Spatial Distribution Of Land Cover Research Articles

Prediction of land cover change in the Belawan watershed using the cellular automata-markov chain model

Belawan Watershed is one of the watersheds that cross Medan City, the capital of North Sumatra province. The spatial distribution of land cover affects the hydrological conditions in this watershed. The purpose of this study is to predict land cover in 2032 so that it can be used as information to mitigate changes in forest land cover. The method used is Cellular Automata-Markov Chain modeling with five change parameters (driving factors): distance from the river, distance from the road, altitude, population density, and slope. Land cover changes in the Belawan watershed used for this modeling include land cover in 2012, 2017, and 2022 and predicted land cover in 2032. The results showed that the predicted land cover is the water body 998.409 ha (1.36%), dryland forest 970.399 ha (1.32%), mangrove forest 3,351.496 ha (4.58%), settlement 11,600.105 ha (15.85%), plantation 38,787.924 ha (53.01%), agriculture 8,674.632 ha (11.85%), rice fields 5,568.183 ha (7.6%) and ponds 3,218.175 ha (4.3%). The area of forests and mangroves tends to continue to decline, so mitigation efforts are needed to reduce the reduction rate in forest and mangrove land cover.

Metal accumulation in salt marsh soils along the East Coast of the United States

Coastal salt marshes are depositional environments that can accumulate pollutants introduced to the environment from human activities. Metals are a contaminant of concern in coastal environments due to their longevity and toxicity. We assessed metal concentrations and accumulation rates in nine salt marsh sites along the U.S. East Coast from Maine to Georgia. Following a metal mobility assay in organic-rich and mineral dominated salt marsh soils under aerobic/anaerobic and freshwater/saltwater conditions, we focused on profiles of chromium, nickel, copper, zinc, cadmium, lead, and uranium in two soil cores from each of the nine marshes that had previously been dated using lead-210 radioisotope techniques. We examined how land cover and the spatial distribution of land cover, marsh vertical accretion, and other watershed characteristics correlated with metal concentrations and depth/time-integrated accumulation of metals. We found statistically significant differences in metal concentrations and/or inventories between sites, with accumulation of metals positively correlated with both developed land cover in the watershed and rates of vertical accretion in the tidal marsh. The accumulation of chromium, cadmium, and lead were significantly correlated with developed land cover while the accumulation of chromium, nickel, copper, zinc, and lead were correlated with factors that determine sediment delivery from the landscape (e.g., riverine suspended sediment, soil erodibility in the watershed, and agricultural land cover skewed towards the coast) and measured wetland accretion rates. We observed declines in the concentration of many metals since 1925 at sites along the U.S. East Coast, indicating pollution mitigation strategies have succeeded in reducing metal pollution and delivery to the coastal zone. However, increasing rates of salt marsh vertical accretion over recent decades largely offset reductions in metal concentrations, resulting in rates of metal accumulation in coastal salt marsh soils that have not changed or, in some instances, increased over time.

Spatial-Temporal Evolution and Prediction of Carbon Storage: An Integrated Framework Based on the MOP–PLUS–InVEST Model and an Applied Case Study in Hangzhou, East China

Land-use/land-cover change (LUCC) is an important factor affecting carbon storage. It is of great practical significance to quantify the relationship between LUCC and carbon storage for regional ecological protection and sustainable socio-economic development. In this study, we proposed an integrated framework based on multiobjective programming (MOP), the patch-level land-use simulation (PLUS) model, and the integrated valuation of ecosystem service and trade-offs (InVEST) model. First, we used the InVEST model to explore the spatial and temporal evolution characteristics of carbon storage in Hangzhou from 2000 to 2020 using land-cover data. Second, we constructed four scenarios of natural development (ND), economic development (ED), ecological protection (EP), and balanced development (BD) using the Markov chain model and MOP, and then simulated the spatial distribution of land cover in 2030 with the PLUS model. Third, the InVEST model was used to predict carbon storage in 2030. Finally, we conducted a spatial correlation of Hangzhou’s carbon storage and delineated carbon storage zoning in Hangzhou. The results showed that: (1) The artificial surfaces grew significantly, while the cultivated land decreased significantly from 2000 to 2020. The overall trend was a decrease in carbon storage, and the changing areas of carbon storage were characterized by local aggregation and sporadic distribution. (2) The areas of artificial surfaces, water bodies, and shrubland will continue to increase up to 2030, while the areas of cultivated land and grassland will continue to decrease. The BD scenario can effectively achieve the multiple objectives of ecological protection and economic development. (3) The carbon storage will continue to decline up to 2030, and the EP scenario will have the highest carbon storage, which will effectively mitigate the carbon storage loss. (4) The spatial distribution of carbon storage in Hangzhou was inextricably linked to the land cover, which was characterized by a high–high concentration and a low–low concentration. The results of the study can provide decision support for the sustainable development of Hangzhou and other cities in the Yangtze River Delta region.

Landscape Analysis of Cobalt Mining Activities from 2009 to 2021 Using Very High Resolution Satellite Data (Democratic Republic of the Congo)

The cobalt mining sector is well positioned to be a key contributor in determining the success of the Democratic Republic of the Congo (DRC) in meeting the Sustainable Development Goals (SDGs) by 2030. Despite the important contribution to the DRC’s economy, the rapid expansion of mining operations has resulted in major social, health, and environmental impacts. The objective of this study was to quantitatively assess the cumulative impact of mining activities on the landscape of a prominent cobalt mining area in the DRC. To achieve this, an object-based method, employing a support vector machine (SVM) classifier, was used to map land cover across the city of Kolwezi and the surrounding mining areas, where long-term mining activity has dramatically altered the landscape. The research used very high resolution (VHR) satellite imagery (2009, 2014, 2019, 2021) to map the spatial distribution of land cover and land cover change, as well as analyse the spatial relationship between land cover classes and visually identified mine features, from 2009 to 2021. Results from the object-based SVM land cover classification produced an overall accuracy of 85.2–90.4% across the time series. Between 2009 and 2021, land cover change accounted to: rooftops increasing by 147.2% (+7.7 km2); impervious surface increasing by 104.7% (+3.35 km2); bare land increasing by 85.4% (+33.81 km2); exposed rock increasing by 56.2% (+27.46 km2); trees decreasing by 4.5% (−0.34 km2); shrub decreasing by 38.4% (−26.04 km2); grass and cultivated land decreasing by 27.1% (−45.65 km2); and water decreasing by 34.6% (−3.28 km2). The co-location of key land cover classes and visually identified mine features exposed areas of potential environmental pollution, with 91.6% of identified water situated within a 1 km radius of a mine feature, and vulnerable populations, with 71.6% of built-up areas (rooftop and impervious surface class combined) situated within a 1 km radius of a mine feature. Assessing land cover patterns over time and the interplay between mine features and the landscape structure allowed the study to amplify the findings of localised on-the-ground research, presenting an alternative viewpoint to quantify the true scale and impact of cobalt mining in the DRC. Filling geospatial data gaps and examining the present and past trends in cobalt mining is critical for informing and managing the sustainable growth and development of the DRC’s mining sector.

Spectral–Spatial Residual Graph Attention Network for Hyperspectral Image Classification

Hyperspectral images (HSIs) not only possess abundant spectral features but also present a detailed spatial distribution of land cover, and they have significant advantages in the fine classification of ground materials. Recently, using convolutional neural networks (CNNs) to extract spectral–spatial features has become an effective way for HSI classification. However, conventional convolution kernels learn features from fixed regular square regions, and rich spatial information has not been effectively explored. In this letter, an end-to-end model named spectral–spatial residual graph attention network (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> RGANet) is developed for HSI classification, and it has two crucial elements, including spectral residual and graph attention convolution modules. At first, two spectral residual modules are employed to capture discriminant spectral features. Then, graphs are constructed to reveal the relationship between points in local neighborhoods. By graph attention mechanism, local spatial information is adaptively aggregated from neighboring nodes. Experiments on two public HSI datasets demonstrate that the S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> RGANet is significantly superior to some state-of-the-art (SOTA) methods with limited training samples.

Assessment of Landscape Character and Absorptivity Based on Digital Terrain Model Analysis—Case Study of Jelenia Góra City in Poland

In an era of significant growth in the availability of spatial data and continued advances in computing technologies, opportunities for new interpretations and solutions to the landscape research problems posed worldwide are emerging. This paper presents different possibilities of applying digital terrain model (DTM) data in research of various aspects of landscape. For this purpose, two different methods were proposed. The first was to identify a set of components of the Jelenia Góra city landscape character on the basis of the topographic position index and spatial distribution of land cover, while the second was to assess the landscape of Jelenia Góra city in terms of the possibility of adopting new elements, using the author’s scenic absorptivity method. The results indicate the structure of the components of the landscape character of Jelenia Góra city together with its spatial distribution, which also allowed for the delineation of landscape units. The scenic absorptivity analysis showed that there are isolated areas within Jelenia Góra city that are capable of accommodating significant size elements that would not adversely affect the city landscape. In conclusion, DTM data are able to significantly improve research methods in landscape studies.

The establishment of a cross-regional differentiated ecological compensation scheme based on the benefit areas and benefit levels of sand-stabilization ecosystem service

A scientific and reasonable ecological compensation scheme (ECS) is an important guarantee for promoting coordinated and equitable development between regions. The existing ECSs usually ignore the premise that the ECS can only be accepted by the stakeholders if there are a clear scope and benefit to the ecosystem services (ES). An ecological compensation scheme should be based on the transmission principle of ES so that a scientific and reasonable scheme can be proposed and accepted by the stakeholders. Based on the theory of ecosystem service flow, this paper analyzed the provision‒benefit mechanism of sand-stabilization ecosystem service (SSS) and selected Ordos City, Inner Mongolia, which is located in Northwest China, as the study area. A revised wind erosion equation (RWEQ) model was used to estimate the sand-stabilization amount of Ordos’s ecosystem in 2015, and a hybrid single-particle Lagrangian integrated trajectory (HYSPLIT) model was used to simulate the path of sand-stabilization ecosystem service flow (SSSF). Then, the benefit areas and levels of SSS were identified, and the spatial distribution of land cover, population, and gross domestic product (GDP) in the ecosystem services beneficiary area (SBA) was evaluated. Based on the identified benefit areas and benefit levels, and combined with the investment and income in the ecological construction of the Ordos, a cross‒regional differentiated ECS was proposed. The results show that the Ordos’s ecosystem played a huge role in sand-stabilization, which have brought huge ecological and economic benefits. In 2015, the sand-stabilization amount of Ordos’s ecosystem was about 7.20×108 tons. The area of SBA is1.66×106Km2, accounting for 17.21% of China’s total area, this mainly involves 16 provinces and cities, including Beijing, Tianjin, Hebei, etc. The amount of dust‒fall (ADF) in the beneficiary area was reduced by 28,738.67 ×104 tons, and investment of 4318.51 ×108 RMB (Renminbi) in dust removal would be avoided. For the ECS, based on the principle of “equity, beneficiary compensation, more benefit and more compensation”, Ordos shall take care of the ecological compensation fee (ECF) of about 36.28% of the total. In 16 provinces and cities, Inner Mongolia costs 66,121.03 ×104 RMB, which is the most. The fees are payable by other SBAs decrease with distance. Hubei Province (Suizhou) pays the least in ecological compensation, at 7.5 ×104 RMB. Based on the theory of ecosystem service flow, this paper proposes a research framework of differentiated ECS of SSS, which can provide an accurate scientific basis for determining the SBA and cross-regional ECS of SSS in the future.

Landuse classification of hyperspectral data by spectral angle mapper and support vector machine in humid tropical region of India

Hyperspectral images are being used in various fields. The main objective of the present study was to use hyperspectral imagery from Hyperion with Spectral Angle Mapper (SAM) and Support Vector Machine (SVM) for discriminating the landuse/landcover classes in Kozhikode district, Kerala which constitutes a combination of different physiographic land features. Hyperion functions from a space platform with modest surface signal levels and a full column of atmosphere persuading the signal, hence, the data derived from this demand careful pre-processing to minimize sensor and atmospheric noise. The atmospheric correction using MODTRAN based FLAASH module as well as the data dimensionality reduction by Principal Component Analysis (PCA) made the Hyperion to allow discrete reflectance values. Advanced classifiers like SAM and SVM could describe the pattern and spatial distribution of landcover. From the accuracy assessments, SVM showed better classified result than SAM with overall accuracy 85.6% and kappa coefficient 0.89. This study suggests that SVM can be used for landuse/landcover classification of hyperspectral data with high accuracy.

Monitoring Land-Use/Land-Cover Changes at a Provincial Large Scale Using an Object-Oriented Technique and Medium-Resolution Remote-Sensing Images

An object-based image analysis (OBIA) technique is replacing traditional pixel-based methods and setting a new standard for monitoring land-use/land-cover changes (LUCC). To date, however, studies have focused mainly on small-scale exploratory experiments and high-resolution remote-sensing images. Therefore, this study used OBIA techniques and medium-resolution Chinese HJ-CCD images to monitor LUCC at the provincial scale. The results showed that while woodland was mainly distributed in the west, south, and east mountain areas of Hunan Province, the west had the largest area and most continuous distribution. Wetland was distributed mainly in the northern plain area, and cultivated land was distributed mainly in the central and northern plains and mountain valleys. The largest impervious surface was the Changzhutan urban agglomerate in the northeast plain area. The spatial distribution of land cover in Hunan Province was closely related to topography, government policy, and economic development. For the period 2000–2010, the areas of cultivated land transformed into woodland, grassland, and wetland were 183.87 km2, 5.57 km2, and 70.02 km2, respectively, indicating that the government-promoted ecologically engineered construction was yielding some results. The rapid economic growth and urbanization, high resource development intensity, and other natural factors offset the gains made in ecologically engineered construction and in increasing forest and wetland areas, respectively, by 229.82 km2 and 132.12 km2 from 2000 to 2010 in Hunan Province. The results also showed large spatial differences in change amplitude (LUCCA), change speed (LUCCS), and transformation processes in Hunan Province. The Changzhutan urban agglomerate and the surrounding prefectures had the largest LUCCA and LUCCS, where the dominant land cover accounted for the conversion of some 189.76 km2 of cultivated land, 129.30 km2 of woodland, and 6.12 km2 of wetland into impervious surfaces in 2000–2010. This conversion was attributed to accelerated urbanization and rapid economic growth in this region.

The spatial-temporal patterns of land cover changes due to mining activities in the Darling Range, Western Australia: A Visual Analytics Approach

The Darling Range in Western Australia is a major bauxite producing region. Clearing, excavation and rehabilitation activities related to bauxite mining have influenced land cover within this region since mining commenced in the 1960s. This paper presents a study that used machine learning and time series visualisation to analyse the land cover changes of the Darling Range using time-lapse multispectral images, with the aim of understanding the impact of the mining activities and land rehabilitation patterns of the region. Land cover changes were analysed using 14 Landsat Thematic Mapper (TM) images between 1988 and 2014. The spatial distribution of land cover was classified automatically using machine learning algorithms, and their temporal changes were visualized for analysis. Supervised classification was carried out based on the six spectral features of the images using three machine learning algorithms, namely support vector machine (SVM), random forest (RF) and Naïve Bayes (NB). The results showed that the RF algorithm achieved overall accuracy, (ratio of correctly classified samples divided by the total number of samples), greater than 95% for all years. The temporal changes of land cover distribution over the study period were visualized using a change map. These changes were compared with land clearing and rehabilitation records of a mining company operating in that region. A close correlation was observed between the automated analysis outputs and the company’s records. This work demonstrates the potential use of machine analysis in improving the accuracy of spatial data related to land clearing; and in monitoring vegetation recovery of closed and rehabilitated mines.

Across the grain: Multi-scale map comparison and land change assessment

Changes in the spatial distribution of land cover and land use can have significant impacts on ecological processes at multiple scales; estimating these changes provides critical data for both monitoring and understanding land-use effects on these processes. One approach to mapping landcover changes, particularly useful over longer periods of time, is comparison of existing landcover maps, (post-classification change analysis). The accuracy of these maps is often unknown and varies depending on data sources and interpretation techniques; therefore, separating change on the ground from differences attributable to sensors and methods is both critical and problematic. Through a novel map comparison method applying major axis regression at multiple spatial grains of analysis, this study partitioned accuracy into components of bias and precision in comparing maps, which aided selection of an optimal analytical grain size. Comparisons between contemporaneous maps showed the magnitude and distribution of error alone, while between-period analyses indicated both cumulative map error and change on the ground. These methods enable exploration of the nature of error and identification of differences between maps, while accounting for the imprecision and bias inherent in the source documents. Mapping landcover change delineates landscapes under recent disturbance pressure, and these measures are more effective as performance indicators for broad-scale evaluation of natural heritage policies and habitat restoration initiatives when error in the data is identified and accounted for.

3D OBJECT CLASSIFICATION BASED ON THERMAL AND VISIBLE IMAGERY IN URBAN AREA

Abstract. The spatial distribution of land cover in the urban area especially 3D objects (buildings and trees) is a fundamental dataset for urban planning, ecological research, disaster management, etc. According to recent advances in sensor technologies, several types of remotely sensed data are available from the same area. Data fusion has been widely investigated for integrating different source of data in classification of urban area. Thermal infrared imagery (TIR) contains information on emitted radiation and has unique radiometric properties. However, due to coarse spatial resolution of thermal data, its application has been restricted in urban areas. On the other hand, visible image (VIS) has high spatial resolution and information in visible spectrum. Consequently, there is a complementary relation between thermal and visible imagery in classification of urban area. This paper evaluates the potential of aerial thermal hyperspectral and visible imagery fusion in classification of urban area. In the pre-processing step, thermal imagery is resampled to the spatial resolution of visible image. Then feature level fusion is applied to construct hybrid feature space include visible bands, thermal hyperspectral bands, spatial and texture features and moreover Principle Component Analysis (PCA) transformation is applied to extract PCs. Due to high dimensionality of feature space, dimension reduction method is performed. Finally, Support Vector Machines (SVMs) classify the reduced hybrid feature space. The obtained results show using thermal imagery along with visible imagery, improved the classification accuracy up to 8% respect to visible image classification.

Landscape Control on the Spatial and Temporal Variability of Chromophoric Dissolved Organic Matter and Dissolved Organic Carbon in Large African Rivers

The characteristics of colored dissolved organic mat- ter (CDOM) as well as the concentrations and stable isotope composition (d 13 C) of dissolved organic car- bon (DOC) were characterized in several large rivers of Africa including the Congo, Niger, Zambezi, and Ogoouebasins. We compared the spatial and tem- poral patterns of dissolved organic matter (DOM) quantity and quality along with various environ- mental gradients, including hydrology, river size, catchment vegetation, and connectivity to land. The optical proxies used include the absorption coeffi- cient at 350 nm, the specific ultra-violet absorbance, and the spectral slope ratio (SR = 275-295-nm slope divided by 350-400-nm slope). Our results show that land cover plays a primary role in controlling both DOC concentration and optical properties of DOM in tropical freshwaters. A higher cover of dense forest in the catchment leads to a higher quantity of highly aromatic DOM in the river network, whereas an increasing savannah cover results in lower DOC concentrations and less absorptive DOM. In addition to land cover, the watershed morphology (expressed by the average slope) exerts a strong control on DOC and CDOM in tropical rivers. Our results also show that the percentage of C3 and C4 vegetation cover is not an accurate predictor for DOM and CDOM quality in rivers due to the importance of the spatial distribution of land cover within the drainage net- work. The comparison of our results with previously published CDOM data in temperate and high-lati- tude rivers highlights that DOM in tropical freshwa- ters is generally more aromatic, and shows a higher capacity for absorbing sunlight irradiance.

USE OF LANDSAT-SERIES DATA IN NATIONAL GEOGRAPHIC CONDITION MONITORING IN CHINA

Abstract. To fully grasp the nature and human geography situation information, solve the problem of ecological environment, economic and social development of the country, monitoring the state of geographic condition by uniform index system has great significance. By collecting the existing standard documents, our paper established a suit of index system considering the characteristics of long time series remote sensing data. The index system includes basic, subject, composite statistical indexes, and statistical indexes based on basic geographic element. The spatial and temporal distribution of geographic condition with Landsat TM image in Haidian district of Beijing from 1983 to 2013 are studies. Results show that farmland decreases by 28.60%, build-up land increases by 38.95% in this period. The amount of land resources in different elevation/slope shows that, with the increase of elevation/slope, farmland and build-up land is gradually reduced, while grassland area is gradually increasing. In plains areas of elevation less than 50m and within the scope of the 0 to 3° slope, farmland and build-up land are the main land cover types, and both show the characteristic of tradeoffs. Urban area extended to the west and the north, meanwhile mass center of Haidian also moves to the northwest. The urban compactness decreases and the fractal index increased gradually, reflecting the city saturation degree become reduced, the city boundary becomes complicated gradually. The comprehensive land cover dynamic degree after the first decrease and then increases. Finally, based on the above statistic results, the spatial distribution of land cover in 2015 is predicted.

Sub-pixel mapping based on artificial immune systems for remote sensing imagery

A new sub-pixel mapping strategy inspired by the clonal selection theory in artificial immune systems (AIS), namely, the clonal selection sub-pixel mapping (CSSM) framework, is proposed for the sub-pixel mapping of remote sensing imagery, to provide detailed information on the spatial distribution of land cover within a mixed pixel. In CSSM, the sub-pixel mapping problem becomes one of assigning land-cover classes to the sub-pixels while maximizing the spatial dependence by the clonal selection algorithm. Each antibody in CSSM represents a possible sub-pixel configuration of the pixel. CSSM evolves the antibody population by inheriting the biological properties of human immune systems, i.e., cloning, mutation, and memory, to build a memory cell population with a diverse set of locally optimal solutions. Based on the memory cell population, CSSM outputs the value of the memory cell and finds the optimal sub-pixel mapping result. Based on the framework of CSSM, three sub-pixel mapping algorithms with different mutation operators, namely, the clonal selection sub-pixel mapping algorithm based on Gaussian mutation (G-CSSM), Cauchy mutation (C-CSSM), and non-uniform mutation (N-CSSM), have been developed. They each have a similar sub-pixel mapping process, except for the mutation processes, which use different mutation operators. The proposed algorithms are compared with the following sub-pixel mapping algorithms: direct neighboring sub-pixel mapping (DNSM), the sub-pixel mapping algorithm based on spatial attraction models (SASM), the BP neural network sub-pixel mapping algorithm (BPSM), and the sub-pixel mapping algorithm based on a genetic algorithm (GASM), using both synthetic images (artificial and degraded synthetic images) and real remote sensing imagery. The experimental results demonstrate that the proposed approaches outperform the previous sub-pixel mapping algorithms, and hence provide an effective option for the sub-pixel mapping of remote sensing imagery.

Hyperion hyperspectral imagery analysis combined with machine learning classifiers for land use/cover mapping

Describing the pattern and the spatial distribution of land cover is traditionally based on remote sensing data analysis and one of the most commonly techniques applied has been image classification. The main objective of the present study has been to evaluate the combined use of Hyperion hyperspectral imagery with the Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) classifiers for discriminating land-cover classes in a typical Mediterranean setting. Accuracy assessment of the derived thematic maps was based on the analysis of the classification confusion matrix statistics computed for each classification map, using for consistency the same set of validation points.Results indicated a close classification accuracy between the two classifiers, with the SVMs somehow outperforming the ANNs by 3.31% overall accuracy and by 0.038 kappa coefficient. Although both classifiers produced close results, SVMs generally appeared most useful in describing the spatial distribution and the cover density of each land cover category. The higher classification accuracy by SVMs was attributed principally to the ability of this classifier to identify an optimal separating hyperplane for classes’ separation which allows a low generalization error, thus producing the best possible classes’ separation. On the other, as a key disadvantage of both techniques was identified that both do not operate on a sub-pixel level, which can significantly reduce their accuracy due to possible mixture problems occurred when coarse spatial resolution remote sensing imagery is used.All in all, this study demonstrated that, provided that a Hyperion hyperspectral imagery can be made available at regular time intervals over a given region, when combined with either SVMs or ANNs classifiers, can potentially enable a wider approach in land use/cover mapping. This can be of particular importance, especially for regions like in the Mediterranean basin, since it can be related to mapping and monitoring of land degradation and desertification phenomena which are evident in such areas.

Spatial distribution of land cover and vegetation activity along topographic gradient in an arid river valley, SW China

Anthropogenic activities have become more and more important in characterizing the landscape, but their impacts are still restricted by natural environments. This paper discusses the interactions of anthropogenic activity, vegetation activity and topography through describing the spatial distribution of land cover and vegetation activity (represented by Normalized Difference Vegetation Index, NDVI) along topographic gradient in a mountainous area of southwestern China. Our results indicate that the existing landscape pattern is controlled by anthropogenic activities as well as topographic factors. Intensive anthropogenic activities mainly occur in areas with relatively low elevation, gentle and concave slopes, as these areas are easy and convenient to attain for human. Because of the destruction by human, some land cover types (mainly grassland and shrub) are only found in relatively harsher environments. This study also finds that topographic wetness index (W) used in other places only reflects runoff generation capacity, but not indicate the real spatial pattern of soil water content in this area. The relationships between NDVI and W, and NDVI and length slope factor (LSF) show that runoff and erosion have complex effects on vegetation activity. Greater values of W and LSF will lead to stronger capacity to produce runoff and transport sediment, and thereby increase soil water content and soil deposition, whereas beyond a certain threshold runoff and erosion are so strong that they would destruct vegetation growth. This study provides information needed to successfully restore native vegetation, improve land management, and promote sustainable development in mountainous areas, especially for developing regions.

Land‐cover classification in the Andes of southern Ecuador using Landsat ETM+ data as a basis for SVAT modelling

A land‐cover classification is needed to deduce surface boundary conditions for a soil–vegetation–atmosphere transfer (SVAT) scheme that is operated by a geoecological research unit working in the Andes of southern Ecuador. Landsat Enhanced Thematic Mapper Plus (ETM+) data are used to classify distinct vegetation types in the tropical mountain forest. Besides a hard classification, a soft classification technique is applied. Dempster–Shafer evidence theory is used to analyse the quality of the spectral training sites and a modified linear spectral unmixing technique is selected to produce abundancies of the spectral endmembers. The hard classification provides very good results, with a Kappa value of 0.86. The Dempster–Shafer ambiguity underlines the good quality of the training sites and the probability guided spectral unmixing is chosen for the determination of plant functional types for the land model. A similar model run with a spatial distribution of land cover from both the hard and the soft classification processes clearly points to more realistic model results by using the land surface based on the probability guided spectral unmixing technique.

Combining Multiple Classifiers: An Application Using Spatial and Remotely Sensed Information for Land Cover Type Mapping

This article discusses two new methods for increasing the accuracy of classifiers used land cover mapping. The first method, called the product rule, is a simple and general method of combining two or more classification rules as a single rule. Stacked regression methods of combining classification rules are discussed and compared to the product rule. The second method of increasing classifier accuracy is a simple nonparametric classifier that uses spatial information for classification. Two data sets used for land cover mapping of Landsat TM scenes from Idaho and Montana illustrate the new methods. For these examples, the product rule compared favorably to the more complex stacked regression methods. The spatial classifier produced substantial increases in estimated accuracy when combined with one or more additional classifiers that used remotely sensed variables for classification. These results suggest that the product rule may produce increases in map accuracy with little additional expense or effort. The spatial classifier may be useful for increasing accuracy when patterns exist in the spatial distribution of land cover.

Coupling past management practice and historic landscape change on John F. Kennedy Space Center, Florida

Historic landcover dynamics in a scrubby flatwoods (Tel-4) and scrub landscape (Happy Creek) on John F. Kennedy Space Center were measured using aerial images from 1943, 1951, 1958, 1969, 1979, and 1989. Landcover categories were mapped, digitized, geometrically registered, and overlaid in ARC/INFO. Both study sites have been influenced by various land use histories, including periods of range management, fire suppression, and fire management. Several analyses were performed to help understand the effects of past land management on the amount and spatial distribution of landcover within the study sites. A chi-squared analysis showed a significant difference between the frequency of landcover occurrence and management period. Markov chain models were used to project observed changes over a 100-year period; these showed current management practices being effective at Tel-4 (restoring historic landscape structure) and much less effective at Happy Creek. Documenting impacts of past management regimes on landcover has provided important insight into current landscape composition and will provide the basis for improving land management on Kennedy Space Center and elsewhere.