A semi-automatic method for analysis of landscape elements using Shuttle Radar Topography Mission and Landsat ETM+ data

doi:10.1016/j.cageo.2007.09.019

Computers & Geosciences

Volume 35, Issue 2, February 2009, Pages 373-389

https://doi.org/10.1016/j.cageo.2007.09.019 Get rights and content

Abstract

In this paper, we demonstrate artificial neural networks—self-organizing map (SOM)—as a semi-automatic method for extraction and analysis of landscape elements in the man and biosphere reserve “Eastern Carpathians”. The Shuttle Radar Topography Mission (SRTM) collected data to produce generally available digital elevation models (DEM). Together with Landsat Thematic Mapper data, this provides a unique, consistent and nearly worldwide data set.

To integrate the DEM with Landsat data, it was re-projected from geographic coordinates to UTM with 28.5 m spatial resolution using cubic convolution interpolation. To provide quantitative morphometric parameters, first-order (slope) and second-order derivatives of the DEM—minimum curvature, maximum curvature and cross-sectional curvature—were calculated by fitting a bivariate quadratic surface with a window size of 9×9 pixels. These surface curvatures are strongly related to landform features and geomorphological processes.

Four morphometric parameters and seven Landsat-enhanced thematic mapper (ETM+) bands were used as input for the SOM algorithm. Once the network weights have been randomly initialized, different learning parameter sets, e.g. initial radius, final radius and number of iterations, were investigated. An optimal SOM with 20 classes using 1000 iterations and a final neighborhood radius of 0.05 provided a low average quantization error of 0.3394 and was used for further analysis. The effect of randomization of initial weights for optimal SOM was also studied. Feature space analysis, three-dimensional inspection and auxiliary data facilitated the assignment of semantic meaning to the output classes in terms of landform, based on morphometric analysis, and land use, based on spectral properties.

Results were displayed as thematic map of landscape elements according to form, cover and slope. Spectral and morphometric signature analysis with corresponding zoom samples superimposed by contour lines were compared in detail to clarify the role of morphometric parameters to separate landscape elements. The results revealed the efficiency of SOM to integrate SRTM and Landsat data in landscape analysis. Despite the stochastic nature of SOM, the results in this particular study are not sensitive to randomization of initial weight vectors if many iterations are used. This procedure is reproducible for the same application with consistent results.

Introduction

Information about landforms and landscape is one of the fundamental requirements for a large variety of modeling problems in environmental science. Most researchers define landscape as an essentially visual phenomenon or as a particular configuration of topography, land use, vegetation cover and settlement pattern (Blankson and Green, 1991; Otero Pastor et al., 2007). Landscapes are dynamic systems that involve interrelation between physical characteristics (such as landform, soil) and anthropogenic processes (such as land use). Relationship between these physical properties and human impact on the land has led to the development of different analysis models. These models vary from visual analysis and quantitative techniques to rule-based geoecosystem techniques (Benefield and Bunce, 1982; Bernert et al., 1997; Blankson and Green, 1991).

However, all these models are based on the common task to find the basic elements of a heterogeneous landscape. The basic concept of natural landscape units, called geochores, was developed in the 1950s and 1960s. The term ‘geochore’ means a geographically defined or limited unit and can be regarded as mosaics of basic topic elements (Bastian, 2000). Landform as physical constituent of landscape may be extracted from digital elevation data using various approaches including classification of morphometric parameters (Dikau, 1989; Dehn et al., 2001), fuzzy set methods and unsupervised (ISODATA) classification (Adediran et al., 2004; Burrough et al., 2000; Irvin et al., 1997), probabilistic clustering algorithm (Stepinski and Collier, 2004; Stepinski and Vilalta, 2005), multivariate descriptive statistics (Dikau, 1989; Evans, 1972; Dehn et al., 2001) and double ternary diagram classification (Crevenna et al., 2005). Landforms possess at least two important properties. They are the result of past geomorphic and geologic processes and provide a controlling boundary condition for actual geomorphic processes (Dehn et al., 2001). For disciplines dealing with landforms, the properties of consideration are different. For geomorphologists both properties of landforms are important. But a common perspective of all landform studies regardless of discipline is to delimit homogeneous areas from digital elevation data. Digital elevation models (DEM) can be compiled from contour lines or other sources like the Shuttle Radar Topography Mission (SRTM). On 11 February 2000, the space shuttle Endeavour with the SRTM payload on board was launched. A single technique, synthetic aperture radar (SAR) interferometry, was used for producing a consistent DEM covering all landmasses on earth between 60°N and 57°S (Blumberg, 2006; Rabus et al., 2003; Wright et al., 2006). The 3 arc sec. (∼90 m) SRTM data are publicly available at http://seamless.usgs.gov.

Describing the shape of surface features on earth using a set of numerical measures (derivatives) such as profile curvature, plan convexity, slope, cross-sectional curvature, minimum and maximum curvature from DEMs is known as morphometry. Morphometric characterization identifies morphometric features such as saddle, channel, ridge and plane based on these measures (Fisher et al., 2004; Pike, 2000; Wood, 1996). Integrating land surface forms (morphometric features) with spectral information from remotely sensed data contributes to the explanation of relationships between landscape component processes (physical, biotic and human activities) on one hand and delimiting boundaries of homogenous landscape elements on the other hand.

In recent years, there has been considerable interest in using neural networks with remotely sensed data. Self-organizing map (SOM) is an unsupervised neural network algorithm, which clusters or visualizes high-dimensional input vectors into low-dimensional (usually two-dimensional) output based on regularities and correlations between them (Jianwen and Bagan, 2005; Kohonen, 2001; Li and Eastman, 2006). SOM has been used in a wide variety of areas such as classification of remote-sensing data (Duda and Canty, 2002; Jianwen and Bagan, 2005), information visualization and knowledge discovery (Koua et al., 2006), class modeling (Marini et al., 2005) and semi-automatic terrain analyses (Ehsani and Quiel, in press).

The main objective of this paper is characterization of landscape elements through the combination of morphometric parameters and remotely sensed spectral data. The emphasis is on morphologically homogeneous landscape elements characterized mainly by similar slope conditions. SOM as unsupervised paradigm of neural networks is used to reduce large multidimensional data to one output layer consisting of 20 map units. This output indicates land cover of landscape elements on one hand and impact of geologic and geomorphological processes (morphometric features) on the other hand.

Section snippets

Study area

The study area is centered on the common border point of Poland, Slovakia and Ukraine and located between 48°52′N and 49°25′N latitude, 21°59′E and 23°1′E longitude with a total area of about 4500 Km² (Fig. 1). It covers the biosphere reserve “Eastern Carpathians” with the Bieszczady national park in Poland, Uzanski national park in Ukraine and Poloniny national park in Slovakia.

Historically, the region had similar land management policies. After World War II, fundamental changes in political

Data

The data set in this study consists of:

•
Landsat ETM+ data path 186, row 26 dated 30 September 2000 (Fig. 1) were acquired from the Global Land Cover Facility (GCLF) server at the University of Maryland, Institute for Advanced Computer Studies (UMIACS). GLCF provides free access to an integrated collection of critical land cover and earth science data (http://glcf.umiacs.umd.edu).
•
The 3 arcsec digital elevation model derived from SRTM data (∼90 m) was acquired from the USGS server in geographic

Optimal self-organizing map

Learning of SOM was performed with randomly initialized weights of the map units. Table 3 shows the 16 SOM with different configuration of learning control parameters.

The initial radius for learning was set to 3, 2 and 1, respectively. The map with an initial radius of three and a final radius of one produced the highest average quantization error. Results indicate that the final radius should be much smaller than 1. In several trials with different configurations of learning parameters, SOM 16

Conclusion

This study demonstrates the effectiveness of self-organizing map (SOM) algorithms of artificial neural networks as semi-automatic methods to extract both spectral and morphometric information from SRTM and Landsat 7 data. Analyzing and interpreting this information yielded 20 classes of homogeneous landscape elements. Morphometric analysis of first- and second-order derivatives of DEM data, such as slope, cross-sectional curvature, maximum curvature and minimum curvature, led to the description

Acknowledgements

We are grateful to the Swedish Institute for funding all travel expenses in the framework of the Visby program. We thank all our colleagues, especially, Docent Ivan Kruhlov, Department of Physical Geography; Ivan Franko, University in Lvov, Ukraine and Dr. Mieczyslaw Sobik, Institute of Geography and Regional Development, University Wroclaw, Poland for interesting discussions and for providing facilities and support. We thank Dr. Kuemmerle for providing his land use map of the project area.

References (37)

A.O. Adediran et al.
Computer-assisted discrimination of morphological units on north-central Crete (Greece) by applying multivariate statistics to local relief gradients
Geomorphology
(2004)
F. Bação et al.
The self organizing map, the Geo-SOM, and relevant variants for geosciences
Computers and Geosciences
(2005)
O. Bastian
Landscape classification in Saxony (Germany)—a tool for holistic regional planning
Landscape and Urban Planning
(2000)
E.J. Blankson et al.
Use of landscape classification as an essential prerequisite to landscape evaluation
Landscape Urban Planning
(1991)
D.G. Blumberg
Analysis of large aeolian (wind-blown) bedforms using the Shuttle Radar Topography Mission (SRTM) digital elevation data
Remote Sensing of Environment
(2006)
P.A. Burrough et al.
High-resolution landform classification using fuzzy k-means
Fuzzy Sets and Systems
(2000)
M. Dehn et al.
Principles of semantic modeling of landform structures
Computers and Geosciences
(2001)
C.H. Grohmann et al.
SRTM-based morphotectonic analysis of the Pocos de Caldas Alkaline Massif, southeastern Brazil
Computers and Geosciences
(2007)
B.J. Irvin et al.
Fuzzy and isodata classification of landform elements from digital terrain data in Pleasant Valley, Wisconsin
Geoderma
(1997)
M. Jianwen et al.
Land-use classification using ASTER data and self-organized neural networks
International Journal of Applied Earth Observation and Geoinformation
(2005)

T. Kuemmerle et al.

Cross-border comparison of land cover and landscape pattern in Eastern Europe using a hybrid classification technique

Remote Sensing of Environment

(2006)

F. Marini et al.

Class-modeling using Kohonen artificial neural networks

Analytica Chimica Acta

(2005)

I. Otero Pastor et al.

Landscape evaluation: comparison of evaluation methods in a region of Spain

Journal of Environmental Management

(2007)

B. Rabus et al.

The Shuttle Radar Topography Mission—a new class of digital elevation models acquired by spaceborne radar

ISPRS (International Society for Photogrammetry and Remote Sensing) Journal of Photogrammetry and Remote Sensing

(2003)

A.J. Richardson et al.

Using self-organizing maps to identify patterns in satellite imagery

Progress in Oceanography

(2003)

R. Wright et al.

An assessment of Shuttle Radar Topography Mission digital elevation data for studies of volcano morphology

Remote Sensing of Environment

(2006)

Benefield, C.B., Bunce, R.G.H., 1982. A preliminary visual presentation of land classes in Britain. Merlewood Research...

J.A. Bernert et al.

A quantitative method for delineating regions: an example for the western Corn Belt plains ecoregion of the USA

Environmental Management

(1997)

Cited by (26)

A fine digital soil mapping by integrating remote sensing-based process model and deep learning method in Northeast China
2024, Soil and Tillage Research
Accurate soil type maps provide an important basis for agricultural decision-making and land degradation control. In soil classification studies, the various environmental covariates are often selected based on the soil-forming framework. Since the mapping area and available observation data are limited, meteorological and vegetation cover factors have not been fully developed, and their role in soil classification needs to be evaluated. In addition, whether deep learning has out-performance in soil classification remains to be tested. The aim of this paper is to evaluate the accuracy of deep learning modelling techniques in classifying soil type using different combinations of input variables, and evaluate the importance of soil-forming variables in soil type classification. Therefore, we collected commonly used environmental covariates in Northeast China (NEC), including multiple meteorological factors and adopted a satellite-based biophysical model (Boreal Ecosystem Productivity Simulator, BEPS) to enrich vegetation cover factors. Next, four modeling strategies were developed: the soil-forming factors of soil and relief were considered as traditional environmental covariates (T), as well as combined with meteorologic variables (T + C), vegetation cover variables (T + V) and all available environmental covariates (T + C + V). Then, the effectiveness of different modeling strategies for soil classification was explored with convolutional neural network (CNN) model and multi-layer random forest (MRF) model based on soil separability. Finally, a 30 m resolution soil type map was established. The results demonstrated that both MRF and CNN can achieve high accuracy soil classification, while the CNN model performs better. The descending order of classification accuracy based on different modeling strategies of the CNN model is shown as T + C + V: 91.08%, T + V: 88.84%, T + C: 86.82%, and T: 83.96%. Meanwhile, the separability of different soil-forming factors for soil classification is soil properties, vegetation cover, temporal variation, meteorologic and relief in descending order. For Castanozems and Brown soils, MRF has higher classification accuracy, while CNN has better performance in Meadow soils and Fluvo-aquic soils. The methodology proposed in this paper aims to achieve high accuracy soil classification, provide an approach to understand the importance of soil-forming factors for the region, as well as for different soil types, and provide references for facilitating the interpretation of misclassified areas. Our results are accurate in the core areas, and therefore, this work facilitates researchers to be able to focus more on areas where different soil types intersect, thus significantly improves efficiency and saves resources, and promises to be a useful tool for future soil surveys.
Self-Organizing Maps for identification of zeolitic diagenesis patterns in closed hydrologic systems on the Earth and its implications for Mars
2021, International Journal of Sediment Research
Citation Excerpt :
SOMs are different from other artificial neural network (ANN) methods since they apply competitive learning instead of error-correction learning, such as backpropagation, and they organize the clusters in a two dimensional space according to the similarity of the cluster centroids themselves (Dowla & Rogers, 1995; Wehrens & Buydens, 2007). SOMs can be applied in every field of geosciences including geochemistry (e.g. Penn, 2005), petrology (e.g. Chang et al., 2002), seismology (e.g. Kohler et al., 2009), GIS (e.g. Bacao et al., 2005) and remote sensing (e.g. Ehsani & Quiel, 2009), geomorphology (e.g. Bue & Stepinski, 2006), volcanology (e.g. Ersoy et al., 2007), and marine geology (e.g. Ferentinou et al., 2012). SOMs can be used for both continuous and categorical data.
We have conducted a survey of zeolite occurrences in saline-alkaline paleolake deposits on Earth to identify the most prominent zeolite alteration patterns and to characterize the most common authigenic minerals and their paragenetic relationships. We collected the bulk mineral assemblages (from previous and our studies) as identified by X-ray diffraction from zeolitic tuff beds and associated sedimentary beds from thirteen paleolake deposits from the USA, Mexico, Greece, and Tanzania. We applied the Kohonen Self-Organizing Maps (SOM) to look for interesting patterns in the tuff bed mineral assemblages without prescribing any specific interpretation, and for information reduction and classification. Decision Tree (DT) method was applied to characterize these clusters. We were able to define clear class boundaries between fresh glass, non-analcime zeolites, analcime, and K feldspar. The non-analcime zeolites were further grouped into several classes based on mineral type. We also discuss the potential implications for Mars, showing that the mineral assemblages of diagenetic facies identified by SOM and DT can be used to test or validate the orbital, in situ, or modeling results, while the trained SOM provides a robust generalized ability to classify the new mineral assemblage data into the most common diagenetic facies identified in saline-alkaline paleoenvironments that contain zeolites. The study concludes that generalizing the complex geochemical behaviors using unsupervised statistical learning methods can help to identify the most prominent geochemical behaviors.
Hyper-temporal remote sensing data in bare soil period and terrain attributes for digital soil mapping in the Black soil regions of China
2020, Catena
Citation Excerpt :
These processed data could represent some characteristics of the study area in a new form (Kunkel et al., 2011; Dobos et al., 2001). Previous studies show that the combination of terrain factors and RS image data could provide more accurate soil type information (Ehsani and Quiel, 2009; Dobos et al., 2000). Terrain is one of the five major soil-forming factors, and is also one of the most commonly used covariates for predicting soil types and properties, especially for DSM (McBratney et al., 2003).
Remote sensing image data are often used as input in digital soil mapping (DSM). However, it is difficult to distinguish and identify soil types with less difference in reflectance spectral characteristics, because a small amount of input is not enough to provide enough common features. We consider that the hyper-temporal remote sensing data can be used to extract more common features of soil. The accuracy of DSM is improved by using the common features of soil or effective terrain attributes. We took Mingshui County of the Songnen Plain in northeast China as study area, which is known as a Black soil region. STRM DEM, legacy soil data, and 20 scenes Landsat images of bare soil period from 1984 to 2018 (April and May are considered a period of cultivated soil exposure in the study area), were used, with a maximum likelihood method classifier. A digital soil mapping model was constructed based on hyper-temporal data. Results from the study show that the accuracy of mapping with hyper-temporal classification characteristics, with an overall accuracy of 85.18% and a Kappa coefficient of 0.772, is higher than that of mono-temporal classification characteristics, with an average overall accuracy of 64.35% and an average Kappa coefficient of 0.467. After the introduction of relief degree of land surface (RDLS), the overall accuracy and Kappa coefficient of hyper-temporal mapping were 88.22% and 0.818, higher than the accuracy of other terrain factors. The research results signal the advantages of hyper-temporal remote sensing data in DSM, and the common features were able to improve the accuracy of DSM extracted from hyper-temporal data. This paper provided new insight to explain the impact of diverse terrain on DSM of Black soil region, and the mapping of soil type level could be accomplished more easily by the combination of the two characteristics.
Algorithms vs. surveyors: A comparison of automated landform delineations and surveyed topographic positions from soil mapping in an Alpine environment
2017, Geoderma
Landform delineation has long been used in digital soil mapping to infer soil-relevant information. While its potential as an environmental variable in soil parameter modeling has been investigated for various automated landform delineations, little research has been invested into the relationship between the delineation of landforms by algorithms based on digital terrain models (DTM) and the perception of landforms by the soil surveyor during field work. Five Open Source automated landform classification algorithms and a support vector machine classifier based on single terrain parameters are investigated with regard to their ability to replicate topographic position, at two different scales, as described by surveyors for soil profile sites in the Alpine environment of South Tyrol. We also analyse how the variation of parameters and cell size affects the distribution of the computed landforms. While a clear trend regarding grid cell size and window size can be observed with regard to the difference between macro and meso scale topographic positions, the overall classification accuracy regarding the different topographic position classes was less promising. Although some automated classifications partly resemble the surveyor's classification, a considerable number of issues remain to be investigated in order to explain the lack of reproducibility of surveyor position, some of which are linked to the Alpine environment of the study area. These include the dominance of the backslope position, the objectivity of the surveyor in rugged terrain under forest cover, and the fuzzy nature of classifying topographic position, especially in steep terrain. By applying a forward stepwise feature selection procedure for a model based on single terrain parameters, we show that at macro scale a regional terrain parameter (topographic wetness index) and curvatures at a coarse DTM resolution of 50 m are the most influential in distinguishing topographic position, whereas at meso scale it is the topographic position index (TPI) with a search radius of just 70 m combined with slope gradient. This study is an important first step towards consolidating topographic perception during field survey and digital terrain analysis, which, at least in Alpine terrain, still requires more investigation.
Hyper-temporal remote sensing for digital soil mapping: Characterizing soil-vegetation response to climatic variability
2017, Geoderma
Citation Excerpt :
Terrain attributes and spectral indices often exhibit considerable cross correlation due to the strong interrelationships between factors in the soil environment. Nonetheless, previous studies have shown that the combination of both terrain and RS data produces the most accurate classifications of soils in complex geomorphic landscapes (Dobos et al., 2000; Ehsani and Quiel, 2009; Martin and Franklin, 2005; Taramelli and Melelli, 2009), indicating that terrain and spectral indices each possess some unique amount of explanatory power. Future research is needed to examine the added benefit of incorporating both hyper-temporal RS and terrain attributes into soil prediction models.
Indices derived from remotely-sensed imagery are commonly used to predict soil properties with digital soil mapping (DSM) techniques. The use of images from single dates or a small number of dates is most common for DSM; however, selection of the appropriate images is complicated by temporal variability in land surface spectral properties. We argue that hyper-temporal remote sensing (RS) (i.e., hundreds of images) can provide novel insights into soil spatial variability by quantifying the temporal response of land surface spectral properties. This temporal response provides a spectral ‘fingerprint’ of the soil-vegetation relationship which is directly related to a range of soil properties. To evaluate the hyper-temporal RS approach, this study first reviewed and synthesized, within the context of temporal variability, previous research that has used RS imagery for DSM. Results from this analysis support the notion that temporal variability in RS spectra, as driven by soil and climate feedbacks, is an important predictor of soil variability. To explicitly evaluate this idea and to demonstrate the utility of the hyper-temporal approach, we present a case study in a semiarid landscape of southeastern Arizona, USA. In this case study surface soil texture and coarse fragment classes were predicted using a 28 year time series of Landsat TM derived normalized difference vegetation index (NDVI) and modeled using support vector machine (SVM) classification, and results evaluated relative to more traditional RS approaches (e.g., mono-, bi-, and multi-temporal). Results from the case study show that SVM classification using hyper-temporal RS imagery was more effective in modeling both soil texture and coarse fragment classes relative to mono-, bi-, or multi-temporal RS, with classification accuracies of 67% and 62%, respectively. Short-term transitions between wet and dry periods (i.e., < 6 months) were the dominant drivers of vegetation spectral variability and corresponded to the general timing of significant RS scenes within in our SVM models, confirming the importance of spectral variability in predicting soil texture and coarse fragment classes. Results from the case study demonstrate the efficacy of the hyper-temporal RS approach in predicting soil properties and highlights how hyper-temporal RS can improve current methods of soil mapping efforts through its ability to characterize subtle changes in RS spectra relating to variation in soil properties.
Uncoupling the complexity of forest soil variation: Influence of terrain indices, spectral indices, and spatial variability
2016, Forest Ecology and Management
Citation Excerpt :
While considerable shared variance can exist between terrain and spectral indices, large portions of modeled variance is also unique to each data type. Previous studies also confirm this where the combination of both terrain and remotely sensed spectral data has been shown to produce the most accurate classifications of soils in complex geomorphic landscapes (Dobos et al., 2000; Ehsani and Quiel, 2009; Martin and Franklin, 2005; Miller et al., 2015; Taramelli and Melelli, 2009). For example, Dobos et al. (2000) found that AVHRR data accurately delineated soils formed on different parent materials, i.e., sandy regions, clayey fluvial deposits, loess areas; however, within each parent material type, different soil classes were found depending upon differences in elevation.
Growing concern over climate and management induced changes to soil nutrient status has prompted interest in understanding the spatial distribution of forest soil properties. Recent advancements in remotely sensed geospatial technologies are providing an increasing array of data sources (e.g., LiDAR, hyper-spectral imagery) relating to forest biophysical properties. While these data sources have the potential to improve spatial predictions of forest soil properties, considerable uncertainty exists regarding which remotely sensed (RS) indices are correlated to soil variability and what underlying pedogenic processes connect them. The main objective of this study was to identify and interpret RS indices that account for soil variability within a 2300 ha forested watershed. Redundancy analysis (RDA) and variation partitioning methods were used to uncouple the complexity of soil–environmental relationships. Thirty-two soil pedons were described, sampled, characterized and analyzed for 22 soil properties within the 0–50 cm soil depth interval. A suite of environmental covariates, comprised of LiDAR derived canopy metrics, land-surface and hydrologic terrain indices, broad-band remotely sensed indices (GeoEye-1), and narrow-band hyper-spectral indices (HyMap), were used as covariates in our RDA models. Principal coordinates of neighbor matrices (PCNM) was used to disentangle the contribution of spatial autocorrelation among sampling locations to the total variance explained by our RDA models. Two groups of soil properties were identified using discriminate analysis of principal components, with each soil property group (SPG) relating to different pedogenic processes occurring with the watershed (SPG1: organic matter-metal cycling; SPG2: base-cation cycling). Our results show there was a relatively strong correspondence between soil properties and terrain/spectral indices; with 61% and 81% of the total variance explained by the first four RDA axes for SPG1 and SPG2, respectively. Variation partitioning analysis revealed that both SPG1 and SPG2 were most strongly related to terrain and canopy indices; although spectral indices were also important, especially for SGP2. Variation in the types of RS indices correlated to each SPG results from variation in the degree to which each environmental covariate relates to the pedogenic process(es) driving soil property development. The approach used in this study can help improve our understanding of soil spatial variability through identifying the most significant environmental covariates related to soil variation. Given the growing demands placed upon forest ecosystems (e.g., timber, recreation, carbon sequestration), improved knowledge of soil variability and the factors that affect the soil resource is essential to facilitate more effective forest management.

View all citing articles on Scopus

¹: Postal address: Brinellvägen 34, 10044 Stockholm, Sweden.

View full text

A semi-automatic method for analysis of landscape elements using Shuttle Radar Topography Mission and Landsat ETM+ data

Abstract

Introduction

Section snippets

Study area

Data

Optimal self-organizing map

Conclusion

Acknowledgements

Geomorphology

Computers and Geosciences

Landscape and Urban Planning

Landscape Urban Planning

Remote Sensing of Environment

Fuzzy Sets and Systems

Computers and Geosciences

Computers and Geosciences

Geoderma

International Journal of Applied Earth Observation and Geoinformation

Remote Sensing of Environment

Analytica Chimica Acta

Journal of Environmental Management

ISPRS (International Society for Photogrammetry and Remote Sensing) Journal of Photogrammetry and Remote Sensing

Progress in Oceanography

Remote Sensing of Environment

A quantitative method for delineating regions: an example for the western Corn Belt plains ecoregion of the USA

Environmental Management