Hyperspectral remote sensing identification of marine oil emulsions based on the fusion of spatial and spectral features

Marine oil spill emulsions are difficult to recover,and the damage to the environment is not easy to eliminate.The use of remote sensing to accurately identify oil spill emulsions is highly important for the protection of marine environments.However,the spectrum of oil emulsions changes due to different water content.Hyperspectral remote sensing and deep learning can use spectral and spatial information to identify different types of oil emulsions.Nonetheless,hyperspectral data can also cause information redundancy,reducing classification accuracy and efficiency,and even overfitting in machine learning models.To address these problems,an oil emulsion deep-learning identification model with spatial-spectral feature fusion is established,and feature bands that can distinguish between crude oil,seawater,water-in-oil emulsion(WO),and oil-in-water emulsion(OW)are filtered based on a standard deviation threshold–mutual information method.Using oil spill airborne hyperspectral data,we conducted identification experiments on oil emulsions in different background waters and under different spatial and temporal conditions,analyzed the transferability of the model,and explored the effects of feature band selection and spectral resolution on the identification of oil emulsions.The results show the following.(1)The standard deviation–mutual information feature selection method is able to effectively extract feature bands that can distinguish between WO,OW,oil slick,and seawater.The number of bands was reduced from 224 to 134 after feature selection on the Airborne Visible Infrared Imaging Spectrometer(AVIRIS)data and from 126 to 100 on the S185 data.(2)With feature selection,the overall accuracy and Kappa of the identification results for the training area are 91.80%and 0.86,respectively,improved by 2.62%and 0.04,and the overall accuracy and Kappa of the identification results for the migration area are 86.53%and 0.80,respectively,improved by 3.45%and 0.05.(3)The oil emulsion identification model has a certain degree of transferability and can effectively identify oil spill emulsions for AVIRIS data at different times and locations,with an overall accuracy of more than 80%,Kappa coefficient of more than 0.7,and F1 score of 0.75 or more for each category.(4)As the spectral resolution decreasing,the model yields different degrees of misclassification for areas with a mixed distribution of oil slick and seawater or mixed distribution of WO and OW.Based on the above experimental results,we demonstrate that the oil emulsion identification model with spatial–spectral feature fusion achieves a high accuracy rate in identifying oil emulsion using airborne hyperspectral data,and can be applied to images under different spatial and temporal conditions.Furthermore,we also elucidate the impact of factors such as spectral resolution and background water bodies on the identification process.These findings provide new reference for future endeavors in automated marine oil spill detection.

Automated Deep Learning Driven Crop Classification on Hyperspectral Remote Sensing Images

Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent images.Hyperspectral remote sensing contains acquisition of digital images from several narrow,contiguous spectral bands throughout the visible,Thermal Infrared(TIR),Near Infrared(NIR),and Mid-Infrared(MIR)regions of the electromagnetic spectrum.In order to the application of agricultural regions,remote sensing approaches are studied and executed to their benefit of continuous and quantitativemonitoring.Particularly,hyperspectral images(HSI)are considered the precise for agriculture as they can offer chemical and physical data on vegetation.With this motivation,this article presents a novel Hurricane Optimization Algorithm with Deep Transfer Learning Driven Crop Classification(HOADTL-CC)model onHyperspectralRemote Sensing Images.The presentedHOADTL-CC model focuses on the identification and categorization of crops on hyperspectral remote sensing images.To accomplish this,the presentedHOADTL-CC model involves the design ofHOAwith capsule network(CapsNet)model for generating a set of useful feature vectors.Besides,Elman neural network(ENN)model is applied to allot proper class labels into the input HSI.Finally,glowworm swarm optimization(GSO)algorithm is exploited to fine tune the ENNparameters involved in this article.The experimental result scrutiny of the HOADTL-CC method can be tested with the help of benchmark dataset and the results are assessed under distinct aspects.Extensive comparative studies stated the enhanced performance of the HOADTL-CC model over recent approaches with maximum accuracy of 99.51%.

The application of hyperspectral remote sensing to coast environment investigation

Requirements for monitoring the coastal zone environment are first summarized. Then the appli- cation of hyperspectral remote sensing to coast environment investigation is introduced, such as the classification of coast beaches and bottom matter, target recognition, mine detection, oil spill identification and ocean color remote sensing. Finally, what is needed to follow on in application of hyperspectral remote sensing to coast environment is recommended.

Progress of Geological Survey Using Airborne Hyperspectral Remote Sensing Data in the Gansu and Qinghai Regions

Hyperspectral remote sensing is now a frontier of the remote sensing technology. Airborne hyperspectral remote sensing data have hundreds of narrow bands to obtain complete and continuous ground-object spectra. Therefore, they can be effectively used to identify these grotmd objects which are difficult to discriminate by using wide-band data, and show much promise in geological survey. At the height of 1500 m, have 36 bands in visible to the CASI hyperspectral data near-infrared spectral range, with a spectral resolution of 19 nm and a space resolution of 0.9 m. The SASI data have 101 bands in the shortwave infrared spectral range, with a spectral resolution of 15 nm and a space resolution of 2.25 m. In 2010, China Geological Survey deployed an airborne CASI/SASI hyperspectral measurement project, and selected the Liuyuan and Fangshankou areas in the Beishan metallogenic belt of Gansu Province, and the Nachitai area of East Kunlun metallogenic belt in Qinghai Province to conduct geological survey. The work period of this project was three years.

Towards a semi-empirical model of the sea ice thickness based on hyperspectral remote sensing in the Bohai Sea

Sea ice thickness is one of the most important input parameters for the prevention and mitigation of sea ice disasters and the prediction of local sea environments and climates. Estimating the sea ice thickness is currently the most important issue in the study of sea ice remote sensing. With the Bohai Sea as the study area, a semiempirical model of the sea ice thickness（SEMSIT） that can be used to estimate the thickness of first-year ice based on existing water depth estimation models and hyperspectral remote sensing data according to an optical radiative transfer process in sea ice is proposed. In the model, the absorption and scattering properties of sea ice in different bands（spectral dimension information） are utilized. An integrated attenuation coefficient at the pixel level is estimated using the height of the reflectance peak at 1 088 nm. In addition, the surface reflectance of sea ice at the pixel level is estimated using the 1 550–1 750 nm band reflectance. The model is used to estimate the sea ice thickness with Hyperion images. The first validation results suggest that the proposed model and parameterization scheme can effectively reduce the estimation error associated with the sea ice thickness that is caused by temporal and spatial heterogeneities in the integrated attenuation coefficient and sea ice surface. A practical semi-empirical model and parameterization scheme that may be feasible for the sea ice thickness estimation using hyperspectral remote sensing data are potentially provided.

Feature extraction and classification of hyperspectral remote sensing image oriented to easy mixed-classified objects

The classification of hyperspectral remote sensing data is an important problem theoretically and practically. With the increase of spectral bands, the separability of objects on remote sensing image should be improved. But the effects of traditional algorithm on feature extraction such as principal component analysis(PCA) is not so good for hyperspectral image. The key problem is that PCA can only represent the linear structure of data set; while the data clouds of different objects on hyperspectral image usually distribute on a nonlinear manifold. This paper established an algorithm of nonlinear feature extraction named as nonlinear principal poly lines, based on the algorithm, a classifier is constructed and the classification accuracy of hyperspectral image can be improved.

Indication of the Expression of Transgene in Rice Plant Based on Hyperspectral Remote Sensing Technique Ⅱ——Growth Monitoring of Samples in the Contrast Experiment

Since the complication of monitoring and evaluating the problems about the transgenic expression and its impacts on the receptor in the transgenic crop breeding and other relevant evaluated works,the authors in the present work tried to assess the differences of spectral parameters of the transgenic rice in contrast with its parent group quantitatively and qualitatively,fulfilling the growth monitoring of the transgenic samples.The spectral parameters(spectral morphological characteristics and indices) chosen are highly related to internal or external stresses to the receipts,and thus could be applied as indicators of biophysical or biochemical processes changes of plant.By ASD portable field spectroradiometer with high-density probe,fine foliar spectra of 8 groups were obtained.By analyzing spectral angle and continuum removal,the spectral morphological differences and their locations of sample spectra were found which could be as auxiliary priori knowledge for quantitative analysis.By investigating spectral indices of the samples,the quantitative differences of spectra were revealed about foliar chlorophyll a+b and carotenoid content.In this study both the spectral differences between transgenic and parent groups and among transgenic groups were investigated.The results show that hyperspectral technique is promising and a helpful auxiliary tool in the study of monitoring the transgenic crop and other relevant researches.By this technique,quantitative and qualitative results of sample spectra could be provided as prior knowledge,as certain orientation,for laboratory professional advanced transgenic breeding study.

Retrieval of chlorophyll a and suspended solid concen-trations by hyperspectral remote sensing in Taihu Lake,China

Chlorophyll a (chl-a) and suspended solid concentrations are two frequently used water quality parameters for monitoring a lake. Traditional measurement of chl-a and suspended solids, requir-ing laborious laboratory work, which is often expensive and time consuming. Hyperspectral re-mote-sensing measurement provides a fast and easy tool for estimating water trophic status. In situ hy-perspectral data on March 7–8, July 6–7, September 20 and December 7–8, 2004 and the corresponding water chemical data were used to regress the algorithm of water quality parameters. Results showed that the peak of water leaving radiance around 700 nm (R700) varied proportionally with chl-a concentration, and moved to infrared when algal bloom occurred. The reflectance ratio of R702/R685 was well correlated with chl-a when water surface in no algal bloom case and the correlation coefficient was better if absorp-tion of phycocyanin was considered. The reflectance ratio R620/R531 was highly correlated to the concen-tration of suspended solids. The relationship between suspended solids and other band groups were also compared. Secchi disk depth could be calculated by non-linear correlation with suspended solids concen-tration.

Applications of Hyperspectral Remote Sensing in Ground Object Identification and Classification

Hyperspectral remote sensing has become one of the research frontiers in ground object identification and classification. On the basis of reviewing the application of hyperspectral remote sensing in identification and classification of ground objects at home and abroad. The research results of identification and classification of forest tree species, grassland and urban land features were summarized. Then the researches of classification methods were summarized. Finally the prospects of hyperspectral remote sensing in ground object identification and classification were prospected.

Spectral Analysis of Water Reflectance for Hyperspectral Remote Sensing of Water Quailty in Estuarine Water

Hyperspectral remote sensing offers an effective approach for frequent, synoptic water quality measurements over a large spatial extent. However, the optical complexity of case 2 water makes the water quality monitoring by remote sensing in estuarine water a challenge. The prime objective of this study was to develop algorithms for hyperspectral remote sensing of water quality based on in situ spectral measurement of water reflectance. In this study, water reflectance spectra R(λ) were acquired by a pair of Ocean Optic 2000 spectroradiometers during the summers from 2008 to 2011 at Patuxent River, a tributary of Chesapeake Bay, USA. Simultaneously, concentrations of chlorophyll a and total suspended solids (TSS), as well as absorption of colored dissolved organic matter (CDOM) were measured. Empirical models that based on spectral features of water reflectance generally showed good correlations with water quality parameters. The retrieval model that using spectral bands at red/NIR showed a high correlation with chlorophyll a concentration (R2 = 0.81). The ratio of green to blue spectral bands is the best predictor for TSS (R2 = 0.75), and CDOM absorption is best correlated with spectral features at blue and NIR regions (R2 = 0.85). These empirical models were further applied to the ASIA Eagle hyperspectral aerial imagery to demonstrate the feasibility of hyperspectral remote sensing of water quality in the optical complex estuarine waters.

Classification of hyperspectral remote sensing images based on simulated annealing genetic algorithm and multiple instance learning

A hybrid feature selection and classification strategy was proposed based on the simulated annealing genetic algorithm and multiple instance learning(MIL).The band selection method was proposed from subspace decomposition,which combines the simulated annealing algorithm with the genetic algorithm in choosing different cross-over and mutation probabilities,as well as mutation individuals.Then MIL was combined with image segmentation,clustering and support vector machine algorithms to classify hyperspectral image.The experimental results show that this proposed method can get high classification accuracy of 93.13% at small training samples and the weaknesses of the conventional methods are overcome.

A Preliminary Assessment of Hyperspectral Remote Sensing Technology for Mapping Submerged Aquatic Vegetation in the Upper Delaware River National Parks (USA)

Hyperspectral remote sensing of submerged aquatic vegetation is a complex and difficult process that is affected by unique constraints on the energy flow profile near and below the water surface. In addition, shallow, winding, lotic systems, such as the Upper Delaware River, present additional remote sensing problems in the form of specular reflectance, variable depth and constituents in the water column and sometimes extremely weak signal strength due to absorption and scattering in the water column that can be statistically overwhelmed by the reflectance from upland vegetation in any individual image scene. Here we test hyperspectral imagery from the Civil Air Patrol’s (CAP), Airborne Real-time Cueing Hyperspectral Enhanced Recon (ARCHER) system in the scenic waters of two National Parks on the Upper Delaware River. A number of unique image processing problems were encountered, including specular reflectance from winding lotic systems, variable depth and flow dynamics of the riverine environment, and disproportionate signal strength from surface reflectance in this riverine environment. These problems were solved by applying a specular reflectance removal algorithm, applying field data collections to classification results and masking upland vegetation so as to not statistically overwhelm the weak reflectance signal from surface and near-surface water. Much was learned about conducting imaging spectroscopy in such difficult conditions. Important results include successful mapping of Submerged Aquatic Vegetation (SAV) presence/absence, advantages of upland masking of the reflectance signal, and a number of processing approaches that are unique to this environment. In this paper we summarize our results and identify unique issues that must be addressed in this environment.

Optimal bandwidth selection for retrieving Cu content in rock based on hyperspectral remote sensing

Hyperspectral remote sensing technology is widely used to detect element contents because of its multiple bands,high resolution,and abundant information.Although researchers have paid considerable attention to selecting the optimal bandwidth for the hyperspectral inversion of metal element contents in rocks,the influence of bandwidth on the inversion accuracy are ignored.In this study,we collected 258 rock samples in and near the Kalatage polymetallic ore concentration area in the southwestern part of Hami City,Xinjiang Uygur Autonomous Region,China and measured the ground spectra of these samples.The original spectra were resampled with different bandwidths.A Partial Least Squares Regression(PLSR)model was used to invert Cu contents of rock samples and then the influence of different bandwidths on Cu content inversion accuracy was explored.According to the results,the PLSR model obtains the highest Cu content inversion accuracy at a bandwidth of 35 nm,with the model determination coefficient(R^(2))of 0.5907.The PLSR inversion accuracy is relatively unaffected by the bandwidth within 5-80 nm,but the accuracy decreases significantly at 85 nm bandwidth(R^(2)=0.5473),and the accuracy gradually decreased at bandwidths beyond 85 nm.Hence,bandwidth has a certain impact on the inversion accuracy of Cu content in rocks using the PLSR model.This study provides an indicator argument and theoretical basis for the future design of hyperspectral sensors for rock geochemistry.

Mapping of Aluminous Rich Laterite Depositions through Hyper Spectral Remote Sensing

Increased dimensionality of the satellite data proves to be very useful for discriminating features with very close spectral matching. Present study concentrates on the retrieval of reflectance spectra from the level one radiometrically corrected data in Koraput district (Orissa) for the Bauxite ore. In the present study, atmospheric correction model FLAASH has been used to retrieve reflectance from the radiance data. Preprocessing of the dataset has been done before applying atmospheric correction on the dataset. Spectral subsetting of noise prone bands has been successfully done. Local destriping of the affected bands has been done using a 3*3 local mean filter. Spectral signatures of samples were derived from the processed data. Spectral signature of each sample and derived features vectors were correlated with the satellite image of the area and distribution of each feature was demarcated. Spatial abundance of each feature was used in preparation of mineral abundance map. Accuracy of the map was assessed using training sets of representative geological units. The mineral abundance mapping using the spectral analysis of the reflectance image involves the endmember collection using the N-Dimensional visualizer tool in ENVI software. Laterite, Bauxite, Iron and silica rich Aluminous laterite soil, Alluvium and Forest were selected as the end members after understanding the geology and analysis of the reflectance image. Various mapping techniques were applied to generate the final classified mineral abundance Map, Linear Spectral Unmixing, Mixture Tune Matched Filtering, Spectral Feature Fitting, Spectral Angle Mapper were the techniques used. Results have revealed the ability of Hyper spectral Remote sensing data for the identification and mapping of Hydrothermal altered products like Bauxite, Aluminous Laterite. This technology can be utilized for targeting minerals in the altered zone.

Encoding Methods of Spectral Vector in Hyperspectral Romote Sensing Image

Taking into account the demands of hyperspectral remote sensing(RS) image retrieval and processing, some encoding methods of spectral vector including direct encoding, feature-based encoding and tree-based encoding methods are proposed and compared. In direct encoding, based on the analysis of binary encoding and quad-value encoding, decimal encoding is proposed. It is proved that quad-value encoding and decimal encoding are suitable to fast processing and retrieval. In absorption feature-based encoding method, five common metrics are compared. Because locations of reflection/absorption features are sensitive to noise, this method is not very effective in retrieval. In tree-based encoding methods, bitree, quadtree, octree and hextree are proposed and discussed. It is proved that 2-level octree and 2-level hextree are more effective than bitree and quadtree. Finally, quad-value encoding, decimal encoding, 2-level octree and 2-level hextree are proposed in spectral vectors encoding, similarity measure and hyperspectral RS image retrieval.

Simulate New Near Equatorial Satellite System by a Novel Multi-Fields and Purposes Remote Sensing Goniometer

Researchers in the remote sensing field use different types of images from satellite systems and simulator devices, such as goniometers. However, no device can simulate the new generation of optical satellite system called near-equatorial satellite system to perform different kinds of remote sensing applications in equatorial regions. This study proposed a newly invented laboratory and fieldwork goniometer designed to simulate and capture intensity variation and measure the bidirectional spectral reflectance of earth surface. The proposed goniometer is a multi-purpose and multi-field device. It is able to simulate different satellite systems and measure the intensity variation and spectral reflectance of earth’s surface features with freely azimuth and zenith angles of sensors and illumination source in fieldwork and/or laboratory. However, the system of invention is focusing on specific satellite orbital to work with the parameters and properties of NEqO satellite system in order to obtain NEqO system imagery for performing different applications such as geometric correction, relative radiometric normalization and change detection for future work. The significant of this invention is that most of the invented goniometers of remote sensing are able to work just in field or just in laboratory and use, carry just optical sensor or hyperspectral sensor. Specifically, our invention can do all these functions that are not available in existing goniometers. The proposed device offers several advantages, namely, high measurement speed, flexibility, low cost, efficiency, and possible measurement depending on the free zenith/azimuth angles of sensors and illumination sources. The proposed goniometer includes ten parts, and two different sensors (optical and hyperspectral).

Remote Sensing Estimation of Crop Lead Pollution Stress Degree Using Wavelet Analysis

Accurate estimation of soil lead pollution degree is one of the key steps in controlling soil lead pollution; vegetable hyperspectral features research provided a new approach to discovering and monitoring soil heavy metal pollution.Spectral reflectance implies information of pollution impacts on vegetation;estimation of lead pollution degree based on the spectral reflectance is equivalent to extraction of weak information.This study puts forward a new feature extraction method based

Hyperspectral Inversion and Analysis of Zinc Concentration in Urban Soil in the Urumqi City of China

Excessive accumulation of zinc(Zn)in urban soil can lead to environmental pollution and pose a potential threat to human health and the ecosystem.How to quickly and accurately monitor the urban soil zinc content on a large scale in real time and dynamically is crucial.Hyperspectral remote sensing technology provides a new method for rapid and nondestructive soil property detection.The main goal of this study is to find an optimal combination of spectral transformation and a hyperspectral estimation model to predict the Zn content in urban soil.A total of 88 soil samples were collected to obtain the Zn contents and related hyperspectral data,and perform 18 transformations on the original spectral data.Then,select important wavelengths by Pearson’s correlation coefficient analysis(PCC)and CARS.Finally,establish a partial least squares regression model(PLSR)and random forest regression model(RFR)with soil Zn content and important wavelengths.The results indicated that the average Zn content of the collected soil samples is 60.88 mg/kg.Pearson’s correlation coefficient analysis(PCC)and CARS for the original and transformed wavelengths can effectively improve the correlations between the spectral data and soil Zn content.The number of important wavelengths selected by CARS is less than the important wavelengths selected by PCC.Partial least squares regression model based on first-order differentiation of the reciprocal by CARS(CARS-RTFD-PLSR)is more stable 2 and has the highest prediction ability(R=0.937,RMSE=8.914,MAE=2.735,RPD=3.985).The CARS-RTFD-PLSR method can be used as a means of prediction of Zn content in soil in oasis cities.The results of the study can provide technical support for the hyperspectral estimation of the soil Zn content.

基于HRS和GIS的城市污染场地动态监测原理分析

选择有代表性的城市场地,运用网格法土壤采样,并通过实验室化学分析得出土壤的重金属等污染物质含量,运用地物光谱仪在实验室设定条件下测定土壤反射光谱,应用偏最小二乘法(PLS)建立高光谱遥感(HRS)影像定量反演模型,预测场地土壤中各种污染物的含量,并在遥感影像中直观表示。结果表明,HRS技术能提供大量、连续性的光谱信息;PLS模型为大尺度城市场地污染快速评价与监测提供了可能性;并通过结合G IS技术可实现城市污染场地的动态监测,为城市公共管理提供决策支持。

Comparison of three models for winter wheat yield prediction based on UAV hyperspectral images

Predicting crop yield timely can considerably accelerate agricultural production management and food policy-making,which are also important requirements for precise agricultural development.Given the development of hyperspectral imaging technology,a simple and efficient modeling method is convenient for predicting crop yield by using airborne hyperspectral images.In this study,the Unmanned Aerial Vehicle(UAV)hyperspectral and maturity yield data in 2014-2015 and 2017-2018 were collected.The winter wheat yield prediction model was established by optimizing Vegetation Indices(VIs)feature scales and sample scales,incorporating Partial Least Squares Regression(PLSR),Random Forest algorithm(RF),and Back Propagation Neural Network algorithm(BPN).Results showed that PLSR stands out as the optimal wheat yield prediction model considering stability and accuracy(RMSE=948.88 kg/hm2).Contrary to the belief that more input features result in higher accuracy,PLSR,RF,and BPN models performed best when trained with the top 3,8,and 4 VIs with the highest correlation,respectively.With an increase in training samples,model accuracy improves,reaching stability when the training samples reach 70.Using PLSR and optimal feature scales,UAV yield prediction maps were generated,holding significant value for field management in precision agriculture.