A multi‐label cellular automata model for land change simulation

The use of cellular automata (CA) has for some time been considered among the most appropriate approaches for modeling land‐use changes. Each cell in a traditional CA model has a state that evolves according to transition rules, taking into consideration its own and its neighbors’ states and characteristics. Here, we present a multi‐label CA model in which a cell may simultaneously have more than one state. The model uses a multi‐label learning method—a multi‐label support vector machine, Rank‐SVM—to define the transition rules. The model was used with a multi‐label land‐use dataset for Luxembourg, built from vector‐based land‐use data using a method presented here. The proposed multi‐label CA model showed promising performance in terms of its ability to capture and model the details and complexities of changes in land‐use patterns. Applied to historical land use data, the proposed model estimated the land use change with an accuracy of 87.2% exact matching and 98.84% when including cells with a misclassification of a single label, which is comparably better than a classical multi‐class model that achieved 83.6%. The multi‐label cellular automata outperformed a model combining CA and artificial neural networks. All model goodness‐of‐fit comparisons were quantified using various performance metrics for predictive models.     

Similarity Weighted Instance‐based Learning for the Generation of Transition Potentials in Land Use Change Modeling

Land use change models are increasingly being used to evaluate the effect of land change on climate and biodiversity and to generate scenarios of deforestation. Although many methods are available to model land transition potentials, they are usually not user‐friendly and require the specification of many parameters, making the task difficult for decision makers not familiar with the tools, as well as making the process difficult to interpret. In this article we propose a simple method for modeling transition potentials. SimWeight is an instance‐based learning algorithm based on the logic of the K‐Nearest Neighbor algorithm. The method identifies the relevance of each driver variable and predicts the transition potential of locations given known instances of change. A case study was used to demonstrate and validate the method. Comparison of results with the Multi‐Layer Perceptron neural network (MLP) suggests that SimWeight performs similarly in its capacity to predict transition potentials, without the need for complex parameters. Another advantage of SimWeight is that it is amenable to parallelization for deployment on a cloud computing platform.     

A Patch‐based Cellular Automaton for Simulating Land‐use Changes at Fine Spatial Resolution

While cellular automata have become popular tools for modeling land‐use changes, there is a lack of studies reporting their application at very fine spatial resolutions (e.g. 5 m resolution). Traditional cell‐based CA do not generate reliable results at such resolutions because single cells might only represent components of land‐use entities (i.e. houses or parks in urban residential areas), while recently proposed entity‐based CA models usually ignore the internal heterogeneity of the entities. This article describes a patch‐based CA model designed to deal with this problem by integrating cell and object concepts. A patch is defined as a collection of adjacent cells that might have different attributes, but that represent a single land‐use entity. In this model, a transition probability map was calculated at each cell location for each land‐use transition using a weight of evidence method; then, land‐use changes were simulated by employing a patch‐based procedure based on the probability maps. This CA model, along with a traditional cell‐based model were tested in the eastern part of the Elbow River watershed in southern Alberta, Canada, an area that is under considerable pressure for land development due to its proximity to the fast growing city of Calgary. The simulation results for the two models were compared to historical data using visual comparison, K_simulation indices, and landscape metrics. The results reveal that the patch‐based CA model generates more compact and realistic land‐use patterns than the traditional cell‐based CA. The K_simulation values indicate that the land‐use maps obtained with the patch‐based CA are in higher agreement with the historical data than those created by the cell‐based model, particularly regarding the location of change. The landscape metrics reveal that the patch‐based model is able to adequately capture the land‐use dynamics as observed in the historical data, while the cell‐based CA is not able to provide a similar interpretation. The patch‐based approach proposed in this study appears to be a simple and valuable solution to take into account the internal heterogeneity of land‐use classes at fine spatial resolutions and simulate their transitions over time.     

Using Pattern‐oriented Modeling (POM) to Cope with Uncertainty in Multi‐scale Agent‐based Models of Land Change

Local land‐use and ‐cover changes (LUCCs) are the result of both the decisions and actions of individual land‐users, and the larger global and regional economic, political, cultural, and environmental contexts in which land‐use systems are embedded. However, the dearth of detailed empirical data and knowledge of the influences of global/regional forces on local land‐use decisions is a substantial challenge to formulating multi‐scale agent‐based models (ABMs) of land change. Pattern‐oriented modeling (POM) is a means to cope with such process and parameter uncertainty, and to design process‐based land change models despite a lack of detailed process knowledge or empirical data. POM was applied to a simplified agent‐based model of LUCC to design and test model relationships linking global market influence to agents’ land‐use decisions within an example test site. Results demonstrated that evaluating alternative model parameterizations based on their ability to simultaneously reproduce target patterns led to more realistic land‐use outcomes. This framework is promising as an agent‐based virtual laboratory to test hypotheses of how and under what conditions driving forces of land change differ from a generalized model representation depending on the particular land‐use system and location.     

A Temporal Variant‐Invariant Validation Approach for Agent‐based Models of Landscape Dynamics

Agent‐based modeling provides a means for addressing the way human and natural systems interact to change landscapes over time. Until recently, evaluation of simulation models has focused on map comparison techniques that evaluate the degree to which predictions match real‐world observations. However, methods that change the focus of evaluation from patterns to processes have begun to surface; that is, rather than asking if a model simulates a correct pattern, models are evaluated on their ability to simulate a process of interest. We build on an existing agent‐based modeling validation method in order to present a temporal variant‐invariant analysis (TVIA). The enhanced method, which focuses on analyzing the uncertainty in simulation results, examines the degree to which outcomes from multiple model runs match some reference to how land use parcels make the transition from one land use class to another over time. We apply TVIA to results from an agent‐based model that simulates the relationships between landowner decisions and wildfire risk in the wildland‐urban interface of the southern Willamette Valley, Oregon, USA. The TVIA approach demonstrates a novel ability to examine uncertainty across time to provide an understanding of how the model emulates the system of interest.     

Calibration of cellular automata models using differential evolution to simulate present and future land use

A key issue in cellular automata (CA) modeling is the minimization of the differences between the actual and simulated patterns, which can be mathematically formulated as an objective function. We develop a new hybrid model (termed DE‐CA) by integrating differential evolution (DE) into CA to solve the objective function and retrieve the optimal CA parameters. Constrained relations among factors were applied in DE to generate different sets of CA parameters for prediction of future scenarios. The DE‐CA model was calibrated using historical spatial data to simulate 2016 land use in Kunming and predict multiple scenarios to the year 2026. Assessment of quantitative accuracy shows that DE‐CA yields 92.4% overall accuracy, where 6.8% is the correctly captured urban growth; further, the model reported only 5.0% false alarms and 2.6% misses. Regarding the simulation ability, our new CA model performs as well as the widely applied genetic algorithm‐based CA model, and outperforms both the logistic regression‐based CA model and a no‐change NULL model. We projected three possible scenarios for the year 2026 using DE‐CA to adequately address the baseline urban growth, environmental protection and urban planning to show the strong prediction ability of the new model.     

Potential of Landsat-8 and Sentinel-2A composite for land use land cover analysis

Abstract

This study proposes the development of a multi-sensor, multi-spectral composite from Landsat-8 and Sentinel-2A imagery referred to as ‘LSC’ for land use land cover (LULC) characterisation and compared with respect to the hyperspectral imagery of the EO1: Hyperion sensor. A three-stage evaluation was implemented based on the similarity observed in the spectral response, supervised classification results and endmember abundance information obtained using linear spectral unmixing. The study was conducted for two areas located around Dhundi and Rohtak in Himachal Pradesh and Haryana, respectively. According to the analysis of the spectral reflectance curves, the spectral response of the LSC is capable of identifying major LULC classes. The kappa accuracy of 0.85 and 0.66 was observed for the classification results from LSC and Hyperion data for Dhundi and Rohtak datasets, respectively. The coefficient of determination was found to be above 0.9 for the LULC classes in both the datasets as compared to Hyperion, indicating a good agreement. Thus, these three-stage results indicated the significant potential of a composite derived from freely available multi-sensor multi-spectral imagery as an alternative to hyperspectral imagery for LULC studies.     

An Automated Approach for Land Cover Classification Based on a Fuzzy Supervised Learning Framework

This paper proposes an automatic framework for land cover classification. In majority of published work by various researchers so far, most of the methods need manually mark the label of land cover types. In the proposed framework, all the information, like land cover types and their features, is defined as prior knowledge achieved from land use maps, topographic data, texture data, vegetation’s growth cycle and field data. The land cover classification is treated as an automatically supervised learning procedure, which can be divided into automatic sample selection and fuzzy supervised classification. Once a series of features were extracted from multi-source datasets, spectral matching method is used to determine the degrees of membership of auto-selected pixels, which indicates the probability of the pixel to be distinguished as a specific land cover type. In order to make full use of this probability, a fuzzy support vector machine (SVM) classification method is used to handle samples with membership degrees. This method is applied to Landsat Thematic Mapper (TM) data of two areas located in Northern China. The automatic classification results are compared with visual interpretation. Experimental results show that the proposed method classifies the remote sensing data with a competitive and stable accuracy, and demonstrate that an objective land cover classification result is achievable by combining several advanced machine learning methods.     

端元可变非线性混合像元分解模型

遥感影像中混合像元普遍存在。端元固定的情况下对混合像元进行分解,很难高精度地识别影像地物。本文基于支持向量机,提出了端元可变的非线性混合像元分解模型。首先,通过构建多个支持向量机获取每个像元的优化端元集,在优化端元集的基础上运用支持向量机与两两配对方法相结合的算法获取像元组分。试验结果表明,本文提出的方法效果优于传统的多端元光谱分解法。     

An approach for establishing correspondence between OpenStreetMap and reference datasets for land use and land cover mapping

OpenStreetMap (OSM) provides free source data for land use and land cover (LULC) mapping of many regions globally. Earlier work has used just manual and subjective approaches to establish correspondence between paired OSM and reference datasets, an essential step for LULC mapping. This study proposes an approach to establish correspondence via three steps: (1) convert line feature(s) into polygon feature(s); (2) merge multiple polygon feature(s) into a single layer; and (3) establish correspondence and reclassify OSM and/or reference datasets. Study areas in Sheffield, London, Rome, and Paris were used for testing, and two measures (overall accuracy, OA and kappa index) were used for evaluation. Experiments were designed to verify this approach, with each pair of OSM and reference datasets initially compared after reclassification. Correspondence from one study area was then applied to another for further validation. Results show that OA was between 70 and 90% and the kappa index varied between 0.6 and 0.8. Evaluation also indicates that the correspondence obtained from one study area is applicable to another, and we illustrate the effectiveness of this approach.     

地表覆盖遥感产品更新完善的研究动向

近年来,多尺度地表覆盖遥感产品的不断涌现,为环境变化研究、地球系统模拟、地理国(世)情监测和可持续发展规划等提供了重要科学数据。为更好地满足广大用户日益增长的应用需求,应对地表覆盖遥感产品进行持续更新完善,保持其时效性、增强时序性、丰富多样性。针对大面积地表覆盖遥感产品更新完善所面临的主要问题,介绍和评述了国内外有关研究动向,包括影像与众源信息相结合的更新、数据类型细化与完善、地表覆盖真实性验证,并作了简要展望。     

Geostatistical techniques for incorporating spatial correlation into land use change models

Land use modeling requires large amounts of data that are typically spatially correlated. This study applies two geostatistical techniques to account for spatial correlation in residential land use change modeling. In the first approach, we combined generalized linear model (GLM) with indicator kriging to estimate the posterior probability of residential development. In the second approach, generalized linear mixed model (GLMM) was used to simultaneously model spatial correlation and regression fixed effects. Spatial agreement between actual and modeled land use change was higher for the GLM incorporating indicator kriging. The GLMM produced more reliable estimates and could be more useful in analyzing the effects of driving factors of land use change for land use planning.     

Cumulative spatial impact layers: A novel multivariate spatio‐temporal analytical summarization tool

Scientific inquiry often requires analysis of multiple spatio‐temporal datasets, ranging in type and size, using complex multi‐step processes demanding an understanding of GIS theory and software. Cumulative spatial impact layers (CSIL) is a GIS‐based tool that summarizes spatio‐temporal datasets based on overlapping features and attributes. Leveraging a recursive quadtree method, and applying multiple additive frameworks, the CSIL tool allows users to analyze raster and vector datasets by calculating data, record, or attribute density. Providing an efficient and robust method for summarizing disparate, multi‐format, multi‐source geospatial data, CSIL addresses the need for a new integration approach and resulting geospatial product. The built‐in flexibility of the CSIL tool allows users to answer a range of spatially driven questions. Example applications are provided in this article to illustrate the versatility and variety of uses for this CSIL tool and method. Use cases include addressing regulatory decision‐making needs, economic modeling, and resource management. Performance reviews for each use case are also presented, demonstrating how CSIL provides a more efficient and robust approach to assess a range of multivariate spatial data for a variety of uses.     

一种时空过程的梯形分级描述框架及其建模实例

以对象建模视图和事件模型为基础的自底向上的时空过程表达方法,缺少对地理时空现象的显式定义,在时空因果链的细化表达方面存在不足。本文设计一种时空过程的梯形分级描述框架STP-TRAP,对时空过程进行自顶向下的显式化建模和集成时空因果链的分级描述,并在事件模型基础上,通过引入约束关系描述扩展时空因果链的表达模式。土地利用变迁过程建模实例与土地利用管理信息系统的设计和实现证明,该框架对土地利用变迁时空过程表达效果较好,为土地利用变更数据管理提供了新的思路。     

A multi‐modal transportation data‐driven approach to identify urban functional zones: An exploration based on Hangzhou City,China

Recent urban studies have used human mobility data such as taxi trajectories and smartcard data as a complementary way to identify the social functions of land use. However, little work has been conducted to reveal how multi‐modal transportation data impact on this identification process. In our study, we propose a data‐driven approach that addresses the relationships between travel behavior and urban structure: first, multi‐modal transportation data are aggregated to extract explicit statistical features; then, topic modeling methods are applied to transform these explicit statistical features into latent semantic features; and finally, a classification method is used to identify functional zones with similar latent topic distributions. Two 10‐day‐long “big” datasets from the 2,370 bicycle stations of the public bicycle‐sharing system, and up to 9,992 taxi cabs within the core urban area of Hangzhou City, China, as well as point‐of‐interest data are tested to reveal the extent to which different travel modes contribute to the detection and understanding of urban land functions. Our results show that: (1) using latent semantic features delineated from the topic modeling process as the classification input outperforms approaches using explicit statistical features; (2) combining multi‐modal data visibly improves the accuracy and consistency of the identified functional zones; and (3) the proposed data‐driven approach is also capable of identifying mixed land use in the urban space. This work presents a novel attempt to uncover the hidden linkages between urban transportation patterns with urban land use and its functions.     

Support Vector Machine for Spatial Variation

Large, multivariate geographic datasets have been used to characterize geographic space with the help of spatial data mining tools. In our study, we explore the sufficiency of the Support Vector Machine (SVM), a popular machine‐learning technique for unsupervised classification and clustering, to help recognize hidden patterns in a college admissions dataset. Our college admissions dataset holds over 10,000 students applying to an undisclosed university during one undisclosed year. Students are qualified almost exclusively by their standardized test scores and school records, and a known admissions decision is rendered based on these criteria. Given that the university has a number of political, social and geographic econometric factors in its admissions decisions, we use SVM to find implicit spatial patterns that may favor students from certain geographic regions. We first explore the characteristics of the applicants in the college admissions case study. Next, we explain the SVM technique and our unique ‘threshold line’ methodology for both discrete (regional) and continuous (k‐neighbors) space. We then analyze the results of the regional and k‐neighbor tests in order to respond to the methodological and geographic research questions.     

顾及格网属性分级与空间关联的人口空间化方法

现有人口空间化方法多基于行政单元构建回归模型并分配格网单元人口,但分析单元的尺度差异引发模型迁移问题。同时,格网特征建模仅考虑格网自身属性,导致格网间空间关联被人为割裂。为此,基于随机森林模型提出一种顾及格网属性分级与空间关联的人口空间化方法。该方法在格网特征建模中:（1）基于自然断点法构造建筑区类别约束的夜间灯光分级特征,并在行政单元尺度统计各等级网格占比作为训练输入,以减小模型跨尺度误差;（2）利用核密度估计刻画邻域兴趣点（point of interest, POI）对当前格网人口分布的影响及距离衰减效应;（3）基于叠置分析统计不同类型建筑区轮廓包含的各类POI数量,提升特征建模精细度。选取武汉市作为实验区域,在街道尺度与WorldPop、GPW及中国公里网格人口数据集进行对比验证方法的有效性。结果表明,该方法的平均绝对值误差仅为对比数据集的1/6~1/3。此外,还探讨了特征构成、格网大小及核密度带宽对精度的影响。     

Use of Very High Spatial Resolution Remotely Sensed Imagery for Assessing Land‐Cover Changes in Shrub Habitat Preserves of Southern California

Abstract

The goal of this research was to explore the utility of very high spatial resolution, digital remotely sensed imagery for monitoring land‐cover changes in habitat preserves within southern California coastal shrublands. Changes were assessed for Los Penasquitos Canyon Preserve, a large open space in San Diego County, over the 1996 to 1999 period for which imagery was available.

Multispectral, digital camera imagery from two summer dates, three years apart, was acquired using the Airborne Data Acquisition and Registration (ADAR) digital‐camera system. These very high resolution (VHR) image data (1m), composed of three visible and one near‐infrared wavebands (V/NIR), were the primary image input for assessing land cover change. Image‐derived datasets generated from georeferenced and registered ADAR imagery included multitemporal overlays and multitemporal band differencing with threshold selection. Two different multitemporal image classifications were generated from these datasets and compared. Single‐date imagery was analyzed interactively with image‐derived datasets and with information from field observations in an effort to discern change types. A ground sampling survey conducted soon after the 1999 image acquisition provided concurrent ground reference data.

Most changes occurring within the three‐year interval were associated with transitional phenological states and differential precipitation effects on herbaceous cover. Variations in air temperatures and timing of rainfall contributed to differences that the seven‐week image acquisition offset may have caused. Disturbance factors of mechanical clearing, erosion, potentially invasive plants, and fire were evident and their influence on the presence, absence, and type of vegetation cover were likely sources of change signals.

The multitemporal VHR, V/NIR image data enabled relatively fine‐scale land cover changes to be detected and identified. Band differencing followed by multitemporal classification provided an effective means for detecting vegetation increase or decrease. Detailed information on short‐term disturbance effects and long‐term vegetation type conversions can be extracted if image acquisitions are carefully planned and geometric and radiometric processing steps are implemented.