Improved Land Cover Mapping Research Articles

Spatio-Temporal monitoring of Qeshm mangrove forests through machine learning classification of SAR and optical images on Google Earth Engine

Mangrove forests are considered one of the most complex and dynamic ecosystems facing various challenges due to anthropogenic disturbance and climate change. The excessive harvesting and land-use change in areas covered by mangrove ecosystems is critical threats to these forests. Therefore, the continuous and regular monitoring of these forests is essential. Fortunately, remote sensing data has made it possible to regularly and frequently monitor this forest type. This study has two goals. Firstly, it combines optical data of Landsat- 8 and Sentinel-2 with Sentinel-1 radar data to improve land cover mapping accuracy. Secondly, it aims to evaluate the SVM machine learning algorithms and random forest to detection and differentiate forest cover from other land types in the Google Earth Engine system. The results show that the support vector machine (SVM) algorithm in the S2 + S1 dataset with a kappa coefficient of 0.94 performs significantly better than when used in the L8 + S1 combination dataset with a kappa coefficient of 0.88. Conversely, the kappa coefficients of 0.89 and 0.85 were estimated for the random forest algorithm in S2 + S1 and L8 + S1 datasets. This again indicates the superiority of Sentinel-2 and Sentinel-1 datasets over Landsat- 8 and Sentinel-1 datasets. In general, the support vector machine (SVM) algorithm yielded better results than the RF random forest algorithm in optical and radar datasets. The results showed that using the Google Earth engine system and machine learning algorithms accelerates the process of mapping mangrove forests and even change detection.

Differentiating oil palm plantations from natural forest to improve land cover mapping in Ghana

Tree crops like oil palm present a unique challenge in land cover mapping, as they are often misclassified as natural forest. The area cultivated with oil palm in Ghana has rapidly expanded since 2000, and production is expected to continue to increase. Sentinel-1 and Sentinel-2 satellite data was used as inputs to a random forest classifier in Google Earth Engine to map mature, closed-canopy oil palm extent in 2019 of a Ghana study area that includes both industrial plantations and smallholders. The combination of Sentinel-1 and Sentinel-2 bands and derived indices outperformed either satellite alone for mapping industrial oil palm (90.3% overall accuracy). A separate accuracy assessment for this combined input approach demonstrated high accuracy mapping smallholders as well (80.4% overall accuracy), a key challenge in the West African context. To validate these findings, results were compared with available production information and a global oil palm remote sensing product. The resulting map can inform sustainable oil palm efforts in Ghana, which is understudied in current oil palm remote sensing literature, and the methodology provides an example for future studies of oil palm sourcing areas using only publicly available data.

Spectral–Spatial Generative Adversarial Network for Super-Resolution Land Cover Mapping With Multispectral Remotely Sensed Imagery

Super-resolution mapping (SRM) can effectively predict the spatial distribution of land cover classes within mixed pixels at a higher spatial resolution than the original remotely sensed imagery. The uncertainty of land cover fraction errors within mixed pixels is one of the most important factors affecting SRM accuracy. Studies have shown that SRM methods using deep learning techniques have significantly improved land cover mapping accuracy but have not coped well with spectral–spatial errors. This study proposes an end-to-end SRM model using a spectral–spatial generative adversarial network (SGS) with the direct input of multispectral remotely sensed imagery, which deals with spectral–spatial error. The proposed SGS comprises the following three parts: first, cube-based convolution for spectral unmixing is adopted to generate land cover fraction images. Second, a residual-in-residual dense block fully and jointly considers spectral and spatial information and reduces spectral errors. Third, a relativistic average GAN is designed as a backbone to further improve the super-resolution performance and reduce spectral–spatial errors. SGS was tested in one synthetic and two realistic experiments with multi/hyperspectral remotely sensed imagery as the input, comparing the results with those of hard classification and several classic SRM methods. The results showed that SGS performed well at reducing land cover fraction errors, reconstructing spatial details, removing unpleasant and unrealistic land cover artifacts, and eliminating false recognition.

Comparing CNNs and Random Forests for Landsat Image Segmentation Trained on a Large Proxy Land Cover Dataset

Land cover mapping from satellite images has progressed from visual and statistical approaches to Random Forests (RFs) and, more recently, advanced image recognition techniques such as convolutional neural networks (CNNs). CNNs have a conceptual benefit over RFs in recognising spatial feature context, but potentially at the cost of reduced spatial detail. We tested the use of CNNs for improved land cover mapping based on Landsat data, compared with RFs, for a study area of approximately 500 km × 500 km in southeastern Australia. Landsat 8 geomedian composite surface reflectances were available for 2018. Label data were a simple nine-member land cover classification derived from reference land use mapping (Catchment Scale Land Use of Australia—CLUM), and further enhanced by using custom forest extent mapping (Forests of Australia). Experiments were undertaken testing U-Net CNN for segmentation of Landsat 8 geomedian imagery to determine the optimal combination of input Landsat 8 bands. The results were compared with those from a simple autoencoder as well as an RF model. Segmentation test results for the best performing U-Net CNN models produced an overall accuracy of 79% and weighted-mean F1 score of 77% (9 band input) or 76% (6 band input) for a simple nine-member land cover classification, compared with 73% and 68% (6 band input), respectively, for the best RF model. We conclude that U-Net CNN models can generate annual land cover maps with good accuracy from proxy training data, and can also be used for quality control or improvement of existing land cover products.

Can a Hierarchical Classification of Sentinel-2 Data Improve Land Cover Mapping?

Monitoring of land cover plays an important role in effective environmental management, assessment of natural resources, environmental protection, urban planning and sustainable development. Increasing demand for accurate and repeatable information on land cover and land cover changes causes rapid development of the advanced, machine learning algorithms dedicated to land cover mapping using satellite images. Free and open access to Sentinel-2 data, characterized with high spatial and temporal resolution, increased the potential to map and to monitor land surface with high accuracy and frequency. Despite a considerable number of approaches towards land cover classification based on satellite data, there is still a challenge to clearly separate complex land cover classes, for example grasslands, arable land and wetlands. The aim of this study is to examine, whether a hierarchal classification of Sentinel-2 data can improve the accuracy of land cover mapping and delineation of complex land cover classes. The study is conducted in the Lodz Province, in central Poland. The pixel-based land cover classification is carried out using the machine learning Random Forest (RF) algorithm, based on a time series of Sentinel-2 imagery acquired in 2020. The following nine land cover classes are mapped: sealed surfaces, woodland broadleaved, woodland coniferous, shrubs, permanent herbaceous (grassy cover), periodically herbaceous (i.e., arable land), mosses, non-vegetated (bare soil) and water bodies. The land cover classification is conducted following two approaches: (1) flat, where all land cover classes are classified together, and (2) hierarchical, where the stratification is applied to first separate the most stable land cover classes and then classifying the most problematic once. The national databases served as the source of the reference sampling plots for the classification process. The process of selection and verification of the reference sampling plots is performed automatically. To assess the stability of the classification models the classification processes are performed iteratively. The results of this study confirmed that the hierarchical approach gave more accurate results compared to the commonly used flat approach. The median of the overall accuracy (OA) of the hierarchical classification was higher by 3–9 percentage points compared to the flat one. Of interest, the OA of the hierarchical classification reached 0.93–0.99, whereas the flat approach reached 0.90. Individual classes are also better classified in the hierarchical approach.

Tree species classification using Sentinel-2 imagery and Bayesian inference

The increased temporal frequency of optical satellite data acquisitions provides a data stream that has the potential to improve land cover mapping, including mapping of tree species. However, for large area operational mapping, partial cloud cover and different image extents can pose challenges. Therefore, methods are needed to assimilate new images in a straightforward way without requiring a total spatial coverage for each new image. This study shows that Bayesian inference applied sequentially has the potential to solve this problem. To test Bayesian inference for tree species classification in the boreo-nemoral zone of southern Sweden, field data from the study area of Remningstorp (58°27′18.35″ N, 13°39′8.03″ E) were used. By updating class likelihood with an increasing number of combined Sentinel-2 images, a higher and more stable cross-validated overall accuracy was achieved. Based on a Mahalanobis distance, 23 images were automatically chosen from the period of 2016 to 2018 (from 142 images total). An overall accuracy of 87% (a Cohen’s kappa of 78.5%) was obtained for four tree species classes: Betula spp., Picea abies, Pinus sylvestris, and Quercus robur. This application of Bayesian inference in a boreo-nemoral forest suggests that it is a practical way to provide a high and stable classification accuracy. The method could be applied where data are not always complete for all areas. Furthermore, the method requires less reference data than if all images were used for classification simultaneously.

Mapping Urban and Peri-Urban Land Cover in Zimbabwe: Challenges and Opportunities

Accurate and current land cover information is required to develop strategies for sustainable development and to improve the quality of life in urban areas. This study presents an approach that combines multi-seasonal Sentinel-1 (S1) and Sentinel-2 (S2) data, and a random forest (RF) classifier in order to map land cover in four major urban centers in Zimbabwe. The specific objective of this study was to assess the potential of multi-seasonal (rainy, post-rainy, and dry season) S1, rainy season S2, post-rainy season, dry season S2, multi-seasonal S2, and multi-seasonal composite S1 and S2 data for mapping land cover in urban areas. The study results show that the combination of multi-seasonal S1 and S2 data improve land cover mapping in urban and peri-urban areas relative to only multi-seasonal S1, mono-seasonal S2, and multi-seasonal S2 data. The overall accuracy scores for the multi-seasonal S1 and S2 land cover maps are above 85% for all urban centers. Our results indicate that rainy and post-rainy S2 spectral bands, as well as dry-season S1 VV and VH bands (ascending orbit) are the most important features for land cover mapping. In particular, S1 data proved useful in separating built-up areas from cropland, which is usually problematic when only optical imagery is used in the study area. While there are notable improvements in land cover mapping, some challenges related to the S1 data analysis still remain. Nonetheless, our land cover mapping approach shows a potential to map land cover in other urban areas in Zimbabwe or in Sub-Sahara Africa. This is important given the urgent need for reliable geospatial information, which is required to implement the United Nations Sustainable Development Goals (UN SDGs) and United Nations New Urban Agenda (NUA) programmes.

Improved land cover map of Iran using Sentinel imagery within Google Earth Engine and a novel automatic workflow for land cover classification using migrated training samples

Accurate information about the location, extent, and type of Land Cover (LC) is essential for various applications. The only recent available country-wide LC map of Iran was generated in 2016 by the Iranian Space Agency (ISA) using Moderate Resolution Imaging Spectroradiometer (MODIS) images with a considerably low accuracy. Therefore, the production of an up-to-date and accurate Iran-wide LC map using the most recent remote sensing, machine learning, and big data processing algorithms is required. Moreover, it is important to develop an efficient method for automatic LC generation for various time periods without the need to collect additional ground truth data from this immense country. Therefore, this study was conducted to fulfill two objectives. First, an improved Iranian LC map with 13 LC classes and a spatial resolution of 10 m was produced using multi-temporal synergy of Sentinel-1 and Sentinel-2 satellite datasets applied to an object-based Random forest (RF) algorithm. For this purpose, 2,869 Sentinel-1 and 11,994 Sentinel-2 scenes acquired in 2017 were processed and classified within the Google Earth Engine (GEE) cloud computing platform allowing big geospatial data analysis. The Overall Accuracy (OA) and Kappa Coefficient (KC) of the final Iran-wide LC map for 2017 was 95.6% and 0.95, respectively, indicating the considerable potential of the proposed big data processing method. Second, an efficient automatic method was developed based on Sentinel-2 images to migrate ground truth samples from a reference year to automatically generate an LC map for any target year. The OA and KC for the LC map produced for the target year 2019 were 91.35% and 0.91, respectively, demonstrating the efficiency of the proposed method for automatic LC mapping. Based on the obtained accuracies, this method can potentially be applied to other regions of interest for LC mapping without the need for ground truth data from the target year.

Enhancing land cover classification for multispectral images using hybrid polarimetry SAR data

ABSTRACT The recent development of hybrid polarimetry synthetic aperture radar (SAR) data with decomposition techniques has improved land cover mapping. The generation of land cover maps using land cover classifications of different scenarios was carried out for Theni district, Tamil Nadu, India using optical and hybrid polarimetry SAR data. The present study focuses on evaluating the capability and contribution of hybrid decomposition techniques from Radar Imaging Satellite-1 (RISAT-1) data to improve the optical image classification accuracy. Hybrid decomposition techniques such as m-delta (m-δ), m-chi (m-χ) and m-alpha (m-α) were extracted using Stokes parameters from circular fine resolution stripmap-1 (cFRS-1) mode of RISAT-1 data. Grey level co-occurrence matrix (GLCM) textural bands were extracted from backscattering images of RISAT-1 and spectral bands of linear imaging self scanning sensor – IV (LISS-IV) image. The hybrid decomposition parameters were used to improve the classification accuracies of SAR and optical images and compared with GLCM textural bands. Support vector machine (SVM) classifier was performed for different scenarios and accuracy assessment was evaluated for all the classified images using confusion matrix with help of reference data. The study observed that the RISAT-1 derived products provided reasonable classification accuracy (54%) and also provided better results when added to spectral bands of LISS-IV (74%). The mean and dissimilarity of GLCM textural bands provided best classification, when added individually with RISAT-1 (66%) and LISS-IV (82%), and combined with RISAT-1 and LISS-IV (80%). The results indicate that the optical sensor performs better for the classification of water bodies, fallow land and settlement, however, plantation and rice crops are better classified when combined with SAR hybrid decomposition parameters. The study also observed that GLCM textural bands may change the pixel values based on the window size. The changed pixel values contributed to improving the classification accuracy by 15%. The selected classification and processing methods resulted in reasonable accuracy in land cover mapping in a hilly area with intermittent plains.

Addressing the need for improved land cover map products for policy support

The continued increase of anthropogenic pressure on the Earth’s ecosystems is degrading the natural environment and then decreasing the services it provides to humans. The type, quantity, and quality of many of those services are directly connected to land cover, yet competing demands for land continue to drive rapid land cover change, affecting ecosystem services. Accurate and updated land cover information is thus more important than ever, however, despite its importance, the needs of many users remain only partially attended. A key underlying reason for this is that user needs vary widely, since most current products – and there are many available – are produced for a specific type of end user, for example the climate modelling community. With this in mind we focus on the need for flexible, automated processing approaches that support on-demand, customized land cover products at various scales. Although land cover processing systems are gradually evolving in this direction there is much more to do and several important challenges must be addressed, including high quality reference data for training and validation and even better access to satellite data. Here, we 1) present a generic system architecture that we suggest land cover production systems evolve towards, 2) discuss the challenges involved, and 3) propose a step forward. Flexible systems that can generate on-demand products that match users’ specific needs would fundamentally change the relationship between users and land cover products – requiring more government support to make these systems a reality.

Incorporation of textural information with SAR and optical imagery for improved land cover mapping

This study focuses on evaluating the capability and contribution of using backscatter intensity image and textural bands from Sentinel-1A synthetic aperture radar (SAR) data for reducing the limitation of optical image classification and improving the classification accuracy. The study was carried out at Theni district of Tamil Nadu, India, which is characterized by very heterogeneous features. The optical multispectral images such as Linear imaging self scanning sensor-IV (LISS-IV), Sentinel-2A and Landsat8 were used. Support vector machine classifier performed on the different combination of SAR, optical image and texture features. Results showed that the optimal window size was 11 × 11, and mean and variance are optimal textural bands of gray-level co-occurrence matrix techniques. The best classification result was achieved with the combination of LISS-IV and Sentinel-1A-derived features (backscatter intensity and texture features) with an overall accuracy up to 78.49% and a kappa coefficient of up to 0.68, respectively. The combination of optical image and Sentinel-1A data decreased the spectral confusions between the classes, provided better classification results, and reasonably improved the accuracy.

An Integrated Land Cover Mapping Method Suitable for Low-Accuracy Areas in Global Land Cover Maps

In land cover mapping, an area with complex topography or heterogeneous land covers is usually poorly classified and therefore defined as a low-accuracy area. The low-accuracy areas are important because they restrict the overall accuracy (OA) of global land cover classification (LCC) data generated. In this paper, low-accuracy areas in China (extracted from the MODIS global LCC maps) were taken as examples, identified as the regions having lower accuracy than the average OA of China. An integrated land cover mapping method targeting low-accuracy regions was developed and tested in eight representative low-accuracy regions of China. The method optimized procedures of image choosing and sample selection based on an existent visually-interpreted regional LCC dataset with high accuracies. Five algorithms and 16 groups of classification features were compared to achieve the highest OA. The support vector machine (SVM) achieved the highest mean OA (81.5%) when only spectral bands were classified. Aspect tended to attenuate OA as a classification feature. The optimal classification features for different regions largely depends on the topographic feature of vegetation. The mean OA for eight low-accuracy regions was 84.4% by the proposed method in this study, which exceeded the mean OA of most precedent global land cover datasets. The new method can be applied worldwide to improve land cover mapping of low-accuracy areas in global land cover maps.

Learning selfhood scales for urban land cover mapping with very-high-resolution satellite images

Abstract Urban land cover mapping with very-high-resolution (VHR) satellite images has raised many concerns in the fields of environmental and social investigations, but the classical per-pixel and object-based mapping results are not accurate enough to serve these applications, owing to the inappropriate analysis scales. Accordingly, this study aims to 1) propose a self-adaptive segmentation scale (i.e., “selfhood scale”), which refers to the optimum scale for analyzing a pixel and depends on the pixel's category and surrounding contrasts; and 2) apply selfhood scales to urban land cover mapping. For the first target, a learning mechanism is presented to estimate selfhood scales; for the second target, two methods (i.e., “zipper merging” and “restricted forest”) using the learned selfhood scales are proposed to respectively improve per-pixel and object-based classification results. The experimental results demonstrate that these methods achieve significant improvements in both per-pixel and object-based land cover mapping in urban areas as their overall accuracies are improved by 2.8% and 7.6% respectively. Moreover, the proposed methods are further used to generate land cover maps in Beijing and Zhuhai cities, which perform much better than the classical methods. Accordingly, it can be concluded that selfhood scales are effective to improve land cover mapping in urban areas.

Mapping erodibility in dust source regions based on geomorphology, meteorology, and remote sensing

AbstractMineral dust in the atmosphere has implications for Earth's radiation budget, biogeochemical cycles, hydrological cycles, human health, and visibility. Currently, the simulated vertical mass flux of dust differs greatly among the existing dust models. While most of the models utilize an erodibility factor to characterize dust sources, this factor is assumed to be static, without sufficient characterization of the highly heterogeneous and dynamic nature of dust source regions. We present a high‐resolution land cover map of the Middle East and North Africa (MENA) in which the terrain is classified by visually examining satellite images obtained from Google Earth Professional and Environmental Systems Research Institute Basemap. We show that the correlation between surface wind speed and Moderate Resolution Imaging Spectroradiometer deep blue aerosol optical depth (AOD) can be used as a proxy for erodibility, which satisfactorily represents the spatiotemporal distribution of soil‐derived dust sources. This method also identifies agricultural dust sources and eliminates the satellite‐observed dust component that arises from long‐range transport, pollution, and biomass burning. The erodible land cover of the MENA region is grouped into nine categories: (1) bedrock: with sediment, (2) sand deposit, (3) sand deposit: on bedrock, (4) sand deposit: stabilized, (5) agricultural and urban area, (6) fluvial system, (7) stony surface, (8) playa/sabkha, and (9) savanna/grassland. Our results indicate that erodibility is linked to the land cover type and has regional variation. An improved land cover map, which explicitly accounts for sediment supply, availability, and transport capacity, may be necessary to represent the highly dynamic nature of dust sources in climate models.

An improved semiautomatic segmentation approach to land cover mapping for identification of land cover change and trend

Worldwide, land cover change is monitored by conventional land cover mapping techniques using satellite imagery. Index method ends with assigning positive values to indicate vegetation, wetland and built-up area. However, not all positive values up to a certain threshold specify desired land cover and might indicate other covers erroneously. Therefore, a threshold value must be determined above which land covers are mapped more accurately. In this research, we employed an improved land cover mapping technique to extract vegetation, wetland and built-up area using semiautomatic segmentation approach. We used double-window flexible pace search technique not only for built-up features but also for vegetation and wetland mapping to increase the accuracy. Study is based on Landsat Thematic Mapper images of 1989, 1999 and 2010 with spatial resolution of 30 m. Integration of simple recoding of derived index images prior to threshold identification entails increased accuracy. Accuracy assessment of land cover mapping is done using high-resolution Google Earth satellite image which substitutes expensive aerial photography and time-consuming ground data collection. Error matrix presents 82.46, 96.83 and 90 % user’s accuracy of mapping built-up area, vegetation and wetland, respectively. Trend analysis discloses an average loss of vegetation and wetland by 2,664.6 and 5,328.8 acres per year, respectively, in study area from 1989 to 2010. Expectantly, future land cover mapping in similar researches will be greatly assisted with the diligent technique used in this study.

Mapping Woodland Cover in the Miombo Ecosystem: A Comparison of Machine Learning Classifiers

Miombo woodlands in Southern Africa are experiencing accelerated changes due to natural and anthropogenic disturbances. In order to formulate sustainable woodland management strategies in the Miombo ecosystem, timely and up-to-date land cover information is required. Recent advances in remote sensing technology have improved land cover mapping in tropical evergreen ecosystems. However, woodland cover mapping remains a challenge in the Miombo ecosystem. The objective of the study was to evaluate the performance of decision trees (DT), random forests (RF), and support vector machines (SVM) in the context of improving woodland and non-woodland cover mapping in the Miombo ecosystem in Zimbabwe. We used Multidate Landsat 8 spectral and spatial dependence (Moran’s I) variables to map woodland and non-woodland cover. Results show that RF classifier outperformed the SVM and DT classifiers by 4% and 15%, respectively. The RF importance measures show that multidate Landsat 8 spectral and spatial variables had the greatest influence on class-separability in the study area. Therefore, the RF classifier has potential to improve woodland cover mapping in the Miombo ecosystem.

Application and evaluation of topographic correction methods to improve land cover mapping using object-based classification

This study applies and evaluates topographic correction methods to reduce radiometric variation due to topography characteristics in rugged terrain. The aim of this study was to improve the capability of satellite images to generate more reliable land cover mapping using object-based classification. Several semi-empirical correction methods, which require the estimation of empirically defined parameters, were selected for this study. Usually, these parameters are estimated relying on a previous land cover map. However, in this work the correction methods were applied considering the unavailability of a previous land cover map and the ease for implementation, so the main land cover type was used to estimate correction parameters to be applied to correct all land cover type. Landsat 5 TM image and topographic data derived from SRTM (Shuttle Radar Topography Mission) over an area located in an agricultural region of southeastern Brazil were used. Land cover classification was carried out using an object-based approach, which includes image segmentation and decision tree classification. The evaluation of topographic correction methods was based on: spectral characteristics expressed by standard deviation and mean values of spectral data within land cover classes; relationship between spectral data and solar illumination angle on the slope (cosi); object (segment) mean size; decision tree structure; visual analysis; and classification accuracy. Results show that the standard deviation of spectral data and the correlation between spectral values and cosi decreased after data correction, but not for all methods for some of the tested TM bands. The methods herein referred as Cosine, S1, Ad2S and SCS methods showed to increase the standard deviation and the correlation compared to the uncorrected data, mainly for bands 1, 2 and 3. Object mean size, in general, decreased after correction, except for C method. The effect on the object size showed to be related to a calculated standard deviation of adjacent pixels values. The decision tree structure given by the number of leaves also decreased after correction. The C, SCS+C and Minnaert methods showed the highest performance, followed by S2 and E-Stat, with a general accuracy increase around 10%. Land cover classification from uncorrected and corrected data differed in a large portion of the total studied area, with values around 29% for all correction methods.

Improved LAI Algorithm Implementation to MODIS Data by Incorporating Background, Topography, and Foliage Clumping Information

Leaf area index (LAI) is one of the essential biogeophysical variables related to terrestrial carbon and biogeochemical cycles. The University of Toronto (UofT) LAI product is developed in order to support the European Space Agency GLOBCARBON project for global and climate change assessments. The climate and global change communities have recently requested for a daily 250-m LAI product in order to improve the spatial and temporal patterns of carbon pools and fluxes knowledge. In light of these considerations, we carry out further improvements on the UofT LAI algorithm, including enhanced spatial resolution (250 m) by considering an improved land cover map, local topography, clumping index, and background reflectance variations in order to produce canopy LAI time series. Here, we present the methodological framework and an evaluation of 250-m UofTv2 LAI estimates in forest stands of the Canadian Carbon Program fluxnet sites. The LAI distributions over Canada and the comparison with ground measurements show an improved LAI estimates from the UofT v2 LAI algorithm as compared with the UofT v1 LAI algorithm. One of the key differences between v1 and v2 UofT LAI product is that the former produces total LAI whereas the latter produces overstorey LAI in forest and total LAI in other vegetated land cover types. A daily LAI product can further be extracted from the 10-day UofT v2 LAI time series by fitting various curve fitting algorithms. Although, we have shown the LAI product only over Canada, the algorithm can also be extended for a global 250-m LAI product.

Improved land cover mapping using aerial photographs and satellite images

AbstractManual Land Cover Mapping using aerial photographs provides sufficient level of resolution for detailed vegetation or land cover maps. However, in some cases it is not possible to achieve the desired information over large areas, for example from historical data where the quality and amount of available images is definitely lower than from modern data. The use of automated and semiautomated methods offers the means to identify the vegetation cover using remotely sensed data. In this paper automated methods were tested on aerial photographs and satellite images to extract better and more reliable information about vegetation cover. These testswere performed by using automated analysis of LANDSAT7 images (with and without the surface model of the Shuttle Radar Topography Mission (SRTM)) and two temporally similar aerial photographs. The spectral bands were analyzed with supervised (maximum likelihood) methods. In conclusion, the SRTM and the combination of two temporally similar aerial photographs from earlier years were useful in separating the vegetation cover on a floodplain area. In addition the different date of the vegetation season also gave reliable information about the land cover. High quality information about old and present vegetation on a large area is an essential prerequisites ensuring the conservation of ecosystems

Improved land cover mapping using high resolution multiangle 8-band WorldView-2 satellite remote sensing data

Here, we discuss the improvements in urban classification that were made using the spatial-spectral-angular information from a WorldView-2 (WV-2) multiangle image sequence. In this study, we evaluate the use of multiangle high resolution WV-2 panchromatic (PAN) and multispectral image (MSI) data for extracting urban geospatial information. Current multiangular WV-2 data were classified into misclassification-prone surfaces, such as vegetation, water bodies, and man-made features, using a cluster of normalized difference spectral index ratios (SIR). A novel multifold methodology protocol was designed to estimate the consequences of multiangularity and germane PAN-sharpening algorithms on the spectral characteristics (distortions) of satellite data and on the resulting land use/land cover (LU/LC) mapping using an array of SIRs. Eight existing PAN-sharpening algorithms were used for data fusion, followed by estimation of multiple SIRs to mitigate spectral distortions arising from the multiangularity of the data. This research highlights the benefits of using traditional PAN-sharpening techniques with a specific set of SIRs on land cover mapping based on five available tiles of satellite data. The research provides a method to overcome the atmospherically triggered spectral distortions of multiangular acquisitions, which will facilitate better mapping and understanding of the earth’s surface.