Land cover change in the Bolivian Amazon and its implications for REDD+ and endemic biodiversity

Sangermano, Florencia; Toledano, James; Eastman, J. Ronald

doi:10.1007/s10980-012-9710-y

Cited by 95 publications

(61 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The soft prediction represented the vulnerability of the land to experience change [41]. The areas mapped are locations that have not changed but have the ideal condition for change, and may transition at some point [37].…”

Section: Modeling the Potential For Changementioning

confidence: 99%

Modeling the Impact of Urban Landscape Change on Urban Wetlands Using Similarity Weighted Instance-Based Machine Learning and Markov Model

Zubair

Weilert

2017

Sustainability

View full text Add to dashboard Cite

Urban wetlands play important roles in providing several ecosystem services that support the urban environment. As such, scientists have studied them to understand the urban processes that lead to their continued decline. However, little attention has been given to the drivers of land-use change that may affect this fragile ecosystem in the future. Understanding this could serve as a critical step towards urban wetland management and sustainability. In this study, we utilized an integrated approach that combined Similarity Weighted Instance-based Machine Learning and Markov chain, both embedded in the IDRISI Land Change Modeler to simulate change in the landscape of three watersheds in the Kansas City Metropolitan area. The purpose was to assess the possible future impacts of urban expansion-induced landscape change on wetlands within the study area, using a retrospective approach. To achieve this, classified SPOT satellite data covering the three watersheds were used to generate historical land cover maps of the study area between 1992 and 2010 to analyze changes to the landscape. In addition, the study identified several drivers of land change associated with the historical change process in the study area, and accounted for their role in the modeling process. On this basis, the study made the prediction of urban landscape transformation to the end date of 2014. The prediction result was verified with a more accurate map that was derived from independently classifying a 2014 SPOT image of the study area. Results from this study show that impervious surfaces, which were used as an index of urban expansion, may increase by approximately the same magnitude experienced historically, which may result in a small but significant loss of wetlands and other land cover classes within the study area.

show abstract

Section: Modeling the Potential For Changementioning

confidence: 99%

Modeling the Impact of Urban Landscape Change on Urban Wetlands Using Similarity Weighted Instance-Based Machine Learning and Markov Model

Zubair

Weilert

2017

Sustainability

View full text Add to dashboard Cite

show abstract

“…Then, land cover maps of the years 2001 and 2010 were performed to create prospective land cover maps of 2030. SimWeight was used to develop suitability maps of the likelihood for transition from one class to another (Sangermano et al, 2012;Lin et al, 2014). It uses a slightly modified variant of the K-nearest neighbor procedure.…”

Section: Historical Changes Transition Potential and Future Modelingmentioning

confidence: 99%

Land cover change modelling in Hyrcanian forests, Northern Iran: a landscape pattern and transformation analysis perspective

Shooshtari

Shayesteh

Gholamalifard

et al. 2018

CIG

View full text Add to dashboard Cite

The main objective of this study is to analyze the spatio-temporal changes in land cover and land use, (1984–2010), as well to simulate future land cover for 2030 in the Neka River Basin, including the Hyrcanian forest, in northern Iran. For this purpose, we used detailed land cover maps for the years 1984, 2001 and 2010. The results showed that the highest deforestation occurred in the boundaries between forest and agriculture areas between 1984 and 2010. Comparing the observed and predicted land cover in 2010 yielded agreement of 96.41%. From 1984 to 2010, landscape metrics showed that the forest area evolved to more fragmentation, with less shape complexity and less connectivity. Projections for the future are consistent with observed changes for the Neka landscape, with a tendency to continue disaggregating and increasing diversity in a number of different patch types. Between 2010 and 2030, we observed the arrival of new crops, rangelands, and urban areas within the remaining areas of homogeneous forest. Changes in the Hyrcanian forest will cause alteration in ecosystem services, such as erosion control, water yield, timber harvest, and ground water reservation. Results of this work may represent a useful tool to provide strategies and territorial planning for sustainable management of the fragile Hyrcanian forest ecosystems in the Neka Basin.

show abstract

“…Finally, a Markovian process is used to allocate land for each claimants of a host class based on the derived quantity of change. The LCM has been used extensively for Reducing Emissions from Deforestation and Forest Degradation projects (REDD; e.g., [50][51][52][53]), as well as to estimate urbanization [54][55][56].…”

Section: Land Change Modelermentioning

confidence: 99%

Comparing Quantity, Allocation and Configuration Accuracy of Multiple Land Change Models

Pickard

Gray

Meentemeyer

2017

Land

View full text Add to dashboard Cite

Abstract:The growing numbers of land change models makes it difficult to select a model at the beginning of an analysis, and is often arbitrary and at the researcher's discretion. How to select a model at the beginning of an analysis, when multiple are suitable, represents a critical research gap currently understudied, where trade-offs of choosing one model over another are often unknown. Repeatable methods are needed to conduct cross-model comparisons to understand the trade-offs among models when the same calibration and validation data are used. Several methods to assess accuracy have been proposed that emphasize quantity and allocation, while overlooking the accuracy with which a model simulates the spatial configuration (e.g., size and shape) of map categories across landscapes. We compared the quantity, allocation, and configuration accuracy of four inductive pattern-based spatial allocation land change models (SLEUTH, GEOMOD, Land Change Modeler (LCM), and FUTURES). We simulated urban development with each model using identical input data from ten counties surrounding the growing region of Charlotte, North Carolina. Maintaining the same input data, such as land cover, drivers of change, and projected quantity of change, reduces differences in model inputs and allows for focus on trade-offs in different types of model accuracy. Results suggest that these four land change models produce representations of urban development with substantial variance, where some models may better simulate quantity and allocation at the trade-off of configuration accuracy, and vice versa. Trade-offs in accuracy exist with respect to the amount, spatial allocation, and landscape configuration of each model. This comparison exercise illustrates the range of accuracies for these models, and demonstrates the need to consider all three types of accuracy when assessing land change model's projections.

show abstract

Land cover change in the Bolivian Amazon and its implications for REDD+ and endemic biodiversity

Cited by 95 publications

References 38 publications

Modeling the Impact of Urban Landscape Change on Urban Wetlands Using Similarity Weighted Instance-Based Machine Learning and Markov Model

Modeling the Impact of Urban Landscape Change on Urban Wetlands Using Similarity Weighted Instance-Based Machine Learning and Markov Model

Land cover change modelling in Hyrcanian forests, Northern Iran: a landscape pattern and transformation analysis perspective

Comparing Quantity, Allocation and Configuration Accuracy of Multiple Land Change Models

Contact Info

Product

Resources

About