Accuracy Kappa Research Articles

Application of Full Polarimetric ALOS PALSAR for Land Cover Mapping In Sleman District

The simplest way to interpret polarimetric imagery for land cover classification is to use visualinterpretation methods. The existence of interpretations key as a tool for visual interpretation becomesimportant when different interpreters can produce different results. The quality of the results of theinterpretation of land cover is then determined by the quality of the interpretation tool, in this case, thekey to the interpretation of land cover. The purpose of this study was to make the key to land coverclass interpretation in the Full Polarimetric ALOS PALSAR image, then the interpretation key wasused for reference in making land cover maps and measuring the accuracy of the results of the visualinterpretation. The image used in this study consisted of HH, VV, HV and VH bands. The location ofthe study was in parts of Sleman District. The analysis is done visually by on-screen digitizing onALOS Palsar composite HH + VV HV + VH HH-HV image, which is then interpreted key. The truetest is done by means of the overall accuracy test and Kappa. Visually, ALOS PALSAR imagery isable to distinguish 12 land cover classes in the research area, namely built land, rice fields, mixedgardens, moorlands, salak garden, grass, forest, shrubs, open land, airports, water bodies and lavawith 83% Overall accuracy, and 78% Kappa accuracy.

Individual tree crown delineation and tree species classification with hyperspectral and LiDAR data.

An international data science challenge, called National Ecological Observatory Network—National Institute of Standards and Technology data science evaluation, was set up in autumn 2017 with the goal to improve the use of remote sensing data in ecological applications. The competition was divided into three tasks: (1) individual tree crown (ITC) delineation, for identifying the location and size of individual trees; (2) alignment between field surveyed trees and ITCs delineated on remote sensing data; and (3) tree species classification. In this paper, the methods and results of team Fondazione Edmund Mach (FEM) are presented. The ITC delineation (Task 1 of the challenge) was done using a region growing method applied to a near-infrared band of the hyperspectral images. The optimization of the parameters of the delineation algorithm was done in a supervised way on the basis of the Jaccard score using the training set provided by the organizers. The alignment (Task 2) between the delineated ITCs and the field surveyed trees was done using the Euclidean distance among the position, the height, and the crown radius of the ITCs and the field surveyed trees. The classification (Task 3) was performed using a support vector machine classifier applied to a selection of the hyperspectral bands and the canopy height model. The selection of the bands was done using the sequential forward floating selection method and the Jeffries Matusita distance. The results of the three tasks were very promising: team FEM ranked first in the data science competition in Task 1 and 2, and second in Task 3. The Jaccard score of the delineated crowns was 0.3402, and the results showed that the proposed approach delineated both small and large crowns. The alignment was correctly done for all the test samples. The classification results were good (overall accuracy of 88.1%, kappa accuracy of 75.7%, and mean class accuracy of 61.5%), although the accuracy was biased toward the most represented species.

ANALISIS DAN PREDIKSI PERUBAHAN TUTUPAN LAHAN DI DAS CITARUM HULU

Land cover is one of factors which is important in watershed management. The changes of land cover in a watershed can affect the hydrology abstraction. Land cover of upstream Citarum watershed is potentially changes. Economy, social, population, and natural hazard are factors that affect the change in land cover. The aim of this research were to analyze spatial change of land cover in upstream Citarum watershed period 2006-2014 and predicting future land cover of 2030 as usual and applying a policy to conserve paddy field and forest. Analysis was carried out applying Cellular automata markov chain of land cover spatial model. The result showed that Kappa and total accuracy for image classification were 0.89 and 0.92. Dominant land cover type in upstream Citarum watershed was paddy field of 25.99 – 26.06%. The average of land cover changes approximately < 1% with conversion of paddy field to built up area is the dominant change. Model validation of 2014 predicted land cover was 0.992, while Kappa for optimum iteration of 7 was 0.994. The land cover for period 2006-2030 was change approximately < 1%. The types of land cover that increase in 2030 were built up area and mixed farming of 0.21% and 0.11%, respectively, while plantation forest, moor, paddy field, and bareland were decreasing approximately 0.17, 0.23, 0.62 and 0.02%. The predicted land cover of 2030 under protection of paddy filed and forest scenario was trigger the increasing of mixed farming 0.36%, while moor and bareland were decrease of 0.22 and 0.10%.

Analysis for Mapping of Built-Up Area Using Remotely Sensed Indices – A Case Study of Rajarhat Block in Barasat Sadar Sub-Division in West Bengal (India)

Abstract Present study investigated mapping and monitoring urban land areas from Landsat8 satellite data using remotely sensed indices. The normalized difference built-up index (NDBI), Enhanced Built-Up and Bareness Index (EBBI), Index-based built-up index (IBI), urban index (UI), normalized difference bareness index (NDBaI) were used to extract the built-up area. The NDBI was more effective at discriminating built-up areas and at increasing accuracy (overall accuracy of 76.45 % and kappa accuracy of 57 %) of the built-up density percentage than other remotely sensed indices. Evidence on built-up area change geographically would permit urban planner and decision makers to comprehend and appraise urban growth pattern in regards to land cover dynamics.

Seafloor mapping based on multibeam echosounder bathymetry and backscatter data using Object-Based Image Analysis: a case study from the Rewal site, the Southern Baltic

Abstract Seafloor mapping is a fast developing multidisciplinary branch of oceanology that combines geophysics, geostatistics, sedimentology and ecology. One of its objectives is to isolate distinct seabed features in a repeatable, fast and objective way, taking into consideration multibeam echosounder (MBES) bathymetry and backscatter data. A large-scale acoustic survey was conducted by the Maritime Institute in Gdańsk in 2010 using Reson 8125 MBES. The dataset covered over 20 km2 of a shallow seabed area (depth of up to 22 m) in the Polish Exclusive Economic Zone within the Southern Baltic. Determination of sediments was possible based on ground-truth grab samples acquired during the MBES survey. Four classes of sediments were recognized as muddy sand, very fine sand, fine sand and clay. The backscatter mosaic created using the Angular Variable Gain (AVG) empirical method was the primary contribution to the image processing method used in this study. The use of the Object-Based Image Analysis (OBIA) and the Classification and Regression Trees (CART) classifier makes it possible to isolate the backscatter image with 87.5% overall and 81.0% Kappa accuracy. The obtained results confirm the possibility of creating reliable maps of the seafloor based on MBES measurements. Once developed, the OBIA workflow can be applied to other spatial and temporal scenes.

Potential of Landsat-8 and Sentinel-2A composite for land use land cover analysis

This study proposes the development of a multi-sensor, multi-spectral composite from Landsat-8 and Sentinel-2A imagery referred to as ‘LSC’ for land use land cover (LULC) characterisation and compared with respect to the hyperspectral imagery of the EO1: Hyperion sensor. A three-stage evaluation was implemented based on the similarity observed in the spectral response, supervised classification results and endmember abundance information obtained using linear spectral unmixing. The study was conducted for two areas located around Dhundi and Rohtak in Himachal Pradesh and Haryana, respectively. According to the analysis of the spectral reflectance curves, the spectral response of the LSC is capable of identifying major LULC classes. The kappa accuracy of 0.85 and 0.66 was observed for the classification results from LSC and Hyperion data for Dhundi and Rohtak datasets, respectively. The coefficient of determination was found to be above 0.9 for the LULC classes in both the datasets as compared to Hyperion, indicating a good agreement. Thus, these three-stage results indicated the significant potential of a composite derived from freely available multi-sensor multi-spectral imagery as an alternative to hyperspectral imagery for LULC studies.

HUBUNGAN ANTARA PERUBAHAN TUTUPAN LAHAN TERHADAP TOTAL PENDUDUK YANG DIPENGARUHI OLEH FENOMENA URBANISASI DI BOGOR, JAWA BARAT

Urbanization is the main issue that altered the environmental condition nowadays. Urbanization means that there are changes in suburban areas to fulfill the function needed in the urban area. Nowadays, urbanization occurred due to the high demand of housing area with lower budget and comfortable environment of living condition. This condition was presented in the Bogor city case. Bogor is one of the oldest cities in Indonesia which is located in the southern part of Jakarta. Due to the increase of population in the capital city and increased of the higher price of housing, people started to looked for place to stay outside the city. Bogor located in the strategic location just close enough for people to commute to Jakarta. The transit city transform into commuting city. People works in Jakarta wanted to live in a more comfortable place of living and cheaper in price than the capital city started to see Bogor as an opportunity. Based on the data obtained by the Central Bureau of Statistics Jakarta in 2015, there are 187.777 total people commuted daily from Bogor to Jakarta. This condition also triggered by the better quality of access in and out Bogor. Mass rapid transportation and highway toll gate create more land cover changes potential to fulfill the high demand of housing. Thus, this research aimed to see the effect of highway toll gate in the land use cover change in Bogor city. Landsat Images was used using the time-series method started since 1978 (the official year of Jagorawi Toll gate operation) with the 10 years interval time, 1989, 1999, 2009 and 2016. In determining the land use cover change, NDVI method was used which has been widely applied in detecting the greeneries. The result then evaluated using the supervised classification and validated using the Kappa Accuracy test. The result of this research shows that land use cover change corresponded with the total population in the citizenship census 2009. Total built area in 2009 is 36.20% which increased by 8.46% since 1999, this result suitable with the total population 949.000 in 2009 Citizenship census which increased by 364.000 since 1999. The highest built area detected is 42.15% in 2016 with total of 1.030.720 population and three active Highway toll gate operated.

Land-use/cover change in Coimbatore urban area (Tamil Nadu, India)—a remote sensing and GIS-based study

The purpose of the present study was to explain land-use/cover changes in Coimbatore City Corporation using Landsat ETM+ and Landsat 8 Operational Land Imager (OLI) and Thermal Infrared Sensor (TIRS) data for the period of 2003-2014. Two Landsat images from years 2003 and 2014 were downloaded from USGS Earth Explorer. Maximum likelihood method was used to classify the images into five classes: urban fabric, vegetation, water bodies, agriculture lands, and barren lands. Overall kappa accuracy measure is about to 87.60 and 86.15% for the years 2003 and 2014, respectively. The change detection analysis has been performed for years 2003 and 2014 postclassified images. The results of the study have indicated that Coimbatore City has experienced rapid modifications in LULC, particularly in terms of urban/built-up area. Over the past 11years, urban/built-up areas have increased by 94.5km2, resulting in a significant drop in the area of agricultural land and vegetation cover. It is found that (1) urban areas are increased 200% due to population growth cum rapid economic progress. (2) Vegetation cover decreased 38.76% due to conversion into urban features. (3) Water bodies in area increased to 15.78% due to eradication of encroachment. (4) There is loss of 1.89% of agricultural lands due to demand for construction activities. (5) About 85.24% of barren lands were converted into other uses, particularly 57.33% to urban areas. (6) Urban growth has accelerated towards north-eastern, northern, and eastern parts, where national highways exist. The built-up areas were dropped from 85.32 to 22.28%, within 5-km distance from the city center.

Monitoring of organic matter and soil salinity by using IRS - LissIII satellite data in the Harat plain, of Yazd province

Current study monitored Electerical Conductivity (EC) as soil salinity index and Organic Matter (OM) in the area of Harat in Yazd, Iran, through remote sensing technology with high spatial and spectral resolution. The images were selected from IRS, LISS III satellites between the years 2008 and 2012. After preprocessing and analyzing the images, the relationship between parameters of (EC) and (OM) spectral reflections were determined, and both two-satellite images were classified using maximum likelihood method. Results showed that during the period (2008-2012) organic matter content of all farmlands increased and the area of saline land decreased. This trend showed that agriculture activities help reduction of desertification. Accuracy classification and coefficient kappa obtained for salinity map in 2008 were equal to 82% and 0.73, and in 2012, were equal to 84% and 0.70 respectively. Accuracy of classification and coefficient kappa obtained for Organic matter map in 2008 were equal to 85.5% and 0.76 and in 2012, were equal to 84% and 0.74 respectively. This research indicates that remote sensing data, especially IRS-LissIIIimages, have high efficiency for detection of soil salinity and organic matter changes and natural resources management.

Analysis of Land Cover change Due to Gold Mining in Bombana using Sentinel 1A Radar Data

The discovery of the gold-mine site in Bombana regency since 2008 brings an economic benefit to local society as well as the threat of environmental damage. Environmental damage poses a serious threat considering that mining activities are essentially destructive by altering the landscape and total environmental ecosystem both on land and in coastal waters. To reduce the potential damage to the environment, a regular monitoring of mining areas needs to be performed. In this research, the change of the land cover area in Bombana due to gold mining activity was evaluated using Synthetic Aperture Radar (SAR) data, especially Sentinel-1A data. We processed 10 Sentinel 1A data recorded within 2015 to 2017 that produced high kappa accuracy of 63.6%. During the 3 years monitoring, the open land area gradually increased followed by the increase of the mine-site area and decrease of the vegetation area. The result of the processed data indicated that there was a land cover change in the Bombana area due to gold mining activities. Unfortunately, the absence of sentinel data prior to gold mining activities in Bombana causing land cover changes before and after mining cannot be monitored accurately.

Assessing the Crown Closure of Nypa on UAV Images using Mean-Shift Segmentation Algorithm

&lt;p&gt;Utilization of very high-resolution images becomes a new trend in forest management, particularly in the detection and identification of forest stand variables. This paper describes the use of mean-shift segmentation algorithm on unmanned aerial vehicles (UAV) images to measure crown closure of nypa (Nypa fructicans) and gap. The 27 combinations of the parameter values such as spatial radius (hs), range radius (hr), and minimum region size (M). Gap detection and nypa crown closure measurements were performed using a hybrid between pixel-based (maximum likelihood classifier) and object-based approaches (segmentation). For evaluation of the approach performance, the accuracy assessment was done by comparing object-based classification results (segmentation) and visual interpretation (ground check). The study found that the best combination of segmentation parameter was the combination of hs 10, hr 10 and M 50, with the overall accuracy of 76,6% and kappa accuracy of 55.7%.&lt;/p&gt;

HUBUNGAN ANTARA PERUBAHAN TUTUPAN LAHAN TERHADAP TOTAL PENDUDUK YANG DIPENGARUHI OLEH FENOMENA URBANISASI DI BOGOR, JAWA BARAT

Urbanization is the main issue that altered the environmental condition nowadays. Urbanization means that there are changes in suburban areas to fulfill the function needed in the urban area. Nowadays, urbanization occurred due to the high demand of housing area with lower budget and comfortable environment of living condition. This condition was presented in the Bogor city case. Bogor is one of the oldest cities in Indonesia which is located in the southern part of Jakarta. Due to the increase of population in the capital city and increased of the higher price of housing , people started to looked for place to stay outside the city. Bogor located in the strategic location just close enough for people to commute to Jakarta. The transit city transform into commuting city. People works in Jakarta wanted to live in a more comfortable place of living and cheaper in price than the capital city started to see Bogor as an opportunity. Based on the data obtained by the Central Bureau of Statistics Jakarta in 2015, there are 187.777 total people commuted daily from Bogor to Jakarta. This condition also triggered by the better quality of access in and out Bogor. Mass rapid transportation and highway toll gate create more land cover changes potential to fulfill the high demand of housing. Thus, this research aimed to see the effect of highway toll gate in the land use cover change in Bogor city. Landsat Images was used using the time-series method started since 1978 (the official year of Jagorawi Toll gate operation) with the 10 years interval time, 1989, 1999, 2009 and 2016. In determining the land use cover change, NDVI method was used which has been widely applied in detecting the greeneries. The result then evaluated using the supervised classification and validated using the Kappa Accuracy test. The result of this research shows that land use cover change corresponded with the total population in the citizenship census 2009. Total built area in 2009 is 36.20% which increased by 8.46% since 1999, this result suitable with the total population 949.000 in 2009 Citizenship census which increased by 364.000 since 1999. The highest built area detected is 42.15% in 2016 with total of 1.030.720 population and three active Highway toll gate operated.

Remote Sensing Image Classification Based on Stacked Denoising Autoencoder

Focused on the issue that conventional remote sensing image classification methods have run into the bottlenecks in accuracy, a new remote sensing image classification method inspired by deep learning is proposed, which is based on Stacked Denoising Autoencoder. First, the deep network model is built through the stacked layers of Denoising Autoencoder. Then, with noised input, the unsupervised Greedy layer-wise training algorithm is used to train each layer in turn for more robust expressing, characteristics are obtained in supervised learning by Back Propagation (BP) neural network, and the whole network is optimized by error back propagation. Finally, Gaofen-1 satellite (GF-1) remote sensing data are used for evaluation, and the total accuracy and kappa accuracy reach 95.7% and 0.955, respectively, which are higher than that of the Support Vector Machine and Back Propagation neural network. The experiment results show that the proposed method can effectively improve the accuracy of remote sensing image classification.

Agricultural Expansion and Intensification in the Foothills of Mount Kenya: A Landscape Perspective

This study spatially assesses, quantifies, and visualizes the agricultural expansion and land use intensification in the northwestern foothills of Mount Kenya over the last 30 years: processes triggered by population growth, and, more recently, by large-scale commercial investments. We made use of Google Earth Engine to access the USGS Landsat data archive and to generate cloud-free seasonal composites. These enabled us to accurately differentiate between rainfed and irrigated cropland, which was important for assessing agricultural intensification. We developed three land cover and land use classifications using the random forest classifier, and assessed land cover and land use change by creating cross-tabulation matrices for the intervals from 1987 to 2002, 2002 to 2016, and 1987 to 2016 and calculating the net change. We then applied a landscape mosaic approach to each classification to identify landscape types categorized by land use intensity. We discuss the impacts of landscape changes on natural habitats, biodiversity, and water. Kappa accuracies for the three classifications lay between 78.3% and 82.1%. Our study confirms that rainfed and irrigated cropland expanded at the expense of natural habitats, including protected areas. Agricultural expansion took place mainly in the 1980s and 1990s, whereas agricultural intensification largely happened after 2000. Since then, not only large-scale producers, but also many smallholders have begun to practice irrigated farming. The spatial pattern of agricultural expansion and intensification in the study area is defined by water availability. Agricultural intensification and the expansion of horticulture agribusinesses increase pressure on water. Furthermore, the observed changes have heightened pressure on pasture and idle land due to the decrease in natural and agropastoral landscapes. Conflicts between pastoralists, smallholder farmers, large-scale ranches, and wildlife might further increase, particularly during the dry seasons and in years of extreme drought.

Comparative Performance of Multi-Source Reference Data to Assess the Accuracy of Classified Remotely Sensed Imagery: Example of Landsat 8 OLI Across Kigali City-Rwanda 2015

Accuracy assessment of remote sensed classified images is considered the backbone of remote sensing image processing to be considered credible. However, reference data to perform this task is also a considerable challenge for the remote sensing analyst. This study was carried out over Kigali city using Landsat remotely sensed imagery acquired on July 15, 2015, to compare multi-sourced reference data performance to assess the accuracy of classified Landsat remote sensed imagery. To achieve this objective, GeoEye-1, WorldView-2, Google earth high-resolution image, and GIS layers have been used to verify the accuracy of remote-sensed data classification. In this study, we applied different reference data sources to Landsat 2015 classified images to assess the accuracy. Therefore, results from GEOEYE-1 image as reference data source displayed the total accuracy and kappa coefficient of 98.5% and 0.98 respectively. WorldView-2 MS Image revealed 97.25% of total accuracy and a 0.96 Kappa coefficient agreement. High-resolution rectified images generated using El-Shayal Smart GIS Editor also show its capabilities to assess the accuracy of Landsat remote sensed data whose results were 94% and 0.92%, respectively, for overall accuracy and total Kappa statistics. Furthermore, the remote sensing analyst should not worry about where or how to find reference data to assess image classification so long as they possess GIS shape files. GIS shape files provide good results where the overall accuracy was 92% and a Kappa coefficient of 0.90. Moreover, GIS shape files results showed a slightly lower accuracy because of data properties; it is recommended to check projection before using any spatial data. This paper strongly focused on soft features during ground reference data collection. Test data from GEOEYE-1 images have shown the best thematic accuracy after being overlaid with Kigali 2015 thematic map. All of the referenced data sources, in general, showed the ability to assess remote sensed classified map in the range of 90% to 98.5% for both total accuracies of the map and kappa accuracy.

Evaluating fire severity in Sudanian ecosystems of Burkina Faso using Landsat 8 satellite images

The fire severity of the 2013–2014 fire season within Sudanian ecosystems in Burkina Faso was evaluated from Landsat 8 images using derivatives of the Normalized Burn Ratio algorithm (NBR). The relationship between the image-derived severity and the field observed severity i.e. Composite Burn Index (CBI) was best described by a nonlinear model of the form y = a + b*EXP(CBI *c) (R2 = 0.66). Classification of the image-derived burned area into burn severity classes achieved a classification Kappa accuracy statistic of 0.56. Highly severely burned areas were mapped with the highest accuracy (user's accuracy 77%, producer's accuracy 86%). The severity of the burn varied across phyto-geographical zones, protected status, land cover regimes, and forest management practices. The south Sudanian zone burned with a higher severity (low = 7%, moderate = 16% and high = 13%) than the north Sudanian zone (low = 5%, moderate = 10% and high = 5%). The mean of the highly severely burned areas differed significantly among the forest management practices (P = 0.005). A pair-wise comparison of the severity mean area indicated that the highly burned areas within forests managed for wildlife purposes differed significantly with that of both forests under the joint management (P = 0.006) and those under no management (P = 0.024). Among the management practices, forests jointly managed by the local communities and the government had the highest unburned area and the least highly severely burned areas reflecting the impacts of bottom-up forestry management where the local communities are actively involved in the management.

Robust Hyperspectral Image Classification by Multi-Layer Spatial-Spectral Sparse Representations

Sparse representation (SR)-driven classifiers have been widely adopted for hyperspectral image (HSI) classification, and many algorithms have been presented recently. However, most of the existing methods exploit the single layer hard assignment based on class-wise reconstruction errors on the subspace assumption; moreover, the single-layer SR is biased and less stable due to the high coherence of the training samples. In this paper, motivated by category sparsity, a novel multi-layer spatial-spectral sparse representation (mlSR) framework for HSI classification is proposed. The mlSR assignment framework effectively classifies the test samples based on the adaptive dictionary assembling in a multi-layer manner and intrinsic class-dependent distribution. In the proposed framework, three algorithms, multi-layer SR classification (mlSRC), multi-layer collaborative representation classification (mlCRC) and multi-layer elastic net representation-based classification (mlENRC) for HSI, are developed. All three algorithms can achieve a better SR for the test samples, which benefits HSI classification. Experiments are conducted on three real HSI image datasets. Compared with several state-of-the-art approaches, the increases of overall accuracy (OA), kappa and average accuracy (AA) on the Indian Pines image range from 3.02% to 17.13%, 0.034 to 0.178 and 1.51% to 11.56%, respectively. The improvements in OA, kappa and AA for the University of Pavia are from 1.4% to 21.93%, 0.016 to 0.251 and 0.12% to 22.49%, respectively. Furthermore, the OA, kappa and AA for the Salinas image can be improved from 2.35% to 6.91%, 0.026 to 0.074 and 0.88% to 5.19%, respectively. This demonstrates that the proposed mlSR framework can achieve comparable or better performance than the state-of-the-art classification methods.

MONITORING THE WHEAT, CORN AND COTTON AREAS IN AN EASTERN MEDITERRANEAN AGRICULTURAL BASIN BETWEEN 2007 AND 2013

Abstract. Detecting the seasonal agricultural crop pattern accurately is a vital part of the agricultural planning. In this extent, Cukurova Region that is located in Eastern Mediterranean Region of Turkey was evaluated on agricultural landscape pattern. This region is the most productive agricultural region of Turkey also crop variability and yield are higher than many parts of the world. The main agricultural part of the area is called Lower Seyhan Plane (LSP) and it has been formed by the Seyhan, Ceyhan and Berdan rivers. The purpose of the study was to define the wheat, corn and cotton crop pattern using multi-temporal Landsat satellite images and object based classification approach for 2007 and 2013 cropping years. Three main crop’s areal difference were evaluated and changes were monitored between 2007 and 2013. The accuracy of the classifications were obtained by the spatial kappa statistics. Overall kappa accuracy was derived to be 0.9. Classification results were shown that wheat areas were decreased 35% and corn and cotton areas were increased 49% and 69% respectively. Particularly, government subventions and market demands were impacted cropping pattern in the region significantly. In addition, multi-temporal Landsat images and object based classification were a great combination to define regional agricultural crop pattern with very good accuracy (&gt;90%).

Using unmanned aerial vehicles for high-resolution remote sensing to map invasive Phragmites australis in coastal wetlands

ABSTRACTThe wetland plant species, Phragmites australis, is present on every continent except Antarctica. Both native and non-native subspecies thrive in the USA with the non-natives quickly displacing native wetland plants. Along the Gulf Coast, Phragmites grows in very dense stands, and at heights of greater than 4.6 m, is usually the tallest grass species in a wetland, estuary, and marsh ecosystems. Phragmites is known to alter the ecology of these wetland systems making them less suitable as habitat for many species of flora and fauna. Furthermore, Phragmites presents a navigation hazard to smaller boats by impairing visibility along shorelines and around bends of canals and rivers. Management efforts targeting non-native Phragmites rely heavily on accurately mapping invaded areas. Historically, mapping has been done through walking the perimeter of a stand with a Global Positioning System (GPS) unit, using satellite imagery, or through the use of aerial photography from manned aircraft. These methods are time consuming, are expensive, can have an inadequate resolution, and in some cases are prone to human error. In this work, an Unmanned Aerial System (UAS) was used to capture visible imagery to create a basin-wide distribution map of a large wetland along the US Pearl River delta in southeastern Louisiana. The imagery was collected in the summer and individual images were mosaicked to create a larger map. We then evaluated the use of texture analysis on the mosaics to automatically map the invasive. Specifically, Gabor filters, grey level co-occurrence matrices, segmentation-based fractal texture analysis, and wavelet-based texture analysis were compared for mapping the Phragmites. Our experimental results, conducted using the imagery we collected over four study areas (approximately 2250 ha) along the US Pearl River delta, indicate the proposed texture-based approach yields an average accuracy of 85%, an average kappa accuracy of 70%. These maps have shown to be very useful for resource managers to hasten the eradication efforts of Phragmites.

Cellular automata modeling approaches to forecast urban growth for adana, Turkey: A comparative approach

The aim of this study was to assess the application of cellular automata in urban modeling to give insights into a wide variety of urban phenomena, using the most commonly used urban modeling approaches including: Markov Chain, SLEUTH, Dinamica EGO modelling with the Logistic Regression (LR), Regression Tree (RT) and Artificial Neural Networks (ANN). The effectiveness of these approaches in forecasting the urban growth was assessed in the example of Adana as a fast growing City in Turkey for the year 2023. Different models have their own merits and advantages, the empirical results and findings of various approaches provided a guide for urban sprawl modeling. The accuracy figures to assess the models were derived using Allocation and Disagreement maps together with Kappa statistics. Calibration data were from remotely sensed images recorded in 1967, 1977, 1987, 1998 and 2007. SLEUTH, Markov Chain and RT models resulted in overall Kappa accuracy measures of 75%, 72% and 71% respectively, measured over the past data using hindcasting. LR and ANN yielded the least accurate results with an overall Kappa accuracy of 66%. Different modeling approaches have their own merits. However, the SLEUTH model was the most accurate for handling the variability in the present urban development.