Integrating TM and Ancillary Geographical Data with Classification Trees for Land Cover Classification of Marsh Area

The main objective of this research is to determine the capacity of land cover classification combining spec- tral and textural features of Landsat TM imagery with ancillary geographical data in wetlands of the Sanjiang Plain, Heilongjiang Province, China. Semi-variograms and Z-test value were calculated to assess the separability of grey-level co-occurrence texture measures to maximize the difference between land cover types. The degree of spatial autocorrelation showed that window sizes of 3×3 pixels and 11×11 pixels were most appropriate for Landsat TM im- age texture calculations. The texture analysis showed that co-occurrence entropy, dissimilarity, and variance texture measures, derived from the Landsat TM spectrum bands and vegetation indices provided the most significant statistical differentiation between land cover types. Subsequently, a Classification and Regression Tree (CART) algorithm was applied to three different combinations of predictors: 1) TM imagery alone (TM-only); 2) TM imagery plus image texture (TM+TXT model); and 3) all predictors including TM imagery, image texture and additional ancillary GIS in- formation (TM+TXT+GIS model). Compared with traditional Maximum Likelihood Classification (MLC) supervised classification, three classification trees predictive models reduced the overall error rate significantly. Image texture measures and ancillary geographical variables depressed the speckle noise effectively and reduced classification error rate of marsh obviously. For classification trees model making use of all available predictors, omission error rate was 12.90% and commission error rate was 10.99% for marsh. The developed method is portable, relatively easy to im- plement and should be applicable in other settings and over larger extents.

Effects of RapidEye Imagery's Red-edge Band and Vegetation Indices on Land Cover Classification in an Arid Region

Land cover classification(LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidE ye images was effective for vegetation identification and could improve LCC accuracy. However, there has been no investigation of the effects of RapidE ye images' red-edge band and vegetation indices on LCC in arid regions where there are spectrally similar land covers mixed with very high or low vegetation coverage information and bare land. This study focused on a typical inland arid desert region located in Dunhuang Basin of northwestern China. First, five feature sets including or excluding the red-edge band and vegetation indices were constructed. Then, a land cover classification system involving plant communities was developed. Finally, random forest algorithm-based models with different feature sets were utilized for LCC. The conclusions drawn were as follows: 1) the red-edge band showed slight contribution to LCC accuracy; 2) vegetation indices had a significant positive effect on LCC; 3) simultaneous addition of the red-edge band and vegetation indices achieved a significant overall accuracy improvement(3.46% from 86.67%). In general, vegetation indices had larger effect than the red-edge band, and simultaneous addition of them significantly increased the accuracy of LCC in arid regions.

Land Cover Classification with Multi-source Data Using Evidential Reasoning Approach

Land cover classification is the core of converting satellite imagery to available geographic data.However,spectral signatures do not always provide enough information in classification decisions.Thus,the application of multi-source data becomes necessary.This paper presents an evidential reasoning (ER) approach to incorporate Landsat TM imagery,altitude and slope data.Results show that multi-source data contribute to the classification accuracy achieved by the ER method,whereas play a negative role to that derived by maximum likelihood classifier (MLC).In comparison to the results derived based on TM imagery alone,the overall accuracy rate of the ER method increases by 7.66% and that of the MLC method decreases by 8.35% when all data sources (TM plus altitude and slope) are accessible.The ER method is regarded as a better approach for multi-source image classification.In addition,the method produces not only an accurate classification result,but also the uncertainty which presents the inherent difficulty in classification decisions.The uncertainty associated to the ER classification image is evaluated and proved to be useful for improved classification accuracy.

Land cover classification in a mixed forest-grassland ecosystem using LResU-net and UAV imagery

Using an unmanned aerial vehicle (UAV) paired with image semantic segmentation to classify land cover within natural vegetation can promote the development of forest and grassland field. Semantic segmentation normally excels in medical and building classification, but its usefulness in mixed forest-grassland ecosystems in semi-arid to semi-humid climates is unknown. This study proposes a new semantic segmentation network of LResU-net in which residual convolution unit (RCU) and loop convolution unit (LCU) are added to the U-net framework to classify images of different land covers generated by UAV high resolution. The selected model enhanced classification accuracy by increasing gradient mapping via RCU and modifying the size of convolution layers via LCU as well as reducing convolution kernels. To achieve this objective, a group of orthophotos were taken at an altitude of 260 m for testing in a natural forest-grassland ecosystem of Keyouqianqi, Inner Mongolia, China, and compared the results with those of three other network models (U-net, ResU-net and LU-net). The results show that both the highest kappa coefficient (0.86) and the highest overall accuracy (93.7%) resulted from LResU-net, and the value of most land covers provided by the producer’s and user’s accuracy generated in LResU-net exceeded 0.85. The pixel-area ratio approach was used to calculate the real areas of 10 different land covers where grasslands were 67.3%. The analysis of the effect of RCU and LCU on the model training performance indicates that the time of each epoch was shortened from U-net (358 s) to LResU-net (282 s). In addition, in order to classify areas that are not distinguishable, unclassified areas were defined and their impact on classification. LResU-net generated significantly more accurate results than the other three models and was regarded as the most appropriate approach to classify land cover in mixed forest-grassland ecosystems.

Fully Polarimetric Land Cover Classification Based on Markov Chains

A novel land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) is employed to characterize land cover pixel by pixel. Cameron’s CTD is employed since it provides a complete set of elementary scattering mechanisms to describe the physical properties of the scatterer. The novelty of the proposed land classification approach lies on the fact that the features used for classification are not the types of the elementary scatterers themselves, but the way these types of scatterers alternate from pixel to pixel on the SAR image. Thus, transition matrices that represent local Markov models are used as classification features for land cover classification. The classification rule employs only the most important transitions for decision making. The Frobenius inner product is employed as similarity measure. Ten different types of land cover are used for testing the proposed method. In this aspect, the classification performance is significantly high.

Integration of SAR Polarimetric Features and Multi-spectral Data for Object-Based Land Cover Classification

An object-based approach is proposed for land cover classification using optimal polarimetric parameters.The ability to identify targets is effectively enhanced by the integration of SAR and optical images.The innovation of the presented method can be summarized in the following two main points:①estimating polarimetric parameters(H-A-Alpha decomposition)through the optical image as a driver;②a multi-resolution segmentation based on the optical image only is deployed to refine classification results.The proposed method is verified by using Sentinel-1/2 datasets over the Bakersfield area,California.The results are compared against those from pixel-based SVM classification using the ground truth from the National Land Cover Database(NLCD).A detailed accuracy assessment complied with seven classes shows that the proposed method outperforms the conventional approach by around 10%,with an overall accuracy of 92.6%over regions with rich texture.

Improving the Interpretability and Reliability of Regional Land Cover Classification by U-Net Using Remote Sensing Data

The accurate and reliable interpretation of regional land cover data is very important for natural resource monitoring and environmental assessment.At present,refined land cover data are mainly obtained by manual visual interpretation,which has the problems of heavy workload and inconsistent interpretation scales.Deep learning has greatly improved the automatic processing and analysis of remote sensing data.However,the accurate interpretation of feature information from massive datasets remains a difficult problem in wide regional land cover classification.To improve the efficiency of deep learning-based remote sensing image interpretation,we selected multisource remote sensing data,assessed the interpretability of the U-Net model based on surface spatial scenes with different levels of complexity,and proposed a new method of stereoscopic accuracy verification(SAV)to evaluate the reliability of the classification result.The results show that classification accuracy is more highly correlated with terrain and landscape than with other factors related to image data,such as platform and spatial resolution.As the complexity of surface spatial scenes increases,the accuracy of the classification results mainly shows a fluctuating declining trend.We also find the distribution characteristics from the SAV evaluation results of different land cover types in each surface spatial scene.Based on the results observed in this study,we consider the distinction of interpretability and reliability in diverse ground object types and design targeted classification strategies for different surface scenes,which can greatly improve the classification efficiency.The key achievement of this study is to provide the theoretical basis for remote sensing information analysis and an accuracy evaluation method for regional land cover classification,and the proposed method can help improve the likelihood that intelligent interpretation can replace manual acquisition.

Diversity-accuracy assessment of multiple classifier systems for the land cover classification of the Khumbu region in the Himalayas

Land cover classification of mountainous environments continues to be a challenging remote sensing problem,owing to landscape complexities exhibited by the region.This study explored a multiple classifier system(MCS)approach to the classification of mountain land cover for the Khumbu region in the Himalayas using Sentinel-2 images and a cloud-based model framework.The relationship between classification accuracy and MCS diversity was investigated,and the effects of different diversification and combination methods on MCS classification performance were comparatively assessed for this environment.We present ten MCS models that implement a homogeneous ensemble approach,using the high performing Random Forest(RF)algorithm as the selected classifier.The base classifiers of each MCS model were developed using different combinations of three diversity techniques:(1)distinct training sets,(2)Mean Decrease Accuracy feature selection,and(3)‘One-vs-All’problem reduction.The base classifier predictions of each RFMCS model were combined using:(1)majority vote,(2)weighted argmax,and(3)a meta RF classifier.All MCS models reported higher classification accuracies than the benchmark classifier(overall accuracy with 95% confidence interval:87.33%±0.97%),with the highest performing model reporting an overall accuracy(±95% confidence interval)of 90.95%±0.84%.Our key findings include:(1)MCS is effective in mountainous environments prone to noise from landscape complexities,(2)problem reduction is indicated as a stronger method over feature selection in improving the diversity of the MCS,(3)although the MCS diversity and accuracy have a positive correlation,our results suggest this is a weak relationship for mountainous classifications,and(4)the selected diversity methods improve the discriminability of MCS against vegetation and forest classes in mountainous land cover classifications and exhibit a cumulative effect on MCS diversity for this context.

Simulated Annealing for Land Cover Classification in PolSAR Images

Simulated Annealing (SA) is used in this work as a global optimization technique applied in discrete search spaces in order to change the characterization of pixels in a Polarimetric Synthetic Aperture Radar (PolSAR) image which have been classified with different label than the surrounding land cover type. Accordingly, Land Cover type classification is achieved with high reliability. For this purpose, an energy function is employed which is minimized by means of SA when the false classified pixels are correctly labeled. All PolSAR pixels are initially classified using 9 specifically selected types of land cover by means of Google Earth maps. Each Land Cover Type is represented by a histogram of the 8 Cameron’s elemental scatterers by means of coherent target decomposition (CTD). Each PolSAR pixel is categorized according to the local histogram of the elemental scatterers. SA is applied in the discreet space of nine land cover types. Classification results prove that the Simulated Annealing approach used is very successful for correctly separating regions with different Land Cover Types.

Fully Polarimetric Land Cover Classification Based on Hidden Markov Models Trained with Multiple Observations

A land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) is employed to characterize each pixel, using a set of canonical scattering mechanisms in order to describe the physical properties of the scatterer. The novelty of the proposed classification approach lies on the use of Hidden Markov Models (HMM) to uniquely characterize each type of land cover. The motivation to this approach is the investigation of the alternation between scattering mechanisms from SAR pixel to pixel. Depending on the observations-scattering mechanisms and exploiting the transitions between the scattering mechanisms we decide upon the HMM-land cover type. The classification process is based on the likelihood of observation sequences been evaluated by each model. The performance of the classification approach is assessed my means of fully polarimetric SLC SAR data from the broader area of Vancouver, Canada and was found satisfactory, reaching a success from 87% to over 99%.

Assessing the Impact of Using Different Land Cover Classification in Regional Modeling Studies for the Manaus Area,Brazil

Land cover classification is one of the main components of the modern weather research and forecasting models, which can influence the meteorological variable, and in turn the concentration of air pollutants. In this study the impact of using two traditional land use classifications, the United States Geological Survey (USGS) and the Moderate-resolution Imaging Spectroradiometer (MODIS), were evaluated. The Weather Research and Forecasting model (WRF, version 3.2.1) was run for the period 18 - 22 August, 2014 (dry season) at a grid spacing of 3 km centered on the city of Manaus. The comparison between simulated and ground-based observed data revealed significant differences in the meteorological fields, for instance, the temperature. Compared to USGS, MODIS classification showed better skill in representing observed temperature for urban areas of Manaus, while the two files showed similar results for nearby areas. The analysis of the files suggests that the better quality of the simulations favorable to the MODIS file is straightly related to its better representation of urban class of land use, which is observed to be not adequately represented by USGS.

Evaluation of temporal compositing algorithms for annual land cover classification using Landsat time series data

In this paper, four widely used temporal compositing algorithms, i.e.median, maximum NDVI, medoid, and weighted scoring-basedalgorithms, were evaluated for annual land cover classification usingmonthly Landsat time series data. Four study areas located in California,Texas, Kansas, and Minnesota, USA were selected for image compositingand land cover classification. Results indicated that images compositedusing weighted scoring-based algorithms have the best spatial fidelitycompared to other three algorithms. In addition, the weighted scoringbasedalgorithms have superior classification accuracy, followed bymedian, maximum NDVI, and medoid in descending order. However, themedian algorithm has a significant advantage in computational efficiencywhich was ~70 times that of weighted scoring-based algorithms, andwith overall classification accuracy just slightly lower (~0.13% onaverage) than weighted scoring-based algorithms. Therefore, werecommended the weighted scoring-based compositing algorithms forsmall area land cover mapping, and median compositing algorithm forthe land cover mapping of large area considering the balance betweencomputational complexity and classification accuracy. The findings of thisstudy provide insights into the performance difference between variouscompositing algorithms, and have potential uses for the selection ofpixel-based image compositing technique adopted for land covermapping based on Landsat time series data.

Land use and cover change and influencing factor analysis in the Shiyang River Basin,China

Land use and cover change(LUCC)is the most direct manifestation of the interaction between anthropological activities and the natural environment on Earth's surface,with significant impacts on the environment and social economy.Rapid economic development and climate change have resulted in significant changes in land use and cover.The Shiyang River Basin,located in the eastern part of the Hexi Corridor in China,has undergone significant climate change and LUCC over the past few decades.In this study,we used the random forest classification to obtain the land use and cover datasets of the Shiyang River Basin in 1991,1995,2000,2005,2010,2015,and 2020 based on Landsat images.We validated the land use and cover data in 2015 from the random forest classification results(this study),the high-resolution dataset of annual global land cover from 2000 to 2015(AGLC-2000-2015),the global 30 m land cover classification with a fine classification system(GLC_FCS30),and the first Landsat-derived annual China Land Cover Dataset(CLCD)against ground-truth classification results to evaluate the accuracy of the classification results in this study.Furthermore,we explored and compared the spatiotemporal patterns of LUCC in the upper,middle,and lower reaches of the Shiyang River Basin over the past 30 years,and employed the random forest importance ranking method to analyze the influencing factors of LUCC based on natural(evapotranspiration,precipitation,temperature,and surface soil moisture)and anthropogenic(nighttime light,gross domestic product(GDP),and population)factors.The results indicated that the random forest classification results for land use and cover in the Shiyang River Basin in 2015 outperformed the AGLC-2000-2015,GLC_FCS30,and CLCD datasets in both overall and partial validations.Moreover,the classification results in this study exhibited a high level of agreement with the ground truth features.From 1991 to 2020,the area of bare land exhibited a decreasing trend,with changes primarily occurring in the middle and lower reaches of the basin.The area of grassland initially decreased and then increased,with changes occurring mainly in the upper and middle reaches of the basin.In contrast,the area of cropland initially increased and then decreased,with changes occurring in the middle and lower reaches.The LUCC was influenced by both natural and anthropogenic factors.Climatic factors and population contributed significantly to LUCC,and the importance values of evapotranspiration,precipitation,temperature,and population were 22.12%,32.41%,21.89%,and 19.65%,respectively.Moreover,policy interventions also played an important role.Land use and cover in the Shiyang River Basin exhibited fluctuating changes over the past 30 years,with the ecological environment improving in the last 10 years.This suggests that governance efforts in the study area have had some effects,and the government can continue to move in this direction in the future.The findings can provide crucial insights for related research and regional sustainable development in the Shiyang River Basin and other similar arid and semi-arid areas.

Land cover classification from remote sensing images based on multi-scale fully convolutional network

Although the Convolutional Neural Network(CNN)has shown great potential for land cover classification,the frequently used single-scale convolution kernel limits the scope of informa-tion extraction.Therefore,we propose a Multi-Scale Fully Convolutional Network(MSFCN)with a multi-scale convolutional kernel as well as a Channel Attention Block(CAB)and a Global Pooling Module(GPM)in this paper to exploit discriminative representations from two-dimensional(2D)satellite images.Meanwhile,to explore the ability of the proposed MSFCN for spatio-temporal images,we expand our MSFCN to three-dimension using three-dimensional(3D)CNN,capable of harnessing each land cover category’s time series interac-tion from the reshaped spatio-temporal remote sensing images.To verify the effectiveness of the proposed MSFCN,we conduct experiments on two spatial datasets and two spatio-temporal datasets.The proposed MSFCN achieves 60.366%on the WHDLD dataset and 75.127%on the GID dataset in terms of mIoU index while the figures for two spatio-temporal datasets are 87.753%and 77.156%.Extensive comparative experiments and abla-tion studies demonstrate the effectiveness of the proposed MSFCN.

Land cover classification of remote sensing imagery based on interval-valued data fuzzy c-means algorithm

There is a certain degree of ambiguity associated with remote sensing as a means of performing earth observations.Using interval-valued data to describe clustering prototype features may be more suitable for handling the fuzzy nature of remote sensing data,which is caused by the uncertainty and heterogeneity in the surface spectral reflectance of ground objects.After constructing a multi-spectral interval-valued model of source data and defining a distance measure to achieve the maximum dissimilarity between intervals,an interval-valued fuzzy c-means(FCM)clustering algorithm that considers both the functional characteristics of fuzzy clustering algorithms and the interregional features of ground object spectral reflectance was applied in this study.Such a process can significantly improve the clustering effect;specifically,the process can reduce the synonym spectrum phenomenon and the misclassification caused by the overlap of spectral features between classes of clustering results.Clustering analysis experiments aimed at land cover classification using remote sensing imagery from the SPOT-5 satellite sensor for the Pearl River Delta region,China,and the TM sensor for Yushu,Qinghai,China,were conducted,as well as experiments involving the conventional FCM algorithm,the results of which were used for comparative analysis.Next,a supervised classification method was used to validate the clustering results.The final results indicate that the proposed interval-valued FCM clustering is more effective than the conventional FCM clustering method for land cover classification using multi-spectral remote sensing imagery.

Multiscale Fusion Transformer Network for Hyperspectral Image Classification

Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.

Characterization of land cover types in Xilin River Basin using multi-temporal Landsat images

This study conducted computer-aided image analysis of land use and land cover in Xilin River Basin, Inner Mongolia, using 4 sets of Landsat TM/ETM+ images acquired on July 31, 1987, August 11, 1991, September 27, 1997 and May 23, 2000, respectively. Primarily, 17 sub-class land cover types were recognized, including nine grassland types at community level: F.sibiricum steppe, S.baicalensis steppe, A.chinensis+ forbs steppe, A.chinensis+ bunchgrass steppe, A.chinensis+ Ar.frigida steppe, S.grandis+ A.chinensis steppe, S.grandis+ bunchgrass steppe, S.krylavii steppe, Ar.frigida steppe and eight non-grassland types: active cropland, harvested cropland, urban area, wetland, desertified land, saline and alkaline land, cloud, water body + cloud shadow. To eliminate the classification error existing among different sub-types of the same gross type, the 17 sub-class land cover types were grouped into five gross types: meadow grassland, temperate grassland, desert grassland, cropland and non-grassland. The overall classification accuracy of the five land cover types was 81.0% for 1987, 81.7% for 1991, 80.1% for 1997 and 78.2% for 2000.

Developing an Automated Land Cover Classifier Using LiDAR and High Resolution Aerial Imagery

The aim of this project is to create high resolution land cover classification as well as tree canopy density maps at a regional level using high resolution spatial data. Modeling and the data manipulation and analysis of LiDAR LAS point cloud dataset as well as multispectral aerial photographs from the National Agriculture Imagery Program (NAIP) were carried out. Using geoprocessing modeling, a land cover map is created based on filtered returns from LiDAR point cloud data (LAS dataset) to extract features based on their class and return values, and traditional classification methods of high resolution multi-spectral aerial photographs of the remaining ground cover for Clarion County in Pennsylvania. The newly developed model produced 7 classes at 10 ft × 10 ft spatial resolution, namely: water bodies, structures, streets and paved surfaces, bare ground, grassland, trees, and artificial surfaces (e.g. turf). The model was tested against areas with different sizes (townships and municipalities) which revealed a classification accuracy between 94% and 96%. A visual observation of the results shows that some tree-covered areas were misclassified as built up/structures due to the nature of the available LiDAR data, an area of improvement for further studies. Furthermore, a geoprocessing service was created in order to disseminate the results of the land cover classification as well as the tree canopy density calculation to a broader audience. The service was tested and delivered in the form of a web application where users can select an area of interest and the model produces the land cover and/or the tree canopy density results (http://maps.clarion.edu/LandCoverExtractor). The produced output can be printed as a final map layout with the highlighted area of interest and its corresponding legend. The interface also allows the download of the results of an area of interest for further investigation and/or analysis.

Supervised polarimetric SAR classification method based on Fisher linear discriminant

A supervised polarimetric SAR land cover classification method was proposed based on the Fisher linear discriminant. The feature parameters used in this classification method could be se- lected flexibly according to land covers to be classified. Polarimetric and texture feature parameters extracted from co-registered multifrequency and multi-temporal polarimetric SAR data could be com- bined together for classification use, without consideration of the dimension difference of each fea- ture parameter and the joint probability density function of those parameters. Experimental result with AGRSAR L/C-band full polarimetric SAR data showed that a total classification accuracy of 94. 33% was achieved by combining the polarimetric with texture feature parameters extracted from L/C dual band SAR data, demonstrating the effectiveness of this method.

Integration of remote sensing and GIS in monitoring the dynamics of land cover in Oroba-Kibos catchment area,Kenya

Land cover in Kenya is in a state of flux at different spatial and temporal scales.This compromises environmental integrity and socioeconomic stability of the population hence increasing their vulnerability to the externalities of environmental change.The Oroba-Kibos catchment area in western Kenya is one locality where rapid land use changes have taken place over the last 30 years.The shrubs,swamps,natural forests and other critical ecosystems have been converted on the altar of agriculture,human settlement,fuel wood and timber.This paper presents the results of a study that aimed at providing spatially-explicit information for effective remedial response through(a) Mapping the land cover;(b) Identifying the spatial distribution of land cover changes;(c) Determining the nature,rates and magnitude of the land cover changes,and;(d) Establishing the drivers of land use leading to land cover changes in Oroba-Kibos catchment area.Bi-temporal Landsat TM imagery,field observation,household survey and ancillary data were obtained.Per-field classification of the Landsat TM imagery was performed in a GIS and the resultant land cover maps assessed using the field observation data.Post-classification comparison of the maps was then done to detect changes in land cover that had occurred between 1994 and 2008.SPSS was used to analyze the household survey data and attribute the detected land cover changes to their causes.The findings showed that 9 broad classes characterize the catchment area including the natural forests,swamps,natural water bodies,woodlands,shrublands,built-up lands,grasslands,bare lands and croplands.Croplands are dominant and accounted for about 65%(57122 ha) of the total land in 1994,which increased at the rate of 0.89% to 73%(64772 ha) in 2008,while natural water bodies has the least spatial coverage accounting for about 0.6%(561 ha) of the total land in 1994,which diminished at the rate of 3.57% to 0.3%(260 ha) in 2008.Climate,altitude,access and rights to land,demographic changes,poverty,political governance,market availability and economic returns are the interacting mix of proximate and underlying factors that drive the land cover changes in Oroba-Kibos catchment area.