Predicting land cover using GIS, Bayesian and evolutionary algorithm methods

Modelling land cover change from existing land cover maps is a vital requirement for anyone wishing to understand how the landscape may change in the future. In order to test any land cover change model, existing data must be used. However, often it is not known which data should be applied to the problem, or whether relationships exist within and between complex datasets. Here we have developed and tested a model that applied evolutionary processes to Bayesian networks. The model was developed and tested on a dataset containing land cover information and environmental data, in order to show that decisions about which datasets should be used could be made automatically. Bayesian networks are amenable to evolutionary methods as they can be easily described using a binary string to which crossover and mutation operations can be applied. The method, developed to allow comparison with standard Bayesian network development software, was proved capable of carrying out a rapid and effective search of the space of possible networks in order to find an optimal or near-optimal solution for the selection of datasets that have causal links with one another. Comparison of land cover mapping in the North-East of Scotland was made with a commercial Bayesian software package, with the evolutionary method being shown to provide greater flexibility in its ability to adapt to incorporate/utilise available evidence/knowledge and develop effective and accurate network structures, at the cost of requiring additional computer programming skills. The dataset used to develop the models included GIS-based data taken from the Land Cover for Scotland 1988 (LCS88), Land Capability for Forestry (LCF), Land Capability for Agriculture (LCA), the soil map of Scotland and additional climatic variables.     

The impact of land use and land cover changes on land surface temperature in a karst area of China

Satellite images have been used extensively to study temporal changes in land use and land cover (LULC) in China. However, few studies have been conducted in the karst areas despite the large area and population involved and the fragile ecosystem. In this study, LULC changes were examined in part of Guizhou Province of southern China from 1991 to 2001 based on Landsat Thematic Mapper (TM) images of November 7, 1991, December 5, 1994, and December 19, 2001. Land surface temperature (LST) and normalized difference vegetation index (NDVI) were computed based on LULC types. The results show that agricultural land decreased, while urban areas expanded dramatically, and forest land increased slightly. Barren land increased from 1991 to 1994, and then decreased from 1994 to 2001. These changes in LULC widened the temperature difference between the urban and the rural areas. The change in LST was mainly associated with changes in construction materials in the urban area and in vegetation abundance both in the urban and rural areas. Vegetation had a dual function in the temperatures of different LULC types. While it could ease the warming trend in the urban or built-up areas, it helped to keep other lands warmer in the cold weather. The study also reveals that due to the government's efforts on reforestation, rural ecosystems in some of the study area were being restored. The time required for the karst ecosystem to recover was shorter than previously thought.     

Lakes,Wetlands, and Streams as Predictors of Land Use/Cover Distribution

The importance of the surrounding landscape to aquatic ecosystems has been well established. Most research linking aquatic ecosystems to landscapes has focused on the one-way effect of land on water. However, to understand fully the complex interactions between aquatic and terrestrial ecosystems, aquatic ecosystems must be seen not only as receptors of human modification of the landscape, but also as potential drivers of these modifications. We hypothesized that the presence of aquatic ecosystems influences the spatial distribution of human land use/cover of the nearby landscape (≤1 km) and that this influence has changed through time from the 1930s to the 1990s. To test this hypothesis, we compared the distribution of residential, agricultural, and forested land use/cover around aquatic ecosystems (lakes, wetlands, and streams) to the overall regional land use/cover proportion in an area in southeast Michigan, USA; we also compared the distribution of land use/cover around county roads/highway and towns (known determinants of many land use/cover patterns) to the regional proportion. We found that lakes, wetlands, and streams were strongly associated with the distribution of land use/cover, that each ecosystem type showed different patterns, and that the magnitude of the association was at least as strong as the association with human features. We also found that the area closest to aquatic ecosystems (<500 m) was more strongly associated with land use/cover distribution than areas further away. Finally, we found that the strength of the association between aquatic ecosystems and land use/cover increased from 1938 to 1995, although the overall patterns were similar through time. Our results show that a more complete understanding is needed of the role of aquatic ecosystems on the distribution of land use/cover.     

Effects of climate and land use changes on groundwater resources in coastal aquifers

To estimate the freshwater loss in coastal aquifers due to salinisation, a numerical model based on the sharp interface assumption has been introduced. The developed methodology will be useful in areas where limited hydrological data are available. This model will elaborate on the changes in fresh groundwater loss with respect to climate change, land use pattern and hydrologic soil condition. The aridity index has been introduced to represent the variations in precipitation and temperature. The interesting finding is that the deforestation leads to increase groundwater recharge in arid areas, because deforestation leads to reduce evapotranspiration even though it favors runoff. The combined climate and land use scenarios show that when the aridity index is less than 60, the agricultural lands give higher groundwater recharge than other land use patterns for all hydrologic soil conditions. The calculated recharge was then used to estimate the freshwater-saltwater interface and percentage of freshwater loss due to salinity intrusion. We found that in arid areas, the fresh groundwater loss increases as the percentage of forest cover increases. The combined effects of deforestation and aridity index on fresh groundwater loss show that deforestation causes an increase in the recharge and existing fresh groundwater resource in areas having low precipitation and high temperature (arid climates).     

Implications of Land Use/Land Cover Change in the Buffer Zone of a National Park in the Tropical Andes

The impacts of land use and land cover (LULC) change in buffer zones surrounding protected ecological reserves have important implications for the management and conservation of these protected areas. This study examines the spatial and temporal patterns of LULC change along the boundary of Rio Abiseo National Park in the Northern Peruvian Andes. Landscape change within four ecological zones was evaluated based on trends expected to occur between 1987 and 2001. Landsat TM and ETM imagery were used to produce LULC classification maps for both years using a hybrid supervised/unsupervised approach. LULC changes were measured using landscape metrics and from-to change maps created by post-classification change detection. Contrary to expectations, tropical upper wet montane forest increased despite being threatened by human-induced fires and cattle grazing of the highland grasslands inside the park. Within the park’s buffer zone, tropical moist forest remnants were fragmented into more numerous and smaller patches between 1987 and 2001; this was in part due to conversion into agricultural land. The methods used in this study provide an effective way to monitor LULC change detection and support the management of protected areas and their surrounding environments.     

Effect of land cover data on nitrous oxide inventory in fen meadows

Landscape representations based on land cover databases differ significantly from the real landscape. Using a land cover database with high uncertainty as input for emission inventory analyses can cause propagation of systematic and random errors. The objective of this study was to analyze how different land cover representations introduce systematic errors into the results of regional N2O emission inventories. Surface areas of grassland, ditches, and ditch banks were estimated for two polders in the Dutch fen meadow landscape using five land cover representations: four commonly used databases and a detailed field map, which most closely resembles the real landscape. These estimated surface areas were scaled up to the Dutch western fen meadow landscape. Based on the estimated surface areas agricultural N2O emissions were estimated using different inventory techniques. All four common databases overestimated the grassland area when compared to the field map. This caused a considerable overestimation of agricultural N2O emissions, ranging from 9% for more detailed databases to 11% for the coarsest database. The effect of poor land cover representation was larger for an inventory method based on a process model than for inventory methods based on simple emission factors. Although the effect of errors in land cover representations may be small compared to the effect of uncertainties in emission factors, these effects are systematic (i.e., cause bias) and do not cancel out by spatial upscaling. Moreover, bias in land cover representations can be quantified or reduced by careful selection of the land cover database.     

梁子湖自然保护区土地利用/土地覆盖动态变化研究

基于梁子湖自然保护区1987年和2004年Landsat-TM影像遥感数据，在Erdas Imagine 8．5图像处理软件的支持下，结合野外实地考察，获得了土地利用现状图，通过对数据的统计分析，研究了保护区近20年来土地利用／土地覆盖的动态变化。研究表明：耕地和水域是保护区内的主要土地利用类型；近20年来，耕地、园地、林地、草地的面积都有减少，其中耕地面积减少了2320．816hm^2，减少比例达到11．78％，是面积减少最多的土地利用类型；居民点、交通、水域用地有所增加，其中池塘面积变化最大，增幅达到213．4％，是面积增加最多的土地利用类型，居民点用地增加了551．18hm^2，增幅达到59．07％，是增长幅度较大的土地利用类型。变化的原因主要是经济的发展、人口数量的增长和旅游业的发展。     

A conceptual framework of agricultural land use planning with BMP for integrated watershed management

Land use planning is an important element of the integrated watershed management approach. It not only influences the environmental processes such as soil and stream bed erosion, sediment and nutrient concentrations in streams, quality of surface and ground waters in a watershed, but also affects social and economic development in that region. Although its importance in achieving sustainable development has long been recognized, a land use planning methodology based on a systems approach involving realistic computational modeling and meta-heuristic optimization is still lacking in the current practice of integrated watershed management. The present study proposes a new approach which attempts to combine computational modeling of upland watershed processes, fluvial processes and modern heuristic optimization techniques to address the water-land use interrelationship in its full complexity. The best land use allocation is decided by a multi-objective function that minimizes sediment yields and nutrient concentrations as well as the total operation/implementation cost, while the water quality and the production benefits from agricultural exploitation are maximized. The proposed optimization strategy considers also the preferences of land owners. The runoff model AnnAGNPS (developed by USDA), and the channel network model CCHE1D (developed by NCCHE), are linked together to simulate sediment/pollutant transport process at watershed scale based on any assigned land use combination. The greedy randomized adaptive Tabu search heuristic is used to flip the land use options for finding an optimum combination of land use allocations. The approach is demonstrated by applying it to a demonstrative case study involving USDA Goodwin Creek experimental watershed located in northern Mississippi. The results show the improvement of the tradeoff between benefits and costs for the watershed, after implementing the proposed optimal land use planning.     

Monitoring Environmental Changes in the Mediterranean Coastal Landscape: The Case of Cukurova, Turkey

This paper describes a remote sensing approach used to monitor temporal land use/cover (LULC) changes in Cukurova, an extensive coastal plain in the southeast Mediterranean coast of Turkey. The area has varied terrain ranging from low-lying alluvial deposits to rocky hills and mountains characterized by limestone outcrops. The ecological and economic importance of the area can be attributed to the existence of important coastal ecosystems (e.g., wetlands and sand dunes) and a wide range of industries located along the eastern coast. Temporal changes in the coastal landscape between 1984 and 2000 were evaluated using digital interpretation of remotely sensed satellite data. Pairwise comparison methods were used to quantify changes from 1984 to 1993 and 1993 to 2000 using multitemporal Landsat TM and ETM+ images, acquired in 1984, 1993, and 2000, respectively. Total change area was 2448 ha from 1984 to 1993 and increased more than twofold, to 6072 ha from 1993 to 2000. Change trends were determined using the information provided from individual change detection outputs of different periods. The most prominent changes were estimated to have occurred in agriculture, urban, and natural vegetation cover. Agriculture has increasingly grown over marginal areas, whereas urban development occurred at the expense of prime croplands across both time steps.     

Land use change and carbon exchange in the tropics: I. Detailed estimates for Costa Rica,Panama, Peru,and Bolivia

Our group, composed of modelers working in conjunction with tropical ecologists, 3 has produced a simulation model that quantifies the net carbon exchange between tropical vegetation and the atmosphere due to land use change. The model calculates this net exchange by combining estimates of land use change with several estimates of the carbon stored in tropical vegetation and general assumptions about the fate of cleared vegetation. In this report, we use estimates of land use and carbon storage organized into sixlife zone (sensu Holdridge) categories to calculate the exchange between the atmosphere and the vegetation of four tropical countries. Our analyses of these countries indicate that this life zone approach has several advantages because (a) the carbon content of vegetation varies significantly among life zones, (b) much of the land use change occurs in life zones of only moderate carbon storage, and (c) the fate of cleared vegetation varies among life zones. Our analyses also emphasize the importance of distinguishing between temporary and permanent land use change, as the recovery of vegetation on abandoned areas decreases the net release of carbon due to clearing. We include sensitivity analysis of those factors that we found to be important but are difficult to quantify at present.     

The consequences of land use change on nutrient exports: a regional scale assessment in south-west Victoria, Australia

Estimation of nutrient load production based on multi-temporal remotely sensed land use data for the Glenelg-Hopkins region in south-west Victoria, Australia, is discussed. Changes in land use were mapped using archived Landsat data and computerised classification techniques. Land use change has been rapid in recent history with 16% of the region transformed in the last 22 years. Total nitrogen and phosphorus loads were estimated using an export coefficient model. The analysis demonstrates an increase in modelled nitrogen and phosphorus loadings from 1980 to 2002. Whilst such increases were suspected from past anecdotal and ad-hoc evidence, our modelling estimated the magnitude of such increases and thus demonstrated the enormous potential of using remote sensing and GIS for monitoring regional scale environmental processes.     

A land suitability model for the evaluation of land-use change

A land suitability model was developed to provide the planner with a quantitative tool for assessing the environmental limitations on proposed land-use changes in the area surrounding Lake Monroe in southern Indiana. The model incorporates a weighting procedure that allows the environmental evaluation of a decision to convert the present land use to another category. The data base for the model was assembled by a multidisciplinary team. A case study is included, which illustrates the advantages and limitations of the land suitability model as it is applied to the evaluation of a site for the Alumni Family Camp.     

Understanding land cover change in a Special Protection Area in Central Spain through the enhanced land cover transition matrix and a related new approach

This work analyses land cover changes occurring between 1990 and 2000 within a Natural Protected Area, southwest of Madrid (Spain). We develop a new methodology that considers the net change in different land cover categories in each municipality of the study area. Our methodology, which uses Factorial Correspondence Analysis, allows identification of the most important changes at the municipality level and groups the municipalities where land use dynamics are similar. This method is a powerful tool for synthesis and can potentially be applied to non-spatial geographical data sources (e.g. agrarian census statistics). Our results show that the land cover around SW Madrid is highly dynamic. The shrub vegetation, arable land, heterogeneous agricultural and human-created area categories show the highest total change. The dynamics of the changes detected are dominated by decreases in the area of different types of crops and increases in forest areas. These changes may have indirect effects on the conservation of natural resources and wildlife if not managed appropriately.     

Statistical evaluation of an agricultural land suitability model

The land evaluation and site assessment (LESA) method has been used extensively in the United States to assess agricultural land suitability for different localities. Despite widespread use, LESA models rarely have been evaluated in a systematic, comprehensive manner. This article discusses development of a LESA system for Hawaii, the first statewide application of the LESA methodology. The empirical model was implemented with a computerized geographic information system (GIS). The system's efficiency, ability to discriminate among land parcels, and robustness to subjective model parameter values are evaluated with statistical analyses and map overlays of GIS data. Results show great potential to simplify the original model specification, primarily through deletion of marginal site assessment factors. System output was generally insensitive to the numeric values selected for model parameters, with exception of the ratio used to combine the land evaluation (LE) and site assessment (SA) component scores. Relative supplies of the differing land attributes measured by the two components must be considered in determining an appropriate LE:SA ratio for a given area.     

Land use change and carbon exchange in the tropics: II. Estimates for the entire region

Determining the effect of tropical land use on the carbon dioxide (CO₂) content of the atmosphere requires: (a) estimates of the rates of land use change, (b) estimates of the difference between the carbon stored in forests and that stored in pastures and cultivated fields, and (c) a consideration of the fate of carbon stored in the cleared vegetation. The first article of this series analyzed land use in four tropical countries and estimated the carbon released to the atmosphere as a consequence of changes in land use. This article estimates the carbon released from the entire tropical region based on the two published studies of land use change for the tropics as a whole that distinguish between temporary and permanent land use: Seiler and Crutzen (1980) and Lanly (1982). We combine these estimates with two estimates of the difference in carbon storage between forests and fields derived from Whittaker and Likens (1975) and Brown and Lugo (1982), and the two scenarios of the fate of cleared vegetation, developed in the previous article, to produce several complete sets of data describing the necessary parameters to calculate carbon exchange. These data sets, entered into our model, produce a range of estimates of the annual release of carbon from tropical vegetation in 1980 of from 0.6 to 1.8 BMT/year, with the more likely range being 0.9–1.2 BMT/year. Our preliminary analysis suggests that the release from tropical soils due to land use change adds about an additional 0.3 BMT C/year, so that the total release is probably between 1.2 and 1.5 BMT C/year. Peng and others (1983) reported that new models of the oceanic carbon cycle can accommodate at least 1.2 BMT C/year in 1980 from forests and soils. Our results indicate that, given the uncertainties in the size of both the biotic release and oceanic uptake, the global carbon budget may be balanced if there is no significant release from nontropical ecosystems due to land use change and all mature ecosystems are in collective equilibrium with the atmosphere.     

Downscaling climate change scenarios in an urban land use change model

The objective of this paper is to describe the process through which climate change scenarios were downscaled in an urban land use model and the results of this experimentation. The land use models (Urban Growth Model [UGM] and the Land Cover Deltatron Model [LCDM]) utilized in the project are part of the SLEUTH program which uses a probabilistic cellular automata protocol. The land use change scenario experiments were developed for the 31-county New York Metropolitan Region (NYMR) of the US Mid-Atlantic Region. The Intergovernmental Panel on Climate Change (IPCC), regional greenhouse gas (GHG) emissions scenarios (Special Report on Emissions Scenarios (SRES) A2 and B2 scenarios) were used to define the narrative scenario conditions of future land use change. The specific research objectives of the land use modeling work involving the SLEUTH program were threefold: (1) Define the projected conversion probabilities and the amount of rural-to-urban land use change for the NYMR as derived by the UGM and LCDM for the years 2020 and 2050, as defined by the pattern of growth for the years 1960-1990; (2) Down-scale the IPCC SRES A2 and B2 scenarios as a narrative that could be translated into alternative growth projections; and, (3) Create two alternative future growth scenarios: A2 scenario which will be associated with more rapid land conversion than found in initial projections, and a B2 scenario which will be associated with a slower level of land conversion. The results of the modeling experiments successfully illustrate the spectrum of possible land use/land cover change scenarios for the years 2020 and 2050. The application of these results into the broader scale climate and health impact study is discussed, as is the general role of land use/land cover change models in climate change studies and associated environmental management strategies.     

Long-term dynamics in land resource use and the driving forces in the Beressa watershed, highlands of Ethiopia

Land degradation in the Ethiopian highlands is considered to be one of the major problems threatening agricultural development and food security in the country. However, knowledge about the forces driving the long-term dynamics in land resources use is limited. This research integrates biophysical information with socio-economic processes and policy changes to examine the dynamics of land resource use and farmers' livelihoods in the Beressa watershed for over 40 years during the second half of the 20th century. It was found that there have been substantial dynamics in land resource use in the area. The natural vegetation cover has been extensively cleared, although most of the cleared areas have since been replaced with plantations. Grazing land has expanded remarkably at the expense of cropland and bare land. However, the expansion of cropland was minimal over the 43-year period despite a quadrupling of the population density. Yields have not increased to compensate for the reduction in per capita cropland, and the soil quality appears to be not that good. Though the farmers perceived it otherwise, the long-term rainfall pattern has improved. In response to soil degradation, water shortage, socio-economic and policy changes, farmers have tended to gradually change from annual cropping to tree planting and livestock production to cope with the problems of soil degradation, water scarcity and smaller farms. Income diversification through the sale of wood and cattle dung is becoming a major livelihood strategy. Apparently, however, little attention has been paid to investments in soil and water conservation (SWC) and local soil fertility amendments. In particular, increased erosion and related high nutrient losses in sediments, as well as the removal of potentially available soil nutrients through the sale of manure threatens to damage agricultural sustainability in the area.     

Mapping socio-economic scenarios of land cover change: a GIS method to enable ecosystem service modelling

We present a GIS method to interpret qualitatively expressed socio-economic scenarios in quantitative map-based terms. (i) We built scenarios using local stakeholders and experts to define how major land cover classes may change under different sets of drivers; (ii) we formalized these as spatially explicit rules, for example agriculture can only occur on certain soil types; (iii) we created a future land cover map which can then be used to model ecosystem services. We illustrate this for carbon storage in the Eastern Arc Mountains of Tanzania using two scenarios: the first based on sustainable development, the second based on 'business as usual' with continued forest-woodland degradation and poor protection of existing forest reserves. Between 2000 and 2025 4% of carbon stocks were lost under the first scenario compared to a loss of 41% of carbon stocks under the second scenario. Quantifying the impacts of differing future scenarios using the method we document here will be important if payments for ecosystem services are to be used to change policy in order to maintain critical ecosystem services.     

A land management history for central Queensland,Australia as determined from land-holder questionnaire and aerial photography

Features of the land management history over a 125,755 km(2) area of central Queensland, Australia were determined from a variety of sources. A random sample of 205 site locations provided the basis for determining trends in land use. Trends in vegetation clearing were determined using sequential aerial photography for the sample sites, revealing a steady rate averaging nearly 1% of the region per annum over 41 years. This measure of sustained clearing over a large region is higher than recently published clearing rates from South America. Land types have been selectively cleared with over 90% of the Acacia on clay land type having been cleared. A land-holder questionnaire pertaining to the random sites yielded a response rate of 71% and provided information on vegetation clearing, ploughing, tree killing (ring-barking or tree poisoning), and fire frequency, season and intensity. The land-holder responses were compared with independent data sources where possible and revealed no mis-information. However, land-holders may have been marginally less likely to respond if the sample area had been cleared, although this effect was not statistically significant. Ploughing and tree killing are variable depending on land type, but the former has affected about 40% of the Acacia on clay land type, effectively eliminating options for natural regrowth. The proportion of decade-site combinations that were reported as having no fires increased from 22% in the 1950s to an average of 42% for subsequent decades, although the reporting of more than one fire per decade has been relatively constant through the study period. The reporting of at least one fire per decade varies from 46% for the Acacia on sand land type to 77% for the Eucalypt on sand land type for decade-site combinations. Fires are more intense when associated with clearing than in uncleared vegetation, but the proportion of cool and hot fires is relatively constant between land types in uncleared vegetation. Nearly all fires reported were either in spring or summer and this seasonally restricted regime is probably at variance with Aboriginal fire regimes. This study describes the rapid transformation of central Queensland. This has yielded substantially increased agricultural production but may also result in a range of negative impacts and these are discussed.     

Land Use Change and Land Degradation in Southeastern Mediterranean Spain

The magnitude of the environmental and social consequences of soil erosion and land degradation in semiarid areas of the Mediterranean region has long been recognized and studied. This paper investigates the interrelationship between land use/cover (LULC) changes and land degradation using remotely sensed and ancillary data for southeastern Spain. The area of study, the Xaló River catchment situated in the north of the Alicante Province, has been subjected to a number of LULC changes during the second half of the 20th century such as agricultural abandonment, forest fires, and tourist development. Aerial photographs dating back to 1956 were used for the delineation of historic LULC types; Landsat ETM+ data were used for the analysis and mapping of current conditions. Two important indicators of land degradation, namely, susceptibility to surface runoff and soil erosion, were estimated for the two dates using easily parametrizable models. The comparison of 1956 to 2000 conditions shows an overall “recuperating” trend over the catchment and increased susceptibility to soil erosion only in 3% of the catchment area. The results also identify potential degradation hot-spots where mitigation measures should be taken to prevent further degradation. The readily implemented methodology, based on modest data requirements demonstrated by this study, is a useful tool for catchment to regional scale land use change and land degradation studies and strategic planning for environmental management.