Vegetation Cover Mapping Research Articles

Digital Mapping of Soil Salinity in the Southern Steppe Zone of Russia Based on Artificial Neural Networks and Linear Regression

Remote sensing data are an important source of information for monitoring and mapping vegetation cover. Machine-learning methods are a modern and powerful tool for data processing. However, machine-learning methods combined with remote sensing data have hardly been used for soil salinity assessment and mapping in the southern steppe zone of Russia. This paper examines the possibility of applying different spectral characteristics to map soil salinization in solonetzic complexes in the southern steppe zone of Russia (Republic of Kalmykia) using machine-learning methods. A number of predictors were considered, including reflectance coefficients in blue, green, red, and infrared spectral zones; vegetation indices (NDVI, NDVIt, TVI, SAVI, MSAVI, EVI1–EVI4); salinity indices (SI1–SI6); intensity indices (Int1, Int2); brightness index (BI); and an index proposed by the authors. High-resolution images from the QuickBird (2.4 m) and SuperView-1 (2 m) satellites were used. Soil salinity was assessed using two indicators: specific electrical conductivity in water suspension (EC1:5) and sodium activity (aNa1 : 5). Two different machine-learning models were applied in the study: linear regression and neural networks. According to the results obtained, the linear regression model for EC1 : 5 in 0- to 30-, 0- to 50-, and 0- to 100-cm layers has coefficients of determination (R2) of 0.53, 0.59, and 0.79 on the training sample; the test sample managed to obtain coefficients of determination of 0.49, 0.58, and 0.70, respectively. The neural-network model has significantly higher coefficients of determination: R2 for EC1 : 5 in 0- to 30-, 0- to 50-, and 0- to 100-cm layers on the training sample is equal to 0.68, 0.91, and 0.97, and on the test sample, 0.87, 0.86, and 0.88, respectively. This fact indicates a greater potential of this model for cartographic modeling of soil salinity. The best predictors were the following indices: NDVIt, TVI, EVI1, and Int1. The study has shown the potential of using the neural-network model and spectral indices obtained with SuperView-1 images for soil salinity mapping of solonetzic complexes in the south of the steppe zone of Russia.

Digital mapping of soil salinity in the southern steppe zone of Russia based on artificial neural networks and linear regression

Remote sensing data is an important source of information for monitoring and mapping vegetation cover. Machine learning methods are a modern and powerful tool for data processing. However, machine learning methods combined with remote sensing data were practically not used for soil salinity assessment and mapping in the southern steppe zone of Russia. This paper examines the possibility of applying various spectral characteristics to soil salinity mapping in solonetzic complexes in the southern steppe zone of Russia (Republic of Kalmykia) using machine learning methods. A number of predictors were considered, including reflectance coefficients in blue, green, red, infrared spectral zones, vegetation indices (NDVI, NDVIt, TVI, SAVI, MSAVI, EVI1-EVI4), salinity indices (SI1-SI6), intensity indices (Int1, Int2), brightness index (BI), and an index proposed by the authors. High-resolution images from QuickBird (2.4 m) and SuperView-1 (2 m) satellites were used. Soil salinity was assessed using two indicators: specific electrical conductivity in water suspension (EC1:5) and sodium activity (aNa1:5). Two different machine learning models were applied in the study: linear regression and neural networks. According to the results obtained, the linear regression model for EC1:5 in 0–30, 0–50, 0–100 cm layers has coefficients of determination (R2) of 0.53, 0.59, 0.79 on the training sample; the test sample managed to obtain coefficients of determination of 0.49, 0.58, 0.70, respectively. The neural network model has significantly higher coefficients of determination: R2 for EC1:5 in layers 0–30, 0–50, 0–100 cm on the training sample is equal to 0.68, 0.91, 0.97; on the test sample is 0.87, 0.86, 0.88, respectively. This indicates a greater potential of this model for cartographic modeling of soil salinity. The best predictors were the following indices: NDVIt, TVI, EVI1, Int1. The study showed the potential of using the neural network model and spectral indices obtained with SuperView-1 images for soil salinity mapping of solonetzic complexes in the south of the steppe zone of Russia.

Improving the Accuracy of RPA Image Classification in Vegetation Mapping of Magsaysay, Occidental Mindoro using RGB Indices, Canopy Heights, and Feature Importance Weighting

Abstract. Mapping vegetation cover is an important step in generating baseline data for various purposes such as smart agriculture, disaster and hazard monitoring, as well as risk assessment and planning. For this purpose, the use of Remotely Piloted Aircraft (RPA) has become prevalent in recent years as an efficient and cost-effective way of obtaining very-high-resolution images. However, it is limited by its lack of spectral bands used for discriminating between land cover classes, especially vegetation. An object-based approach was used due to its suitability with high-resolution input datasets, as it can recognize complex shapes and patterns aside from spectral characteristics. The drone images were segmented using optimal parameters to produce image objects which were subsequently classified through supervised learning using the Random Forest (RF) algorithm. This study incorporated non-conventional spectral indices that use RGB bands only, such as Triangular Greenness Index (TGI), Excess Green (ExG), and Tree-Grass Differentiation Index (TGDI), as well as the canopy height data derived from RPA photogrammetry to improve classification accuracy. To further improve model performance, appropriate band weights for segmentation were determined by running a RF classifier to obtain band importance values. Accuracy assessments reveal that using additional indices and heights improved the accuracy resulting in a 20% increase in the average f1-score, with the vegetation classes improving by a 25% increase in their f1-scores (8–41% improvement per class). Using the integration of band importance values as weights to the object-based segmentation slightly decreased accuracy values for the vegetation classes by an average of 0.04 in the f-1 score. The methods developed to improve the accuracy of RPA image classification make it more suitable for mapping vegetation.

Assessing the Potential of UAV for Large-Scale Fractional Vegetation Cover Mapping with Satellite Data and Machine Learning

Fractional vegetation cover (FVC) is an essential metric for valuating ecosystem health and soil erosion. Traditional ground-measuring methods are inadequate for large-scale FVC monitoring, while remote sensing-based estimation approaches face issues such as spatial scale discrepancies between ground truth data and image pixels, as well as limited sample representativeness. This study proposes a method for FVC estimation integrating uncrewed aerial vehicle (UAV) and satellite imagery using machine learning (ML) models. First, we assess the vegetation extraction performance of three classification methods (OBIA-RF, threshold, and K-means) under UAV imagery. The optimal method is then selected for binary classification and aggregated to generate high-accuracy FVC reference data matching the spatial resolutions of different satellite images. Subsequently, we construct FVC estimation models using four ML algorithms (KNN, MLP, RF, and XGBoost) and utilize the SHapley Additive exPlanation (SHAP) method to assess the impact of spectral features and vegetation indices (VIs) on model predictions. Finally, the best model is used to map FVC in the study region. Our results indicate that the OBIA-RF method effectively extract vegetation information from UAV images, achieving an average precision and recall of 0.906 and 0.929, respectively. This method effectively generates high-accuracy FVC reference data. With the improvement in the spatial resolution of satellite images, the variability of FVC data decreases and spatial continuity increases. The RF model outperforms others in FVC estimation at 10 m and 20 m resolutions, with R2 values of 0.827 and 0.929, respectively. Conversely, the XGBoost model achieves the highest accuracy at a 30 m resolution, with an R2 of 0.847. This study also found that FVC was significantly related to a number of satellite image VIs (including red edge and near-infrared bands), and this correlation was enhanced in coarser resolution images. The method proposed in this study effectively addresses the shortcomings of conventional FVC estimation methods, improves the accuracy of FVC monitoring in soil erosion areas, and serves as a reference for large-scale ecological environment monitoring using UAV technology.

Post-wildfire boreal forest vegetation cover change mapping via information fusion for secondary disaster risk assessments

Post-wildfire vegetation cover damage and loss can escalate the risks of secondary disasters such as flood, landslide, and water contamination, particularly in a major wildfire affected region where human settlements are situated. In assessments of the secondary disaster risks, the post-wildfire vegetation cover change plays a key role in influencing the distribution and intensity of the risks. In this work, a processing framework for mapping post-wildfire vegetation cover changes through information fusion has been generated and tested using Landsat8 and WorldView imagery data. The test site was the boreal forest region surrounding Fort McMurray, Alberta, Canada, affected by a massive wildfire in May 2016. The derived map results indicate that the fusion process in the framework is effective for generation of post-wildfire vegetation cover change information. The use of WorldView data revealed more variation details in distribution of the vegetation cover burn damages than use of Landsat data. Moreover, the uncertainty in vegetation burn severity using Landsat-based Differenced Normalized Burn Ratio (dNBR) index exists in the areas with low dNBR reading values due to the sub-pixel effect. The forest burn severity measured with dNBR index can be underestimated due to the quick herbaceous cover recovery after wildfire. These uncertainties in the post-wildfire vegetation cover mapping should be taken into consideration when the derived information is being used for risk assessments.

Long-term continuous changes of vegetation cover in desert oasis of a hyper-arid endorheic basin with LandTrendr algorithm

Ecological water diversion projects (EWDP) is one of the most important initiatives for oases restoration in arid endorheic basins. Fine monitoring of the long-term and continuous changes in vegetation cover before and after the EWDP is important to evaluate the effects of EWDP on ecosystem restoration. In this study, a trajectory-based change detection approach was applied with the Landsat-based detection of trends in disturbance and recovery (LandTrendr) algorithm on Google Earth Engine to map vegetation cover change trajectories in Ejina Oasis in the lower Heihe River Basin of China during 1990–2020. In addition to monotonic changes (i.e., continuous greening and continuous browning), LandTrendr also can flexibly capture the breaks of greening or browning events, including the greening with negative break, browning with positive break, browning to greening, and greening to browning. These changes mainly happened in shrub land and the area with land use transition. Approximately 82 % of the oasis ecosystem has been restored by the implementation of EWDP since 2000. However, in the past decade, the EWDP also caused some negative effects on vegetation cover in some areas. Both the categories of browning with positive break and greening to browning became widespread after 2010, with the cumulative proportions accounting for 79.4 % and 70.1 % of each category. The mean magnitude and slope of change in NDVI in these two categories after 2010 were −0.03 and −0.008 yr−1, −0.12 and −0.035 yr−1, respectively. This research demonstrated that the proposed approach was effective and useful for continuously monitoring the timing and extent of vegetation recovery processes in the hyper-arid endorheic basin. The EWDP plays an important role in vegetation restoration, but we also need to continuously monitor negative impacts which are crucial for environmental assessment and policy making in the arid endorheic basin.

Obtaining LULC distribution at 30-m resolution from Pixxel’s first technology demonstrator hyperspectral imagery

ABSTRACT The recent deployment of new satellite-based hyperspectral imaging sensors, along with advances in classification methods, has enhanced the acquisition of information on the spatiotemporal patterns of Land Use/Land Cover (LULC).. With this context, the study presented in this paper seeks to assess the combined utilization of the Pixxel’s technology demonstrator hyperspectral satellite mission with the Support Vector Machines (SVM) and Random Forest (RF) machine learning classifiers for LULC mapping in an agricultural area located in Queensland, Australia. Accuracy assessment of the resulting LULC maps has been done based on relevant classification accuracy metrics. It has been observed that SVMs outperformed RF in terms of both overall classification and urban vegetation cover mapping accuracy. An overall accuracy of 92.34% with kappa of 0.90 was reported for the SVMs’ results, whereas for RF, the accuracy was 89.65% with 0.89 kappa, respectively. Both classifiers produced similar results for the classes of mango tree and sugarcane crops, whereas minor differences were observed in the depiction of water bodies and artificial surfaces. Our study findings provide insightful perspectives on the potential of Pixxel datasets for delineating the spatiotemporal distribution of LULC in agricultural landscapes, showcasing Pixxel’s hyperspectral sensors’ promising potential in this field.

Integrated Assessment of the Runoff and Heat Mitigation Effects of Vegetation in an Urban Residential Area

Urban vegetation has an essential role in maintaining the hydrological and energy balance. These processes in urban areas have been long overlooked due to the fragmentation and uneven feature of land use and vegetation distribution. Recent advances in remote sensing and the ease of data acquisition have allowed a more precise mapping of vegetation and land cover, making it possible to simulate the above processes at micro scales. This research selects a small typical residential catchment in Japan as the study area and the purpose of this research is to investigate the impact of urban vegetation on mitigating urban runoff and the heat island effect. The remote-sensed Normalized Difference Vegetation Index (NDVI) data were used to represent vegetation spatial distribution and seasonal variation. A single layer canopy model and the Storm Water Management Model were coupled to simulate interception, evapotranspiration, and runoff generation processes. The effects of vegetation amount and landscape patterns on the above processes were also considered. The results showed that the coupled model had a satisfactory performance in the modeling of these processes. When the vegetation amount was set to 1.4 times its original value, the summer total runoff had a 10.7% reduction and the average surface temperature had a 2.5 °C reduction. While the vegetation amount was 0.8 times its original value, the total runoff increased by 6%, and the average surface temperature in summer increased by 1.5 °C. The combination of green roof and dense street trees showed the best mitigation performance among the different landscape patterns. The results of this study could be used as a reference for future green infrastructure development in areas with similar climate and vegetation characteristics.

Analysis of Vegetation Cover Change with Satellite Images using Landsat 8 in the Inambari District in the Period 2013-2023

Multi-temporal analysis of vegetation cover allows the detection and monitoring of changes in vegetation cover, such as deforestation, reforestation, urban expansion or changes in land use, and also provides valuable information for territorial planning and land use management. . , those responsible for urban, regional and environmental planning can use these analyzes to make informed decisions about how to use and conserve natural resources in a sustainable way and also facilitate the environmental impact assessment of human activities, such as agriculture, mining or urbanization. The objective of this article is to identify and quantify the changes in vegetation cover in the Inambari district using Landsat 8 satellite images, which is non-experimental and quantitative in approach, the Arcgis 10.5 software was applied to make the maps of vegetation cover and was carried out in the District of Inambari, Province of Tambopata and Department of Madre de Dios, where the comparison of changes in vegetation cover was carried out in the years 2013, 2015, 2017 and 2023. The results showed that the variation The maximum vegetation cover was between the years 2015 and 2017 in the soil without vegetation cover, which was from 45190.27 to 264766.32 hectares with a percentage variation of 45.3% and the minimum variation was between the years 2013 to 2015 in the soil without vegetation cover, which It was from 25528.08 to 45190.27 Hectares with an increase of 4.1%.

UAV approaches for improved mapping of vegetation cover and estimation of carbon storage of small saltmarshes: examples from Loch Fleet, northeast Scotland

Abstract. Saltmarsh environments are recognised as key components of many biophysical and biochemical processes at the local and global scale. Accurately mapping these environments, and understanding how they are changing over time, is crucial for better understanding these systems. However, traditional surveying techniques are time-consuming and are inadequate for understanding how these dynamic systems may be changing temporally and spatially. The development of uncrewed aerial vehicle (UAV) technology presents an opportunity for efficiently mapping saltmarsh extent. Here we develop a methodology which combines field vegetation surveys with multispectral UAV data collected at two scales to estimate saltmarsh area and organic carbon storage at three saltmarshes in Loch Fleet (Scotland). We find that the Normalised Difference Vegetation Index (NDVI) values for surveyed saltmarsh vegetation communities, in combination with local tidal data, can be used to reliably estimate saltmarsh area. Using these area estimates, together with known plant community and soil organic carbon relationships, saltmarsh soil organic carbon storage is modelled. Based on our most reliable UAV-derived saltmarsh area estimates, we find that organic carbon storage is 15 %–20 % lower than previous area estimates would indicate. The methodology presented here potentially provides a cheap, affordable, and rapid method for saltmarsh mapping which could be implemented more widely to test and refine existing estimates of saltmarsh extent and is particularly well-suited to the mapping of small areas of saltmarsh environments.

Evaluation of Drought Using Meteorological Drought Indices, a Case Study: Alanya (Türkiye)

Drought is one of the most important challenges that many countries, especially countries in the Middle East region, are struggling with. Based on this, the study and monitoring of hydrological and drought factors is an important issue that can have a significant impact on management decisions in the field of water resources, especially in crisis management. Therefore, investigating the drought parameters is very important to understand the drought situation of a region. In this study, Alanya region, which is located on the southern coast of Turkey, was selected as a case study for drought analysis. Four drought indices for the selected region including: China Z-Index (CZI), Standardized Precipitation Index (SPI), Modified China Z-Index (MCZI) and Z-Score Index (ZSI) have been investigated. All these indicators have been investigated and evaluated using time scales of 1, 6, 12 and 24 months, the coefficient of determination (R2) has been calculated for each drought index with a different time scale and their results have been compared. The findings of the research showed that SPI and CZI drought indices performed better than other selected drought indices in identifying and effectively tracking drought severity. In addition to the study of dry events, wet events were also investigated, which indicates the presence of consecutive floods in the last years of the studied period in the region. The results indicated similar very dry events for the selected indicators in the 6-month period. Also, the rainfall trend for the period of 2015-2022 was taken into consideration to examine the rainfall of the last eight years. The results show that precipitation has decreased in recent years and has a downward trend in most months of the period in question, and the possibility of flood events due to sudden showers in the region has increased due to the continuation of droughts experienced in the years before 2015. Investigating soil moisture and vegetation for the selected period in the study area is also important for the evaluation of the drought level. Evaluation of the available land (vegetation) cover maps of the years 1975, 1985, 2000, 2010, 2020 and 2022 show that the vegetation cover has weakened over the years, and it has been evaluated as an indicator that the danger of drought in the region has increased.

Environmental Changes and Food Security in Ado-Ekiti, Nigeria

This study aims at evaluating the role of Geo-spatial techniques in vegetation cover analysis and mapping, environmental changes and food security in Nigeria. The challenges of food security in Nigeria especially in urban centres are enormous. The unmitigated rural-urban drift as a result of socio-economic development has made it imperative to address the problem of food security in the study area. Also, the issue of rapid urban development without appropriate attention given to the important issue of food security with persistent deteriorating infrastructure for urban food processing has led to rapid price changes, in food and other agricultural products. This study, therefore, attempts to demonstrate that the recent advancements in remote sensing integration with Geographic Information System technologies provide powerful tools for mapping and detecting changes in land use and land cover using Ado-Ekiti as a case study. The digital image processing techniques of remote sensing (RS) was employed to enable speedy, accurate and objective interpretation of the multispectral data used for the study, in order to understand the extent, rate and the magnitude of land use and land cover dynamics in the study area. The study reveals that the agricultural land and natural vegetation have the highest change. Much of their land areas were converted to built-up areas for the three study epochs (1992,2007,2022). The study concludes that there is a progressive encroachment of built-up areas to other land use in the study area, thereby resulting in significant environmental changes and affecting food security.

Assessing vegetation cover and valuing ecosystem services in southwestern Ethiopia: Implications for conservation.

The Bench-Sheko zone, parts of the Eastern Afromontane Biodiversity Hotspot, is characterized by its rich biodiversity. However, recent reductions in vegetation cover have drawn concern, highlighting the critical role of remote sensing in monitoring these alterations is critical. Furthermore, this study evaluates the economic value of the ecosystem services rendered by the diverse types of vegetation cover class in the area. The classification of vegetation types and measuring their ecosystem benefits are crucial for monitoring vegetation and analyzing land cover changes. estimating the value of ecosystem services is vital for environmental impact assessments, cost-benefit analyses, and creating payment schemes for these natural services. For the vegetation cover map, it uses Sentinel-2 satellite data and a Random Forest classifier using Google Earth Engine. Based on a properly chosen reference, ecosystem service assessment approaches include benefit transfer, direct market value, and the social cost of carbon. The results highlight the vegetation classes' enormous value and the services they offer. The largest value for Supporting Services (2829.3 USD ha⁻1yr⁻1) is found in the Remnant Forest, which makes up 30.98% of the total area. With the highest value for both cultural services (2847.7 USD ha⁻1yr⁻1) and regulatory services (5063.9 USD ha⁻1yr⁻1), the wetlands, which make up 4.35% of the total area, stand out. The total annual value of all ecosystem services provided by all vegetation classes is estimated to be 2.089 billion USD. When paired with methods for tracking and assessing changes in vegetation cover over time, high-resolution satellite images and precise classification algorithms can offer insightful information on the condition of the environment and support informed decision-making. In order to evaluate and convey to society and policymakers the advantages of vegetation cover, the value of ecosystem services is essential.

Catchment-scale patterns of geomorphic activity and vegetation distribution in an alpine glacier foreland (Kaunertal Valley, Austria)

The interaction between geomorphological and ecological processes plays a significant role in determining landscape patterns in glacier forelands. However, the spatial organization of this biogeomorphic mosaic remains unclear due to limited catchment-scale data. To address this gap, we used a multi-proxy analysis to map potential geomorphic activity related to surface changes induced by sediment transport on drift-mantled slopes and a glaciofluvial plain. High-resolution vegetation data were used to generate a catchment-scale map delineating vegetation cover and stability thresholds. The two maps were integrated, and an exploratory regression analysis was conducted to investigate the influence of geomorphic activity on vegetation colonization. The multi-proxy analysis resulted in an accurate mapping of catchment-wide geomorphic activity, with a validation accuracy ranging from 75.3% through field mapping to 85.9% through plot sampling. Through vegetation cover mapping, we identified biogeomorphic stability thresholds, revealing a mosaic of vegetation distribution. Distinct colonization patterns emerged across different geomorphic process groups, influenced by process magnitude and the time since the last disturbance event. The exploratory regression analysis showed that vegetation distribution is significantly affected by geomorphic processes. Based on the overlay of results regarding geomorphic activity and vegetation distribution, we suggest an age-independent framework that indicates four potential situations of biogeomorphic succession.

Satellite-derived plant cover maps vary in performance depending on version and product

Understanding the accuracy and appropriate application scale of satellite-derived maps of vegetation cover is essential for effective management of the vast, remote rangelands of the world. However, the underlying models are updated frequently and may combine with rapidly changing vegetation conditions to cause variations in accuracy and precision over time. We sought to assess how model performance changed between different versions of satellite-derived cover products (Rangeland Analysis Platform, RAP, and Rangeland Condition Monitoring and Assessment Protocol, RCMAP) and how the performance of LandCart compared to RAP and RCMAP. Additionally, we asked how variability in agreement between LandCart and field-based models varied with scale. We utilized an intensive dataset of grid-point intercept functional group cover data collected between 2016 and 2020 across the ∼113 kHA 2015 Soda Wildfire to 1) evaluate r2 agreement between versions of each satellite-derived product and plot-level field data and 2) assess relative standard error of agreement in cover between LandCart and continuous field-based Empirical Bayesian Kriging (EBK) regression models. Agreement between satellite- compared to field-plot values of cover (r2) increased for RCMAP Version 5.0 compared to Version 2.0, but there were negligible changes between versions of RAP. Despite this, r2 values of RCMAP and LandCart were nearly always less than RAP. Variability in agreement between EBK regression model cover and LandCart-derived cover decreased with the scale of consideration. Variability in agreement between satellite-derived cover products and field-based metrics is lowest at larger scale (mega-fire or regional) and varies from year to year and across versions, which could complicate detection of temporal changes in plant cover.

Conservation of tree phylogenetic diversity in the Brazilian Atlantic Forest: Dry habitats matter

Conservation assessments that aim to represent the pool of lineages that exist within a region are challenging due to incomplete knowledge of the spatial distribution and environmental preferences of distinct lineages. In this context, community-level models represent a powerful tool that can be used to predict spatial variation in phylogenetic composition. If lineages composition and habitat loss present a non-random spatial pattern within a region, we can expect that some lineages are more threatened by habitat loss than others. To test this hypothesis we combined multivariate analysis and a modelling approach to predict the phylogenetic composition of angiosperm tree/shrub communities in Rio de Janeiro State, southeastern Brazil, which is regarded as a plant endemism center within the Brazilian Atlantic forest biome. Then we correlated the resulting models with maps of vegetation cover and protected areas, to identify lineages subjected to higher habitat loss and clades that receive less protection. We found that angiosperm tree/shrub lineages are highly structured across distinct vegetation types and that a gradient of deforestation and land protection parallels the phylogenetic gradient formed by the distinct vegetation types. Consequently, some vegetation types and its associated angiosperm lineages are much more threatened by habitat loss and are less protected than others. Specifically, Ericales (asterids), Caryophyllales and Santalales are the most threatened clades in this region, along with their preferred habitats, seasonal forests and coastal white-sand forests (restingas). Protecting and restoring these dry habitats is critical for the conservation of tree and shrub phylogenetic diversity in the Brazilian Atlantic forest.

Thermodynamic Entropy: A Natural Metric for Landcover Classification

Most landcover (LC) studies employ physical characteristics involving spectral reflectance. This study employs the concept of energy and entropy for LC classification. Satellite imageries from Landsat-8, the Operational Land Imager (OLI) and the Thermal Infra-Red Sensor (TIRS) captured at 100 m for three years (2013, 2015 and 2017) and resampled to a spatial resolution of 30 m for multispectral measurements were acquired. The normalized difference vegetation index (NDVI) of the study area was computed for both the wet (September/October) and dry (March) seasons of years 2013, 2015 and 2017, respectively; and the vegetation cover maps and landcover classification of the area based on the NDVI values were generated. Land surface temperature (LST) and net radiation of the surface area were computed and used as inputs for computing the surface entropy flux (SEF) of the study area. Overall, the dry season of 2017 had the highest vegetation cover while the wet season vegetation cover was highest in 2015. The high dry season vegetation cover in 2017 is attributable to higher level of living biomass than previous years. NDVI-based LC classification of the area showed an overlap in distinguishing between built-up areas and vegetation cover as well as between bare (land) surface and free water bodies. This is attributable to skewed measure of centrality for the sample distribution possibly resulting from the quality (resolution) of data used or sampling techniques. Free water bodies had the highest SEF values that fall within expected behavior for bodies of such state (liquids). The vegetation covers had the second highest SEF values for the entire site and the highest on land surface, which could be attributed to higher latent heat fluxes of such covers resulting from the evapotranspiration processes. The bare surfaces and built-up area of the study area were observed to have the lowest SEF values. The LC of the study area was reclassified based on SEF values via ground truthing i.e., by taking statistical distribution of well-known surface classes across the years under study. This was successful in distinguishing vegetation cover, surfaces of free water bodies and bare surfaces. A regression analysis revealed that LST influences SEF by up to 69 – 75% while vegetation cover has no appreciable influence on SEF. A two-sample t-test showed a significant (P = 0.05) difference between the SEF for bare surfaces and that for vegetation cover. All these presents SEF as a reliable natural metric for LC classification.

Pemanfaatan Foto Udara Multispektral Untuk Sidik Cepat Kerapatan Tutupan Vegetasi Di Wilayah Perkotaan

Current technology enables NDVI analysis of multispectral aerial photographs, providing fast, detailed actual vegetation cover information. However, no study shows the best threshold value for mapping vegetation cover in urban areas. This study aims 1) to compare the area of vegetation cover on a semi-detailed and detailed scale, and 2) to determine the best NDVI threshold for mapping vegetation cover in urban areas. This study uses multispectral aerial photographs and Sentinel-2 satellite imagery (positioned as the baseline). Aerial imagery and photographs are processed for visible, red, and NIR bands. Band image processing and aerial photographs were used for NDVI analysis. The results show that the best threshold is at NDVI 0.2. The results of the identification of vegetation cover with Sentinel-2 imagery showed an area of 6.37 hectares or 28,2%, while the aerial photos resulted in an area of 11.4 hectares or 50,5%. The difference in area between the two spatial data is due to differences in the resolution of Sentinel-2 imagery with aerial photographs, 4 cm, and 10 m.

Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography

Woody vegetation landscape features, such as hedges, tree patches, and riparian vegetation, are important elements of landscape and biotic diversity. For the reason that biodiversity loss is one of the major ecological problems in the EU, it is necessary to establish efficient workflows for the registration and monitoring of woody vegetation landscape features. In the paper, we propose and evaluate a methodology for automated detection of changes in woody vegetation landscape features from a digital orthophoto (DOP). We demonstrate its ability to capture most of the actual changes in the field and thereby provide valuable support for more efficient maintenance of landscape feature layers, which is important for the shaping of future environmental policies. While the most reliable source for vegetation cover mapping is a combination of LiDAR and high-resolution imagery, it can be prohibitively expensive for continuous updates. The DOP from cyclic aerial photography presents an alternative source of up-to-date information for tracking woody vegetation landscape features in-between LiDAR recordings. The proposed methodology uses a segmentation neural network, which is trained with the latest DOP against the last known ground truth as the target. The output is a layer of detected changes, which are validated by the user before being used to update the woody vegetation landscape feature layer. The methodology was tested using the data of a typical traditional Central European cultural landscape, Goričko, in north-eastern Slovenia. The achieved F1 of per-pixel segmentation was 83.5% and 77.1% for two- and five-year differences between the LiDAR-based reference and the DOP, respectively. The validation of the proposed changes at a minimum area threshold of 100 m2 and a minimum area percentage threshold of 20% showed that the model achieved recall close to 90%.

Retaining natural vegetation to safeguard biodiversity and humanity.

Global efforts to deliver internationally agreed goals to reduce carbon emissions, halt biodiversity loss, and retain essential ecosystem services have been poorly integrated. These goals rely in part on preserving natural (e.g., native, largely unmodified) and seminatural (e.g., low intensity or sustainable human use) forests, woodlands, and grasslands. To show how to unify these goals, we empirically derived spatially explicit, quantitative, area-based targets for the retention of natural and seminatural (e.g., native) terrestrial vegetation worldwide. We used a 250-m-resolution map of natural and seminatural vegetation cover and, from this, selected areas identified under different international agreements as being important for achieving global biodiversity, carbon, soil, and water targets. At least 67 million km2 of Earth's terrestrial vegetation (∼79% of the area of vegetation remaining) required retention to contribute to biodiversity, climate, soil, and freshwater conservation objectives under 4 United Nations' resolutions. This equates to retaining natural and seminatural vegetation across at least 50% of the total terrestrial (excluding Antarctica) surface of Earth. Retention efforts could contribute to multiple goals simultaneously, especially where natural and seminatural vegetation can be managed to achieve cobenefits for biodiversity, carbon storage, and ecosystem service provision. Such management can and should co-occur and be driven by people who live in and rely on places where natural and sustainably managed vegetation remains in situ and must be complemented by restoration and appropriate management of more human-modified environments if global goals are to be realized.