Ground Cover Maps Research Articles

Predicting Ground Cover with Deep Learning Models—An Application of Spatio-Temporal Prediction Methods to Satellite-Derived Ground Cover Maps in the Great Barrier Reef Catchments

Livestock grazing is a major land use in the Great Barrier Reef Catchment Area (GBRCA). Heightened grazing density coupled with inadequate land management leads to accelerated soil erosion and increased sediment loads being transported downstream. Ultimately, these increased sediment loads impact the water quality of the Great Barrier Reef (GBR) lagoon. Ground cover mapping has been adopted to monitor and assess the land condition in the GBRCA. However, accurate prediction of ground cover remains a vital knowledge gap to inform proactive approaches for improving land conditions. Herein, we explored two deep learning-based spatio-temporal prediction models, including convolutional LSTM (ConvLSTM) and Predictive Recurrent Neural Network (PredRNN), to predict future ground cover. The two models were evaluated on different spatial scales, ranging from a small site (i.e., <5 km2) to the entire GBRCA, with different quantities of training data. Following comparisons against 25% withheld testing data, we found the following: (1) both ConvLSTM and PredRNN accurately predicted the next-season ground cover for not only a single site but also the entire GBRCA. They achieved this with a Mean Absolute Error (MAE) under 5% and a Structural Similarity Index Measure (SSIM) exceeding 0.65; (2) PredRNN superseded ConvLSTM by providing more accurate next-season predictions with better training efficiency; (3) The accuracy of PredRNN varies seasonally and spatially, with lower accuracy observed for low ground cover, which is underestimated. The models assessed in this study can serve as an early-alert tool to produce high-accuracy and high-resolution ground cover prediction one season earlier than observation for the entire GBRCA, which enables local authorities and grazing property owners to take preventive measures to improve land conditions. This study also offers a new perspective on the future utilization of predictive spatio-temporal models, particularly over large spatial scales and across varying environmental sites.

Evaluation of hydrological and sediment connectivity in catchments with mining activity in semiarid central Mexico

Source–sink systems in arid and semiarid regions contain low plant cover areas (inter-patches) functioning as sources of runoff, sediments, and nutrients that are retained by vegetated patches, which act as sinks. The spatial configuration of these hydrological units largely determines the connectivity network of runoff sources. At the same time, their dynamics are essential for assessing ecohydrological functionality, which mining can modify through the alteration of the system's ability to retain water and sediments, causing increased runoff and soil erosion. The objectives of this work were to: (1) identify the spatio-temporal changes in ground cover (i.e., vegetated patches and inter-patches) in two areas with mining activity: Cerro de San Pedro (1970–2015) and Villa de la Paz (1983–2014); and (2) evaluate, from an ecohydrological perspective, the changes in hydrological and sediment connectivity as the result of changes in ground cover in the two periods within each study area. Ground cover maps were obtained from aerial photographs and high-resolution WorldView 2 satellite images calibrated with 2 × 2 m plots measured in the field. For each study area, a transition matrix was used to assess spatio-temporal changes of patches and inter-patches, while hydrological and sediment connectivity were evaluated with the index of connectivity (IC). The results showed that the area with vegetated patches has decreased in Cerro de San Pedro and Villa de la Paz, leading to increased hydrological and sediment connectivity related to mining infrastructure and urbanization. The results can be used to prioritize areas for restoring ecohydrological functioning by reducing the connectivity of runoff sources.

Comparison of Hyperspectral Versus Traditional Field Measurements of Fractional Ground Cover in the Australian Arid Zone

The collection of high-quality field measurements of ground cover is critical for calibration and validation of fractional ground cover maps derived from satellite imagery. Field-based hyperspectral ground cover sampling is a potential alternative to traditional in situ techniques. This study aimed to develop an effective sampling design for spectral ground cover surveys in order to estimate fractional ground cover in the Australian arid zone. To meet this aim, we addressed two key objectives: (1) Determining how spectral surveys and traditional step-point sampling compare when conducted at the same spatial scale and (2) comparing these two methods to current Australian satellite-derived fractional cover products. Across seven arid, sparsely vegetated survey sites, six 500-m transects were established. Ground cover reflectance was recorded taking continuous hyperspectral readings along each transect while step-point surveys were conducted along the same transects. Both measures of ground cover were converted into proportions of photosynthetic vegetation, non-photosynthetic vegetation, and bare soil for each site. Comparisons were made of the proportions of photosynthetic vegetation, non-photosynthetic vegetation, and bare soil derived from both in situ methods as well as MODIS and Landsat fractional cover products. We found strong correlations between fractional cover derived from hyperspectral and step-point sampling conducted at the same spatial scale at our survey sites. Comparison of the in situ measurements and image-derived fractional cover products showed that overall, the Landsat product was strongly related to both in situ methods for non-photosynthetic vegetation and bare soil whereas the MODIS product was strongly correlated with both in situ methods for photosynthetic vegetation. This study demonstrates the potential of the spectral transect method, both in its ability to produce results comparable to the traditional transect measures, but also in its improved objectivity and relative logistic ease. Future efforts should be made to include spectral ground cover sampling as part of Australia’s plan to produce calibration and validation datasets for remotely sensed products.

Distinguishing Photosynthetic and Non-Photosynthetic Vegetation: How Do Traditional Observations and Spectral Classification Compare?

Remotely sensed ground cover maps are routinely validated using field data collected by observers who classify ground cover into defined categories such as photosynthetic vegetation (PV), non-photosynthetic vegetation (NPV), bare soil (BS), and rock. There is an element of subjectivity to the classification of PV and NPV, and classifications may differ between observers. An alternative is to estimate ground cover based on in situ hyperspectral reflectance measurements (HRM). This study examines observer consistency when classifying vegetation samples of wheat (Triticum aestivum var. Gladius) covering the full range of photosynthetic activity, from completely senesced (0% PV) to completely green (100% PV), as photosynthetic or non-photosynthetic. We also examine how the classification of spectra of the same vegetation samples compares to the observer results. We collected HRM and photographs, over two months, to capture the transition of wheat leaves from 100% PV to 100% NPV. To simulate typical field methodology, observers viewed the photographs and classified each leaf as either PV or NPV, while spectral unmixing was used to decompose the HRM of the leaves into proportions of PV and NPV. The results showed that when a leaf was ≤25% or ≥75% PV observers tended to agree, and assign the leaf to the expected category. However, as leaves transitioned from PV to NPV (i.e., PV ≥ 25% but ≤ 75%) observers’ decisions differed more widely and their classifications showed little agreement with the spectral proportions of PV and NPV. This has significant implications for the reliability of data collected using binary methods in areas containing a significant proportion of vegetation in this intermediate range such as the over/underestimation of PV and NPV vegetation and how reliably this data can then be used to validate remotely sensed products.

Development of Hybrid Unsupervised Classification Techniques for Accuracy Enhancement of Land Use/Land Cover Mapping Using Geo-spatial Technology: Hoshangabad, District Madhya Pradesh, India

A Hybrid approach of Land-use/land-cover (LU/LC) classification has been carried out in the study using Resource Sat-2 LISS-III Satellite data having a resolution of 23.5 m. With the help of ERDAS Imagine image processing software, unsupervised classification process of the satellite image has been made to obtain the required land use/land cover classes. During the classification study, a common mixed class assigned as Common Observed Classes (COC) used for the separation of the required classes to obtain undefined mixed land use/land cover classes with the help of ArcGIS model plate tool. Furthermore, more accuracy gained inthe classification of separated mixed land cover classes by revising unsupervised classification processes. After that pre-defined unsupervised land cover classes and COC unsupervised classes were merged by using ArcGIS model plate tool to generate a new classified image with enhanced accuracy. Finally, the comparison between both supervised and COC hybrid unsupervised classes was made and better results are seen in hybrid unsupervised classification. Therefore, application of this new approach in land use/land cover studies, ground cover mapping, forest management, water resources management, sustainable urban development, agricultural studies, natural resources management and manmade resources development management planning change deduction etc. will provide better results as compared to other classification approaches techniques.

A New Sparse Source Separation-Based Classification Approach

In many geoscience applications, we have to convert remotely sensed images to ground cover maps. Numerous approaches to extract ground cover information have been developed. Recently, blind source separation (BSS) of remote-sensing data has received significant attention due to its suitability to recover sources when no information is available about the scanned zone, hence the term blind. In the remote-sensing context, associating each source to a significant land cover theme is difficult and constitutes the real challenge of this paper. Many authors have pointed out that BSS is overwhelmingly a question of contrast and diversity. This reasoning motivates this work which takes advantage of both decorrelation and sparsity to propose a two-level novel approach to separate our different land covers called sources. The first separation stage is based on second-order statistics or decorrelation. It gives a suitable representation of the remote-sensing images. However, decorrelation is a natural way of differentiating statistically between sources but is unable to identify and extract finer features with physical meaning. The aim of the second separation stage is to overcome this problem by an increasingly popular and powerful assumption which is the sparse representation. The last leads to good separation because most of the energy in the defined basis, at any time instant, belongs to a single source. This allows the extraction of physical features and the capture of image essential structures. The innovative aspect of this study concerns the development of a new image classification approach that integrates the BSS at the feature extraction level to provide the most relevant sources from remotely sensed images. It can be viewed as an unsupervised classification method. The second-order separation process is used as a preprocessing step to remove the interband correlation which sometimes brings ill effect to image classification. However, the second-order process is unable to uncover the underlying sources. The basic idea behind our approach is that heterogeneous multichannel data provide sparse spectral signatures in addition to sparse spatial morphologies in specified dictionaries. Hence, sparse modeling can be used to disentangle the land covers from observed mixtures. From the sparse representation, the data space is transformed into a feature space composed of mutually exclusive classes. Finally, we will merge these classes at the decision level in order to enhance the semantic capability and the reliability of land cover classification. The effectiveness of the proposed approach was demonstrated by operating two experiments to study respectively the source separation and the image classification capability of the developed approach. The different results on remote-sensing images illustrate the good performance of the new sparse approach and its robustness to noise. These experiments show that the sparse representation enhances the separation quality and allows extracting more easily the essential structures of the scanned zone. The proposed approach offers an interesting solution to the classification process with limited knowledge of ground truth.

Remote sensing and geologic mapping of glaciovolcanic deposits in the region surrounding Askja (Dyngjufjöll) volcano, Iceland

The surface geology of the Northern Volcanic Zone in Iceland is dominated by volcanic ridges, central volcanoes, shield volcanoes, and tuyas. The largest features are typically ice-confined (glaciovolcanic) in origin, and are overlain by voluminous Holocene (subaerial) lavas and glacial outwash deposits. The literature has focused heavily on prominent or very young features, neglecting small and older volcanic features. The purpose of this study is to demonstrate the application of remote-sensing mapping techniques to the glaciovolcanic environment in order to identify dominant lithologies and determine locations for textural, stratigraphic, and age studies. The deposits targeted in this study occur on and around Askja volcano, in central Iceland, including Pleistocene glaciovolcanic tuffs and subaerial pumice from the 1875 rhyolitic eruption of Askja. Data from the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) were used in conjunction with previously published geologic and remote-sensing data sets and recent field work on glaciovolcanic deposits of Askja for validation. Remotely acquired data sets include aerial photographs and one ASTER scene obtained in August 2010. Visible and near-infrared (VNIR) and thermal infrared (TIR) classifications and linear deconvolution of the TIR emissivity data were performed using end-members derived from regions of interest and laboratory spectra. End-members were selected from samples of representative lithologic units within the field area, including glaciovolcanic deposits (pillow lavas, tuffs, etc.), historical deposits (1875 pumice, 1920s basaltic lavas), and Holocene basaltic lavas from Askja. The results demonstrate the potential for remote sensing-based ground cover mapping of areas of glaciovolcanic deposits relevant to palaeo-ice reconstructions in areas such as Iceland, Antarctica, and British Columbia. Remote sensing-based mapping will benefit glaciovolcanic studies, by determining the lithologic variability of these relatively inaccessible massifs and serving as an important springboard for the identification of future field sites in remote areas.

Assessing ground cover at patch and hillslope scale in semi-arid woody vegetation and pasture using fused Quickbird data

The amount and distribution of vegetation and ground cover are important factors that influence resource transfer (e.g. runoff, sediment) in patterned semi-arid landscapes. Identifying and describing these features in detail is an essential part of measuring and understanding ecohydrological processes at hillslope scales that can then be applied at broader scales. The aim of this study was to develop a comprehensive methodology to map ground cover using high resolution Quickbird imagery in woody and non-woody (pasture) vegetation. The specific goals were to: (1) investigate the use of several techniques of image fusion, namely principal components analysis (PCA), Brovey transform, modified intensity–hue–saturation (MIHS) and wavelet transform to increase the spatial detail of multispectral Quickbird data; (2) evaluate the performance of the red and near-infra-red bands (NIR), the difference vegetation index (DVI), and the normalised difference vegetation index (NDVI) in estimating ground cover, and (3) map and assess spatial and temporal changes in ground cover at hillslope scale using the most appropriate method or combination of methods. Estimates of ground cover from the imagery were compared with a subset of observed ground cover estimates to determine map accuracy. The MIHS algorithm produced images that best preserved spectral and spatial integrity, while the red band fused with the panchromatic band produced the most accurate ground cover maps. The patch size of the ground cover beneath canopies was similar to canopy size, and percent ground cover (mainly litter) increased with canopy size. Ground cover was mapped with relative accuracies of 84% in the woody vegetation and 86% in the pasture. From 2008 to 2009, ground cover increased from 55% to 65% in the woody vegetation and from 40% to 45% in the pasture. These ground cover maps can be used to explore the spatial ecohydrological interactions between areas of different ground cover at hillslope scale with application to management at broader scales.

Classifying historical remotely sensed imagery using a tempo-spatial feature evolution (T-SFE) model

Large and growing archives of orbital imagery of the earth’s surface collected over the past 40 years provide an important resource for documenting past and current land cover and environmental changes. However uses of these data are limited by the lack of coincident ground information with which either to establish discrete land cover classes or to assess the accuracy of their identification. Herein is proposed an easy-to-use model, the Tempo-Spatial Feature Evolution (T-SFE) model, designed to improve land cover classification using historical remotely sensed data and ground cover maps obtained at later times. This model intersects (1) a map of spectral classes (S-classes) of an initial time derived from the standard unsupervised ISODATA classifier with (2) a reference map of ground cover types (G-types) of a subsequent time to generate (3) a target map of overlaid patches of S-classes and G-types. This model employs the rules of Count Majority Evaluation, and Subtotal Area Evaluation that are formulated on the basis of spatial feature evolution over time to quantify spatial evolutions between the S-classes and G-types on the target map. This model then applies these quantities to assign G-types to S-classes to classify the historical images. The model is illustrated with the classification of grassland vegetation types for a basin in Inner Mongolia using 1985 Landsat TM data and 2004 vegetation map. The classification accuracy was assessed through two tests: a small set of ground sampling data in 1985, and an extracted vegetation map from the national vegetation cover data (NVCD) over the study area in 1988. Our results show that a 1985 image classification was achieved using this method with an overall accuracy of 80.6%. However, the classification accuracy depends on a proper calibration of several parameters used in the model.

Level Set Hyperspectral Image Classification Using Best Band Analysis

We present a supervised hyperspectral classification procedure consisting of an initial distance-based segmentation method that uses best band analysis (BBA), followed by a level set enhancement that forces localized region homogeneity. The proposed method is tested on two hyperspectral images of an urban and rural nature. The proposed method is compared to the maximum likelihood (ML) method using BBA. Quantitative results are compared using segmentation and classification accuracies. Results show that both the initial classification using BBA features and the level set enhancement produced high-quality ground cover maps and outperformed the ML method, as well as previous studies by the authors. For example, with the compact airborne spectrographic imager image, the ML method resulted in accuracies les95.5%, whereas the level set segmentation approach resulted in accuracies as high as 99.7%.