Initial Land Cover Research Articles

Comparing long-term patterns of spread of native and invasive plants in a successional forest.

A fundamental question in invasive plant ecology is whether invasive and native plants have different ecological roles. Differences in functional traits have been explored, but we lack a comparison of the factors affecting the spread of co-occurring natives and invasives. Some have proposed that to succeed, invasives would colonize a wider variety of sites, would disperse farther, or would be better at colonizing sites with more available light and soil nutrients than natives. We examined patterns of spread over 70years in a regenerating forest in Connecticut, USA, where both native and invasive species acted as colonizers. We compared seven invasive and 19 native species in the characteristics of colonized plots, variation in these characteristics, and the importance of site variables for colonization. We found little support for the hypotheses that invasive plants succeed by dispersing farther than native plants or by having a broader range of site tolerances. Colonization by invasives was also not more dependent on light than colonization by natives. Like native understory species, invasive plants spread into closed-canopy forest and species-rich communities despite earlier predictions that these communities would resist invasion. The biggest differences were that soil nitrate and the initial land cover being open field increased the odds of colonization for most invasives but only for some natives. In large part, though, the spread of native and invasive plants was affected by similar factors.

Land cover differentially affects abundance of common and rare birds.

While rare species are vulnerable to global change, large declines in common species (i.e., those with large population sizes, large geographic distributions, and/or that are habitat generalists) also are of conservation concern. Understanding if and how commonness mediates species' responses to global change, including land cover change, can help guide conservation strategies. We explored avian population responses to land cover change along a gradient from common to rare species using avian data from the North American Breeding Bird Survey and land cover data from the National Land Cover Database for the conterminous United States. Specifically, we used generalized linear mixed effects models to ask if species' commonness affected the relationship between land cover and counts, using the initial amount of and change in land cover surrounding each North American Breeding Bird Survey route from 2001 to 2016. We quantified species' commonness as a continuous metric at the national scale using the logarithm (base 10) of each species' total count across all routes in the conterminous United States in 2001. For our focal 15-year period, we found that higher proportions of initial natural land cover favored (i.e., was correlated with higher) counts of rare but not common species. We also found that commonness mediated how change in human land cover, but not natural land cover, was associated with species' counts at the end of the study period. Increases in developed lands did not favor populations of any species. Increases in agriculture and declines in pasture favored populations of common but not rare species. Our findings show a signal of commonness in how species respond to a major dimension of global change. Evaluating how and why commonness mediates species' responses to land cover change can help managers design conservation portfolios that sustain the spectrum of common to rare species.

Integrated Stochastic Life Cycle Assessment and Techno-Economic Analysis for Shrub Willow Production in the Northeastern United States

The refereed literature contains few studies that analyze life cycle assessment (LCA) and techno-economic analysis (TEA) methodologies together for lignocellulosic bioenergy systems, using a stochastic modeling approach. This study seeks to address this gap by developing an integrated framework to quantify the environmental and financial impacts of producing and delivering shrub willow in the Northeastern United States. This study analyses four different scenarios from a combination of two different initial land cover types (grassland, cropland) prior to willow establishment, and two harvesting conditions (leaf-on, leaf-off). Monte Carlo simulations were performed to quantify the uncertainty of the results based on a range of financial, logistical, and biophysical variable input parameters (e.g., land rental rates, transportation distance, biomass yield, etc.). Growing willow biomass on croplands resulted in net negative GHG emissions for both leaf on and leaf off scenarios for the baseline. The GHG emissions were lowest for the leaf-off harvest on cropland (−172.50 kg CO2eq Mg−1); this scenario also had the lowest MSP ($76.41 Mg−1). The baseline grassland scenario with leaf-on harvest, results in the highest net GHG emissions (44.83 kg CO2eq Mg−1) and greatest MSP ($92.97 Mg−1). The results of this analysis provide the bioenergy field and other interested stakeholders with both environmental and financial trade-offs of willow biomass to permit informed decisions about the future expansion of willow fields in the landscape, which have the potential to contribute to GHG reduction targets and conversion into fuels, energy, or bioproducts for carbon sequestration and financial benefits.

Spatial Dynamic Models for Assessing the Impact of Public Policies: The Case of Unified Educational Centers in the Periphery of São Paulo City

Cities continuously evolve and dynamically organize themselves in unbalanced ways and by means of complex processes. Efforts to minimize or solve the problems resulting from spatial inequalities tend to fail when relying on traditional public policies. This work is committed to analyzing the context for implementing public policies and their impacts on the periphery of São Paulo, Brazil. São Paulo is a city characterized by territorial and social heterogeneity and inequality. The materialization of these public policies involves the construction of unified educational centers in peripheral neighborhoods that, in addition to education, offer sports, leisure, and entertainment activities not only to enrolled students but to the wider residents’ community. The adopted methodology was based on cellular automata models driven by remotely sensed images designed to investigate land use and land cover patterns in the surroundings of these educational centers before and after their construction. The achieved results demonstrate that the initial land use and land cover configurations have a great influence on the land use and land cover spatial arrangements after the construction of the educational centers. However, in all the test sites of this research, it was observed that these social infrastructure facilities favored the reproduction of real estate market logic, marked by socially exclusive differentiation and an uneven appreciation of the urban environment.

A Methodology to Generate Integrated Land Cover Data for Land Surface Model by Improving Dempster-Shafer Theory

Land cover type is a key parameter for simulating surface processes in many land surface models (LSMs). Currently, the widely used global remote sensing land cover products cannot meet the requirements of LSMs for classification systems, physical definition, data accuracy, and space-time resolution. Here, a new fusion method was proposed to generate land cover data for LSMs by fusing multi-source remote sensing land cover data, which was based on improving Dempster-Shafer evidence theory with mathematical models and knowledge rules optimization. The new method has the ability to deal with seriously disagreement information, thereby improving the robustness of the theory. The results showed the new method can reduce the disagreement between input data and realized the conversion of multiple land cover classification systems to into a single land cover classification system. China Fusion Land Cover data (CFLC) in 2015 generated by the new method maintained the classification accuracy of the China land use map (CNLULC), which is based on visual image interpretation and further enriched land cover classes of input data. Compared with Geo-Wiki observations in 2015, the overall accuracy for CFLC is higher than other two global land cover data. Compared with the observations, the 0–10 cm soil moisture simulated by the CFLC in Noah–MP LSM during the growing season in 2014 had better performance than that simulated by initial land cover data and MODIS land cover data. Our new method is highly portable and generalizable to generate higher quality land cover data with a specific land cover classification system for LSMs by fusing multiple land cover data, providing a new approach to land cover mapping for LSMs.

Mapping Urban Slum Settlements Using Very High-Resolution Imagery and Land Boundary Data

Accurate mapping of slums is crucial for urban planning and management. This article proposes a machine learning, hierarchical object-based method to map slum settlements using very high-resolution (VHR) imagery and land boundary data to support slum upgrading. The proposed method is tested in Kingston Metropolitan Area, Jamaica. First, the VHR imagery is classified into major land cover classes (i.e., the initial land cover map). Second, the VHR imagery and land boundary layer are used to obtain homogenous neighborhoods (HNs). Third, the initial land cover map is used to derive multiple context, spectral, and texture image features according to the local physical characteristics of slum settlements. Fourth, a machine-learning classifier, classification and regression trees, is used to classify HNs into slum and nonslum settlements using only the effective image features. Finally, reference data collected manually are used to assess the accuracy of the classification. In the training site, an overall accuracy of 0.935 is achieved. The effective image indicators for slum mapping include the building layout, building density, building roof characteristics, and distance from buildings to gullies. The classifier and those features selected from the training site are further used to map slums in two validating sites to assess the transferability of our approach. Overall accuracy of the two validating sites reached 0.928 and 0.929, respectively, suggesting that the features and classification model obtained from one site has the potential to be transferred to other areas in Jamaica and possibly other developing Caribbean countries with similar situation and data availability.

Mapping Annual Urban Change Using Time Series Landsat and NLCD

Annual urban change information is important for an improved understanding of urban dynamics and continuous modeling of urban ecosystem processes. This study examined Landsat-derived Normalized Difference Vegetation Index (NDVI) time series for characterizing annual urban change. To reduce impacts from cloud contamination and missing data, United States Geological Survey (USGS) Landsat Analysis Ready Data were processed to derive annual NDVI layers using a maximum value composite algorithm. National Land Cover Database land cover products from 2001 and 2011 were used as references for generating a decadal urban change mask. Within the decadal urban change mask and using annual NDVI as input, we examined three time-series change detection methods to pinpoint specific year of urban change: (a) minimum-value method, (b) break-point detection, and (c) simple-threshold identification. For accuracy assessment, we divided change pixels into urbanization and urban-intensification pixel groups, defined by initial land cover types. We used Google Earth's High-Resolution Imagery Archive as primary reference data for detailed accuracy assessment. Overall, the urbanization pixel group has good change detection accuracies of above 82% for all three change detection algorithms. The break-point detection method resulted in the highest overall accuracy of 88%. Overall accuracies for urban intensification pixel group were in the range of 35%–76%, depending on choice of change detection algorithm, length of input time-series, and further division of pixel subgroups.

Insights from watershed simulations around the world: Watershed service-based restoration does not significantly enhance streamflow

Increased water yield and baseflow and decreased peak flow are common goals of watershed service programs. However, is the forest management often used in such programs likely to provide these beneficial watershed services? Many watershed service investments such as water funds typically change less than 10% of watershed land cover. We simulate the effects of 10% forest-cover change on water yield, low flow, and high flow in hydrologic models of 29 watersheds around the world. The forest-cover changes considered are: forest restoration from degraded natural lands or agriculture, forest conversion to agriculture, and forest conversion to urban cover. We do not consider grassland restoration by removal of alien tree species from riparian zones, which does increase water yield and low flow. Forest restoration from locally-predominant agricultural land resulted in median loss in annual water yield of 1.4%. Forest restoration reduced low flow and high flow by ∼3%. After forest restoration, low flow increased in ∼25% of cases while high flow and water yield declined in nearly all cases. Development of forest to agriculture or urban cover resulted in a 1–2% median increase in water yield, a 0.25–1% increase in low flow, and a 5–7% increase in high flow. We show that hydrologic responses to forest cover changes are not linearly related to climate, physiography, initial land cover, nor a multitude of watershed characteristics in most cases. These results suggest that enhanced streamflow watershed services anticipated from forest restoration or conservation of 10% or less of a watershed are generally modest.

The Impacts of Native Forests and Forest Plantations on Water Supply in Chile

Over the past 40 years, south-central Chile has experienced important land-use-induced land cover changes, with massive conversion from native forests (NF) to Pinus radiata D.Don and Eucalyptus spp. exotic forest plantations (FP). Several case studies have related this conversion to a reduction in water supply within small catchments (<100 ha). In this work, we explore the impacts of NF and FP on streamflow by using a large-sample catchment dataset recently developed for Chile. We select 25 large forested catchments (>20,000 ha) in south-central Chile (35° S–41° S), analyze their land cover and precipitation spatial distributions, and fit a regression model to quantify the influence of NF, FP, grassland (GRA) and shrubland (SHR) partitions on annual runoff. To assess potential effects of land cover changes on water supply, we use the fitted model (R2 = 0.84) in synthetic experiments where NF, GRA and SHR covers within the catchments are replaced by patches of FP. We show that annual runoff consistently decreases with increments of FP, although the magnitude of the change (ranging from 2.2% to 7.2% mean annual runoff decrease for 10,000 ha increment in FP) depends on several factors, including the initial land cover partition within the basin, the replaced land cover class, the area of the catchment, and the type of catchment (drier or humid). Finally, in the context of the mitigation strategies pledged in the Chilean NDC (Nationally Determined Contributions defined after the Paris Agreement), which include the afforestation of 100,000 ha (mainly native forest) by 2030, we quantify the impacts on water supply due to the afforestation of 100,000 ha with different combinations of NF and FP. We show that annual runoff is highly sensitive to the relative area of FP to NF: ratios of FP to NF areas of 10%, 50% and 90% would lead to 3%, −18% and −40% changes in mean annual runoff, respectively. Our results can be used in the discussion of public policies and decision-making involving forests and land cover changes, as they provide scientifically-based tools to quantify expected impacts on water resources. In particular, this knowledge is relevant for decision making regarding mitigation strategies pledged in the Chilean NDC.

Mapping land cover change in northern Brazil with limited training data

Deforestation in the Amazon has important implications for biodiversity and climate change. However, land cover monitoring in this tropical forest is a challenge because it covers such a large area and the land cover change often occurs quickly, and sometimes cyclically. Here we adapt a method which eliminates the need to collect new training data samples for each update of an existing land cover map. We use the state-of-the-art probabilistic classifier Import Vector Machines and Landsat 8 Operational Land Imager (OLI) scenes of the area surrounding Novo Progresso, northern Brazil, to create an initial land cover map for 2013 with associated classification probabilities. We then conduct spectral change detection between 2013 and 2015 using a pair of Landsat images in order to identify the areas where land cover has changed between the two dates, and then reclassify these areas using a supervised classification algorithm, using pixels from the unchanged areas of the map as training data. In this study, we use the pixels with the highest classification probabilities to train the classifier for 2015 and compare the results to those obtained when pixels are chosen randomly. The use of probabilities in the selection of training samples improves the results compared to a random selection, with the highest overall accuracy achieved when 250 training samples with high probabilities are used. For training sample sizes greater than 1000, the differences in overall accuracy between the two approaches to training sample selection are reduced. The final updated 2015 map has an overall accuracy of 80.1%, compared to an overall accuracy of 82.5% for the 2013 map. The results show that this probabilistic method has potential to efficiently map the dynamic land cover change in the Amazon with limited training data, although some challenges remain.

Sensitivity assessment and evaluation of a spatially explicit land-use model for Southern Amazonia

Land-use and land cover change (LULCC), in particular in Amazonia has exerted and will exert crucial influence on global climate and environmental change. Many models were applied to reproduce observed LULCC and explore possible future conversion trends. Results thus far have shown that LULCC modeling, especially in a regional context in Amazonia, needs further research in order to assess the change trajectories that were observed since the end of the 20th century in a complete and cogent way. The lack of modeling results that reproduce observed LULCC dynamics is mostly based upon uncertainties that arise when employing different sets of initial land use data, model input data (drivers), and methods to estimate parameter weights. Also uncertainties in regard to model structure and, thus different representations of modeled processes, have to be taken into account. We therefore chose the well-established dynamic, spatially explicit, integrated LULCC modeling framework, LandSHIFT, to investigate the effect of (1) different initial land-cover products, (2) input variables derived from the most commonly utilized databases and (3) the variety of model parameter weights for suitability analysis resulting from different methods used for model parameterization, on modeling results. We then analyzed the resulting model output in order to determine the ability of the model to capture observed LULCC with respect to the chosen combination of input and methods. We measured the predictive performance of the land-use modeling framework by calculating model efficiency as well as Fuzzy Kappa coefficient. The two Brazilian federal states Mato Grosso and Pará were chosen as focus of this study because they are characterized by highly dynamic LULCC processes as well as large areas of intact natural vegetation that are threatened to be destroyed due to agricultural and pasture expansion. Our findings show that a high degree of uncertainty regarding LULCC can be expected, depending on the choice of initial land cover product, input variable source, and method used to estimate parameter weights.

Land Cover Classification with GF-3 Polarimetric Synthetic Aperture Radar Data by Random Forest Classifier and Fast Super-Pixel Segmentation.

Chinese Gaofen-3 (GF-3), a vital satellite for high-resolution earth observation, was the first C-band polarimetric synthetic aperture radar (SAR) launched in China with a resolution of up to one meter. Polarimetric SAR can obtain the complete physical scattering mechanisms of targets, thereby having the potential to differentiate objects. In this paper, several classification methods are briefly summarized and the types of features that should be chosen during classification are discussed. A pre-classification step is introduced to reduce the workload of precise labeling. The Random Forest classifier, which performs well for many other classification tasks, is used for the initial land cover classification. Then, based on a polarimetric constant false-alarm rate (CFAR) edge detector, a fast super-pixel generation method for polarimetric SAR image is proposed, which does not require the adjustment of parameters in advance. Following that, majority vote is conducted on the initial classification result based on the super-pixels, so that the classification result can be optimized to better meet the mapping requirements. The experimental results based on GF-3 polarimetric SAR data verify the effectiveness of proposed procedure and demonstrate that GF-3 data has excellent performance in land cover classification.

Object-based land-cover change detection applied to Brazilian seasonal savannahs using geostatistical features

ABSTRACTA new method for remote-sensing land-use/land-cover (LULC) change detection is proposed to eliminate the effects of forest phenology on classification results. This method is insensitive to spectral changes caused by vegetation seasonality and uses an object-based approach to extract geostatistical features from bitemporal Landsat TM (Thematic Mapper) images. We first create image objects by multiresolution segmentation to extract geostatistical features (semivariogram parameters and indices) and spectral information (average values) from NDVI (normalized difference vegetation index), acquired in the wet and dry seasons, as input data to train a Support Vector Machine algorithm. We also used the image difference traditional change-detection method to validate the effectiveness of the proposed method. We used two classes: (1) LULC change class and (2) seasonal change class. Using the most geostatistical features, the change detection results are considerably improved compared with the spectral features and image differencing technique. The highest accuracy was achieved by the sill (σ2 overall variability) semivariogram parameter (95%) and the AFM (area first lag–first maximum) semivariogram index (88.33%), which were not affected by vegetation seasonality. The results indicate that the geostatistical context makes possible the use of bitemporal NDVI images to address the challenge of accurately detecting LULC changes in Brazilian seasonal savannahs, disregarding changes caused by phenological differences, without using a dense time series of remote-sensing images. The challenge of extracting accurate semivariogram curves from objects of long and narrow shapes requires further study, along with the relationship between the scale of segmentation and image spatial resolution, including the type of change and the initial land-cover class.

Diverse multi-decadal changes in streamflow within a rapidly urbanizing region

The impact of urbanization on streamflow depends on a variety of factors (e.g., climate, initial land cover, inter-basin transfers, water withdrawals, wastewater effluent, etc.). The purpose of this study is to examine trends in streamflow from 1986 to 2015 in a range of watersheds within the rapidly urbanizing Atlanta, GA metropolitan area. This study compares eight watersheds over three decades, while minimizing the influence of inter-annual precipitation variability. Population and land-cover data were used to analyze changes over approximately twenty years within the watersheds. Precipitation totals for the watersheds were estimated using precipitation totals at nearby weather stations. Multiple streamflow variables, such as annual streamflow, frequencies of high-flow days (HFDs), flashiness, and precipitation-adjusted streamflow, for the eight streams were calculated using daily streamflow data. Variables were tested for significant trends from 1986 to 2015 and significant differences between 1986–2000 and 2001–2015. Flashiness increased for all streams without municipal water withdrawals, and the four watersheds with the largest increase in developed land had significant increases in flashiness. Significant positive trends in precipitation-adjusted mean annual streamflow and HFDs occurred for the two watersheds (Big Creek and Suwanee Creek) that experienced the largest increases in development, and these were the only watersheds that went from majority forest land in 1986 to majority developed land in 2015. With a disproportionate increase in HFD occurrence during summer, Big Creek and Suwannee Creek also had a reduction in intra-annual variability of HFD occurrence. Watersheds that were already substantially developed at the beginning of the period and did not have wastewater discharge had declining streamflow. The most urbanized watershed (Peachtree Creek) had a significant decrease in streamflow, and a possible cause of the decrease was increasing groundwater infiltration into sewers. The impacts of urbanization on streamflow within the metropolitan area have undoubtedly been felt by a wide of range of communities.

A land cover change detection and classification protocol for updating Alaska NLCD 2001 to 2011

Monitoring and mapping land cover changes are important ways to support evaluation of the status and transition of ecosystems. The Alaska National Land Cover Database (NLCD) 2001 was the first 30-m resolution baseline land cover product of the entire state derived from circa 2001 Landsat imagery and geospatial ancillary data. We developed a comprehensive approach named AKUP11 to update Alaska NLCD from 2001 to 2011 and provide a 10-year cyclical update of the state's land cover and land cover changes. Our method is designed to characterize the main land cover changes associated with different drivers, including the conversion of forests to shrub and grassland primarily as a result of wildland fire and forest harvest, the vegetation successional processes after disturbance, and changes of surface water extent and glacier ice/snow associated with weather and climate changes. For natural vegetated areas, a component named AKUP11-VEG was developed for updating the land cover that involves four major steps: 1) identify the disturbed and successional areas using Landsat images and ancillary datasets; 2) update the land cover status for these areas using a SKILL model (System of Knowledge-based Integrated-trajectory Land cover Labeling); 3) perform decision tree classification; and 4) develop a final land cover and land cover change product through the postprocessing modeling. For water and ice/snow areas, another component named AKUP11-WIS was developed for initial land cover change detection, removal of the terrain shadow effects, and exclusion of ephemeral snow changes using a 3-year MODIS snow extent dataset from 2010 to 2012. The overall approach was tested in three pilot study areas in Alaska, with each area consisting of four Landsat image footprints. The results from the pilot study show that the overall accuracy in detecting change and no-change is 90% and the overall accuracy of the updated land cover label for 2011 is 86%. The method provided a robust, consistent, and efficient means for capturing major disturbance events and updating land cover for Alaska. The method has subsequently been applied to generate the land cover and land cover change products for the entire state of Alaska.

Sensitivity of land use change emission estimates to historical land use and land cover mapping

AbstractThe carbon emissions from land use and land cover change (ELUC) are an important anthropogenic component of the global carbon budget. Yet these emissions have a large uncertainty. Uncertainty in historical land use and land cover change (LULCC) maps and their implementation in global vegetation models is one of the key sources of the spread of ELUC calculated by global vegetation models. In this study, we used the Organizing Carbon and Hydrology in Dynamic Ecosystems terrestrial biosphere model to investigate how the different transition rules to define the priority of conversion from natural vegetation to agricultural land affect the historical reconstruction of plant functional types (PFTs) and ELUC. First, we reconstructed 10 sets of historical PFT maps using different transition rules and two methods. Then, we calculated ELUC from these 10 different historical PFT maps and an additional published PFT reconstruction, using the difference between two sets of simulations (with and without LULCC). The total area of forest loss is highly correlated with the total simulated ELUC (R2 = 0.83, P < 0.001) across the reconstructed PFT maps, which indicates that the choice of transition rules is a critical (and often overlooked) decision affecting the simulated ELUC. In addition to the choice of a transition rule, the initial land cover map and the reconstruction method for the reconstruction of historical PFT maps have an important impact on the resultant estimates of ELUC.

Terrain Extraction in Built-Up Areas from Satellite Stereo-Imagery-Derived Surface Models: A Stratified Object-Based Approach

Very high spatial resolution (VHSR) stereo-imagery-derived digital surface models (DSM) can be used to generate digital elevation models (DEM). Filtering algorithms and triangular irregular network (TIN) densification are the most common approaches. Most filter-based techniques focus on image-smoothing. We propose a new approach which makes use of integrated object-based image analysis (OBIA) techniques. An initial land cover classification is followed by stratified land cover ground point sample detection, using object-specific features to enhance the sampling quality. The detected ground point samples serve as the basis for the interpolation of the DEM. A regional uncertainty index (RUI) is calculated to express the quality of the generated DEM in regard to the DSM, based on the number of samples per land cover object. The results of our approach are compared to a high resolution Light Detection and Ranging (LiDAR)-DEM, and a high level of agreement is observed—especially for non-vegetated and scarcely-vegetated areas. Results show that the accuracy of the DEM is highly dependent on the quality of the initial DSM and—in accordance with the RUI—differs between the different land cover classes.

An Iterative Interpolation Deconvolution Algorithm for Superresolution Land Cover Mapping

Superresolution mapping (SRM) is a method to produce a fine-spatial-resolution land cover map from coarse-spatial-resolution remotely sensed imagery. A popular approach for SRM is a two-step algorithm, which first increases the spatial resolution of coarse fraction images by interpolation and then determines class labels of fine-resolution pixels using the maximum a posteriori (MAP) principle. By constructing a new image formation process that establishes the relationship between the observed coarse-resolution fraction images and the latent fine-resolution land cover map, it is found that the MAP principle only matches with area-to-point interpolation algorithms and should be replaced by deconvolution if an area-to-area interpolation algorithm is to be applied. A novel iterative interpolation deconvolution (IID) SRM algorithm is proposed. The IID algorithm first interpolates coarse-resolution fraction images with an area-to-area interpolation algorithm and produces an initial fine-resolution land cover map by deconvolution. The fine-spatial-resolution land cover map is then updated by reconvolution, back-projection, and deconvolution iteratively until the final result is produced. The IID algorithm was evaluated with simulated shapes, simulated multispectral images, and degraded Landsat images, including comparison against three widely used SRM algorithms: pixel swapping, bilinear interpolation, and Hopfield neural network. Results show that the IID algorithm can reduce the impact of fraction errors and can preserve the patch continuity and the patch boundary smoothness simultaneously. Moreover, the IID algorithm produced fine-resolution land cover maps with higher accuracies than those produced by other SRM algorithms.

Improving Seasonal Land Cover Maps of Poyang Lake Area in China by Taking into Account Logical Transitions

Land cover maps are fundamental materials for resource management and change detection. Remote sensing technology is crucial for fast mapping with low cost. However, besides the inherent classification errors in the land cover products, numerous illogical transitions exist between the neighboring time points. In this study, we introduce a series of logical codes for all the land cover types according to the ecological rules in the study area. The codes represent the transformational logicality of species between different seasons. The classification performance and the codes for all the seasons are imposed on the initial land cover maps which have been produced independently by the conventional hierarchical strategy. We exploit the proposed modified hierarchical mapping strategy to map the land cover of Poyang Lake Basin area, Middle China. The illogical transitions between neighboring seasons and the accuracies based on the labeled samples are calculated for both the initial and modified strategies. The number of illogical pixels have been reduced by 13%–35% for different seasons and the average accuracy has been improved by 9.7% for the specific land cover maps. The accuracy of land cover changes has also presented great improvement of the proposed strategy. The experimental results have suggested the scheme is effective.

An examination of historical and future land use changes in Uganda using change detection methods and agent-based modelling

We analyse historical land use/land cover changes beginning from 1996 to 2013 and apply an agent-based model to simulate potential agricultural land use change scenarios in Uganda. The model incorporates farmers’ decision-making processes into biophysical and socioeconomic factors and uses these to analyse the effect of farmers’ decisions on agricultural land use changes. Geographic information system tools are employed to build spatial relations between farmers and land cover systems. Satellite images are used to represent the initial land cover conditions and serve as observed land cover datasets to calibrate the simulated results. Significant agricultural and grassland cover and urban land uses are experienced in 72 and 36% of the regions, respectively, while wetland land uses increased significantly in 82% of the regions. On the other hand, 91% of the regions experience reductions in forest cover except for Teso region which reports gains of 62% in forest cover. Acholi is the only region (extreme outlier) that reports dramatic gains in wetlands of over 880%. The results of the simulation model are promising, and the model was successful at representing historical and future scenarios of agricultural land use patterns at a national level.