Using the Relative Operating Characteristic to Quantify Certainty in Prediction of Location of Land Cover Change in India

Pontius, Robert G.; Batchu, Kiran

doi:10.1111/1467-9671.00159

Cited by 75 publications

(46 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ROC curve statistic can examine the accuracy of prediction at several different threshold levels, then aggregate the information at all thresholds into one measure of agreement [26]. So, this method can give overall assessment for prediction ability of a stochastic probability model, for example, SLEUTH.…”

Section: The Effectiveness Of the Multi-methods For Assessment Of Modmentioning

confidence: 99%

Performance Evaluation of the SLEUTH Model in the Shenyang Metropolitan Area of Northeastern China

et al. 2008

Environ Model Assess

View full text Add to dashboard Cite

Performance evaluation is crucial for the development and improvement of an urban cellular automata model, such as SLEUTH. In this paper, we employed multiple methods for map comparison and model validation to evaluate the simulation performance of the SLEUTH urban growth model in the Shenyang metropolitan area of China. These multiple methods included the relative operating characteristic (ROC) curve statistic, multiple-resolutions error budget, and landscape metrics. They were used to quantitatively examine model performance in terms of the amount and spatial location of urban development, urban spatial pattern and prediction ability. The assessment results showed that SLEUTH performed well in the way of the quantitative simulation of urban growth for this case study. Similar to other urban growth models, however, the simulation accuracy for spatial location of new development at the pixel scale and urban spatial pattern still needs to be improved greatly. These inaccuracies might be attributed to the structure and nature of SLEUTH, local urban development characteristics, and the temporal and spatial scale of its application. Finally, many valuable suggestions had been put forward to improve simulation performance of SLEUTH model for spatial location of urban development in the Shenyang metropolitan area.

show abstract

Section: The Effectiveness Of the Multi-methods For Assessment Of Modmentioning

confidence: 99%

Performance Evaluation of the SLEUTH Model in the Shenyang Metropolitan Area of Northeastern China

et al. 2008

Environ Model Assess

View full text Add to dashboard Cite

show abstract

“…Finally, the receiver operating characteristic (ROC) curve analysis is a quantitative measurement tool to validate the goodness of fit of an LUCC model [20,[76][77][78]. Sensitivity (true positive rate) and specificity (true negative rate) are calculated using the formula below, based on the overall agreement cell score outputs.…”

Section: Accuracy and Reliabilitymentioning

confidence: 99%

Forecasting Urban Vacancy Dynamics in a Shrinking City: A Land Transformation Model

Lee

Newman

2017

IJGI

View full text Add to dashboard Cite

Abstract:In the past two centuries, many American urban areas have experienced significant expansion in both populating and depopulating cities. The pursuit of bigger, faster, and more growth-oriented planning parallels a situation where municipal decline has also been recognized as a global epidemic. In recent decades many older industrial cities have experienced significant depopulation, job loss, economic decline, and massive increases in vacant and abandoned properties due primarily to losses in industry and relocating populations. Despite continuous economic decline and depopulation, many of these so-called 'shrinking cities' still chase growth-oriented planning policies, due partially to inabilities to accurately predict future urban growth/decline patterns. This capability is critical to understanding land use alternation patterns and predicting future possible scenarios for the development of more proactive land use policies dealing with urban decline and regeneration. In this research, the city of Chicago, Illinois, USA is used as a case site to test an urban land use change model that predicts urban decline in a shrinking city, using vacant land as a proxy. Our approach employs the Land Transformation Model (LTM), which combines Geographic Information Systems and artificial neural networks to forecast land use change. Results indicate that the LTM is a good resource to simulate urban vacant land changes. Mobility and housing market conditions seem to be the primary variables contributing to decline.

show abstract

“…False positive rates and true positive rates are plotted along X and Y axes for each threshold. The area under the ROC curve represents the model accuracy [43]. The calculated PCM (90%) and ROC (85%) indicated that the accuracy of trained model was high enough to be used for future land cover prediction [30].…”

Section: Model Calibrationmentioning

confidence: 99%

Long-Term Land Cover Data for the Lower Peninsula of Michigan, 2010–2050

Tayyebi

Smidt

Pijanowski

2017

Data

View full text Add to dashboard Cite

Land cover data are often used to examine the impacts of landscape alterations on the environment from the local to global scale. Although various agencies produce land cover data at various spatial scales, data are still limited at the regional scale over extended timescales. This is a critical data gap since decision-makers often use future and long-term land cover maps to develop effective policies for sustainable environmental systems. As a result, land change science incorporates common data mining tools to create future land cover maps that extend over long timescales. This study applied one of the well-known land cover change models, called Land Transformation Model (LTM), to produce urbanization maps for the Lower Peninsula of Michigan in United States from 2010 to 2050 with five year intervals. Long-term urbanization data in the Lower Peninsula of Michigan can be used in various environmental studies such as assessing the impact of future urbanization on climate change, water quality, food security and biodiversity.Data Set: available as a supplementary file. Data Set License: CCBY

show abstract

Using the Relative Operating Characteristic to Quantify Certainty in Prediction of Location of Land Cover Change in India

Cited by 75 publications

References 10 publications

Performance Evaluation of the SLEUTH Model in the Shenyang Metropolitan Area of Northeastern China

Performance Evaluation of the SLEUTH Model in the Shenyang Metropolitan Area of Northeastern China

Forecasting Urban Vacancy Dynamics in a Shrinking City: A Land Transformation Model

Long-Term Land Cover Data for the Lower Peninsula of Michigan, 2010–2050

Contact Info

Product

Resources

About