.13 °C and a standard deviation of 0.04 °C. On an average of a day, the relative importance of the 2D and 3D urban form indicators was 77.25 % and 22.75 %, respectively. Enhancing the dispersion of trees or improving the integrity of non-tree vegetation patches proves to be an effective strategy for augmenting CE. The results can be further used in urban planning to improve urban thermal resilience and adaptability.

Big Data-driven MLOps workflow for annual high-resolution land cover classification models

Developing an annual and global high-resolution land cover map is one of the most ambitious tasks in remote sensing, with increasing importance due to the continual rise in validated data and satellite imagery. The success of land cover classification models largely hinges on the data quality, coupled with the application of Big Data techniques and distributed computing. This is essential for efficiently processing the extensive volume of available satellite data. However, maintaining the lifecycle of several annual Machine Learning models presents a complex challenge. The rise of Machine Learning Operations offers an opportunity to automate the maintenance of these models, a feature particularly beneficial in systems that require generating new models each year alongside the continuous integration of validated data. This article details the development of an end-to-end MLOps workflow, meticulously integrating land cover classification models that employ Big Data strategies for processing large-scale, high-resolution spatial data. The workflow is designed within a Kubernetes environment, achieving on-demand auto-scaling, distributed computing, and load balancing. This integration demonstrates the practicality and efficiency of managing and deploying models that treat satellite imagery in an automated, scalable framework, thus marking a significant advancement in remote sensing and MLOps.

Urban impervious cover characterization for rainfall-runoff analysis: Impacts of data availability and resolution

Urban watershed hydrologic and water quality models, and stormwater control measure (SCM) designs, rely on accurate determination of stormwater runoff volume and impervious areas contributing to runoff. This research assesses the impacts of data availability and spatial resolution on two of the main indicators of urban impervious cover: total impervious area (TIA) and directly connected impervious area (DCIA). The research also explores the relationship between TIA, DCIA, and the effective impervious area (EIA), another important indicator of urban impervious cover. Using spatial programming, surface runoff was tracked, from originated to discharged locations, in nine urban catchments (ranging from 16 to 2035 ha) in Minnesota, USA, under various scenarios combining geospatial data types and resolutions. TIA fractions derived from low-resolution, nationally available imperviousness data were not statistically different than those from high-resolution land cover (LC) data modified by “unshading” to remove tree canopies overlaying impervious surfaces. Comparison of DCIA and EIA values indicated that modified LC is preferable for accurate DCIA delineation in ungauged catchments. EIA was 65 % of DCIA under the assumption that all rooftops were connected to sewer systems, while it exceeded DCIA by 34 % assuming all rooftops were unconnected, underscoring the importance of rooftop connectivity information in urban areas. The assumption of 0 % to 40 % rooftop connectivity resulted in comparable DCIA and EIA values in the study catchments. Using roads as the runoff collection system (instead of sewer inlets) did not significantly alter DCIA values at 5 % level, when unshaded LC was used. Given the absence of observed runoff data in most urban areas, DCIA serves as an appropriate imperviousness indicator for determining runoff in ungauged urban watersheds. However, achieving accurate DCIA delineation necessitates high-resolution LC data, emphasizing the need for relevant urban management organizations to develop such data.

Centrality to the metapopulation is more important for population genetic diversity than habitat area or fragmentation.

Drift and gene flow affect genetic diversity. Given that the strength of genetic drift increases as population size decreases, management activities have focused on increasing population size through preserving habitats to preserve genetic diversity. Few studies have empirically evaluated the impacts of drift and gene flow on genetic diversity. Kryptolebias marmoratus, henceforth 'rivulus', is a small killifish restricted to fragmented New World mangrove forests with gene flow primarily associated with ocean currents. Rivulus form distinct populations across patches, making them a well-suited system to test the extent to which habitat area, fragmentation and connectivity are associated with genetic diversity. Using over 1000 individuals genotyped at 32 microsatellite loci, high-resolution landcover data and oceanographic simulations with graph theory, we demonstrate that centrality (connectivity) to the metapopulation is more strongly associated with genetic diversity than habitat area or fragmentation. By comparing models with and without centrality standardized by the source population's genetic diversity, our results suggest that metapopulation centrality is critical to genetic diversity regardless of the diversity of adjacent populations. While we find evidence that habitat area and fragmentation are related to genetic diversity, centrality is always a significant predictor with a larger effect than any measure of habitat configuration.

Generating 10-Meter Resolution Land Use and Land Cover Products Using Historical Landsat Archive Based on Super Resolution Guided Semantic Segmentation Network

Generating high-resolution land cover maps using relatively lower-resolution remote sensing images is of great importance for subtle analysis. However, the domain gap between real lower-resolution and synthetic images has not been permanently resolved. Furthermore, super-resolution information is not fully exploited in semantic segmentation models. By solving the aforementioned issues, a deeply fused super resolution guided semantic segmentation network using 30 m Landsat images is proposed. A large-scale dataset comprising 10 m Sentinel-2, 30 m Landsat-8 images, and 10 m European Space Agency (ESA) Land Cover Product is introduced, facilitating model training and evaluation across diverse real-world scenarios. The proposed Deeply Fused Super Resolution Guided Semantic Segmentation Network (DFSRSSN) combines a Super Resolution Module (SRResNet) and a Semantic Segmentation Module (CRFFNet). SRResNet enhances spatial resolution, while CRFFNet leverages super-resolution information for finer-grained land cover classification. Experimental results demonstrate the superior performance of the proposed method in five different testing datasets, achieving 68.17–83.29% and 39.55–75.92% for overall accuracy and kappa, respectively. When compared to ResUnet with up-sampling block, increases of 2.16–34.27% and 8.32–43.97% were observed for overall accuracy and kappa, respectively. Moreover, we proposed a relative drop rate of accuracy metrics to evaluate the transferability. The model exhibits improved spatial transferability, demonstrating its effectiveness in generating accurate land cover maps for different cities. Multi-temporal analysis reveals the potential of the proposed method for studying land cover and land use changes over time. In addition, a comparison of the state-of-the-art full semantic segmentation models indicates that spatial details are fully exploited and presented in semantic segmentation results by the proposed method.

Impact of High-Resolution Land Cover on Simulation of a Warm-Sector Torrential Rainfall Event in Guangzhou

This study on the warm-sector heavy rainfall event in Guangzhou on 7 May 2017, examined the effects and mechanisms of incorporating 30 m high-resolution land surface data into its numerical simulation. The updated 1km numerical model, integrating 30 m high-resolution land surface data, successfully captured the initiation, back-building, and organized development of warm-sector convections in Huadu and Zengcheng District. The analysis revealed that the high spatial resolution of the surface data led to a reduced urban area footprint (urban −6.31%), increased vegetation cover (forest 11.63%, croplands 1%), and enhanced surface runoff (water 2.77%) compared with a model’s default land cover (900 m). These changes mitigated the urban heat island (UHI) effect within the metropolitan area and decreased the surface sensible heat flux. This reduction contributed to a pronounced temperature gradient between Huadu Mountain and the urban area. Additionally, a stronger high-pressure recirculation and sea–land breezes facilitated the transport of warm and moist air from the sea inland, creating a humid corridor along the sea–land interface. The consistent influx of warm and moist air near the mountain front, where strong temperature gradients were present, forcibly triggered warm-sector convection, intensifying its organization. This study highlighted the critical role of high-resolution land surface data in the accurate numerical simulation of warm-sector heavy rainfall.

A Spatial Analysis of Urban Tree Canopy Using High-Resolution Land Cover Data for Chattanooga, Tennessee

Urban tree canopy (UTC) provides urban residents with numerous benefits, including positive mental and physical health, the mitigation and prevention of urban heat islands, and a sense of place. Numerous studies have shown that as the wealth of a community decreases, so does the amount of UTC found in the community; thus, wealthier communities are more likely to enjoy the benefits that urban forests provide. Emerging technologies in remote sensing and GIS are allowing for new opportunities to study and understand the relationships between urban neighborhoods and UTC. In this study, land cover data for Chattanooga, Tennessee were derived from high-resolution (50 cm) multispectral imagery to assess the previously unknown extent and distribution of UTC and to measure the extent of UTC by neighborhood and census block group level. Using exploratory regression analysis, variables representing income, population density, race, educational attainment, and urban heat islands were analyzed to investigate the influence of UTC on neighborhood characteristics. This study found that UTC represented half of the total land cover composition, the tree equity was not as profound as shown in other cities, and the lack of UTC likely influences the prevalence of urban heat islands. This study also shows the importance and utility of using high-resolution imagery and land cover to assess and understand the impact and distribution of UTC in urban environments.

Local feature acquisition and global context understanding network for very high-resolution land cover classification

Very high-resolution remote sensing images hold promising applications in ground observation tasks, paving the way for highly competitive solutions using image processing techniques for land cover classification. To address the challenges faced by convolutional neural network (CNNs) in exploring contextual information in remote sensing image land cover classification and the limitations of vision transformer (ViT) series in effectively capturing local details and spatial information, we propose a local feature acquisition and global context understanding network (LFAGCU). Specifically, we design a multidimensional and multichannel convolutional module to construct a local feature extractor aimed at capturing local information and spatial relationships within images. Simultaneously, we introduce a global feature learning module that utilizes multiple sets of multi-head attention mechanisms for modeling global semantic information, abstracting the overall feature representation of remote sensing images. Validation, comparative analyses, and ablation experiments conducted on three different scales of publicly available datasets demonstrate the effectiveness and generalization capability of the LFAGCU method. Results show its effectiveness in locating category attribute information related to remote sensing areas and its exceptional generalization capability. Code is available at https://github.com/lzp-lkd/LFAGCU.

Impervious cover change as an indicator of environmental equity

Pattern-focused environmental equity research has been underpinned by high-resolution remotely sensed data to uncover spatial relationships between environmental amenities (e.g., urban tree cover) and socio-economic status (SES). A constraint imposed by reliance on high-resolution data is the inability to examine temporal patterns, primarily because of the cost of data production and the nascent state of high-resolution land cover mapping. The lack of temporal monitoring is a clear gap in pattern-focused environmental equity research. We examined temporal (2001–2019) relationships between a disamenity, impervious cover (IC), and demographic attributes for the entirety of the conterminous United States. Our main finding was 2001–2019 increases in IC were more pervasive in minority communities but these communities were not necessarily poor, and only rarely poorly educated or non-English speaking. We supported our use of IC from moderate resolution data by comparing it to high-resolution data for 24 cities within the conterminous United States. Mean Absolute Deviation (MAD) was 4.8% overall, ranging from 2.2% to 11.3% across the 24 locations. Differences in classification objectives contributed to differences in %IC estimates between the two sources.

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.

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.

Post-drainage vegetation, microtopography and organic matter in Arctic drained lake basins

Wetlands in Arctic drained lake basins (DLBs) have a high potential for carbon storage in vegetation and peat as well as for elevated greenhouse gas emissions. However, the evolution of vegetation and organic matter is rarely studied in DLBs, making these abundant wetlands especially uncertain elements of the permafrost carbon budget. We surveyed multiple DLB generations in northern Alaska with the goal to assess vegetation, microtopography, and organic matter in surface sediment and pond water in DLBs and to provide the first high-resolution land cover classification for a DLB system focussing on moisture-related vegetation classes for the Teshekpuk Lake region. We associated sediment properties and methane concentrations along a post-drainage succession gradient with remote sensing-derived land cover classes. Our study distinguished five eco-hydrological classes using statistical clustering of vegetation data, which corresponded to the land cover classes. We identified surface wetness and time since drainage as predictors of vegetation composition. Microtopographic complexity increased after drainage. Organic carbon and nitrogen contents in sediment, and dissolved organic carbon (DOC) and dissolved nitrogen (DN) in ponds were high throughout, indicating high organic matter availability and decomposition. We confirmed wetness as a predictor of sediment methane concentrations. Our findings suggest moderate to high methane concentrations independent of drainage age, with particularly high concentrations beneath submerged patches (up to 200 μmol l−1) and in pond water (up to 22 μmol l−1). In our DLB system, wet and shallow submerged patches with high methane concentrations occupied 54% of the area, and ponds with high DOC, DN and methane occupied another 11%. In conclusion, we demonstrate that DLB wetlands are highly productive regarding organic matter decomposition and methane production. Machine learning-aided land cover classification using high-resolution multispectral satellite imagery provides a useful tool for future upscaling of sediment properties and methane emission potentials from Arctic DLBs.

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.

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.