Search

This manuscript provides guidance concerning how to use the Total Operating Characteristic (TOC) when (1) analyzing change through time, (2) ranking a categorical independent variable, and (3) constraining the extent for a gaining category. The illustrative variable is the marsh land-cover category in the Plum Island Ecosystems of northeastern Massachusetts, USA. The data are an elevation map and maps showing the land categories of water, marsh, and upland in 1938, 1971, and 2013. There were losses and gains near the edge of the marsh between 1938 and 1972 and between 1972 and 2013. The TOC curves show that marsh gained most intensively at intermediate elevations during the first time interval and then had a weaker association with elevation during the second time interval. Marsh gains more intensively from water than from upland during both time intervals. The TOC curves also demonstrate that the marsh gains occurred where marsh was previously lost, a phenomenon called Alternation. Furthermore, eliminating far distances and extreme elevations from the spatial extent decreased the area under the curve (AUC) for distance and increased the AUC for elevation. We invite scientists to use the TOC because the TOC is easier to interpret and shows more information than the Relative Operative Characteristic. [ABSTRACT FROM AUTHOR]

Numerous models exist for users to simulate land change to communicate with an audience concerning future land change. This article raises four fundamental questions to help model users decide whether to use any model: (1) Can the user understand the model? (2) Can the audience understand the model? (3) Can the user control the model? (4) Does the model address the goals of the specific application? This article applies these questions to the popular cellular automata–Markov (CA–Markov) model as IDRISI's CA–Markov module expresses. Sensitivity analysis examines 120 ways to set the module's parameters. Verification compares the module's behavior to the software's documentation. Results show that the cellular automata's allocation fails to follow the quantity of change that the Markov module computes. The module's behavior is likely to cause users to misinterpret the validation metrics and to miscommunicate with audiences. Thus, the answers to the four questions were not satisfactory for this article's case study. This article's framework helps users to judge a model's appropriateness for a specific application by combining sensitivity analysis with verification in a manner that helps to interpret validation. Users should answer the four questions as they decide whether to use any software's modules. [ABSTRACT FROM AUTHOR]

The Flow matrix is a novel method to describe and extrapolate transitions among categories. The Flow matrix extrapolates a constant transition size per unit of time on a time continuum with a maximum of one incident per observation during the extrapolation. The Flow matrix extrapolates linearly until the persistence of a category shrinks to zero. The Flow matrix has concepts and mathematics that are more straightforward than the Markov matrix. However, many scientists apply the Markov matrix by default because popular software packages offer no alternative to the Markov matrix, despite the conceptual and mathematical challenges that the Markov matrix poses. The Markov matrix extrapolates a constant transition proportion per time interval during whole-number multiples of the duration of the calibration time interval. The Markov extrapolation allows at most one incident per observation during each time interval but allows repeated incidents per observation through sequential time intervals. Many Markov extrapolations approach a steady state asymptotically through time as each category size approaches a constant. We use case studies concerning land change to illustrate the characteristics of the Flow and Markov matrices. The Flow and Markov extrapolations both deviate from the reference data during a validation time interval, implying there is no reason to prefer one matrix to the other in terms of correspondence with the processes that we analyzed. The two matrices differ substantially in terms of their underlying concepts and mathematical behaviors. Scientists should consider the ease of use and interpretation for each matrix when extrapolating transitions among categories. [ABSTRACT FROM AUTHOR]

Vector GIS represents shorelines as polylines that show the boundaries between land and water. This article compares two methods to measure how boundaries move among time points. The Area method converts the polylines at various time points into polygons of either land or water. The Area method measures temporal change as loss or gain of land areas. The Transect method requires subjective decisions to draw a baseline near the shorelines and then to draw transects that emanate from the baseline to intersect the shorelines. The Transect method measures temporal change as the distance between the intersection points along each transect as in the software packages AMBUR and DSAS. This article compares the conceptual foundations of the two methods. We illustrate how the Area method produces results for cases where the Transect method encounters practical difficulties. We list each method's characteristics, so researchers can align the method with their research question. [ABSTRACT FROM AUTHOR]

The data employed in urban gain modeling classes are often imbalanced, negatively affecting the accuracy of traditional and standard data mining and machine learning models. This study presents a new framework on the basis of clustering-based modeling and ensemble models to deal with the class imbalance problem in urban gain modeling. The random forest (RF), artificial neural network (ANN) and support vector machine (SVM) models served as the base models for the generation and evaluation of the results within this framework. The changes in urban land-use pattern of Isfahan in Iran in two time intervals of 1994-2004 and 2004-2014 were considered for the modeling. The findings showed that the proposed sampling strategy yields higher Hits and Correct Rejections rates than the strategies applied in previous studies in all three models. In the second part of the proposed framework (ensemble models), there was no substantial difference in the confusion matrix entries. [ABSTRACT FROM AUTHOR]

The Receiver Operating Characteristic (ROC) is widely used for assessing the performance of classification algorithms. In GIScience, ROC has been applied to assess models aimed at predicting events, such as land use/cover change (LUCC), species distribution and disease risk. However, GIS software packages offer few statistical tests and guidance tools for ROC analysis and interpretation. This paper presents a suite of GIS tools designed to facilitate ROC curve analysis for GIS users by applying proper statistical tests and analysis procedures. The tools are freely available as models and submodels of Dinamica EGO freeware. The tools give the ROC curve, the area under the curve (AUC), partial AUC, lower and upper AUCs, the confidence interval of AUC, the density of event in probability bins and tests to evaluate the difference between the AUCs of two models. We present first the procedures and statistical tests implemented in Dinamica EGO, then the application of the tools to assess LUCC and species distribution models. Finally, we interpret and discuss the ROC-related statistics resulting from various case studies. [ABSTRACT FROM AUTHOR]

Object-based image analysis (OBIA) uses object features (or attributes) that relateto the pixels contained by the image object to assist in image classification. These object features include spectral, shape, texture and context features. With hundreds of available features, the identification of those that can improve separability between classes is critical for OBIA. The Separability and Thresholds (SEaTH) algorithm calculates the SEaTH of object-classes for the given features. The SEaTH algorithm avoids time-consuming trial-and-error practice for seeking important features and thresholds. This article tests the SEaTH algorithm on Landsat-7 Enhanced Thematic Mapper (ETM+) imagery in a heterogeneous landscape with multiple land cover classes. The results suggest SEaTH is a strong alternative to other automated approaches, yielding an agreement of 79% with reference data. In comparison, an object-based nearest neighbour classifier yielded 66% agreement and a pixel-based maximum likelihood classifier yielded 69% agreement. [ABSTRACT FROM AUTHOR]

This paper proposes a method to quantify the goodness-of-fit of a land change projection along a gradient of an explanatory variable, by classifying pixels as one of four types: null successes, false alarms, hits, and misses. The method shows: (1) how the correctness and error of a land change projection are distributed along the gradient of an explanatory variable, (2) how the gradient of the explanatory variable relates to the stationarity of the land transition processes, and (3) how to use the insights from the previous two points to search for additional explanatory variables. The paper illustrates the method through a case study that applies the model Geomod in Central Massachusetts, USA. Results reveal that the model predicts more than the observed amount of change on flat slopes and less than the observed amount of change on steep slopes. One reason for these types of errors is that the land change process during the calibration interval is different than the process during the prediction interval with respect to slope. The method allows modelers to use the validation step as a diagnostic tool to search for potentially influential missing variables and to gain insight into land transition processes. The technique is designed to be applicable to a variety of types of land change models. [ABSTRACT FROM AUTHOR]

We use remote sensing and GIS to map changes in land cover and to identify systematic land-cover transitions in Southwestern Ghana. Landsat Thematic Mapper satellite imagery of 1990 and 2000 is used to create two land-cover classifications, and the two maps are then compared to produce transition matrices both for protected and for unprotected areas. These matrices are analyzed according to their various components to identify systematic landscape transitions based on deviations between the transitions observed and the transitions expected owing to random processes of change. The results show that closed forest regions inside the protected area transition systematically to bare ground or bush fire, but closed forest outside the protected area transitions systematically to open cultivated woodland. These results are consistent with the hypothesis that logging is the main cause of the loss of closed forest inside the protected areas whereas farming is the main cause of the loss of closed forest outside the protected areas. The research highlights the need for the implementation of this methodological approach to landscape change. Identification of strong signals of forest transformation is particularly important in the light of efforts by policy makers to curb deforestation in Ghana. [ABSTRACT FROM AUTHOR]

The article focuses on the success and challenges experienced by the Clark University in Worcester, Massachusetts during the seven years of its formal undergraduate research program called Human-Environment Regional Observatory (HERO) which uses Geographic Information Science (GISci) to examine human-environment interactions. It outlines the university's objectives, undergraduate pedagogical goals of the program and its success. It concludes that the HERO reinforced the faculty that a sustained monitoring/data collection and analysis effort is required in advancing the university's frontiers and engaging undergraduate students in the initiative that can be productive.

This paper gives a technique to extrapolate the anticipated accuracy of a prediction of land-use and land-cover change (LUCC) to any point in the future. The method calibrates a LUCC model with information from the past in order to simulate a map of the present, so that it can compute an objective measure of validation with empirical data. Then it uses that observed measurement of predictive accuracy to anticipate how accurately the model will predict a future landscape. The technique assumes that the accuracy of the model will decay to randomness as the model predicts farther into the future and estimates how fast the decay in accuracy will occur based on prior model performance. Results are presented graphically in terms of percentage of pixels classified correctly so that nonexperts can interpret the accuracy visually. The percentage correct is budgeted by three components: agreement due to chance, agreement due to the predicted quantity of each land category, and agreement due to the predicted location of each land category. The percentage error is budgeted by two components: disagreement due to the predicted location of each land category and disagreement due to the predicted quantity of each land category. Therefore, model users can see the sources of the accuracy and error of the model. The entire analysis is computable for multiple resolutions, so users can see how the results are sensitive to changes in scale. We illustrate the method with an application of the land-use change model Geomod to Central Massachusetts, where the predictive accuracy of the model decays to 90% over fourteen years and to near complete randomness over 200 years. [ABSTRACT FROM AUTHOR]

This paper offers techniques of validation that land-use and -cover change (LUCC) modelers should find useful because the methods give information that is useful to improve LUCC models and to set the agenda for future LUCC research. Specifically, the validation technique: (a) budgets sources of agreement and disagreement between the prediction map and the reference map, (b) compares the predictive model to a Null model that predicts pure persistence, (c) compares the predictive model to a Random model that predicts change evenly across the landscape, and (d) evaluates the goodness-of-fit at multiple-resolutions to see how scale influences the assessment. This paper introduces a new criterion called the Null Resolution, which is the spatial resolution at which the predictive model is as accurate as the Null model.For illustration, these techniques are applied to assess an LUCC model called Geomod, which predicts land change in the 22 towns of the Ipswich River Watershed in northeastern Massachusetts, USA. For this application, the Null Resolution is approximately 1 km. At resolutions finer than 1 km, the Null model performs better than Geomod, which performs better than the Random model. At resolutions coarser than 1 km, both Geomod and the Random models perform better than the Null model, but Geomod and the Random models are nearly indistinguishable beyond the 1 km resolution. [Copyright &y& Elsevier]