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.     

Monitoring habitat preserves in southern California using high spatial resolution multispectral imagery

Habitat preserve systems have been established adjacent to the densely populated regions of southern California to support indigenous plant and animal species that are listed as rare, threatened, or endangered. Monitoring the condition of habitat across these broad preserves is necessary to ensure their long-term viability and may be effectively accomplished using remote sensing techniques with high spatial resolution visible and near-infrared (VNIR) multispectral imagery. The utility of 1 m spatial resolution VNIR imagery for detailed change detection and monitoring of Mediterranean-type ecosystems is assessed here. Image acquisition and preprocessing procedures were conducted to ensure that image-detected changes represented real changes and not artifacts. Change classification products with six spectral-based transition classes were generated using multiband image differencing (MID) for three change periods: 1998-1999, 1998-2001, and 1998-2005. Land cover changes relevant to habitat quality monitoring such as human-induced disturbance, fire, vegetation growth/recovery, and drought related vegetation stress were readily detected using the multitemporal VNIR imagery. Suggestions for operational habitat monitoring using image products and mobile geographic information system technologies are provided.     

Predicting field capacity,wilting point,and the other physical properties of soils using hyperspectral reflectance spectroscopy: two different statistical approaches

In this study, we examined the ability of reflectance spectroscopy to predict some of the most important soil parameters for irrigation such as field capacity (FC), wilting point (WP), clay, sand, and silt content. FC and WP were determined for 305 soil samples. In addition to these soil analyses, clay, silt, and sand contents of 145 soil samples were detected. Raw spectral reflectance (raw) of these soil samples, between 350 and 2,500-nm wavelengths, was measured. In addition, first order derivatives of the reflectance (first) were calculated. Two different statistical approaches were used in detecting soil properties from hyperspectral data. Models were evaluated using the correlation of coefficient (r), coefficient of determination (R ²), root mean square error (RMSE), and residual prediction deviation (RPD). In the first method, two appropriate wavelengths were selected for raw reflectance and first derivative separately for each soil property. Selection of wavelengths was carried out based on the highest positive and negative correlations between soil property and raw reflectance or first order derivatives. By means of detected wavelengths, new combinations for each soil property were calculated using rationing, differencing, normalized differencing, and multiple regression techniques. Of these techniques, multiple regression provided the best correlation (P?<?0.01) for selected wavelengths and all soil properties. To estimate FC, WP, clay, sand, and silt, multiple regression equations based on first(2,310)-first(2,360), first(2,310)-first(2,360), first(2,240)-first(1,320), first(2,240)-first(1,330), and raw(2,260)-raw(360) were used. Partial least square regression (PLSR) was performed as the second method. Raw reflectance was a better predictor of WP and FC, whereas first order derivative was a better predictor of clay, sand, and silt content. According to RPD values, statistically excellent predictions were obtained for FC (2.18), and estimations for WP (2.0), clay (1.8), and silt (1.63) were acceptable. However, sand values were poorly predicted (RDP?=?0.63). In conclusion, both of the methods examined here offer quick and inexpensive means of predicting soil properties using spectral reflectance data.     

Restoring habitat corridors in fragmented landscapes using optimization and percolation models

Landscape fragmentation and habitat loss are significant threats to the conservation of biological diversity. Creating and restoring corridors between isolated habitat patches can help mitigate or reverse the impacts of fragmentation. It is important that restoration and protection efforts be undertaken in the most efficient and effective way possible because conservation budgets are often severely limited. We address the question of where restoration should take place to efficiently reconnect habitat with a landscape-spanning corridor. Building upon findings in percolation theory, we develop a shortest-path optimization methodology for assessing the minimum amount of restoration needed to establish such corridors. This methodology is applied to large numbers of simulated fragmented landscapes to generate mean and variance statistics for the amount of restoration needed. The results provide new information about the expected level of resources needed to realize different corridor configurations under different degrees of fragmentation and different characterizations of habitat connectivity (“neighbor rules”). These results are expected to be of interest to conservation planners and managers in the allocation of conservation resources to restoration projects.     

An exploration of the relationships betweenmacroinvertebrate community composition and physical andchemical habitat characteristics in farm dams

Recently, Australian interest in farm dams has focused on rates of harvest of surface waters (runoff), and the impact this has on nearby natural systems. Little research has been directed towards the role of these artificial water bodies in sustaining biological reserves within the wider ecosystem. Macroinvertebrate communities in three farm dams in the Central Tablelands of New South Wales were surveyed, and water quality variables were correlated with species richness and abundance. Community responses to habitat factors including sediment depth, stock use, vegetation and debris were also examined. Communities were described at several taxonomic levels in addition to allocation to trophic groups and primary functional feeding groups.Species richness and abundance of communities were found to vary between dams and between habitat types within dams. The extent of these differences was decreased when communities were described by either trophic status or functional feeding mechanisms. Habitats were influenced by water quality and by physical features of the habitat, with the two factors interacting to define equilibrium conditions. Localised conditions resulted in different macroinvertebrate communities. Physicochemical parameters that correlated most closely with communities included light penetration, chlorophyll-a and conductivity. Habitat factors that were most frequently linked with communities were sediment depth and canopy cover, with localised disturbances related to stock use affecting feeding groups rather than specific taxa.One of the major problems associated with increasing modification of landscapes by agriculture or urbanisation is the fragmentation of undisturbed habitats. Creation of joint aquatic and woodland habitats enhances biodiversity corridors. The recognition of the potential for farm dams as reservoirs of biodiversity and development of management practices that optimise this neglected biodiversity reserve may have much wider benefits biologically, aesthetically and productively.     

Mapping trees outside forests using high-resolution aerial imagery: a comparison of pixel- and object-based classification approaches

Discrete trees and small groups of trees in nonforest settings are considered an essential resource around the world and are collectively referred to as trees outside forests (ToF). ToF provide important functions across the landscape, such as protecting soil and water resources, providing wildlife habitat, and improving farmstead energy efficiency and aesthetics. Despite the significance of ToF, forest and other natural resource inventory programs and geospatial land cover datasets that are available at a national scale do not include comprehensive information regarding ToF in the United States. Additional ground-based data collection and acquisition of specialized imagery to inventory these resources are expensive alternatives. As a potential solution, we identified two remote sensing-based approaches that use free high-resolution aerial imagery from the National Agriculture Imagery Program (NAIP) to map all tree cover in an agriculturally dominant landscape. We compared the results obtained using an unsupervised per-pixel classifier (independent component analysis—[ICA]) and an object-based image analysis (OBIA) procedure in Steele County, Minnesota, USA. Three types of accuracy assessments were used to evaluate how each method performed in terms of: (1) producing a county-level estimate of total tree-covered area, (2) correctly locating tree cover on the ground, and (3) how tree cover patch metrics computed from the classified outputs compared to those delineated by a human photo interpreter. Both approaches were found to be viable for mapping tree cover over a broad spatial extent and could serve to supplement ground-based inventory data. The ICA approach produced an estimate of total tree cover more similar to the photo-interpreted result, but the output from the OBIA method was more realistic in terms of describing the actual observed spatial pattern of tree cover.     

Evaluating climate change effects on water and salt resources in Salt Lake, Turkey using multitemporal SPOT imagery

The main goal of this study is to investigate the dimension of climate change effects in Salt Lake and its vicinity in Turkey using satellite remote sensing data. The first stage of the study includes evaluation of the multitemporal climatic data on the Salt Lake Basin Area, Turkey for a period of 35 years (1970–2005). The changes in mean temperature and precipitation are evaluated for the study area by comparing two periods, 1970–1992 and 1993–2005. In the second stage, the effects of climate changes in the Salt Lake are investigated by evaluating water and salt reserve changes through seasonal and multitemporal SPOT imagery collected in 1987 and 2005. The climatic data and remotely sensed and treated satellite images show that water and salt reserve in Salt Lake has decreased between 1987 and 2005 due to drought and uncontrolled water usage. It is suggested that the use of water supplies, especially underground waters, around the Salt Lake should be controlled and the lake should regularly be monitored by current remote sensing data for an effective management of water and salt resources in the region.     

Detecting new Buffel grass infestations in Australian arid lands: evaluation of methods using high-resolution multispectral imagery and aerial photography

We assess the feasibility of using airborne imagery for Buffel grass detection in Australian arid lands and evaluate four commonly used image classification techniques (visual estimate, manual digitisation, unsupervised classification and normalised difference vegetation index (NDVI) thresholding) for their suitability to this purpose. Colour digital aerial photography captured at approximately 5 cm of ground sample distance (GSD) and four-band (visible–near-infrared) multispectral imagery (25 cm GSD) were acquired (14 February 2012) across overlapping subsets of our study site. In the field, Buffel grass projected cover estimates were collected for quadrates (10 m diameter), which were subsequently used to evaluate the four image classification techniques. Buffel grass was found to be widespread throughout our study site; it was particularly prevalent in riparian land systems and alluvial plains. On hill slopes, Buffel grass was often present in depressions, valleys and crevices of rock outcrops, but the spread appeared to be dependent on soil type and vegetation communities. Visual cover estimates performed best (r ² 0.39), and pixel-based classifiers (unsupervised classification and NDVI thresholding) performed worst (r ² 0.21). Manual digitising consistently underrepresented Buffel grass cover compared with field- and image-based visual cover estimates; we did not find the labours of digitising rewarding. Our recommendation for regional documentation of new infestation of Buffel grass is to acquire ultra-high-resolution aerial photography and have a trained observer score cover against visual standards and use the scored sites to interpolate density across the region.     

Integrated groundwater resource management in Indus Basin using satellite gravimetry and physical modeling tools

Reliable and frequent information on groundwater behavior and dynamics is very important for effective groundwater resource management at appropriate spatial scales. This information is rarely available in developing countries and thus poses a challenge for groundwater managers. The in situ data and groundwater modeling tools are limited in their ability to cover large domains. Remote sensing technology can now be used to continuously collect information on hydrological cycle in a cost-effective way. This study evaluates the effectiveness of a remote sensing integrated physical modeling approach for groundwater management in Indus Basin. The Gravity Recovery and Climate Experiment Satellite (GRACE)-based gravity anomalies from 2003 to 2010 were processed to generate monthly groundwater storage changes using the Variable Infiltration Capacity (VIC) hydrologic model. The groundwater storage is the key parameter of interest for groundwater resource management. The spatial and temporal patterns in groundwater storage (GWS) are useful for devising the appropriate groundwater management strategies. GRACE-estimated GWS information with large-scale coverage is valuable for basin-scale monitoring and decision making. This frequently available information is found useful for the identification of groundwater recharge areas, groundwater storage depletion, and pinpointing of the areas where groundwater sustainability is at risk. The GWS anomalies were found to favorably agree with groundwater model simulations from Visual MODFLOW and in situ data. Mostly, a moderate to severe GWS depletion is observed causing a vulnerable situation to the sustainability of this groundwater resource. For the sustainable groundwater management, the region needs to implement groundwater policies and adopt water conservation techniques.     

Habitat evaluation using suitability index and habitat type diversity: a case study involving a shallow forest stream in central Taiwan

In recent years, the Taiwanese government has strongly promoted the concept of ecological engineering in the hope that doing so will encourage the maintenance of the ecosystem and its integrity. As a result, the riprap spur dike is one of the most commonly used measures for protecting stream banks. Traditionally, a spur dike is used at concave banks to prevent their scouring and/or to increase their stabilization. An additional benefit of deflector structures, like spur dikes, may be to increase the weighted usable area (WUA) for aquatic life survival during periods of increased flow (examples include typhoon, flood, etc.). A two-dimensional river habitat simulation program (River2D) coupled with a developed shallow water habitat type diversity module was used for the case study at a headwater stream in central Taiwan. The habitat suitability index for this study was established using substrate, depth, and velocity from field surveys for the fish family Cyprinidae by prepositioned area electrofisher. The ungauged flood conditions were calculated using digital elevation models within a watershed delineation and hydrological modeling system in accordance with local regulations. Simulated results indicate that the spur dikes currently in use on the stream in this study need be improved from a WUA point of view more effectively handle a flood event.