Soil Salinity Detection in Semi-Arid Region Using Spectral Unmixing, Remote Sensing and Ground Truth Measurements

Soil salinity is one of the serious environmental problems ravaging the soils of arid and semi-arid region, thereby affecting crop productivity, livestock, increase level of poverty and land degradation. Hyperspectral remote sensing is one of the important techniques to monitor, analyze and estimate the extent and severity of soil salt at regional to local scale. In this study we develop a model for the detection of salt-affected soils in arid and semi-arid regions and in our case it’s Ghannouch, Gabes. We used fourteen spectral indices and six spectral bands extracted from the Hyperion data. Linear Spectral Unmixing technique (LSU) was used in this study to improve the correlation between electrical conductivity and spectral indices and then improve the prediction of soil salinity as well as the reliability of the model. To build the model a multiple linear regression analysis was applied using the best correlated indices. The standard error of the estimate is about 1.57 mS/cm. The results of this study show that hyperion data is accurate and suitable for differentiating between categories of salt affected soils. The generated model can be used for management strategies in the future.

Timely monitoring of soil water-salt dynamics within cropland by hybrid spectral unmixing and machine learning models

Soil salinization and water scarcity are main restrictive factors for irrigated agriculture development in arid regions.Knowing dynamics of soil water and salt content is an important antecedent in remediating salinized soils and optimizing irrigation management.Previous studies mostly used remote sensing technologies to individually monitor water or salt content dynamics in agricultural areas.Their ability to asses different levels of crop water and salt management has been less explored.Therefore,how to extract effective diagnostic features from remote sensing images derived spectral information is crucial for accurately estimating soil water and salt content.In this study,Linear spectral unmixing method(LSU)was used to obtain the contribution of soil water and salt to each band spectrum(abundance),and endmember spectra from Sentinel-2 images.Calculating spectral indices and selecting optimal spectal combination were individually based on soil water and salt endmember spectra.The estimation models were constructed using six machine learning algorithms:BP Neural Network(BPNN),Support Vector Regression(SVR),Partial Least Squares Regression(PLSR),Random Forest Regression(RFR),Gradient Boost Regression Tree(GBRT),and eXtreme Gradient Boosting tree(XGBoost).The results showed that the spectral indices calculated from endmember spectra were able to effectively characterize the response of crop spectral properties to soil water and salt,which circumvent spectral ambiguity induced by water-salt mixing.NDRE spectral index was a reliable indicator for estimating water and salt content,with determination coefficients(R2)being 0.55 and 0.57,respectively.Compared to other models,LSU-XGBoost model achieved the best performance.This model properly reflected the process of soil water-salt dynamics in farmland during crop growth period.This study provided new methods and ideas for soil water-salt estimation in dry irrigated agricultural areas,and provided decision support for gover-nance of salinized land and optimal management of irrigation.

Minimum distance constrained nonnegative matrix factorization for hyperspectral data unmixing

This paper considers a problem of unsupervised spectral unmixing of hyperspectral data. Based on the Linear Mixing Model （ LMM）, a new method under the framework of nonnegative matrix fac- torization （NMF） is proposed, namely minimum distance constrained nonnegative matrix factoriza- tion （MDC-NMF）. In this paper, firstly, a new regularization term, called endmember distance （ED） is considered, which is defined as the sum of the squared Euclidean distances from each end- member to their geometric center. Compared with the simplex volume, ED has better optimization properties and is conceptually intuitive. Secondly, a projected gradient （PG） scheme is adopted, and by the virtue of ED, in this scheme the optimal step size along the feasible descent direction can be calculated easily at each iteration. Thirdly, a finite step （ no more than the number of endmem- bers） terminated algorithm is used to project a point on the canonical simplex, by which the abun- dance nonnegative constraint and abundance sum-to-one constraint can be accurately satisfied in a light amount of computation. The experimental results, based on a set of synthetic data and real da- ta, demonstrate that, in the same running time, MDC-NMF outperforms several other similar meth- ods proposed recently.

Target-to-Background Separation for Spectral Unmixing in In-Vivo Fluorescence Imaging

We present a novel fluorescence spectral unmixing based on target-to-background separation preprocessing, which effectively separates the multi-target fluorescence from all background autofluorescence(BF)without any hardware-based BF acquisition and tissue specific BF estimation. Specifically, we first enhance the intrinsic accumulation contrast in target-to-background fluorescence using h-dome transformation; then separate multi-target fluorescence areas from the background in sparse multispectral data utilizing kernel maximum autocorrelation factor analysis; we further use fast marching-based image inpainting method to patch up the removed target fluorescence areas and reconstruct the multispectral BF; with the BF matrix being subtracted from the original data, the multi-target fluorophores are easily unmixed from the subtracted data using multivariate curve resolution-alternating least squares method. In two preliminary in-vivo experiments, the proposed method demonstrated excellent performance to unmix multi-target fluorescences while other state-of-art unmixing methods failed to get desired results.

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

Vegetation phenology is commonly studied using time series of multispectral 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.

Hypergraph Regularized Deep Autoencoder for Unsupervised Unmixing Hyperspectral Images

Deep learning(DL)has shown its superior performance in dealing with various computer vision tasks in recent years.As a simple and effective DL model,autoencoder(AE)is popularly used to decompose hyperspectral images(HSIs)due to its powerful ability of feature extraction and data reconstruction.However,most existing AE-based unmixing algorithms usually ignore the spatial information of HSIs.To solve this problem,a hypergraph regularized deep autoencoder(HGAE)is proposed for unmixing.Firstly,the traditional AE architecture is specifically improved as an unsupervised unmixing framework.Secondly,hypergraph learning is employed to reformulate the loss function,which facilitates the expression of high-order similarity among locally neighboring pixels and promotes the consistency of their abundances.Moreover,L_(1/2)norm is further used to enhance abundances sparsity.Finally,the experiments on simulated data,real hyperspectral remote sensing images,and textile cloth images are used to verify that the proposed method can perform better than several state-of-the-art unmixing algorithms.

A Novel Fuzzy Inference System-Based Endmember Extraction in Hyperspectral Images

Spectral unmixing helps to identify different components present in the spectral mixtures which occur in the uppermost layer of the area owing to the low spatial resolution of hyperspectral images.Most spectral unmixing methods are globally based and do not consider the spectral variability among its endmembers that occur due to illumination,atmospheric,and environmental conditions.Here,endmember bundle extraction plays a major role in overcoming the above-mentioned limitations leading to more accurate abundance fractions.Accordingly,a two-stage approach is proposed to extract endmembers through endmember bundles in hyperspectral images.The divide and conquer method is applied as the first step in subset images with only the non-redundant bands to extract endmembers using the Vertex Component Analysis(VCA)and N-FINDR algorithms.A fuzzy rule-based inference system utilizing spectral matching parameters is proposed in the second step to categorize endmembers.The endmember with the minimum error is chosen as the final endmember in each specific category.The proposed method is simple and automatically considers endmember variability in hyperspectral images.The efficiency of the proposed method is evaluated using two real hyperspectral datasets.The average spectral angle and abundance angle are used to analyze the performance measures.

B2 adrenergic receptors and morphological changes of the enteric nervous system in colorectal adenocarcinoma

To study the morphology of the enteric nervous system and the expression of beta-2 adrenergic (B2A) receptors in primary colorectal cancer.METHODSIn this study, we included forty-eight patients with primary colorectal cancer and nine patients for control tissue from the excision of a colonic segment for benign conditions. We determined the clinicopathological features and evaluated the immunohistochemical expression pattern of B2A receptors as well as the morphological changes of the enteric nervous system (ENS). In order to assess statistical differences, we used the student t-test for comparing the means of two groups and one-way analysis of variance with Bonferroni’s post hoc analysis for comparing the means of more than two groups. Correlations were assessed using the Pearson’s correlation coefficient.RESULTSB2A receptors were significantly associated with tumor grading, tumor size, tumor invasion, lymph node metastasis (P < 0.05), while there were no statistically significant associations with gender, CRC location and gross appearance (P > 0.05). We observed, on one hand, a decrease of the relative area for both Auerbach and Meissner plexuses with the increase of the tumor grading, and on the other hand, an increase of the relative area of other nervous elements not in the Meissner plexus or in the Auerbach plexus with the tumor grading. For G1 tumors we found that epithelial B2A area showed an inverse correlation with the Auerbach plexus areas [r(14) = -0.531, P < 0.05], while for G2 tumors, epithelial B2A areas showed an indirect variation with both the Auerbach plexus areas [r(14) = -0.453, P < 0.05] and the Meissner areas [r(14) = -0.825, P < 0.01]. For G3 tumors, the inverse dependence increased for both Auerbach [r(14) = -0.587, P < 0.05] and Meissner [r(14) = -0.934, P < 0.05] plexuses.CONCLUSIONB2A receptors play an important role in colorectal carcinogenesis and can be utilized as prognostic factors. Furthermore, study of the ENS in colorectal cancer may lead to targeted molecular therapies.

Speed-up for N-FINDR algorithm

N-FINDR is a very popular algorithm of endmember (EM) extraction for its automated property and high efficiency. Unfortunately, innumerable volume calculation, initial random selection of EMs and blind searching for EMs lead to low speed of the algorithm and limit the applications of the algorithm. So in this paper two measures are proposed to speed up the algorithm. One of the measures is substituting distance calculation for volume calculation. Thus the avoidance of volume calculation greatly decreases the computational cost. The other measure is resorting dataset in terms of pixel purity likelihood based on pixel purity index (PPI) concept. Then, initial EMs can be selected well-founded and a fast searching for EMs is achieved. Numerical experiments show that the two measures speed up the original algorithm hundreds of times as the number of EMs is more than ten.

The paleoclimatic environment reconstruction of Lop Nur in NW China in UAV spectroscopy

The change in the ecological environment in the arid core area is a critical issue in the context of global warming.To study the paleoclimate evolution,precise identification of minerals deposited in Asia’s arid hinterland,Lop Nur Salt Lake,NW China was conducted.The hyperspectral data of the salt crust was sampled to identify the species and content of sedimentary minerals,and the multispectral photos were used to reconstruct the salt crust morphology using the unmanned aerial vehicles platform.The SUnSAL(sparse unmixing by variable splitting and augmented Lagrangian)method was employed to inverse the sedimentary mineral components along the shoreline.The heterogeneity of salt and clay minerals in bright and dark ear-shaped strips was evaluated.The paleoclimatic environment associated with salt lake extinction was reconstructed by analyzing paleoclimate records of sediments,spectral reflectance and morphology of the salt crust.Results show that:(1)the variations in the micro-geomorphology of the salt crust are obviously the reason for the formation of bright and dark ear-shaped strips and the differences in the species and relative content of the sedimentary minerals are the microscopic reason.The high ratio of sedimentary salt minerals to clay minerals(RS/C)contributes to the high reflectivity,and the salt crust presents a bright texture.The low RS/C results in the low reflectivity,salt crust presents a dark texture;(2)the bright and dark ear-shaped strips represent warm-arid and cold-humid climates.The shape of the Lop Nur Lake shoreline evolved due to alternating warm-dry and cold-humid paleoclimate changes.

Recent advances in hyperspectral image processing

Hyperspectral images(HSI)provide a new way to exploit the internal physical composition of the land scene.The basic platform for acquiring HSI data-sets are airborne or spaceborne spectral imaging.Retrieving useful information from hyperspectral images can be grouped into four categories.(1)Classification:Hyperspectral images provide so much spectral and spatial information that remotely sensed image classification has become a complex task.(2)Endmember extraction and spectral unmixing:Among images,only HSI have a complete model to represent the internal structure of each pixel where the endmembers are the elements.Identification of endmembers from HSI thus becomes the foremost step in interpretation of each pixel.With proper endmembers,the corresponding abundances can also be exactly calculated.(3)Target detection:Another practical problem is how to determine the existence of certain resolved or full pixel objects from a complex background.Constructing a reliable rule for separating target signals from all the other background signals,even in the case of low target occurrence and high spectral variation,comprises the key to this problem.(4)Change detection:Although change detection is not a new problem,detecting changes from hyperspectral images has brought new challenges,since the spectral bands are so many,accurate band-to-band correspondences and minor changes in subclass land objects can be depicted in HSI.In this paper,the basic theory and the most canonical works are discussed,along with the most recent advances in each aspect of hyperspectral image processing.

Mapping alteration minerals using sub-pixel unmixing of ASTER data in the Sarduiyeh area,SE Kerman,Iran

This paper is an attempt to introduce the role of earth observation technology and a type of digital earth processing in mineral resources exploration and assessment.The sub-pixel distribution and quantity of alteration minerals were mapped using linear spectral unmixing(LSU)and mixture tuned matched filtering(MTMF)algorithms in the Sarduiyeh area,SE Kerman,Iran,using the visible-near infrared(VNIR)and short wave infrared(SWIR)bands of the Advanced Spaceborne Thermal Emission and Reflection Radiometer(ASTER)instrument and the results were compared to evaluate the efficiency of methods.Three groups of alteration minerals were identified:(1)pyrophylite-alunite(2)sericite-kaolinite,and(3)chlorite-calcite-epidote.Results showed that high abundances within pixels were successfully corresponded to the alteration zones.In addition,a number of unreported altered areas were identified.Field observations and X-ray diffraction(XRD)analysis of field samples confirmed the dominant mineral phases identified remotely.Results of LSU and MTMF were generally similar with overall accuracy of 82.9 and 90.24%,respectively.It is concluded that LSU and MTMF are suitable for sub-pixel mapping of alteration minerals and when the purpose is identification of particular targets,rather than all the elements in the scene,the MTMF algorithm could be proposed.

Assessing tree crown fire damage integrating linear spectral mixture analysis and supervised machine learning on Sentinel-2 imagery

Crown fire damage is a mixture of three principal fire-related components:charred material,scorched foliage,and unaltered green canopy.This study estimated the abundance of these physical alterations in two immediate post-fire Mediterranean forest contexts(Portugal and Italy)by applying linear spectral mixture analysis(LSMA)on Sentinel-2 imagery.The tree crowns fire damage was subsequently mapped,integrating fractional abundance information in a random forest(RF)algorithm,comparing the accuracy resulting from the adoption of generic or image spectral libraries as the primary investigative goal.Although image-derived endmembers resulted in more effectiveness in terms of fire-related components abundance quantification(LMSAderived RMSE<0.1),the F-scores always were≥90%whether generic endmembers or image endmembers derived information was employed.The environmental heterogeneity of the two study areas affected the fire severity gradients,with a prevalence of the charred(PT)(45–46%)and green class(IT)(44–53%).Post-fire temporal monitoring was initialized by applying the proposed strategies,and the preliminary results showed a positive recovery trend in forest vegetation from the first year following the fire event,with a reduced charcoal predominance and an increasing proportion of green components.