Vegetation Mapping Research Articles

Contribution of time-series data cubes to classify urban vegetation types by remote sensing

Mapping urban vegetation types is important for urban planning and assessing environmental justice. Nowadays, despite data cubes projects are providing Analysis Ready Data to facilitate time-series analysis, we did not found studies employing these data for improving urban vegetation mapping. By relying solely on open data and software, this work proposes and evaluates the integration of time-series data cubes in a hybrid image classification method to map the intra-urban space, differentiating Tree cover and Herb-shrub. The urban area of Goiânia, Goiás, Brazil, is the study area. The hybrid method combined object-based classification of a pan-sharpened CBERS-4A WPM image (spatial resolution of 2 m) with the pixel-based classification of Sentinel-2 MSI time-series data cubes (10 m). Both approaches used the Random Forest algorithm. Objects from the CBERS-4A segmentation composed the spatial unit of analysis and the class assignment depended on the Sentinel-2 time-series urban land cover probabilities. Based on both Maps probabilities, Shannon entropy was calculated to attribute the final urban land cover to the objects. Urban land cover probabilities presented similar spatial distribution patterns for both classification approaches. Regarding the thematic maps, the Herb-shrub cover area was 35% higher in Sentinel-2 time-series classification than in GEOBIA classification, but Tree cover was 21% lower. In general, 75% of the study area was equally classified by the initial approaches. However, for 9% of the remaining area, the hybrid classification improved vegetation classes accuracies by 35%, contributing to the vegetation covers identification. Thus, this study contributes to methodological procedures for urban land cover study and demonstrates that hybrid maps based on open data are effective to reduce classification mistakes, allowing more accurate monitoring, planning, and designing of different urban vegetation types. Future research efforts should focus on scale compatibility between data of different spatial resolutions and expand the use of data cubes to integrate time-series information into the GEOBIA classification.

The species composition of local flea assemblages at a small scale in two South American regions is predominantly driven by niche-based mechanisms.

We applied a step-down factor analysis (SDFA) and multi-site generalised dissimilarity modelling (MS-GDM) to local flea communities harboured by small mammals (i.e., collected at small sampling sites over a short time period) in two South American regions (Patagonia and the Northwestern Argentina) with the aim of understanding whether these communities were assembled via niche-based or dispersal-based processes. The SDFA allows us to determine whether clusters of flea assemblages across different types of climates, vegetation and soils can be distinguished (suggesting niche-based assembly). MS-GDM allows us to determine whether a substantial proportion of the variation in flea species turnover is explained by specific climate-associated, vegetation-associated and soil-associated variables (indicating niche-based assembly) or host turnover (indicating dispersal-based assembly). Mapping of assemblages on climate, vegetation and soil maps, according to their loadings on axis 1 or axis 2 of the SDFA, did not provide clear-cut results. Clusters of similar loadings could be recognized within some, but not other, climate, vegetation and soil types. However, MS-GDM demonstrated that the effect of environmental variables (especially air temperature) on flea compositional turnover was much stronger than that of host turnover, indicating the predominance of niche-based processes in local community assembly. A comparison of our results with those on the mechanisms that drive species assembly in regional communities allows us to conclude that local and regional communities result from the joint action of niche-based and dispersal-based processes, with the former more important at a smaller spatial scale and the latter at a larger spatial scale.

A new regional vegetation mapping method based on terrain-climate-remote sensing and its application on the Qinghai-Xizang Plateau

A new regional vegetation mapping method based on terrain-climate-remote sensing and its application on the Qinghai-Xizang Plateau

Integrating Vegetation Indices and Spectral Features for Vegetation Mapping from Multispectral Satellite Imagery Using AdaBoost and Random Forest Machine Learning Classifiers

Vegetation mapping is an active research area in the domain of remote sensing. This study proposes a methodology for the mapping of vegetation by integrating several vegetation indices along with original spectral bands. The Land Use Land Cover classification was performed by two powerful Machine Learning techniques, namely Random Forest and AdaBoost. The Random Forest algorithm works on the concept of building multiple decision trees for the final prediction. The other Machine Learning technique selected for the classification is AdaBoost (adaptive boosting), converts a set of weak learners into strong learners. Here, multispectral satellite data of Dehradun, India, was utilised. The results demonstrate an increase of 3.87% and 4.32% after inclusion of selected vegetation indices by Random Forest and AdaBoost respectively. An Overall Accuracy (OA) of 91.23% (kappa value of 0.89) and 88.59% (kappa value of 0.86) was obtained by means of the Random Forest and AdaBoost classifiers respectively. Although Random Forest achieved greater OA as compared to AdaBoost, interestingly AdaBoost provided better class-specific accuracy for the Shrubland class compared to Random Forest. Furthermore, this study also evaluated the importance of each individual feature used in the classification. Results demonstrated that the NDRE, GNDVI, and RTVIcore vegetation indices, and spectral bands (NIR, and Red-Edge), obtained higher importance scores.

LOW-COST MAPPING OF FOREST UNDER-STOREY VEGETATION USING SPHERICAL PHOTOGRAMMETRY

Abstract. This paper is an attempt to respond to the growing need and demand of 3D data in forestry, especially for 3D mapping. The use of terrestrial laser scanners (TLS) dominates contemporary literature for under-storey vegetation mapping as this technique provides precise and easy-to-use solutions for users. However, TLS requires substantial investments in terms of device acquisition and user training. The search for and development of low-cost alternatives is therefore an interesting field of inquiry. Here, we use low-cost 360° cameras combined with spherical photogrammetric principles for under-storey vegetation mapping. While we fully assume that this low-cost approach will not generate results on par with either TLS or classical close-range photogrammetry, its main aim is to investigate whether this alternative is sufficient to meet the requirements of forest mapping. In this regard, geometric analyses were conducted using both TLS and close-range photogrammetry as comparison points. The diameter at breast height (DBH), a parameter commonly used in forestry, was then computed from the 360° point cloud using three different methods to determine if a similar order of precision to the two reference datasets can be obtained. The results show that 360° cameras were able to generate point clouds with a similar geometric quality as the references despite their low density, albeit with a significantly higher amount of noise. The effect of the noise is also evident in the DBH computation, where it yielded an average error of 3.5 cm compared to both the TLS and close-range photogrammetry.

Comparison of common classification strategies for large-scale vegetation mapping over the Google Earth Engine platform

• We assessed the effect of various sample properties on classification performance. • The use of pixel time series from fusion data achieved optimal results. • Target class proportions and sample time frames affected accuracy. • Suboptimal methods had a larger impact on the accuracy of minority classes. • The combined use of Sentinel MSI and SAR data provided accurate vegetation maps. Vegetation resources have an essential role in sustainable development due to their close relationship with natural resource management and environmental protection. The monitoring of land use and cover is key for a more sustainable management of these resources, and Earth Observation satellites have provided an increasingly powerful platform for performing this task. To date, numerous classification algorithms have been developed for vegetation mapping, but a comparative evaluation of the strategies commonly used in large-scale applications (50000 km 2 and above) is lacking. We developed a classification framework based on random forests and Sentinel data within the Google Earth Engine platform to assess the performance of various strategies over a complex landscape with a wide range of vegetation classes, plot configurations, and agricultural practices. These strategies differed in key aspects related to the characteristics of the classifier and the sample, and were evaluated by class-specific and general accuracy metrics. We found that the use of pixel time series features from fusion data, class-balanced labels, and multi-season time frames enhanced overall performance by 1.3%–14.1% over alternative approaches, but in some cases also generated tradeoffs of 1.6%–8.5% between recall and precision. In general, suboptimal strategies were particularly ineffective for the detection of infrequent classes. Finally, the different parameter values used in the random forests did not have a significant influence over the results. Our results demonstrate the importance of algorithm design in the effective classification of multiple vegetation classes, corroborate the usefulness of Sentinel data to generate mapping products of high resolution and accuracy, and highlight the importance of cloud computing tools for the development of vegetation mapping tools in large-scale applications. These findings provide general guidelines for the design of future classification frameworks, which are necessary for facilitating a sustainable management of natural resources worldwide.

Brazilian Cerrado native vegetation mapping with Google Earth Engine

Cerrado is the second largest biome of South America, with the major extension located in Brazil. This biome is considered a world biodiversity hotspot due to the rich and important biodiversity contrasting with the high threat of destruction. Monitoring using remote sensing approaches is a crucial tool for maintaining and preserving this large-scale biome. Through this context, this study compared and assessed different scenarios with Landsat 8 OLI multispectral bands and Vegetation Indices (EVI, NDVI, and SAVI) for the Cerrado mapping in Mato Grosso do Sul state, Brazil. An amount of 512 sample polygons were distributed into 2 classes: native vegetation and non-native vegetation. The Google Earth Engine platform was applied to the training and classification processes using the Random Forest method. The results showed that using Landsat 8 OLI bands obtained better results than the vegetation indices, with an overall accuracy and kappa index of 97.08% and 0.94, respectively. The mapping verified the existence of 26,80% of Cerrado original native vegetation in Mato Grosso do Sul state in 2019.

Machine-Learning Applications in Geosciences: Comparison of Different Algorithms and Vegetation Classes’ Importance Ranking in Wildfire Susceptibility

Susceptibility mapping represents a modern tool to support forest protection plans and to address fuel management. With the present work, we continue with a research framework developed in a pioneristic study at the local scale for Liguria (Italy) and recently adapted to the national scale. In these previous works, a random-forest-based modeling workflow was developed to assess susceptibility to wildfires under the influence of a number of environmental predictors. The main novelties and contributions of the present study are: (i) we compared models based on random forest, multi-layer perceptron, and support vector machine, to estimate their prediction capabilities; (ii) we used a more accurate vegetation map as predictor, allowing us to evaluate the impacts of different types of local and neighboring vegetation on wildfires’ occurrence; (iii) we improved the selection of the testing dataset, in order to take into account the temporal variability of the burning seasons. Wildfire susceptibility maps were finally created based on the output probabilistic predicted values from the three machine-learning algorithms. As revealed with random forest, vegetation is so far the most important predictor variable; the marginal effect of each type of vegetation was then evaluated and discussed.

Site-specific nitrogen recommendations’ empirical algorithm for maize crop based on the fusion of soil and vegetation maps

The Oklahoma State University algorithm (OSU) is the most widespread recommendation system to calculate the optimal nitrogen (N) rate in cereal crops. This system is based on the map of a crop vegetation index and N-rich strips in the field, serving as a reference for crop vigour. Based on these inputs, yield potential and in-season crop response to N fertilisation are predicted. The system does not consider other factors influencing the spatial variability of crop growth (e.g., soil), even if the integration of additional data sources could provide more correct N recommendations by considering simultaneously the main drivers of crop growth and production variability. Therefore, the main aims of this study were to modify the OSU algorithm by merging maps of soil electrical conductivity and crop vegetation index (NDRE) to identify management zones instead of using vegetation index alone and to implement and apply the algorithm to define crop response to nitrogen, specific by management zones using a statistical approach instead of N-rich strips in the field. The proposed algorithm was calibrated for maize in northern Italy on four experimental fields in 2021. A comparison among the proposed, the original algorithm and one its previous modification (at Clemson University) was carried out in terms of spatial accuracy and levels of recommended N rates. The proposed algorithm, thanks to the integrated approach, distinguished more in detail different crop responses to N within each management zone and provided N recommendations that match the within-field variability better than the original algorithm and subsequent similar modifications. The new approach resulted in potential average N savings of about 12% compared to uniform management. We conclude that the potential of merging soil and vegetation indices and the definition of N rates with a statistical approach could improve performances and, at the same time, facilitate the adoption of the OSU algorithm. Field validation is needed to confirm the promising results shown in this work.

Cement Dust Spread as Influenced by Wind and Its Impacts on Settlement Patterns and the Biophysical Environment

Distance between cement factories and human settlements is key to determining the extent to which neighbourhoods are affected by cement dust. A key influencer of settlement patterns is zoned development and physical planning for healthy living. Wind patterns are also a factor in determining the proximity of settlements, an aspect requiring zoned development. This study focuses on cement factories in Athi River Township, established as early as 1933 when there was barely any settlement. They include East African Portland Cement Company (1933), Bamburi (1951), Athi River Mining (1974) and Mombasa (2007). Zoning development failure and unclear guidelines on the appropriate distance away from cement factories are major threats to human health. This study uses Geographic Information System and Remote Sensing Techniques for proximity analysis of the spatial relations between cement factories and homes. Study results show that residential homes are built on the wind shadow side of factories, thus affected by dust blown by easterly flowing winds. More than 1,888 residential homes in Athi River are within the 3.5 km buffer protection area. 47% of interviewed respondents consider cement factories as the main pollution source. Key Informant Interviews were administered to health officials from the nearby hospital. They reported, from hospital records, that 29.42% (n = 5084) were upper respiratory infections (URI), 17.20% skin infections (n = 2972), 7.72% (n = 1335) eye irritations, 16.32% pneumonia (n = 2821) and 11.49 % (n =1985) asthma, all traced to cement dust. Vegetation mapping using Landsat imagery classification showed a variance in the area under pasture (0.54%) and cropland (4.42%). These impacts point to a need for the implementation of zoned development to safeguard communities against cement dust impacts

Identification method of vegetation cover changes derived from mosaic Landsat-8 Data: Case Study Sumatera, Kalimantan, and Java Island

Vegetation cover changes information is essential in forest and plantation management. Low-resolution remote sensing in mosaic data format has been widely used for vegetation cover change mapping on a global scale by implementing the threshold method. However, the problem with this method in Landsat-8 - which has a higher resolution - is that it is challenging to obtain the appropriate value due to the diversity of Indonesia’s land ecosystems. This research aimed to determine the threshold value for detecting devegetation and revegetation to identify vegetation cover changes rapidly. This research used Oldeman Climate Classification with zone A and B as the references. The threshold values to classify vegetation cover changes were derived from the delta Normalized Burn Ratio (dNBR) of Analysis Ready Data (ARD) Landsat-8 - taken in Sumatera as the pilot area. Moreover, the proposed method was also applied to Kalimantan and Java Islands, with have identical climates. The results indicated that dNBR threshold for devegetation was more than 0.376, while revegetation was less than -0.269. These results were evaluated using high-resolution satellite imagery and ground-truth information. It concluded that Kalimantan Island obtained good results in mapping vegetation cover change with the threshold; however, Java Island required further adjustment for the threshold.

Combination of Hyperspectral and Quad-Polarization SAR Images to Classify Marsh Vegetation Using Stacking Ensemble Learning Algorithm

Combinations of multi-sensor remote sensing images and machine learning have attracted much attention in recent years due to the spectral similarity of wetland plant canopy. However, the integration of hyperspectral and quad-polarization synthetic aperture radar (SAR) images for classifying marsh vegetation has still been faced with the challenges of using machine learning algorithms. To resolve this issue, this study proposed an approach to classifying marsh vegetation in the Honghe National Nature Reserve, northeast China, by combining backscattering coefficient and polarimetric decomposition parameters of C-band and L-band quad-polarization SAR data with hyperspectral images. We further developed an ensemble learning model by stacking Random Forest (RF), CatBoost and XGBoost algorithms for marsh vegetation mapping and evaluated its classification performance of marsh vegetation between combinations of hyperspectral and full-polarization SAR data and any of the lone sensor images. Finally, this paper explored the effect of different polarimetric decomposition methods and wavelengths of radar on classifying wetland vegetation. We found that a combination of ZH-1 hyperspectral images, C-band GF-3, and L-band ALOS-2 quad-polarization SAR images achieved the highest overall classification accuracy (93.13%), which was 5.58–9.01% higher than that only using C-band or L-band quad-polarization SAR images. This study confirmed that stacking ensemble learning provided better performance than a single machine learning model using multi-source images in most of the classification schemes, with the overall accuracy ranging from 77.02% to 92.27%. The CatBoost algorithm was capable of identifying forests and deep-water marsh vegetation. We further found that L-band ALOS-2 SAR images achieved higher classification accuracy when compared to C-band GF-3 polarimetric SAR data. ALOS-2 was more sensitive to deep-water marsh vegetation classification, while GF-3 was more sensitive to shallow-water marsh vegetation mapping. Finally, scattering model-based decomposition provided important polarimetric parameters from ALOS-2 SAR images for marsh vegetation classification, while eigenvector/eigenvalue-based and two-component decompositions produced a great contribution when using GF-3 SAR images.

Understanding the Vegetation Dynamics of NCT- Delhi Using Remote Sensing

Urban vegetation is a crucial ecosystem component that keeps the environment in check. The existence of a well-distributed vegetation cover helps to ensure the city's long-term sustainability and aesthetic appeal. Rapid urban expansion has direct and indirect effects on vegetation growth and its distribution. This paper studied the vegetation cover dynamics using remotely sensed Landsat series datasets in the National Capital Territory (NCT) of Delhi. The study examined the vegetation change over 28 years and observed a reduction of about 15% due to rapid urbanization. This work studied the prominent Green Spaces (GS) in NCT- Delhi and highlighted their significance. The study also investigated the district-wise change in the vegetation cover. The vegetation mapping of the region can be utilized as a tool for integrated spatial planning to address urban challenges like air pollution, reducing the effects of urban heat islands, and public health improvement.

Usage PlanetScope Images and LiDAR Point Clouds for Characterizing the Forest Succession Process in Post-Agricultural Areas

The paper investigates using PlanetScope satellite images together with LiDAR data for automation of land use/cover (LULC) mapping and 3D vegetation characteristics in the aspect of mapping and monitoring of the secondary forest succession areas. The study was performed for the tested area in the Biskupice district (South of Poland), where a forest succession occurs on post-agricultural lands. The research area was parcels where the forest overgrowing process was identified. It was verified whether the image processing allows for reliable LULC classification as an identification forest succession area. The PlanetScope classification showed forested areas as 62.77 ha (44.91% of the analyzed area). The overall accuracy of the image classification was 96.40% The airborne laser scanning (ALS) point clouds were used for deriving detailed information about the forest succession process. The precise vegetation parameters i.e., height and canopy cover were determined and presented as raster maps, histograms, or profiles.

Mapping Floristic Composition Using Sentinel-2A and a Case Study Evaluation of Its Application in Elephant Movement Ecology in Sagalla, Kenya

The quantification of vegetation structure and composition at local and global scales provides valuable information for understanding the balance of the natural and human-made environment, which is crucial for natural resource planning and management, and the sustenance of ecosystem biodiversity. In this study, we proposed using the Sentinel 2A imagery to classify vegetation cover into communities based on the floristic association of individual vegetation species. We apply traditional remote sensing techniques to process the satellite image and identify training regions of interest (ROI) which are thoroughly assessed for spectral uniqueness before using the pixel-based supervised classification algorithms for our classification. Ground truthing assessment and species dominance computations are done to determine the vegetation community composition and naming based on floristic associations. We apply the floristic compositions output in analysing elephant movement tracks in the area, to assess the potential influence the location of specific vegetation species and communities utilized by elephants has on their movement and presence, as well as on elephant bulls and family groupings. The results show that the 10 m spatial resolution Sentinel-2A is suitable for investigating and mapping vegetation species in communities for large-scale mapping operations. We determined Near-Infrared band 8 and shortwave Infrared band 11 as key for identifying and differentiating ROIs at the floristic association community vegetation mapping level. We attained an overall accuracy of 87.395%. The analysis proved the 10 m spatial resolution of Sentinel 2A to be sufficient in distinguishing vegetation communities, including those with similar dominant species but variations in other contributing species. We also found a direct connection between vegetation location and elephant movement based on the summative analysis of utilised vegetation by the different elephant groupings. Bull elephants were predominantly present in areas with Combretum, family groups in areas with Commiphora, and mixed groups with both bulls and families in areas with Commiphora, and Cissus. This study shows the value that remote-sensing scientific support can offer conservationists and governments in objective evidence-based land management, policy making and governance.

The Application of Remote Sensing Techniques and Spectral Analyzes to Assess the Content of Heavy Metals in Soil – A Case Study of Barania Góra Reserve, Poland

The understanding of the spatial and temporal dynamics of farmland processes is essential to ensure the proper crop monitoring and early decision making needed to support efficient resource management in agriculture. By creating appropriate crop management strategies, one can increase harvest efficiency while reducing costs, waste, chemical spraying, and inhibiting the impact of biotic and abiotic factors on crop stress. Only reliable spatial information makes it possible to comprehend the influence of various factors on the environment. The main objective of the research presented in the paper was to assess the possibility of using maps of vegetation and soil indices, such as NDVI, SAVI, IRECI, CIred-edge, PSRI and HMSSI, calculated on the basis of images from the Sentinel-2 satellite, to qualitatively determine the increased amount of heavy metals in the soil in the areas of small agricultural plots around the Barania Góra nature reserve in Poland.The conducted pilot project shows that the spectral indices: NDVI, SAVI, IRECI, CIred-edge, PSRI, and HMSSI, calculated on the basis of images from Sentinel-2, have the potential to assess the content of nickel zinc, chromium and cobalt in the soil on agricultural plots. However, the confirmation of the obtained results requires continuation of the research.

Monitoring and Mapping Vegetation Cover Changes in Arid and Semi-Arid Areas Using Remote Sensing Technology: A Review

Vegetation cover change is one of the key indicators used for monitoring environmental quality. It can accurately reflect changes in hydrology, climate, and human activities, especially in arid and semi-arid regions. The main goal of this paper is to review the remote sensing satellite sensors and the methods used for monitoring and mapping vegetation cover changes in arid and semi-arid. Arid and semi-arid lands are eco-sensitive environments with limited water resources and vegetation cover. Monitoring vegetation changes are especially important in arid and semi-arid regions due to the scarce and sensitive nature of the plant cover. Due to expected changes in vegetation cover, land productivity and biodiversity might be affected. Thus, early detection of vegetation cover changes and the assessment of their extent and severity at the local and regional scales become very important in preventing future biodiversity loss. Remote sensing data are useful for monitoring and mapping vegetation cover changes and have been used extensively for identifying, assessing, and mapping such changes in different regions. Remote sensing data, such as satellite images, can be obtained from satellite-based and aircraft-based sensors to monitor and detect vegetation cover changes. By combining remotely sensed images, e.g., from satellites and aircraft, with ground truth data, it is possible to improve the accuracy of monitoring and mapping techniques. Additionally, satellite imagery data combined with ancillary data such as slope, elevation, aspect, water bodies, and soil characteristics can detect vegetation cover changes at the species level. Using analytical methods, the data can then be used to derive vegetation indices for mapping and monitoring vegetation.

Habitat-specific diversity in Central European birds

ABSTRACT Capsule Bird species richness was highest in forest and urban habitat types, lower in grassland and wetland, and lowest in cropland. Aims To investigate bird species richness patterns across different habitat types in Czechia, Central Europe. Methods Data from a national breeding bird monitoring scheme in Czechia, based on mapping of positions of individual birds along transects, were used to express the number of species in habitat polygons. Each polygon was represented by one of the eight habitat types (coniferous, mixed and deciduous forest, cropland, grassland and other open habitat types, urban habitat, and wetland) obtained by detailed country-wide vegetation mapping. Species richness of individual polygons was related to polygon habitat type and area by linear mixed effects models, taking the surrounding land cover composition into account. Results Bird species richness was highest in forest, as predicted, and respective forest habitat types did not differ from each other. Urban habitat hosted a similar number of species as forest. Species richness varied greatly between different open habitat types: cropland was the most species-poor of all the habitat types considered, whereas grassland and other types of open habitats hosted significantly more species, albeit fewer than forests, and did not differ from wetland. Slopes of species-area relationships in respective habitat types largely followed the patterns in species richness. Conclusions The observed patterns are partly driven by natural habitat characteristics, such as high vertical stratification of forest vegetation facilitating coexistence of a higher number of species. However, biogeography may also play a role, for example, and the relatively short time periods for colonization from Eastern European source areas may underpin lower bird species richness in grasslands. In addition, human interventions may drive the steep slope of the species-area relationship in forest, presumably caused by mosaic harvesting, as well as the shallow slope of this relationship in cropland and wetland, as a result of their intensive exploitation.

How vegetation classification and mapping may influence conservation: The example of Brazil’s Native Vegetation Protection Law

The way vegetation is officially named, classified, and identified has critical implications for ecosystems and biodiversity conservation. Yet little attention is given to how such issues hinder the efficacy of laws mandating environmental conservation on private land. In the Brazilian Amazon where half of the land is now already under private tenure or is available for future land-uses, differences in vegetation mapping and interpretation directly affect the level of protection in private rural properties, especially in transition areas where forest and savanna areas intermingle. Since Brazil’s Native Vegetation Protection Law (NVPL) attaches a higher percentage of protection to forest-located properties, landowners may be tempted to use conflicting mappings and different vegetation classifications to claim their properties are located in areas other than forests to reduce their conservation requirements. In this paper, we compare three official vegetation databases and examine different law interpretation scenarios to assess the extent to which the level of private conservation may fluctuate. We found a difference of up to 430,000 km2 of protected vegetation (an area the size of Iraq) according to the database and vegetation characteristics chosen. This technical ambiguity may lead to make additional deforestation legal or reduce sharply the amount of vegetation to be restored for these areas, if left unaddressed. Clarifying the database and criteria used to define forest is critical, especially as Brazilian states may make different choices in that regard, and cases in which loopholes are exploited occurred in the recent past. Given the importance of this region for global biodiversity conservation and climate, we highlight the urgent need to: (1) support additional research to clarify vegetation characteristics and location; (2) agree on a harmonized methodology to determine forests for NVPL implementation, and (3) explore alternative criteria for defining forests when databases conflict.

An Empirical Approach to Monitor the Flood-Prone Regions of North India Using Sentinel-1 Images

Floods in India is among the perilous natural disasters with a high impact on its economic sectors. One of the critical factors to handle such hazardous events is monitoring the affected areas and changes in flood patterns. Flood management is a very complex issue, largely owing to the growing population and investments in flood-affected regions. Satellite images especially Synthetic Aperture Radar (SAR) images are very useful and effective because SAR images are acquired day and night in all types of weather conditions. This research analyzes a combination of machine learning algorithms implemented on Sentinel-1A (SAR) data using supervised classification techniques to monitor the flooded areas in the North Indian region. Random Forest (RF) and the K-nearest neighbour (KNN) classification is applied to classify the different land covers such as water bodies, land, vegetation, and bare soil land covers. The outcomes of the presented work depict that the SAR data provides efficient information that helps in monitoring the flooded extents and the analysis shows that Sentinel-1 images are quite effective to detect changes in flood patterns in urban, vegetation, and regular water areas of the selected regions. The distribution of flooded areas was 16.6% and 16.8% in the respective region which is consistent with the resultant images of the proposed approach using RF and KNN classifiers. The obtained results indicate that both classifiers used in the work generate higher classification accuracy. These classifiers define the potential of multi-polarimetric SAR data in the classification of flood-affected areas. For a thorough evaluation and comparison, the RF and KNN are utilized as benchmarked classifiers. The classification accuracies based on the investigated results from the three SAR images can be improved by incorporating spatial and polarimetric features. In the future, the deep-learning classification techniques using ensemble strategies are expected to achieve an increased accuracy level with an overall classification strategy of urban and vegetation mapping.