Regional-scale boreal forest cover and change mapping using Landsat data composites for European Russia

Boreal forests are a critical component of the global carbon cycle, and timely monitoring allows for assessing forest cover change and its impacts on carbon dynamics. Earth observation data sets are an important source of information that allow for systematic monitoring of the entire biome. Landsat imagery, provided free of charge by the USGS Center for Earth Resources Observation and Science (EROS) enable consistent and timely forest cover updates. However, irregular image acquisition within parts of the boreal biome coupled with an absence of atmospherically corrected data hamper regional-scale monitoring efforts using Landsat imagery. A method of boreal forest cover and change mapping using Landsat imagery has been developed and tested within European Russia between circa year 2000 and 2005. The approach employs a multi-year compositing methodology adapted for incomplete annual data availability, within-region variation in growing season length and frequent cloud cover. Relative radiometric normalization and cloud/shadow data screening algorithms were employed to create seamless image composites with remaining cloud/shadow contamination of less than 0.5% of the total composite area. Supervised classification tree algorithms were applied to the time-sequential image composites to characterize forest cover and gross forest loss over the study period. Forest cover results when compared to independently-derived samples of Landsat data have high agreement (overall accuracy of 89%, Kappa of 0.78), and conform with official forest cover statistics of the Russian government. Gross forest cover loss regional-scale mapping results are comparable with individual Landsat image pair change detection (overall accuracy of 98%, Kappa of 0.71). The gross forest cover loss within European Russia 2000-2005 is estimated to be 2210 thousand hectares, and constitutes a 1.5% reduction of year 2000 forest cover. At the regional scale, the highest proportional forest cover loss is estimated for the most populated regions (Leningradskaya and Moskovskaya Oblast). Our results highlight the forest cover depletion around large industrial cities as the hotspot of forest cover change in European Russia.     

Spatial, spectral and temporal patterns of tropical forest cover change as observed with multiple scales of optical satellite data

This article describes the development of a methodology for scaling observations of changes in tropical forest cover to large areas at high temporal frequency from coarse resolution satellite imagery. The approach for estimating proportional forest cover change as a continuous variable is based on a regression model that relates multispectral, multitemporal MODIS data, transformed to optimize the spectral detection of vegetation changes, to reference change data sets derived from a Landsat data record for a study site in Central America. A number of issues involved in model development are addressed here by exploring the spatial, spectral and temporal patterns of forest cover change as manifested in a time-series of multi-scale satellite imagery.The analyses highlighted the distinct spectral change patterns from year-to-year in response to the possible land cover trajectories of forest clearing, regeneration and changes in climatic and land cover conditions. Spectral response in the MODIS Calibrated Radiances Swath data set followed more closely with the expected patterns of forest cover change than did the spectral response in the Gridded Surface Reflectance product. With forest cover change patterns relatively invariant to the spatial grain size of the analysis, the model results indicate that the best spectral metrics for detecting tropical forest clearing and regeneration are those that incorporate shortwave infrared information from the MODIS calibrated radiances data set at 500-m resolution, with errors ranging from 7.4 to 10.9% across the time periods of analysis.     

Time–space radiometric normalization of TM/ETM+ images for land cover change detection

A novel approach to image radiometric normalization for change detection is presented. The approach referred to as stratified relative radiometric normalization (SRRN) uses a time-series of imagery to stratify the landscape for localized radiometric normalization. The goal is to improve the detection accuracy of abrupt land cover changes (human-induced, natural disaster, etc.) while decreasing false detection of natural vegetation changes that are not of interest. These vegetation changes may be associated with such phenomena as phenology, growth and stress (e.g. drought), which occur at varying spatial and temporal scales, depending on landscape position, vegetation type, season, precipitation history and historic episodes of local disturbance. The SRRN approach was tested for a study area on the Californian border between the USA and Mexico using Landsat Thematic Mapper and Enhanced Thematic Mapper Plus satellite imagery. Change products were generated from imagery radiometrically normalized using the SRRN procedure and with imagery normalized using a traditional empirical line technique. Reference data derived from high spatial resolution airborne imagery were utilized to validate the two change products. The SRRN procedure provided several benefits and was found to improve the overall accuracy of detecting abrupt land cover changes by nearly 20%.     

A comparison of local variance,fractal dimension,and Moran's I as aids to multispectral image classification

The accuracy of traditional multispectral maximum‐likelihood image classification is limited by the multi‐modal statistical distributions of digital numbers from the complex, heterogenous mixture of land cover types in urban areas. This work examines the utility of local variance, fractal dimension and Moran's I index of spatial autocorrelation in segmenting multispectral satellite imagery with the goal of improving urban land cover classification accuracy. Tools available in the ERDAS Imagine^TM software package and the Image Characterization and Modeling System (ICAMS) were used to analyse Landsat ETM?+ imagery of Atlanta, Georgia. Images were created from the ETM?+ panchromatic band using the three texture indices. These texture images were added to the stack of multispectral bands and classified using a supervised, maximum likelihood technique. Although each texture band improved the classification accuracy over a multispectral only effort, the addition of fractal dimension measures is particularly effective at resolving land cover classes within urbanized areas, as compared to per‐pixel spectral classification techniques.     

基于多时相协同变化检测的耕地撂荒遥感监测

针对地表覆被复杂、地块破碎等原因导致的撂荒地提取精度较低问题,提出一种基于多时相协同变化检测的耕地撂荒信息提取方法。以河北省石家庄市鹿泉区为研究区,采用Sentinel-2A和Landsat 7多光谱影像,在野外样本的支持下,分析耕地各种覆盖类型的归一化植被指数（Normalized Difference Vegetation Index,NDVI）季相变化规律,以季节性撂荒、常年性撂荒、冬小麦、多年生园地为分类体系,构建多时相协同变化检测模型,开展研究区耕地撂荒状态遥感监测。研究结果表明：基于Sentinel-2A影像的季节性撂荒和常年撂荒耕地的分类精度分别为95.83%和96.55%;基于Landsat 7影像的季节性撂荒和常年撂荒耕地的分类精度分别为91.67%和93.10%;2019年鹿泉区季节性撂荒占耕地面积的4.7%,常年撂荒耕地占7.1%。利用该方法能够快速、准确地获取研究区耕地空间分布、面积等信息,对于不同分辨率的影像均具有较好的撂荒地提取精度。     

Discriminating native and plantation forests in a Landsat time-series for land use policy design

The Warren River Catchment of south-western Australia is an area of high biodiversity threatened by the loss of native vegetation and dryland salinity. Over the last 20 years, it has been the target of a series of policies that encourage conversion of agricultural land to plantation forest. Remote sensing has a key role in measuring trends in the area of plantation forest observed across the landscape and hence the effectiveness of policy initiatives. Despite its importance to land use policy, accurate data on historical land use and land cover (LULC) dynamics of two spectrally similar but ecologically distinct forest types – such as native forest and plantation forest – are not readily available for south-western Australia, largely due to prohibitive data delivery costs. However, we argue that regular low-cost monitoring of long-term change in the spatial distribution of plantation forest through remote sensing is a critical input into environmental policy for the catchment. To this end, a 35-year time-series of Landsat imagery was acquired, and three different classifiers were tested (Support Vector Machines – SVM; Random Forests – RF; and Classification and Regression Trees – CART) on spectral and textural indices applied to four spectral bands. The six major LULC classes considered were agriculture, water, native forest, sand dunes, plantation forest and harvested native forest. In classifying the imagery the SVM and RF outperformed the CART across all classes. However, the SVM classifier gave a slightly higher F-score for most individual classes than the RF. Eucalypt dominated plantation forest reaching full canopy cover was subject to the highest rates of misclassification inasmuch as it shares spectral properties with the Eucalypt dominant native forest. When applied to Landsat time-series imagery, SVM classifier combined with four bands held in common between the four Landsat sensors, and derived textures metrics are valuable in classifying plantation and native forest, particularly where these have a similar species composition. The differences in prediction accuracy when including additional Landsat bands were not statistically significant, as demonstrated by the McNemar test. Thus, we achieved a trade-off in reducing processing time without significantly impacting on classification accuracy (≥86%). The relatively high accuracy of the proposed method enables the effects of past policy initiatives to be observed, and hence the efficient design of environmental and conservation policy in the future.     

Urban built-up land change detection with road density and spectral information from multi-temporal Landsat TM data

In this article, Landsat TM images acquired during the same season from both 1984 and 1997 were analysed for urban built-up land change detection in Beijing, China, where great changes have taken place during the recent decades. To reduce the spectral confusion between urban 'built-up' and rural 'non built-up' land cover categories, we propose a new structural method based on road density combined with spectral bands for change detection. The road density represents one type of structural information while the multiple Landsat TM bands represent spectral information. Road density maps for both dates were produced using a gradient direction profile analysis (GDPA) algorithm and then integrated with spectral bands. Results from the spectral-structural postclassification comparison (SSPCC) and spectral-structural image differencing (SSID) methods were evaluated and compared with spectral-only change detection methods. The proposed SSPCC method greatly reduced spectral confusion and increased the accuracy of land cover classification compared with spectral classification, which in turn improved the change detection results. This article also shows that the SSID change detection result complemented spectral band differencing by detecting areas with greater structural changes, some of which were missed, by spectral band differencing.     

Detecting war‐induced abandoned agricultural land in northeast Bosnia using multispectral,multitemporal Landsat TM imagery

The use of satellite technology by military planners has a relatively long history as a tool of warfare, but little research has used satellite technology to study the effects of war. This research addresses this gap by applying satellite remote sensing imagery to study the effects of war on land‐use/land‐cover change in northeast Bosnia. Although the most severe war impacts are visible at local scales (e.g. destroyed buildings), this study focuses on impacts to agricultural land. Four change detection methods were evaluated for their effectiveness in detecting abandoned agricultural land using Landsat Thematic Mapper (TM) data from before, during and after the 1992–95 war. Ground reference data were collected in May 2006 at survey sites selected using a stratified random sampling approach based on the derived map of abandoned agricultural land. Fine‐resolution Quickbird imagery was also used to verify the accuracy of the classification. Results from these analyses show that a supervised classification of the Landsat TM data identified abandoned agricultural land with an overall accuracy of 82.5%. The careful use of freely available Quickbird imagery, both as training data for the supervised classifier and as supplementary ground reference data, suggests that these methods are applicable to other civil wars too dangerous for researchers' fieldwork.     

Mapping coffee plantations with Landsat imagery: an example from El Salvador

Considering the potential of shaded coffee plantations mixed with natural vegetation for promoting biodiversity conservation, this project assessed the utility of multi-date Landsat Thematic Mapper (TM) satellite imagery for the characterization of natural vegetation versus coffee plantations in western El Salvador. For assembling a multi-temporal Landsat TM data set, we applied a regression analysis model to remove cloud cover and cloud shadows. Then, through a hybrid classification approach, a nine-class land use/land cover (LULC) map was generated. We identified two types of coffee plantations (‘open-canopy’ and ‘close-canopy’) along with natural forest/shrubland, mangrove, water bodies, sandy coastal soils, bare soil, urban areas and agriculture. Notwithstanding the small sample size of the accuracy data, our assessment revealed an overall accuracy of 76.7% (Kappa coefficient?=?0.68), considering only the four classes with independent field data. The overall classification accuracy for distinguishing coffee plantations from non-mangrove natural forest was 81.6% and the classification accuracy for distinguishing ‘open-canopy’ from ‘close-canopy’ coffee plantations was 85.7%. We are encouraged by the results of this prototype study. They indicate that remote-sensing techniques can be used to distinguish different classes of coffee production systems and to differentiate coffee from natural forest.     

Land‐cover classification in the Brazilian Amazon with the integration of Landsat ETM+ and Radarsat data

Land‐cover classification with remotely sensed data in moist tropical regions is a challenge due to the complex biophysical conditions. This paper explores techniques to improve land‐cover classification accuracy through a comparative analysis of different combinations of spectral signatures and textures from Landsat Enhanced Thematic Mapper Plus (ETM+) and Radarsat data. A wavelet‐merging technique was used to integrate Landsat ETM+ multispectral and panchromatic data or Radarsat data. Grey‐level co‐occurrence matrix (GLCM) textures based on Landsat ETM+ panchromatic or Radarsat data and different sizes of moving windows were examined. A maximum‐likelihood classifier was used to implement image classification for different combinations. This research indicates the important role of textures in improving land‐cover classification accuracies in Amazonian environments. The incorporation of data fusion and textures increases classification accuracy by approximately 5.8–6.9% compared to Landsat ETM+ data, but data fusion of Landsat ETM+ multispectral and panchromatic data or Radarsat data cannot effectively improve land‐cover classification accuracies.     

A new Landsat 8 cloud discrimination algorithm using thresholding tests

ABSTRACT

In this work, we propose a Cloud Discrimination Algorithm for Landsat 8 (CDAL8) to improve a high-frequency automatic land change detection system developed at the National Institute of Advanced Industrial Science and Technology (AIST), Japan for large-scale satellite image analysis. Although the land change detection system can process several kinds of satellite remote sensing data, improvements are needed to enable practical applications using Landsat 8 data. Cloud discrimination is a necessary pre-processing step for land cover change detection. Currently, most of the prediction errors on land change detection are caused by the false cloud discrimination results as a pre-processing step. Therefore, we introduce an improved cloud discrimination algorithm (CDAL8) in this study to improve the overall performance of our land change detection system. The algorithm was developed based on a Moderate Resolution Imaging Spectroradiometer (MODIS) cloud mask algorithm and Cloud and Aerosol Unbiased Decision Intellectual Algorithm (CLAUDIA). CDAL8 is distinct in that it switches judgment tests and their thresholds using a threshold brightness temperature and uses separate features in cloud judgment and clear-sky judgment. To evaluate the accuracy of the proposed algorithm, we compared it with the Automated Cloud-Cover Assessment algorithm (ACCA) and Function of Mask (Fmask) version 3.3 using US Geological Survey Landsat 8 cloud cover assessment validation data, which contain 96 cloud masks. Our proposed cloud discrimination algorithm (CDAL8) have promising results with an accuracy of 88.1%, which was greater than that of the ACCA (82.5%) and Fmask (84.6%). Furthermore, we also confirmed that the average accuracy of CDAL8 was approximately 91.2% when low solar elevation scenes were removed.     

Land cover mapping of large areas using chain classification of neighboring Landsat satellite images

Satellite imagery is the major data source for regional to global land cover maps. However, land cover mapping of large areas with medium-resolution imagery is costly and often constrained by the lack of good training and validation data. Our goal was to overcome these limitations, and to test chain classifications, i.e., the classification of Landsat images based on the information in the overlapping areas of neighboring scenes. The basic idea was to classify one Landsat scene first where good ground truth data is available, and then to classify the neighboring Landsat scene using the land cover classification of the first scene in the overlap area as training data. We tested chain classification for a forest/non-forest classification in the Carpathian Mountains on one horizontal chain of six Landsat scenes, and two vertical chains of two Landsat scenes each. We collected extensive training data from Quickbird imagery for classifying radiometrically uncorrected data with Support Vector Machines (SVMs). The SVMs classified 8 scenes with overall accuracies between 92.1% and 98.9% (average of 96.3%). Accuracy loss when automatically classifying neighboring scenes with chain classification was 1.9% on average. Even a chain of six images resulted only in an accuracy loss of 5.1% for the last image compared to a reference classification from independent training data for the last image. Chain classification thus performed well, but we note that chain classification can only be applied when land cover classes are well represented in the overlap area of neighboring Landsat scenes. As long as this constraint is met though, chain classification is a powerful approach for large area land cover classifications, especially in areas of varying training data availability.     

Classification of Remote Sensing Image based on Object-oriented Method:A Case Study of Baixiang County

Remote sensing is the main means of extracting land cover types,which has important significance for monitoring land use change and developing national policies.Object-based classification methods can provide higher accuracy data than pixel-based methods by using spectral,shape and texture information.In this study,we choose GF-1 satellite’s imagery and proposed a method which can automatically calculate the optimal segmentation scale.The object-based methods for classifying four typical land cover types are compared using multi-scale segmentation and three supervised machine learning algorithms.The relationship between the accuracy of classification results and the training sample proportion is analyzed and the result shows that object-based methods can achieve higher classification results in the case of small training sample ratio,overall accuracies are higher than 94%.Overall,the classification accuracy of support vector machine is higher than that of neural network and decision tree during the process of object-oriented classification.     

Haze removal for new generation optical sensors

Haze and cloud contamination is a common problem in optical remote-sensing imagery, as it can lead to the inaccurate estimation of physical properties of the surface derived from remote sensing and reduced accuracy of land cover classification and change detection. Haze optimized transform (HOT) is a methodology applicable to radiometric compensation of additive haze effects in visible bands that exhibits a spatially complex distribution over an image. The generic approach of HOT allows for the use of older satellite imaging sensors that include at least two visible bands (e.g. Landsat Thematic Mapper (TM) and Landsat Multispectral Scanner (MSS) sensors). This study proposes modifications to extend HOT applicability to new sensors. The improvements and extended functionality adapt the method to the higher radiometric resolution specifications of newer generation sensors and use percentile-based minimum in the correction procedure to avoid causing fake minimum. Alternative filters are also evaluated to smooth raw HOT output and the cloud mask is generated as an additional output. A Landsat 8 scene of Los Angeles is used to demonstrate the improved methodology. The methodology is applicable to sensors such as QuickBird, Worldview 2/3. More than 20 additional scenes were used to evaluate the effectiveness of the methodology.     

基于多地表特征参数的遥感影像分类研究

地表特征是反映地表信息的重要参数,是了解地表时空多变信息的定量要素。提出基于多地表特征参数的遥感影像分类方法,并利用武汉市的Landsat ETM+影像为例进行试验。试验选择通用植被指数(VIUPD)、地表温度和纹理特征等多地表特征参数,在考虑光谱特征和空间信息的前提下,结合分层思想的决策树方法,对遥感影像进行分类。结果证明利用多地表特征参数的决策树分类方法与传统的基于光谱反射率特征的决策树分类方法和SVM分类方法相比较,分类精度有了明显的提高。     

Automated cloud and shadow detection and filling using two-date Landsat imagery in the USA

A simple, efficient, and practical approach for detecting cloud and shadow areas in satellite imagery and restoring them with clean pixel values has been developed. Cloud and shadow areas are detected using spectral information from the blue, shortwave infrared, and thermal infrared bands of Landsat Thematic Mapper or Enhanced Thematic Mapper Plus imagery from two dates (a target image and a reference image). These detected cloud and shadow areas are further refined using an integration process and a false shadow removal process according to the geometric relationship between cloud and shadow. Cloud and shadow filling is based on the concept of the Spectral Similarity Group (SSG), which uses the reference image to find similar alternative pixels in the target image to serve as replacement values for restored areas. Pixels are considered to belong to one SSG if the pixel values from Landsat bands 3, 4, and 5 in the reference image are within the same spectral ranges. This new approach was applied to five Landsat path/rows across different landscapes and seasons with various types of cloud patterns. Results show that almost all of the clouds were captured with minimal commission errors, and shadows were detected reasonably well. Among five test scenes, the lowest producer's accuracy of cloud detection was 93.9% and the lowest user's accuracy was 89%. The overall cloud and shadow detection accuracy ranged from 83.6% to 99.3%. The pixel-filling approach resulted in a new cloud-free image that appears seamless and spatially continuous despite differences in phenology between the target and reference images. Our methods offer a straightforward and robust approach for preparing images for the new 2011 National Land Cover Database production.     

Hierarchical Land Cover Classification based on MODIS NDVI Time-series

In this paper,we mainly used MODIS NDVI time-series dataset at 16-days temporal resolution and 250-meters spatial resolution to analyze land cover mapping of northeastern China.We used two different filter methods to fit NDVI time-series dataset,and compared their average classes’ separability based on Jeffries-Matusita distance index.In addition,we made use of hierarchical classification method to complete classification,combined with short-wave infrared spectral reflectance data and DEM.We conformed to the principle that separate area hierarchically into several parts first and then classify each part further,and use a single characteristic band first and then multiple feature bands.In the process of classification,we adopted threshold value method,support vector machine,artificial net neural and C5.0 decision tree classification to distinguish each land-cover type hierarchically.Finally,we evaluated the accuracy of the final classification of study area using known land-cover classification data and high-resolution remote sensing imagery,overall accuracy is 84.61%,Kappa coefficient is 0.8262.     

Object‐based land‐cover classification for the Phoenix metropolitan area: optimization vs. transportability

An object‐based approach was utilized in the development of two urban land‐cover classification schemes on high‐resolution (0.6 m), true‐colour aerial photography of the Phoenix metropolitan area, USA. An initial classification scheme was heavily weighted by standard nearest‐neighbour (SNN) functions generated by samples from each of the classes, which produced an enhanced accuracy (84%). A second classification was developed from the initial classification scheme in which SNN functions were transformed into a fuzzy‐rule set, creating a product transportable to different areas of the same imagery, or for land‐cover change detection with similar imagery. A comprehensive accuracy assessment revealed a slightly lower overall accuracy (79%) for the rule‐based classification. We conclude that the transportable classification scheme is satisfactory for general land‐cover analyses; yet classification accuracy can be enhanced at site‐specific venues with the incorporation of nearest‐neighbour functions using class samples.     

Cloud cover in Landsat observations of the Brazilian Amazon

High spatial resolution Landsat imagery is employed in efforts to understand the impact of human activities on ecological, biogeochemical and atmospheric processes in the Amazon basin. The utility of Landsat multi-spectral data depends both on the degree to which surface properties can be estimated from the radiometric measurements and on the ability to observe the surface through the atmosphere. Clouds are a major obstacle to optical remote sensing of humid tropical regions, therefore cloud cover probability analysis is a fundamental prerequisite to land-cover change and Earth system process studies in these regions. This paper reports the results of a spatially explicit analysis of cloud cover in the Landsat archive of Brazilian Amazonia from 1984 to 1997. Monthly observations of any part of the basin are highly improbable using Landsat-like optical imagers. Annual observations are possible for most of the basin, but are improbable in northern parts of the region. These results quantify the limitations imposed by cloud cover to current Amazon land-cover change assessments using Landsat data. They emphasize the need for improved radar and alternative optical data fusion techniques to provide time-series analyses of biogeophysical properties for regional modelling efforts.     

Land cover mapping in a tropical hillsides environment: A case study in the Cauca region of Colombia

Results are presented from a study of land cover mapping undertaken in a tropical hillsides environment. The study area is located in the foothills of the Cordillera Central of Colombia, where a conventional maximum likelihood classification was performed upon Landsat TM imagery. A comprehensive accuracy assessment procedure performed on the resultant land cover map suggested that relatively low rates of classification accuracy were achieved. However, reported accuracy levels were found to vary substantially, depending on the specific methodology used to generate them. This suggests that caution is needed when making comparisons between classification accuracy figures reported by different workers, unless their methodologies are also clearly identified. It is further argued that a low accuracy land cover map still makes a valuable contribution to our knowledge of this hitherto little studied environment, provided that its limitations are understood and respected.