A new multiscale approach for monitoring vegetation using remote sensing-based indicators in laboratory, field, and landscape

Remote sensing is an important tool for studying patterns in surface processes on different spatiotemporal scales. However, differences in the spatiospectral and temporal resolution of remote sensing data as well as sensor-specific surveying characteristics very often hinder comparative analyses and effective up- and downscaling analyses. This paper presents a new methodical framework for combining hyperspectral remote sensing data on different spatial and temporal scales. We demonstrate the potential of using the “One Sensor at Different Scales” (OSADIS) approach for the laboratory (plot), field (local), and landscape (regional) scales. By implementing the OSADIS approach, we are able (1) to develop suitable stress-controlled vegetation indices for selected variables such as the Leaf Area Index (LAI), chlorophyll, photosynthesis, water content, nutrient content, etc. over a whole vegetation period. Focused laboratory monitoring can help to document additive and counteractive factors and processes of the vegetation and to correctly interpret their spectral response; (2) to transfer the models obtained to the landscape level; (3) to record imaging hyperspectral information on different spatial scales, achieving a true comparison of the structure and process results; (4) to minimize existing errors from geometrical, spectral, and temporal effects due to sensor- and time-specific differences; and (5) to carry out a realistic top- and downscaling by determining scale-dependent correction factors and transfer functions. The first results of OSADIS experiments are provided by controlled whole vegetation experiments on barley under water stress on the plot scale to model LAI using the vegetation indices Normalized Difference Vegetation Index (NDVI) and green NDVI (GNDVI). The regression model ascertained from imaging hyperspectral AISA-EAGLE/HAWK (DUAL) data was used to model LAI. This was done by using the vegetation index GNDVI with an R ² of 0.83, which was transferred to airborne hyperspectral data on the local and regional scales. For this purpose, hyperspectral imagery was collected at three altitudes over a land cover gradient of 25 km within a timeframe of a few minutes, yielding a spatial resolution from 1 to 3 m. For all recorded spatial scales, both the LAI and the NDVI were determined. The spatial properties of LAI and NDVI of all recorded hyperspectral images were compared using semivariance metrics derived from the variogram. The first results show spatial differences in the heterogeneity of LAI and NDVI from 1 to 3 m with the recorded hyperspectral data. That means that differently recorded data on different scales might not sufficiently maintain the spatial properties of high spatial resolution hyperspectral images.     

Monitoring and identification of spatiotemporal landscape changes in multiple remote sensing images by using a stratified conditional Latin hypercube sampling approach and geostatistical simulation

This study develops a stratified conditional Latin hypercube sampling (scLHS) approach for multiple, remotely sensed, normalized difference vegetation index (NDVI) images. The objective is to sample, monitor, and delineate spatiotemporal landscape changes, including spatial heterogeneity and variability, in a given area. The scLHS approach, which is based on the variance quadtree technique (VQT) and the conditional Latin hypercube sampling (cLHS) method, selects samples in order to delineate landscape changes from multiple NDVI images. The images are then mapped for calibration and validation by using sequential Gaussian simulation (SGS) with the scLHS selected samples. Spatial statistical results indicate that in terms of their statistical distribution, spatial distribution, and spatial variation, the statistics and variograms of the scLHS samples resemble those of multiple NDVI images more closely than those of cLHS and VQT samples. Moreover, the accuracy of simulated NDVI images based on SGS with scLHS samples is significantly better than that of simulated NDVI images based on SGS with cLHS samples and VQT samples, respectively. However, the proposed approach efficiently monitors the spatial characteristics of landscape changes, including the statistics, spatial variability, and heterogeneity of NDVI images. In addition, SGS with the scLHS samples effectively reproduces spatial patterns and landscape changes in multiple NDVI images.     

Evaluating Change in Rangeland Condition using Multitemporal AVHRR Data and Geographic Information System Analysis

Coarse-scale, multitemporal satellite image data were evaluated as a tool for detecting variation in vegetation productivity, as a potential indicator of change in rangeland condition in the western U.S. The conterminous U.S. Advanced Very High Resolution Radiometer (AVHRR) biweekly composite data set was employed using the six-year time series 1989–1994. Normalized Difference Vegetation Index (NDVI) image bands for the state of New Mexico were imported into a Geographic Information System (GIS) for analysis with other spatial data sets. Averaged NDVI was calculated for each year, and a series of regression analyses were performed using one year as the baseline. Residuals from the regression line indicated 14 significant areas of NDVI change: two with lower NDVI, and 11 with higher NDVI. Rangeland management changes, cross-country military training activities, and increases in irrigated cropland were among the identified causes of change.     

Remote sensing as a tool for monitoring water quality parameters for Mediterranean Lakes of European Union water framework directive (WFD) and as a system of surveillance of cyanobacterial harmful algae blooms (SCyanoHABs)

Remote sensing has been used from the 1980s to study inland water quality. However, it was not until the beginning of the twenty-first century that CHRIS (an experimental multi-angle sensor with good spectral and spatial resolutions) and MERIS (with good temporal and spectral resolutions) started to acquire imagery with very good resolutions, which allowed to develop a reliable imagery acquisition system so as to consider remote sensing as an inland water management tool. This paper presents the methodology developed, from the field data acquisition with which to build a freshwater spectral library and the study of different atmospheric correction systems for CHRIS mode 2 and MERIS images, to the development of algorithms to determine chlorophyll-a and phycocyanin concentrations and bloom sites. All these algorithms allow determining water eutrophic and ecological states, apart from generating surveillance maps of toxic cyanobacteria with the main objective of Assessment of the Water Quality as it was used for Monitoring Ecological Water Quality in smallest Mediterranean Reservoirs integrated in the Intercalibration Exercise of European Union Water Framework Directive (WFD). We keep on using it to monitor the Ecological Quality Ratio (EQR) in Spain inland water.     

Preliminary investigation of submerged aquatic vegetation mapping using hyperspectral remote sensing

The use of airborne hyperspectral remote sensing imagery for automated mapping of submerged aquatic vegetation (SAV) in the tidal Potomac River was investigated for near to real-time resource assessment and monitoring. Airborne hyperspectral imagery and field spectrometer measurements were obtained in October of 2000. A spectral library database containing selected ground-based and airborne sensor spectra was developed for use in image processing. The spectral library is used to automate the processing of hyperspectral imagery for potential real-time material identification and mapping. Field based spectra were compared to the airborne imagery using the database to identify and map two species of SAV (Myriophyllum spicatum and Vallisneria americana). Overall accuracy of the vegetation maps derived from hyperspectral imagery was determined by comparison to a product that combined aerial photography and field based sampling at the end of the SAV growing season. The algorithms and databases developed in this study will be useful with the current and forthcoming space-based hyperspectral remote sensing systems.     

A comparison of radiometric correction techniques in the evaluation of the relationship between LST and NDVI in Landsat imagery

Atmospheric corrections for multi-temporal optical satellite images are necessary, especially in change detection analyses, such as normalized difference vegetation index (NDVI) rationing. Abrupt change detection analysis using remote-sensing techniques requires radiometric congruity and atmospheric correction to monitor terrestrial surfaces over time. Two atmospheric correction methods were used for this study: relative radiometric normalization and the simplified method for atmospheric correction (SMAC) in the solar spectrum. A multi-temporal data set consisting of two sets of Landsat images from the period between 1991 and 2002 of Penang Island, Malaysia, was used to compare NDVI maps, which were generated using the proposed atmospheric correction methods. Land surface temperature (LST) was retrieved using ATCOR3_T in PCI Geomatica 10.1 image processing software. Linear regression analysis was utilized to analyze the relationship between NDVI and LST. This study reveals that both of the proposed atmospheric correction methods yielded high accuracy through examination of the linear correlation coefficients. To check for the accuracy of the equation obtained through linear regression analysis for every single satellite image, 20 points were randomly chosen. The results showed that the SMAC method yielded a constant value (in terms of error) to predict the NDVI value from linear regression analysis-derived equation. The errors (average) from both proposed atmospheric correction methods were less than 10%.     

Applying Satellite Imagery to Triage Assessment of Ecosystem Health

Considerable evidence documents that certain changes in vegetation and soils result in irreversibly degraded rangeland ecosystems. We used Advanced Very High Resolution Radiometer (AVHRR) imagery to develop calibration patterns of change in the Normalized Difference Vegetation Index (NDVI) over the growing season for selected sites for which we had ground data and historical data characterizing these sites as irreversibly degraded. We used the NDVI curves for these training sites to classify and map the irreversibly degraded rangelands in southern New Mexico. We composited images into four year blocks: 1988–1991, 1989–1992, and 1990–1993. The overlap in pixels classified as irreversibly degraded ranged from 42.6% to 84.3% in year block comparisons. Quantitative data on vegetation composition and cover were collected at 13 sites within a small portion of the study area. Wide coverage reconnaissance of boundaries between vegetation types was also conducted for comparisons with year block maps. The year block 1988–1991 provided the most accurate delineation of degraded areas. The rangelands of southern New Mexico experienced above average precipitation from 1990–1993. The above average precipitation resulted in spatially variable productivity of ephemeral weedy plants on the training sites and degraded rangelands which resulted in much smaller areas classified as irreversibly degraded. We selected imagery for a single year, 1989, which was characterized by the absence of spring annual plant production in order to eliminate the confounding effect of reflectance from annual weeds. That image analysis classified more than 20% of the rangelands as irreversibly degraded because areas with shrub-grass mosaic were included in the degraded classification. The single year image included more than double the area classified as irreversibly degraded by the year blocks. AVHRR imagery can be used to make triage assessments of irreversibly degraded rangeland but such assessment requires understanding productivity patterns and variability across the landscapes of the region and careful selection of the years from which imagery is chosen.     

Pattern of NDVI-based vegetation greening along an altitudinal gradient in the eastern Himalayas and its response to global warming

The eastern Himalayas, especially the Yarlung Zangbo Grand Canyon Nature Reserve (YNR), is a global hotspot of biodiversity because of a wide variety of climatic conditions and elevations ranging from 500 to > 7000 m above sea level (a.s.l.). The mountain ecosystems at different elevations are vulnerable to climate change; however, there has been little research into the patterns of vegetation greening and their response to global warming. The objective of this paper is to examine the pattern of vegetation greening in different altitudinal zones in the YNR and its relationship with vegetation types and climatic factors. Specifically, the inter-annual change of the normalized difference vegetation index (NDVI) and its variation along altitudinal gradient between 1999 and 2013 was investigated using SPOT-VGT NDVI data and ASTER global digital elevation model (GDEM) data. We found that annual NDVI increased by 17.58 % in the YNR from 1999 to 2013, especially in regions dominated by broad-leaved and coniferous forests at lower elevations. The vegetation greening rate decreased significantly as elevation increased, with a threshold elevation of approximately 3000 m. Rising temperature played a dominant role in driving the increase in NDVI, while precipitation has no statistical relationship with changes in NDVI in this region. This study provides useful information to develop an integrated management and conservation plan for climate change adaptation and promote biodiversity conservation in the YNR.     

Spatial–temporal dynamics of NDVI and Chl-a concentration from 1998 to 2009 in the East coastal zone of China: integrating terrestrial and oceanic components

Annual normalized difference vegetation index (NDVI) and chlorophyll-a (Chl-a) concentration are the most important large-scale indicators of terrestrial and oceanic ecosystem net primary productivity. In this paper, the Sea-viewing Wide Field-of-view Sensor level 3 standard mapped image annual products from 1998 to 2009 are used to study the spatial–temporal characters of terrestrial NDVI and oceanic Chl-a concentration on two sides of the coastline of China by using the methods of mean value (M), coefficient of variation (CV), the slope of unary linear regression model (Slope), and the Hurst index (H). In detail, we researched and analyzed the spatial–temporal dynamics, the longitudinal zonality and latitudinal zonality, the direction, intensity, and persistency of historical changes. The results showed that: (1) spatial patterns of M and CV between NDVI and Chl-a concentration from 1998 to 2009 were very different. The dynamic variation of terrestrial NDVI was much mild, while the variation of oceanic Chl-a concentration was relatively much larger; (2) distinct longitudinal zonality was found for Chl-a concentration and NDVI due to their hypersensitivity to the distance to shoreline, and strong latitudinal zonality existed for Chl-a concentration while terrestrial NDVI had a very weak latitudinal zonality; (3) overall, the NDVI showed a slight decreasing trend while the Chl-a concentration showed a significant increasing trend in the past 12 years, and both of them exhibit strong self-similarity and long-range dependence which indicates opposite future trends between land and ocean.     

A Special Vegetation Index for the Weed Detection in Sensor Based Precision Agriculture

Many technologies in precision agriculture (PA) require image analysis and image- processing with weed and background differentiations. The detection of weeds on mulched cropland is one important image-processing task for sensor based precision herbicide applications. The article introduces a special vegetation index, the Difference Index with Red Threshold (DIRT), for the weed detection on mulched croplands. Experimental investigations in weed detection on mulched areas point out that the DIRT performs better than the Normalized Difference Vegetation Index (NDVI). The result of the evaluation with four different decision criteria indicate, that the new DIRT gives the highest reliability in weed/background differentiation on mulched areas. While using the same spectral bands (infrared and red) as the NDVI, the new DIRT is more suitable for weed detection than the other vegetation indices and requires only a small amount of additional calculation power. The new vegetation index DIRT was tested on mulched areas during automatic ratings with a special weed camera system. The test results compare the new DIRT and three other decision criteria: the difference between infrared and red intensity (Diff), the soil-adjusted quotient between infrared and red intensity (Quotient) and the NDVI. The decision criteria were compared with the definition of a worse case decision quality parameter Q, suitable for mulched croplands. Although this new index DIRT needs further testing, the index seems to be a good decision criterion for the weed detection on mulched areas and should also be useful for other image processing applications in precision agriculture. The weed detection hardware and the PC program for the weed image processing were developed with funds from the German Federal Ministry of Education and Research (BMBF).     

Exploring the relationship between vegetation spectra and eco-geo-environmental conditions in karst region, Southwest China

Remote sensing of local environmental conditions is not accessible if substrates are covered with vegetation. This study explored the relationship between vegetation spectra and karst eco-geo-environmental conditions. Hyperspectral remote sensing techniques showed that there were significant differences between spectral features of vegetation mainly distributed in karst and non-karst regions, and combination of 1,300- to 2,500-nm reflectance and 400- to 680-nm first-derivative spectra could delineate karst and non-karst vegetation groups. Canonical correspondence analysis (CCA) successfully assessed to what extent the variation of vegetation spectral features can be explained by associated eco-geo-environmental variables, and it was found that soil moisture and calcium carbonate contents had the most significant effects on vegetation spectral features in karst region. Our study indicates that vegetation spectra is tightly linked to eco-geo-environmental conditions and CCA is an effective means of studying the relationship between vegetation spectral features and eco-geo-environmental variables. Employing a combination of spectral and spatial analysis, it is anticipated that hyperspectral imagery can be used in interpreting or mapping eco-geo-environmental conditions covered with vegetation in karst region.     

Evaluating the difference between the normalized difference vegetation index and net primary productivity as the indicators of vegetation vigor assessment at landscape scale

Both the net primary productivity (NPP) and the normalized difference vegetation index (NDVI) are commonly used as indicators to characterize vegetation vigor, and NDVI has been used as a surrogate estimator of NPP in some cases. To evaluate the reliability of such surrogation, here we examined the quantitative difference between NPP and NDVI in their outcomes of vegetation vigor assessment at a landscape scale. Using Landsat ETM+ data and a process model, the Boreal Ecosystem Productivity Simulator, NPP distribution was mapped at a resolution of 90 m, and total NDVI during the growing season was calculated in Heihe River Basin, Northwest China in 2002. The results from a comparison between the NPP and NDVI classification maps show that there existed a substantial difference in terms of both area and spatial distribution between the assessment outcomes of these two indicators, despite that they are strongly correlated. The degree of difference can be influenced by assessment schemes, as well as the type of vegetation and ecozone. Overall, NDVI is not a good surrogate of NPP as the indicators of vegetation vigor assessment in the study area. Nonetheless, NDVI could serve as a fairish surrogate indicator under the condition that the target region has low vegetation cover and the assessment has relatively coarse classification schemes (i.e., the class number is small). It is suggested that the use of NPP and NDVI should be carefully selected in landscape assessment. Their differences need to be further evaluated across geographic areas and biomes.     

Using NDVI to Assess Vegetative Land Cover Change in Central Puget Sound

We used the Normalized Difference Vegetation Index (NDVI) in the rapidly growing Puget Sound region over three 5-year time blocks between 1986–1999 at three spatial scales in 42 Watershed Administrative Units (WAUs) to assess changes in the amounts and patterns of green vegetation. On average, approximately 20% of the area in each WAU experienced significant NDVI change over each 5-year time block. Cumulative NDVI change over 15 years (summing change over each 5-year time block) was an average of approximately 60% of each WAU, but was as high as 100% in some. At the regional scale, seasonal weather patterns and green-up from logging were the primary drivers of observed increases in NDVI values. At the WAU scale, anthropogenic factors were important drivers of both positive and negative NDVI change. For example, population density was highly correlated with negative NDVI change over 15 years (r = 0.66, P < 0.01), as was road density (r = 0.71, P < 0.01). At the smallest scale (within 3 case study WAUs) land use differences such as preserving versus harvesting forest lands drove vegetation change. We conclude that large areas within most watersheds are continually and heavily impacted by the high levels of human use and development over short time periods. Our results indicate that varying patterns and processes can be detected at multiple scales using changes in NDVIa values.     

Yield and leaf area index estimations for sunflower plants using unmanned aerial vehicle images

Vegetation is commonly monitored to improve efficiency of various agricultural practices. Spatial and temporal changes in plant growth and development can be monitored with the aid of remote sensing techniques employing ground, aerial, and satellite platforms. Unmanned aerial vehicles (UAV) and multi-spectral cameras developed for UAVs have an important potential for agricultural management activities with high-resolution spatial and temporal images. However, UAV images should be assessed based on ground measurements for using these images as a decision-support tool in agriculture. This study was conducted to estimate sunflower leaf area index (LAI) and yield with the aid of Normalized Difference Vegetation Index (NDVI) images generated from raw UAV images. Furthermore, UAV-based NDVI values were compared with NDVI values calculated by using hyper-spectral measurements carried out with a ground-based spectroradiometer. Between July and August of 2017, six flight missions were conducted and spectral measurements were made simultaneously. A significant correlation (R²?=?0.77) was determined between NDVI values that belong to UAV platform and spectroradiometer. Also, regression models developed for sunflower LAI and yield estimation depending UAV-based NDVI have R² values of 0.88 and 0.91, respectively.     

Hyperspectral Characteristics of Canopy Components and Structure for Phenological Assessment of an Invasive Weed

Spectral reflectance values of four canopy components (stems, buds, opening flowers, and postflowers of yellow starthistle (Centaurea solstitialis)) were measured to describe their spectral characteristics. We then physically combined these canopy components to simulate the flowering stage indicated by accumulated flower ratios (AFR) 10%, 40%, 70%, and 90%, respectively. Spectral dissimilarity and spectral angles were calculated to quantitatively identify spectral differences among canopy components and characteristic patterns of these flowering stages. This study demonstrated the ability of hyperspectral data to characterize canopy components, and identify different flowering stages. Stems had a typical spectral profile of green vegetation, which produced a spectral dissimilarity with three reproduction organs (buds, opening flowers, and postflowers). Quantitative differences between simulated flower stages depended on spectral regions and phenological stages examined. Using full-range canopy spectra, the initial flowering stage could be separated from the early peak, peak, and late flowering stages by three spectral regions, i.e. the blue absorption (around 480 nm) and red absorption (around 650 nm) regions and NIR plateau from 730 nm to 950 nm. For airborne CASI data, only the red absorption region and NIR plateau could be used to identify the flowering stages in the field. This study also revealed that the peak flowering stage was more easily recognized than any of the other three stages.     

Mapping urban forest tree species using IKONOS imagery: preliminary results

A stepwise masking system with high-resolution IKONOS imagery was developed to identify and map urban forest tree species/groups in the City of Tampa, Florida, USA. The eight species/groups consist of sand live oak (Quercus geminata), laurel oak (Quercus laurifolia), live oak (Quercus virginiana), magnolia (Magnolia grandiflora), pine (species group), palm (species group), camphor (Cinnamomum camphora), and red maple (Acer rubrum). The system was implemented with soil-adjusted vegetation index (SAVI) threshold, textural information after running a low-pass filter, and brightness threshold of NIR band to separate tree canopies from non-vegetated areas from other vegetation types (e.g., grass/lawn) and to separate the tree canopies into sunlit and shadow areas. A maximum likelihood classifier was used to identify and map forest type and species. After IKONOS imagery was preprocessed, a total of nine spectral features were generated, including four spectral bands, three hue?Cintensity?Csaturation indices, one SAVI, and one texture image. The identified and mapped results were examined with independent ground survey data. The experimental results indicate that when classifying all the eight tree species/ groups with the high-resolution IKONOS image data, the identifying accuracy was very low and could not satisfy a practical application level, and when merging the eight species/groups into four major species/groups, the average accuracy is still low (average accuracy = 73%, overall accuracy = 86%, and ???=?0.76 with sunlit test samples). Such a low accuracy of identifying and mapping the urban tree species/groups is attributable to low spatial resolution IKONOS image data relative to tree crown size, to complex and variable background spectrum impact on crown spectra, and to shadow/shaded impact. The preliminary results imply that to improve the tree species identification accuracy and achieve a practical application level in urban area, multi-temporal (multi-seasonal) or hyperspectral data image data should be considered for use in the future.     

基于无人机高光谱遥感在太湖蓝藻水华监测中的一次应用

采用机载高光谱视频相机,在4个季节对太湖蓝藻进行7次、18个架次的有效拍摄。对拍摄到的高光谱影像进行辐射定标、几何拼接等预处理后,提取不同浓度蓝藻和水草等其他物体的高光谱数据,发现不同浓度的蓝藻光谱在680 nm后表现出较大差异。采用主成分分析（PCA）对高光谱数据降维后,结合k-近邻（kNN）分类算法,可实现对蓝藻的精准定位。定性识别结果经光谱预处理后,采用连续投影算法（SPA）进行特征波段提取,发现蓝藻光谱的季节差异主要表现在450 nm~570 nm和760 nm~910 nm波段。     

基于RS和GIS技术的贵州省植被生态环境监测分析

为阐明贵州省植被生态环境变化的整体状况,基于RS和GIS技术,应用美国国家航空航天局最新的全球植被指数变化研究数据（GIMMS）,通过计算月归一化植被指数（NDVI）变化率,并对研究区一元线性回归模拟,分析了贵州省1982年-2003年的地表植被覆盖。结果表明：22年来,研究区植被覆盖呈增加趋势,表明贵州省植被生态环境向好的方向发展;贵州省平均植被覆盖在春季和秋季呈上升趋势,夏季和冬季呈下降趋势,其中春季对植被覆盖总变化量的贡献最大;植被覆盖程度增减因区域不同而异,变化程度呈增加的区域主要位于贵,ki-I省的中部地区;变化程度呈减小的区域分布在贵州省的四周边缘。     

Analysis of the changes of vegetation coverage of western Beijing mountainous areas using remote sensing and GIS

Mentougou District acts as a crucial component in the ecological buffer in western Beijing mountainous areas, Beijing, China. Using two Landsat MSS/TM images acquired on July 14, 1979 and July 23, 2005, the vegetation coverage of Mentougou District was calculated based on normalized difference vegetation index and spectral mixture analysis (NDVI-SMA) model. Its temporal and spatial changes were analyzed according to digital elevation model (DEM) image, social and economic data. The results showed that the vegetation coverage decreased from 76.4% in 1979 to 72.7% in 2005. Vegetation degradation was probably the result of human disturbance, such as outspreading of resident areas, and coal and stone mining activities, while vegetation restoration might be contributed by the combined effects of both natural processes and ecological construction effort. Vegetation changes were closely related to topographical characteristics. Plants at high altitude were more stable and less degraded than the plants at low altitude, while the plants on steep slope or northwest aspect were more vulnerable to degradation. During the period of 26 years, landscape appeared to become more fragmental, and ecological quality of the land seemed deteriorated sharply in that highly-covered vegetation area has been decreased by 24%.     

Invasive species change detection using artificial neural networks and CASI hyperspectral imagery

For monitoring and controlling the extent and intensity of an invasive species, a direct multi-date image classification method was applied in invasive species (salt cedar) change detection in the study area of Lovelock, Nevada. With multidate Compact Airborne Spectrographic Imager (CASI) hyperspectral data sets, two types of hyperspectral CASI input data and two classifiers have been examined and compared for mapping and monitoring the salt cedar change. The two types of input data are all two-date original CASI bands and 12 principal component images (PCs) derived from the two-date CASI images. The two classifiers are an artificial neural network (ANN) and linear discriminant analysis (LDA). The experimental results indicate that (1) the direct multitemporal image classification method applied in land cover change detection is feasible either with original CASI bands or PCs, but a better accuracy was obtained from the CASI PCA transformed data; (2) with the same inputs of 12 PCs, the ANN outperforms the LDA due to the ANN’s non-linear property and ability of handling data without a prerequisite of a certain distribution of the analysis data.