基于随机森林的土地利用分类与景观格局分析

基于景观格局分析方法,分别选取8个反映景观格局类型和6个反映景观水平格局指数用于探索土地利用变化状况.实验结果表明:①基于选择合适的训练样本下,对3期遥感影像采用随机森林的监督分类方法,总体精度均在94％以上,kappa系数均为90％以上;②综合来看,研究期内建设用地为优势景观类型.研究区斑块数量增加,破碎化程度有所加...     

Time-Series Analysis of Land Cover Using Landscape Metrics

Time series of thematic land-cover maps are used to measure changes in land cover over time. However, pixel-to-pixel comparisons of such maps are often not advisable when these maps are generated from different sources (i.e., satellite data, aerial photography, or historical land survey data). The purpose of this study was to examine the historical changes in land cover from 1827 to 1999 using landscape metrics calculated on maps created from different sources. Regression and power law analyses were conducted to identify significant trends and threshold effects associated with land-cover change at Fort Benning, Georgia. Results indicated that since 1827 the landscape has become more fragmented with the introduction of farming, military training, and forest management practices.     

Primitives as building blocks for constructing land cover maps

Land cover maps play an integral role in environmental management. However, countries and institutes encounter many challenges with producing timely, efficient, and temporally harmonized updates to their land cover maps. To address these issues we present a modular Regional Land Cover Monitoring System (RLCMS) architecture that is easily customized to create land cover products using primitive map layers. Primitive map layers are a suite of biophysical and end member maps, with land cover primitives representing the raw information needed to make decisions in a dichotomous key for land cover classification. We present best practices to create and assemble primitives from optical satellite using computing technologies, decision tree logic and Monte Carlo simulations to integrate their uncertainties. The concept is presented in the context of a regional land cover map based on a shared regional typology with 18 land cover classes agreed on by stakeholders from Cambodia, Laos PDR, Myanmar, Thailand, and Vietnam. We created annual map and uncertainty layers for the period 2000–2017. We found an overall accuracy of 94% when taking uncertainties into account. RLCMS produces consistent time series products using free long term historical Landsat and MODIS data. The customizable architecture can include a variety of sensors and machine learning algorithms to create primitives and the best suited smoothing can be applied on a primitive level. The system is transferable to all regions around the globe because of its use of publicly available global data (Landsat and MODIS) and easily adaptable architecture that allows for the incorporation of a customizable assembly logic to map different land cover typologies based on the user's landscape monitoring objectives     

Linking land cover dynamics with driving forces in mountain landscape of the Northwestern Iberian Peninsula

The mountainous areas of the northwestern Iberian Peninsula have undergone intense land abandonment. In this work, we wanted to determine if the abandonment of the rural areas was the main driver of landscape dynamics in Gerês–Xurés Transboundary Biosphere Reserve (NW Iberian Peninsula), or if other factors, such as wildfires and the land management were also directly affecting these spatio-temporal dynamics. For this purpose, we used earth observation data acquired from Landsat TM and ETM + satellite sensors, complemented by ancillary data and prior field knowledge, to evaluate the land use/land cover changes in our study region over a 10-year period (2000–2010). The images were radiometrically calibrated using a digital elevation model to avoid cast- and self-shadows and different illumination effects caused by the intense topographic variations in the study area. We applied a maximum likelihood classifier, as well as other five approaches that provided insights into the comparison of thematic maps. To describe the land cover changes we addressed the analysis from a multilevel approach in three areas with different regimes of environmental protection. The possible impact of wildfires was assessed from statistical and spatially explicit fire data. Our findings suggest that land abandonment and forestry activities are the main factors causing the changes in landscape patterns. Specifically, we found a strong decrease of the ‘meadows and crops’ and ‘sparse vegetation areas’ in favor of woodlands and scrublands. In addition, the huge impact of wildfires on the Portuguese side have generated new ‘rocky areas’, while on the Spanish side its impact does not seem to have been a decisive factor on the landscape dynamics in recent years. We conclude rural exodus of the last century, differences in land management and fire suppression policies between the two countries and the different protection schemes could partly explain the different patterns of changes recorded in these covers.     

The Palestine Exploration Fund Map (1871–1877) of the Holy Land as a Tool for Analysing Landscape Changes: the Coastal Dunes of Israel as a Case Study

Abstract

The Palestine Exploration Fund (PEF) maps (1871–1877) are highly praised for their accuracy and completeness; however, no systematic analysis of their accuracy has been done to date. To study the potential of these 1:63,360 maps for a quantitative analysis of land cover changes over a period of time, I have compared them to 20th century topographic maps. The map registration error of the PEF maps was 74.4 m using 123 control points of trigonometrical stations and a 1st order polynomial. The median RMSE of all control and test points (n = 1104) was 153.6 m. As a case study of land cover changes, the area of coastal dunes as shown on the PEF maps was compared with that shown on British Mandate 1:20,000 topo-cadastral maps from c. 1930. In five of the six areas analysed, the yearly dunes movement rate was above the estimated annual error due to data resolution (2.96 m/year). The rate of dune movement south of Acre was found to be between 3.9 and 6.3 m/year (depending on the method used for map registration) between 1874 and 1930. Care should be taken when analysing historical maps, as it cannot be assumed that their accuracy is consistent at different parts or for different features depicted on them.     

Introducing landscape accuracy metric for spatial performance evaluation of land use/land cover change models

Performance evaluation is a critical step for land use/land cover (LULC) change modelling. It can be conducted through pixel quantity and its geographical location according to majority of current approaches. It is hence important to know to what extent spatial patterns of a given landscape are properly replicated in simulated LULC maps. Therefore, a new validation metric, named as landscape accuracy metric (LAM), is introduced by inspiration from landscape ecology. Unlike pixel quantity validation metrics, model performance is measured by LAM through quantifying spatial patterns including structure, composition and configuration attributes. The functionality of LAM was studied to assess the performance of the built-up change simulation under historical, ecological and stochastic scenarios, applying Cellular Automata Markov model. LAM is a flexible measure such that modellers can apply this metric through adding or eliminating various metrics of their interest in a selective manner and under different environmental circumstances.     

Classifying historical remotely sensed imagery using a tempo-spatial feature evolution (T-SFE) model

Large and growing archives of orbital imagery of the earth’s surface collected over the past 40 years provide an important resource for documenting past and current land cover and environmental changes. However uses of these data are limited by the lack of coincident ground information with which either to establish discrete land cover classes or to assess the accuracy of their identification. Herein is proposed an easy-to-use model, the Tempo-Spatial Feature Evolution (T-SFE) model, designed to improve land cover classification using historical remotely sensed data and ground cover maps obtained at later times. This model intersects (1) a map of spectral classes (S-classes) of an initial time derived from the standard unsupervised ISODATA classifier with (2) a reference map of ground cover types (G-types) of a subsequent time to generate (3) a target map of overlaid patches of S-classes and G-types. This model employs the rules of Count Majority Evaluation, and Subtotal Area Evaluation that are formulated on the basis of spatial feature evolution over time to quantify spatial evolutions between the S-classes and G-types on the target map. This model then applies these quantities to assign G-types to S-classes to classify the historical images. The model is illustrated with the classification of grassland vegetation types for a basin in Inner Mongolia using 1985 Landsat TM data and 2004 vegetation map. The classification accuracy was assessed through two tests: a small set of ground sampling data in 1985, and an extracted vegetation map from the national vegetation cover data (NVCD) over the study area in 1988. Our results show that a 1985 image classification was achieved using this method with an overall accuracy of 80.6%. However, the classification accuracy depends on a proper calibration of several parameters used in the model.     

煤田火区特征的土地覆盖分类方法 ——以乌达煤田火区为例

土地覆盖变化是土地分析与评价和生态环境变化预测的重要科学基础, 通过精确的土地覆盖分类方法 获取高精度的土地覆盖图是研究煤田火区生态环境变化的必要手段。本文以最大似然法、光谱角度法、面向对象 分类法和基于复合分区的分层分类法进行乌达煤田火区土地覆盖分类的方法研究。研究结果表明, 基于复合分区的 分层分类方法分类精度较高, 总体分类精度为92.97%, kappa 系数为0.9155。该方法通过基于地表热辐射特征、热 异常状况、地貌类型, 以及对生态系统扰动状况等的划分, 减少了地物信息的混淆度, 即通过提     

Comparison and relative quality assessment of the GLC2000, GLOBCOVER,MODIS and ECOCLIMAP land cover data sets at the African continental scale

Land cover dynamics at the African continental scale is of great importance for global change studies. Actually, four satellite-derived land cover maps of Africa now available, e.g. ECOCLIMAP, GLC2000, MODIS and GLOBCOVER, are based on images acquired in the 2000s. This study aims at stressing the compliances and the discrepancies between these four land cover classifications systems. Each of them used different mapping initiatives and relies on different mapping standards, which supports the present investigation. In order to do a relative comparison of the four maps, a preamble was to reconcile their thematic legends into more aggregated categories after a projection into the same spatial resolution. Results show that the agreement between the four land cover products is between 56 and 69%. While all these land cover datasets show a reasonable agreement in terms of surface types and spatial distribution patterns, mapping of heterogeneous landscapes in the four products is not very successful. Land cover products based on remote sensing imagery can indeed significantly be improved by using smarter algorithms, better timing of image acquisition, improved class definitions. Either will help to improve the accuracy of future land cover maps at the African continental scale. Data producers may use the areas of spatial agreement for training area selection while users might need to verify the information in the areas of disagreement using additional data sources.     

Multi-temporal remote sensing data applied in automatic land cover update using iterative training sample selection and Markov Random Field model

Automatic land cover update was an effective means to obtain objective and timely land cover maps without human disturbance. This study investigated the efficacy of multi-temporal remote sensing data and advanced non-parametric classifier on improving the classification accuracy of the automatic land cover update approach integrating iterative training sample selection and Markov Random Fields model when the historical remote sensing data were unavailable. The results indicated that two-temporal remote sensing data acquired in one crop growth season could significantly improve the classification accuracy of the automatic land cover update approach by approximately 3–4%. However, the support vector machine (SVM) classifier was not suitable to be integrated in the automatic land cover update approach, because the huge initially selected training samples made the training of the SVM classifier unrealizable.     

Drivers of land cover and land use changes in St. Louis metropolitan area over the past 40 years characterized by remote sensing and census population data

In this study, we explored the spatial and temporal patterns of land cover and land use (LCLU) and population change dynamics in the St. Louis Metropolitan Statistical Area. The goal of this paper was to quantify the drivers of LCLU using long-term Landsat data from 1972 to 2010. First, we produced LCLU maps by using Landsat images from 1972, 1982, 1990, 2000, and 2010. Next, tract level population data of 1970, 1980, 1990, 2000, and 2010 were converted to 1-km square grid cells. Then, the LCLU maps were integrated with basic grid cell data to represent the proportion of each land cover category within a grid cell area. Finally, the proportional land cover maps and population census data were combined to investigate the relationship between land cover and population change based on grid cells using Pearson's correlation coefficient, ordinary least square (OLS), and local level geographically weighted regression (GWR). Land cover changes in terms of the percentage of area affected and rates of change were compared with population census data with a focus on the analysis of the spatial-temporal dynamics of urban growth patterns. The correlation coefficients of land cover categories and population changes were calculated for two decadal intervals between 1970 and 2010. Our results showed a causal relationship between LCLU changes and population dynamics over the last 40 years. Urban sprawl was positively correlated with population change. However, the relationship was not linear over space and time. Spatial heterogeneity and variations in the relationship demonstrate that urban sprawl was positively correlated with population changes in suburban area and negatively correlated in urban core and inner suburban area of the St. Louis Metropolitan Statistical Area. These results suggest that the imagery reflects processes of urban growth, inner-city decline, population migration, and social spatial inequality. The implications provide guidance for sustainable urban planning and development. We also demonstrate that grid cells allow robust synthesis of remote sensing and socioeconomic data to advance our knowledge of urban growth dynamics from both spatial and temporal scales and its association with population change.     

Monitoring Urban Landscape Dynamics Over Delhi (India) Using Remote Sensing (1998–2011) Inputs

Urbanization is increasingly becoming a widespread phenomenon at all scales of development around the globe. Be it developing or developed nations, all are witnessing urbanization at very high pace. In order to study its impacts, various methodologies and techniques are being implemented to measure growth of urban extents over spatial and temporal domains. But urbanization being a very dynamic phenomenon has been facing ambiguities regarding methods to study its dynamism. This paper aims at quantifying urban expansion in Delhi, the capital city of India. The process has been studied using urban land cover pattern derived from Landsat TM/ETM satellite data for two decades (1998–2011). These maps show that built-up increased by 417 ha in first time period (1998–2003) and 6,633 ha during next period (2003–2011) of study. For quantification of metrics for urban expansion, the Urban Landscape Analysis Tool (ULAT) was employed. Land cover mapping was done with accuracy of 92.67 %, 93.3 % and 96 % respectively for years 1998, 2003 and 2011. Three major land covers classes mapped are; (i) built-up, (ii) water and (iii) other or non-built-up. The maps were then utilized to extract degree of urbanization based on spatial density of built-up area consisting of seven classes, (i) Urban built-up, (ii) Suburban built-up,(iii) Rural built-up, (iv) Urbanized open land, (v) Captured open land, (vi) Rural open land and (vii) Water. These classes were demarcated based on the urbanness of cells. Similarly urban footprint maps were generated. The two time maps were compared to qualitatively and quantitatively capture the dynamics of urban expansion in the city. Along with urbanized area and urban footprint maps, the new development areas during the study time periods were also identified. The new development areas consisted of three major categories of developments, (i) infill, (ii) extension and (iii) leapfrog.     

Estimating the uncertainty of land-cover extrapolations while constructing a raster map from tabular data

This paper presents novel techniques to estimate the uncertainty in extrapolations of spatially-explicit land-change simulation models. We illustrate the concept by mapping a historic landscape based on: 1) tabular data concerning the quantity in each land cover category at a distant point in time at the stratum level, 2) empirical maps from more recent points in time at the grid cell level, and 3) a simulation model that extrapolates land-cover change at the grid cell level. This paper focuses on the method to show uncertainty explicitly in the map of the simulated landscape at the distant point in time. The method requires that validation of the land-cover change model be quantified at the grid-cell level by Kappa for location (Klocation). The validation statistic is used to estimate the certainty in the extrapolation to a point in time where an empirical map does not exist. As an example, we reconstruct the 1951 landscape of the Ipswich River Watershed in Massachusetts, USA. The technique creates a map of 1951 simulated forest with an overall estimated accuracy of 0.91, with an estimated users accuracy ranging from 0.95 to 0.84. We anticipate that this method will become popular, because tabular information concerning land cover at coarse stratum-level scales is abundant, while digital maps of the specific location of land cover are needed at a finer spatial resolution. The method is a key to link non-spatial models with spatially-explicit models.     

Landscape transform and spatial metrics for mapping spatiotemporal land cover dynamics using Earth Observation data-sets

Analysis of Earth observation (EO) data, often combined with geographical information systems (GIS), allows monitoring of land cover dynamics over different ecosystems, including protected or conservation sites. The aim of this study is to use contemporary technologies such as EO and GIS in synergy with fragmentation analysis, to quantify the changes in the landscape of the Rajaji National Park (RNP) during the period of 19 years (1990–2009). Several statistics such as principal component analysis (PCA) and spatial metrics are used to understand the results. PCA analysis has produced two principal components (PC) and explained 84.1% of the total variance, first component (PC1) accounted for the 57.8% of the total variance while the second component (PC2) has accounted for the 26.3% of the total variance calculated from the core area metrics, distance metrics and shape metrics. Our results suggested that notable changes happened in the RNP landscape, evidencing the requirement of taking appropriate measures to conserve this natural ecosystem.     

Estimating the starting time and identifying the type of urbanization based on dense time series of landsat-derived Vegetation-Impervious-Soil (V-I-S) maps – A case study of North Taiwan from 1990 to 2015

Land cover and land use change (LCLUC) is a global phenomenon, and LCLUC in urbanizing regions has substantial impacts on humans and their environments. In this paper, a semi-automatic approach to identifying the type and starting time of urbanization was developed and tested based on dense time series of Vegetation-Impervious-Soil (V-I-S) maps derived from Landsat surface reflectance imagery. The accuracy of modeled V-I-S fractions and the estimated time of initial change in impervious cover were assessed. North Taiwan, one of the regions of the island of Taiwan that experienced the greatest urban LCLUC, was chosen as a test area, and the study period is 1990 to 2015, a period of substantial urbanization. In total, 295 dates of Landsat imagery were used to create 295 V-I-S fraction maps that were used to construct fractional cover time series for each pixel. Root Mean Square Error (RMSE)s for the modeled Vegetation, Impervious, and Soil were 25 %, 22 %, 24 % respectively. The time of Urban Expansion is estimated by logistic regression applied to Impervious cover time series, while the time of change for Urban Renewal is determined by the period of brief Soil exposure. The identified location and estimated time for newly urbanized lands were generally accurate, with 80% of Urban Expansion estimated within ±2.4 years. However, the accuracy of identified Urban Renewal was relatively low. Our approach to identifying Urban Expansion with dense time series of Landsat imagery is shown to be reliable, while Urban Renewal identification is not.     

Forest cover monitoring using remote sensing and GIS — A case study in Dhaulkhand range of Rajaji National Park,Uttar pradesh

Rajaji National Park in U.P. is a protected area where large number of nomad population live within the park area. Their dependence on the forest for cattle rearing and firewood has caused degradation of the forests. Proximity to settlements outside the park further adds to the problems. In the present study, forest cover and river, bed changes have been attempted by using temporal aerospace data of the year 1960 and 1993. Subsequently, PAMAP GIS package has been used for the change detection analysis. The study indicates that the land cover changes are mainly due to biotic factors. Some of the important changes in forest cover are: (i) transformation of mixed forest to scrub forest in 67 ha (ii) the sal mixed and mixed sal forest categories have replaced sal forest in 262 ha (iii) significant increase in forest plantation i.e. 2075 ha in the year 1960 to 3793 ha in 1993 (iv) eighteen times increase in Chirpine area, it increased from 13 ha in 1960 to 230 ha in 1993. The land cover changes in 6663 ha (45%) out of 14962 ha of the study area. The consequential changes in the river beds due to the change in the forest cover was also analyzed. During this period river beds with boulders have increased by 87 ha. These river bed changes include lengthening and broadening of river and change in river course.     

Evaluating the Performance of Multi-Class and Single-Class Classification Approaches for Mountain Agriculture Extraction Using Time-Series NDVI

Supervised multi-class classification (MCC) approach is widely being used for regional-level land use–land cover (LULC) mapping and monitoring. However, it becomes inefficient if the end user wants to map only one particular class. Therefore, an improved single-class classification (SCC) approach is required for quick and reliable map production purpose. In this regard, the current study attempts to evaluate the performance of MCC and SCC approaches for extracting mountain agriculture area using time-series normalized differential vegetation index (NDVI). At first, samples of eight LULC classes were acquired using Google Earth image, and corresponding temporal signatures (TS) were extracted from time-series NDVI to perform classification using minimum distance to mean (MDM) and spectral angle mapper (i.e., multi-class SAM—MCSAM) under MCC approach. Secondly, under SCC approach, the TS of three agriculture classes (i.e., agriculture, mixed agriculture and plantation) were utilized as a reference to extract agriculture extent using Euclidean distance (ED) and SAM (i.e., single-class SAM—SCSAM) algorithms. The area of all four maps (i.e., MDM—19.77% of total geographical area (TGA), MCSAM—21.07% of TGA, ED—15.23% of TGA, SCSAM—13.85% of TGA) was compared with reference agriculture area (14.54% of TGA) of global land cover product, and SCC-based maps were found to have close agreement. Also, the class-wise detection accuracy was evaluated using random sample point-based error matrix which reveals the better performance of ED-based map than rest three maps in terms of overall accuracy and kappa coefficient.     

Measures of spatio-temporal accuracy for time series land cover data

Remote sensing is a useful tool for monitoring changes in land cover over time. The accuracy of such time-series analyses has hitherto only been assessed using confusion matrices. The matrix allows global measures of user, producer and overall accuracies to be generated, but lacks consideration of any spatial aspects of accuracy. It is well known that land cover errors are typically spatially auto-correlated and can have a distinct spatial distribution. As yet little work has considered the temporal dimension and investigated the persistence or errors in both geographic and temporal dimensions. Spatio-temporal errors can have a profound impact on both change detection and on environmental monitoring and modelling activities using land cover data. This study investigated methods for describing the spatio-temporal characteristics of classification accuracy. Annual thematic maps were created using a random forest classification of MODIS data over the Jakarta metropolitan areas for the period of 2001–2013. A logistic geographically weighted model was used to estimate annual spatial measures of user, producer and overall accuracies. A principal component analysis was then used to extract summaries of the multi-temporal accuracy. The results showed how the spatial distribution of user and producer accuracy varied over space and time, and overall spatial variance was confirmed by the principal component analysis. The results indicated that areas of homogeneous land cover were mapped with relatively high accuracy and low variability, and areas of mixed land cover with the opposite characteristics. A multi-temporal spatial approach to accuracy is shown to provide more informative measures of accuracy, allowing map producers and users to evaluate time series thematic maps more comprehensively than a standard confusion matrix approach. The need to identify suitable properties for a temporal kernel are discussed.     

Utility of image point cloud data towards generating enhanced multitemporal multisensor land cover maps

Multitemporal land cover classification over urban areas is challenging, especially when using heterogeneous data sources with variable quality attributes. A prominent challenge is that classes with similar spectral signatures (such as trees and grass) tend to be confused with one another. In this paper, we evaluate the efficacy of image point cloud (IPC) data combined with suitable Bayesian analysis based time-series rectification techniques to improve the classification accuracy in a multitemporal context. The proposed method uses hidden Markov models (HMMs) to rectify land covers that are initially classified by a random forest (RF) algorithm. This land cover classification method is tested using time series of remote sensing data from a heterogeneous and rapidly changing urban landscape (Kuopio city, Finland) observed from 2006 to 2014. The data consisted of aerial images (5 years), Landsat data (all 9 years) and airborne laser scanning data (1 year). The results of the study demonstrate that the addition of three-dimensional image point cloud data derived from aerial stereo images as predictor variables improved overall classification accuracy, around three percentage points. Additionally, HMM-based post processing reduces significantly the number of spurious year-to-year changes. Using a set of 240 validation points, we estimated that this step improved overall classification accuracy by around 3.0 percentage points, and up to 6 to 10 percentage points for some classes. The overall accuracy of the final product was 91% (kappa = 0.88). Our analysis shows that around 1.9% of the area around Kuopio city, representing a total area of approximately 0.61 km², experienced changes in land cover over the nine years considered.     

Monitoring of deforestation and land use changes (1925–2012) in Idukki district,Kerala, India using remote sensing and GIS

The studies on forest cover change can reveal the status of forests and facilitate for its conservation planning. Idukki is the largest district in the state of Kerala having a total geographical area of 5019 km². The objectives of the present study are to map forest cover in Idukki district using multi-temporal remote sensing data (1975, 1990, 2001 and 2012) and topographical maps (1925), to analyze the trends in deforestation and land use changes. Overall statistics for the period of 1925 indicate that about 4675.7 km² (93.2 %) of the landscape was under forest. The forest cover in 2012 was estimated as 2613.4 km² (52.1 %). Recently, due to the implementation of policies and protection efforts, the rate of deforestation was greatly reduced. The commencement of hydroelectric projects during 1925–1990 responsible for an increase of area under water bodies by inundating other land uses. The long term analysis shows agricultural area been decreasing and commercial plantations been increasing in the district. There has been a significant increase in the area of plantations from 1236.2 km² (1975) to 1317.3 km² (2012).