Subpixel Land Cover Mapping Research Articles

Land cover fraction mapping across global biomes with Landsat data, spatially generalized regression models and spectral-temporal metrics

Mapping land cover in highly heterogeneous landscapes is challenging, and classifications have inherent limitations where the spatial resolution of remotely sensed data exceeds the size of small objects. For example, classifications based on 30-m Landsat data do not capture urban or other heterogeneous environments well. This limitation may be overcome by quantifying the subpixel fractions of different land cover types. However, the selection process and transferability of models designed for subpixel land cover mapping across biomes is yet challenging. We asked to what extent (a) locally trained models can be used for sub-pixel land cover fraction estimates in other biomes, and (b) training data from different regions can be combined into spatially generalized models to quantify fractions across global biomes. We applied machine learning regression-based fraction mapping to quantify land cover fractions of 18 regions in five biomes using Landsat data from 2022. We used spectral-temporal metrics to incorporate intra-annual temporal information and compared the performance of local, spatially transferred, and spatially generalized models. Local models performed best when applied to their respective sites (average mean absolute error, MAE, 9–18%), and also well when transferred to other sites within the same biome, but not consistently so for out-of-biome sites. However, spatially generalized models that combined input data from many sites worked very well when analyzing sites in many different biomes, and their MAE values were only slightly higher than those of the respective local models. A weighted training data selection approach, preferring training data with a lower spectral distance to the image data to be predicted, further enhanced the performance of generalized models. Our results suggest that spatially generalized regression-based fraction models can support multi-class sub-pixel fraction estimates based on medium-resolution satellite images globally. Such products would have great value for environmental monitoring in heterogeneous environments and where land cover varies along spatial or temporal gradients.

Spatio-Temporal Sub-Pixel Land Cover Mapping of Remote Sensing Imagery Using Spatial Distribution Information From Same-Class Pixels

The generation of land cover maps with both fine spatial and temporal resolution would aid the monitoring of change on the Earth’s surface. Spatio-temporal sub-pixel land cover mapping (STSPM) uses a few fine spatial resolution (FR) maps and a time series of coarse spatial resolution (CR) remote sensing images as input to generate FR land cover maps with a temporal frequency of the CR data set. Traditional STSPM selects spatially adjacent FR pixels within a local window as neighborhoods to model the land cover spatial dependence, which can be a source of error and uncertainty in the maps generated by the analysis. This paper proposes a new STSPM using FR remote sensing images that pre- and/or post-date the CR image as ancillary data to enhance the quality of the FR map outputs. Spectrally similar pixels within the locality of a target FR pixel in the ancillary data are likely to represent the same land cover class and hence such same-class pixels can provide spatial information to aid the analysis. Experimental results showed that the proposed STSPM predicted land cover maps more accurately than two comparative state-of-the-art STSPM algorithms.

Subpixel Land-Cover Mapping Based on Extended Random Walker

In this letter, a novel subpixel mapping (SPM) based on extended random walker (ERW) (SPMERW) is proposed. First, the resolution of the original coarse remote sensing image is upsampled by bicubic interpolation. Second, the class proportions of subpixel are produced by unmixing the upsampled image. Irregular objects are generated by adaptive segmentation of the first principal component of the upsampled image. Third, the class proportions of the object are derived by averaged fusion of the class proportions of subpixel belonging to each object in the segmentation image. Object spatial dependence including the spatial information among and within the objects is obtained by the ERW algorithm. Finally, a class allocation method based on units of the object is utilized to obtain the SPM result according to the object spatial dependence. Experimental results on two remote sensing data sets show that the proposed SPMERW outperforms the state-of-the-art SPM methods.

Subpixel Land Cover Mapping Based on Dual Processing Paths for Hyperspectral Image

The subpixel mapping (SPM) technique can handle coarse fractional images derived by unmixing coarse original hyperspectral (HS) image to produce a fine land cover map at the subpixel scale. A popular SPM approach is a two-step model. It first increases the spatial resolution of coarse fractional images by subpixel sharpening to produce fine fractional images and then assigns class labels to each subpixel by the class allocation method. However, there is only a single processing path of the current SPM algorithm, and the information type of the fine fractional images is not rich. To enrich the information type, SPM based on dual processing paths (DPP) is proposed. DPP contains two processing paths, namely spatial–spectral path and multiscale path. First, the coarse original HS image and the high spatial resolution multispectral image are fused by component substitution to produce the fine fractional images with more spatial–spectral information in the spatial–spectral path. At the same time, deep Laplacian pyramid networks are used to obtain the fine fractional images with multiscale information in the multiscale path. The fine fractional images from the two paths are then integrated to generate the improved fraction images with multiscale spatial–spectral information. Finally, the multiscale spatial–spectral information is utilized to allocate class labels by the class allocation method. Experimental results on three real HS remote sensing data show that the proposed DPP outperforms the other SPM methods, demonstrating the effectiveness of the use of DPP in enriching the information type of the fine fractional images.

Subpixel land cover mapping based on a new spatial attraction model with spatial-spectral information

ABSTRACTSubpixel mapping (SPM) is a technique for handling mixed pixels to derive hard classification map at finer spatial resolution. Due to simplicity and explicit physical meanings, spatial attraction model (SAM) has been proven to be an effective SPM method. SAM methods mostly differ in the way in which they compute the spatial attraction, for example, subpixel/pixel spatial attraction model (SPSAM), subpixel/subpixel spatial attraction model (MSPSAM), and the mixed spatial attraction model (MSAM). However, these methods are difficult to fully utilize the spatial-spectral information of the original remote sensing image due to diversity of the land cover classes and the limitation of the resolution of the sensor. To solve this problem, spatial attraction model with spatial-spectral information (SAM-SS) is proposed here. SAM-SS can pick up more spatial-spectral information of the original image by adding a new processing path, namely interpolation followed by spectral unmixing. Based on visual comparison and quantitative accuracy assessment, the SAM-SS shows the best performance in the four experimental results.

Multiobjective Subpixel Land-Cover Mapping

The hyperspectral subpixel mapping (SPM) technique can generate a land-cover map at the subpixel scale by modeling the relationship between the abundance map and the spatial distribution image of the subpixels. However, this is an inverse ill-posed problem. The most widely used way to resolve the problem is to introduce additional information as a regularization term and acquire the unique optimal solution. However, the regularization parameter either needs to be determined manually or it cannot be determined in a fully adaptive manner. Thus, in this paper, the multiobjective subpixel land-cover mapping (MOSM) framework for hyperspectral remote sensing imagery is proposed, in which the two function terms [the fidelity term and the prior term (i.e., the regularization term)] can be optimized simultaneously, and there is no need to determine the regularization parameter explicitly. In order to achieve this goal, two strategies are designed in MOSM: 1) a high-resolution distribution image-based individual encoding strategy is designed in order to calculate the prior term accurately and 2) a subfitness-based individual comparison strategy is designed in order to generate subpixel land-cover mapping solutions with a high quality to update the population. Four data sets (one simulated, two synthetic, and one real hyperspectral image) were used to test the proposed method. The experimental results show that MOSM can perform better than the other subpixel land-cover mapping methods, demonstrating the effectiveness of MOSM in balancing the fidelity term and prior term in the SPM model.

Subpixel urban impervious surface mapping: the impact of input Landsat images

Due to the heterogeneity of urban environments, subpixel urban impervious surface mapping is a challenging task in urban environmental studies. Factors, such as atmospheric correction, climate conditions, seasonal effect, urban settings, substantially affect fractional impervious surface estimation. Their impacts, however, have not been well studied and documented. In this research, we performed direct and comprehensive examinations to explore the impacts of these factors on subpixel estimation when using an effective machine learning technique (Random Forest) and provided solutions to alleviate these influences. Four conclusions can be drawn based on the repeatable experiments in three study areas under different climate conditions (humid continental, tropical monsoon, and Mediterranean climates). First, the performance of subpixel urban impervious surface mapping using top-of-atmosphere (TOA) reflectance imagery is comparable to, and even slightly better than, the surface reflectance imagery provided by U.S. Geological Services in all seasons and in all testing regions. Second, the effect of images with leaf-on/off season varies, and is contingent upon different climate regions. Specifically, humid continental areas may prefer the leaf-on imagery (e.g., summer), while the tropical monsoon and Mediterranean regions seem to favor the fall and winter imagery. Third, the overall estimation performance in the humid continental area is somewhat better than the other regions. Finally, improvements can be achieved by using multi-season imagery, but the increments become less obvious when including more than two seasons. The strategy and results of this research could improve and accommodate regional/national subpixel land cover mapping using Landsat images for large-scale environmental studies.

Isolating type-specific phenologies through spectral unmixing of satellite time series

ABSTRACTVegetation phenology is commonly studied using time series of multi-spectral vegetation indices derived from satellite imagery. Differences in reflectance among land-cover and/or plant functional types are obscured by sub-pixel mixing, and so phenological analyses have typically sought to maximize the compositional purity of input satellite data by increasing spatial resolution. We present an alternative method to mitigate this ‘mixed-pixel problem’ and extract the phenological behavior of individual land-cover types inferentially, by inverting the linear mixture model traditionally used for sub-pixel land-cover mapping. Parameterized using genetic algorithms, the method takes advantage of the discriminating capacity of calibrated surface reflectance measurements in red, near infrared, and short-wave infrared wavelengths, as well as the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Water Index. In simulation, the unmixing procedure reproduced the reflectances and phenological signals of grass, crop, and deciduous forests with high fidelity (RMSE < 0.007 NDVI); and in empirical tests, the algorithm extracted the phenological characteristics of evergreen trees and seasonal grasses in a semi-arid savannah. The approach shows potential for a wide range of ecological applications, including detection of differential responses to climate, soil, or other factors among vegetation types.

A New Super Resolution Mapping Algorithm by Combining Pixel and Subpixel-Level Spatial Dependences With Colorimetry

Super resolution mapping is a continuously growing area of remote sensing. Satellite images coupled with a very high spectral resolution, and are suitable for detection and classification of surfaces and different elements in the observed image. The main problem with high resolution data for these applications is the (relatively) low spatial resolution, which can vary from a few to tens of meters. In the case of classification purposes, the major problem caused by low spatial resolution is related to subpixels, i.e., pixels in the image where more than one land cover class is within the same pixel. In such a case, the pixel cannot be considered as belonging to just one class, and the assignment of the pixel to a single class will inevitably lead to a loss of information, no matter what class is chosen. A new super resolution mapping (SRM) algorithm by combining pixel and subpixel-level spatial dependences with colorimetry is proposed in this paper. The pixel-level dependence is measured by the spatial attraction model with either surrounding or quadrant neighborhood, while the subpixel-level dependence is characterized by either the mean filter or the exponential weighting function. Both pixel-level and subpixel-level dependences are then fused as the weighted dependence for quickly obtaining the optimal spatial distribution of subpixels by employing the colorimetric algorithm. Synthetic imagery and a QuickBird image are tested for validation of the proposed method. The results demonstrate that the proposed method can achieve results with greater accuracy than two traditional subpixel mapping (SPM) methods and the mixed spatial attraction model method. Meanwhile, the proposed method needs considerably less computation time than the conventional mixed spatial attraction model method, and hence it provides a new solution to subpixel land cover mapping.

A subpixel mapping algorithm combining pixel-level and subpixel-level spatial dependences with binary integer programming

A new subpixel mapping (SPM) algorithm combining pixel-level and subpixel-level spatial dependences is proposed in this letter. The pixel-level dependence is measured by the spatial attraction model (SAM) with either surrounding or quadrant neighbourhood, while the subpixel-level dependence is characterized by either the mean filter or the exponential weighting function. Both pixel-level and subpixel-level dependences are then fused as the weighted dependence in the constructed objective function. The branch-and-bound algorithm is employed to solve the optimization problem, and thus, obtain the optimal spatial distribution of subpixel classes. An artificial image and a set of real remote sensing images were tested for validation of the proposed method. The results demonstrated that the proposed method can achieve results with greater accuracy than two traditional SPM methods and the mixed SAM method. Meanwhile, the proposed method needs less computation time than the mixed SAM, and hence it provides a new solution to subpixel land cover mapping.

A Spatio–Temporal Pixel-Swapping Algorithm for Subpixel Land Cover Mapping

The aim of this letter is to present a spatio-temporal pixel-swapping algorithm (STPSA), based on conventional pixel-swapping algorithms (PSAs), in which both spatial and temporal contextual information from previous land cover maps or observed samples are well integrated and utilized to improve subpixel mapping accuracy. Unlike conventional pixel-swapping algorithms, STPSA is capable of utilizing prior information, which was previously ignored, to predict the attractiveness based on pairs of subpixels. This algorithm involves three main steps and operates in an iterative manner: 1) it predicts the maximum and minimum attractiveness of each pair of pixels; 2) ranks the swapping scores based on the attractiveness of all the pairs; and 3) swaps the locations of the pair of pixels with a maximum score to increase the objective function. Experiments with actual satellite images have demonstrated that the proposed algorithm performs better than other algorithms. In comparison, the proposed STPSA's better performance is due to the fact that prior information used in other algorithms is restricted to a percentage level rather than the real subpixel level.

Indicator Cokriging-Based Subpixel Land Cover Mapping With Shifted Images

Subpixel mapping (SPM) is a technique for predicting the spatial distribution of land cover classes in remote sensing images at a finer spatial resolution level than those of the input images. Indicator cokriging (ICK) has been found to be an effective and efficient SPM method. The accuracy of this model, however, is limited by insufficient constraints. In this paper, the accuracy of the ICK-based SPM model is enhanced by using additional information gained from multiple shifted images (MSIs). First, each shifted image is utilized to compute the conditional probability of class occurrence at any fine spatial resolution pixel (i.e., subpixel) using ICK, and a set of conditional probability maps for all classes are generated for each image. The multiple ICK-derived conditional probability maps are then integrated, according to the estimated subpixel shifts of MSI. Lastly, class allocation at the subpixel scale is implemented to produce SPM results. The proposed algorithm was tested on two synthetic coarse spatial resolution remote sensing images and a set of real Moderate Resolution Imaging Spectroradiometer (MODIS) data. It was evaluated both visually and quantitatively. The experimental results showed that more accurate SPM results can be generated with MSI than with a single observed coarse image in conventional ICK-based SPM. In addition, the accuracy of the proposed method is higher than that of the existing Hopfield neural network (HNN)-based SPM and the HNN with MSI.

Mapping impervious surfaces from superresolution enhanced CHRIS/Proba imagery using multiple endmember unmixing

In this paper, the potential of superresolution (SR) image reconstruction methods for sub-pixel land-cover mapping in dense urban areas is studied. A multiple endmember approach (MESMA) is used for unmixing both original hyperspectral CHRIS/Proba and SR enhanced CHRIS/Proba data. Validation based on high resolution orthophotos (25cm) shows that land-cover fraction maps generated from SR-enhanced CHRIS/Proba data (9m) have a lower overall fractional error compared to the land-cover fractions produced from the original CHRIS data (18m), when validating both results at the 18m resolution. Validation of SR results at the 9m resolution produces an overall mean absolute error (OMAE) of 16.7% compared to an OMAE of 14.3% at the 18m resolution, with the original data, yet the impervious surface map produced at 9m has a much higher level of detail than the original map, better representing the built-up pattern of the urban environment. Detailed analysis of impervious surface mapping results for different reference proportion intervals points at smaller average fractional errors for impervious surface fractions produced from SR-enhanced data when validation is done at the original 18m resolution, over the entire range of proportions. Only for pixels not containing any impervious surface cover the fractional error is marginally higher than with the original data. These results demonstrate the potential of SR-enhanced data for more accurate impervious surface mapping in dense and heterogeneous urban areas.

Sub-pixel land-cover mapping with improved fraction images upon multiple-point simulation

Outputs of soft classification inherently contain uncertainty. As an input for the sub-pixel mapping (SPM) method, the uncertainty is propagated to SPM result especially the boundary region between classes. Therefore, reducing the uncertainty within the outputs of soft classification is worth exploring. This paper firstly utilizes multiple-point simulation (MPS) through training images for characterizing the spatial structural properties of a surface object/class. Consequently, MPS results are used to increase the accuracy of the fraction image of the surface object/class. The improved fraction image then inputs to the SPM method for producing the land cover map with finer spatial resolution. In order to validate the proposed method, a remotely sensed image from Landsat TM 30m over the Qianyanzhou red earth hill region in China is used. This experimental study not only compares the results from SPM with improved fraction images with MPS and results from SPM with original fraction images, but also investigates the performances of different soft classifiers. It has been demonstrated that this proposed method is an effective way to reduce the uncertainty in outputs of different soft classification, increase the recognition accuracies of boundary regions and thus increase the accuracies of SPM simulated images.

Subpixel Land Cover Mapping by Integrating Spectral and Spatial Information of Remotely Sensed Imagery

Subpixel mapping (SPM) is a technique to predict spatial locations of land cover classes within mixed pixels in remotely sensed imagery. The two-step approach first estimates fraction images by spectral unmixing and then inputs fraction images into an SPM algorithm to generate the final subpixel land cover map. A shortcoming of this approach is that the information about the credibility of fraction images is not considered. In this letter, we proposed a general framework of SPM which is directly applied to original coarse resolution remotely sensed imagery by integrating spectral and spatial information. Based on the proposed framework, the linear unmixing model and the maximal spatial dependence model were combined to construct a novel SPM model aiming to minimize the least squares error of spectral signature and make the subpixel land cover map spatially smooth, simultaneously. By applying to an Airborne Visible/Infrared Imaging Spectrometer hyperspectral image, the proposed model was evaluated both visually and quantitatively by comparing it with hard classification and the two-step SPM approach. The results showed that the regularization parameter, which balances the influence of spectral and spatial terms, plays an important role on the solution. The L-curve approach was a reasonable method to select the regularization parameter, with which an increased accuracy of the proposed model was obtained.

Approaches to fractional land cover and continuous field mapping: A comparative assessment over the BOREAS study region

Subpixel land cover mapping involves the estimation of surface properties using sensors whose spatial sampling is coarse enough to produce mixtures of the properties within each pixel. This study evaluates five algorithms for mapping subpixel land cover fractions and continuous fields of vegetation properties within the BOREAS study area. The algorithms include a conventional “hard”, per-pixel classifier, a neural network, a clustering/look-up-table approach, multivariate regression, and linear least squares inversion. A land cover map prepared using a Landsat TM mosaic was adopted as the source of fine scale calibration and validation data. Coarse scale mixtures of five basic land cover classes and continuous vegetation fields, both corresponding to the field of view of SPOT-VEGETATION imagery (1.15-km pixel size), were synthesised from the TM mosaic using a modelled point spread function. Two measures of land cover distribution were used, fractions of fine scale land cover categories and continuous fields of vegetation structural characteristics. The subpixel algorithms were applied using both proximate (<100 km) and distant (>400 km) separation between training and validation regions. “Hard” classification performed poorly in estimating proportions or continuous fields. The neural network, look-up-table and multivariate regression algorithms produced good matches of spatial patterns and regional land cover composition for the proximate treatment. However, all three methods exhibited substantial biases with the distant treatment due to the characteristics of the training data. Linear least squares inversion offers a relatively unbiased but less precise alternative for subpixel proportion and fraction mapping as it avoids calibration to the a priori distribution of land cover in the training data. In general, a combination of multivariate regression for proximate training data and linear least squares inversion for distant training data resulted in woody fraction estimates within 20% of the Landsat TM classification-based estimates.

Sub-pixel land cover mapping for per-field classification

A method was developed to transform a soft land cover classification into hard land cover classes at the sub-pixel scale for subsequent per-field classification. First, image pixels were segmented using vector boundaries. Second, the pixel segments (ranked by area) were labelled with a land cover class (ranked by class typicality). Third, a hard per-field classification was generated by examining each polygon (representing a land cover parcel, or field) in its entirety (by grouping the fragments of the polygon contained within different image pixels) and assigning to it the modal land cover class. The accuracy of this technique was considerably higher than that of both a corresponding hard per-pixel classification and a perfield classification based on hard per-pixel classified imagery.