Parcel-level Land Research Articles

Fine-Grained Land Use Classification at the City Scale Using Ground-Level Images

Multimedia researchers have exploited large collections of community-contributed geo-referenced images to better understand a particular image, such as its subject matter or where it was taken, as well as to better understand a geographic location, such as the most visited tourist spots in a city or what the local cuisine is like. The goal of this paper is to better understand location. In particular, we use geo-referenced image collections to better understand what occurs in different parts of a city at fine spatial and activity class scales. This problem is known as land use mapping in the geographical sciences. We propose a novel framework to perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of geo-referenced, ground-level images suggest an alternate approach to this geographic knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the city of San Francisco, CA, USA. Individual images are classified using a novel convolutional neural network containing two streams: one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several novel strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geovisualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level that represents a strong baseline for the challenging 45-way land use classification problem, especially given the noisiness of the image data.

An Estimation of the Extent of Rent-Free Farmland Transfer and Its Driving Forces in Rural China: A Multilevel Logit Model Analysis

In recent years, the rent-free farmland transfer has become increasingly prominent in rural China. By employing multiple data sources, this study estimates the extent of rent-free land transfer from 1986 to 2015 and develops a multilevel logit model to identify its drivers. The results show that the extent of rent-free land transfer has been increasing, especially since 2002, and 30% to 50% of the land that has been transferred does not receive any rent, both in terms of the number of land parcels and the land area. There are obvious regional differences for the rent-free phenomenon in the process of land transfer, especially in mountainous areas, where the proportion is more than 70%. The cost-benefit analysis at the land parcel level shows that the average net income of rent-free land per mu that has been transferred (1 mu = 1/15 ha) is at a loss of 66 yuan, at 35 yuan. The rent-free land transfer is affected by factors at the levels of the land parcel, farmer and village. The land parcel size, quality level and irrigation condition are the key factors at the land parcel level; the ratio of the non-agricultural income in the family and land fragmentation are the key factors at the farmer level, and the inter-village gap is the key factor at the village level. The land parcel features account for approximately 40% of the variation in the rent-free land transfer. In sum, the increase in the labour cost is the direct reason for the rent-free land transfer, and land parcel features and the marginalization of mountainous areas are the preconditions for the rent-free land transfer. A rent-free land transfer is reasonable to some extent, but it is not an informal land transfer, and land rent does not play an effective role in allocating land resources. In this process, the idle or abandoned land resources in mountainous areas become relatively rich. The government should reasonably introduce urban capital and fully tap relatively rich land resources to realize the land capital appreciation and develop the local economy, and it should further regulate the land rental market and lay an emphasis on the integration of land resources, while moderating scale operations in mountainous areas.

From walking buffers to active places: An activity-based approach to measure human-scale urban form

Urban form measures have been increasingly used in multidisciplinary research, yet few studies have conceptualized different meanings of human-scale urban form for various population groups. This study proposes an activity-based approach that builds direct links between urban form measures and travel-activity patterns of various population groups. With a case study on older adults' walking activity in Toronto, this study maps potential activity spaces for each population group, and measures the potential of social interaction at a land-parcel level. Based on a population-representative survey data and an open source routing algorithm, this study provides an exploratory method to conceptualize and measure human-scale urban form for different population groups. Further, this method helps to understand the non-linear relationships between conventional urban form measures and travel-activity patterns, and to inform planning interventions on urban form features that are particularly important for a specific population group.

Establishing a Demographic, Development and Environmental Geospatial Surveillance Platform in India: Planning and Implementation.

BackgroundInadequate administrative health data, suboptimal public health infrastructure, rapid and unplanned urbanization, environmental degradation, and poor penetration of information technology make the tracking of health and well-being of populations and their social determinants in the developing countries challenging. Technology-integrated comprehensive surveillance platforms have the potential to overcome these gaps.ObjectiveThis paper provides methodological insights into establishing a geographic information system (GIS)-integrated, comprehensive surveillance platform in rural North India, a resource-constrained setting.MethodsThe International Clinical Epidemiology Network Trust International established a comprehensive SOMAARTH Demographic, Development, and Environmental Surveillance Site (DDESS) in rural Palwal, a district in Haryana, North India. The surveillance platform evolved by adopting four major steps: (1) site preparation, (2) data construction, (3) data quality assurance, and (4) data update and maintenance system. Arc GIS 10.3 and QGIS 2.14 software were employed for geospatial data construction. Surveillance data architecture was built upon the geospatial land parcel datasets. Dedicated software (SOMAARTH-1) was developed for handling high volume of longitudinal datasets. The built infrastructure data pertaining to land use, water bodies, roads, railways, community trails, landmarks, water, sanitation and food environment, weather and air quality, and demographic characteristics were constructed in a relational manner.ResultsThe comprehensive surveillance platform encompassed a population of 0.2 million individuals residing in 51 villages over a land mass of 251.7 sq km having 32,662 households and 19,260 nonresidential features (cattle shed, shops, health, education, banking, religious institutions, etc). All land parcels were assigned georeferenced location identification numbers to enable space and time monitoring. Subdivision of villages into sectors helped identify socially homogenous community clusters (418/676, 61.8%, sectors). Water and hygiene parameters of the whole area were mapped on the GIS platform and quantified. Risk of physical exposure to harmful environment (poor water and sanitation indicators) was significantly associated with the caste of individual household (P=.001), and the path was mediated through the socioeconomic status and density of waste spots (liquid and solid) of the sector in which these households were located. Ground-truthing for ascertaining the land parcel level accuracies, community involvement in mapping exercise, and identification of small habitations not recorded in the administrative data were key learnings.ConclusionsThe SOMAARTH DDESS experience allowed us to document and explore dynamic relationships, associations, and pathways across multiple levels of the system (ie, individual, household, neighborhood, and village) through a geospatial interface. This could be used for characterization and monitoring of a wide range of proximal and distal determinants of health.

Dynamic Geospatial Modeling of the Building Stock To Project Urban Energy Demand.

In the United States, buildings account for more than 40% of total energy consumption and the evolution of the urban form will impact the effectiveness of strategies to reduce energy use and mitigate emissions. This paper presents a broadly applicable approach for modeling future commercial, residential, and industrial floorspace, thermal consumption (heating and cooling), and associated GHG emissions at the tax assessor land parcel level. The approach accounts for changing building standards and retrofitting, climate change, and trends in housing and industry. We demonstrate the automated workflow for California and project building stock, thermal energy consumption, and associated GHG emissions out to 2050. Our results suggest that if buildings in California have long lifespans, and minimal energy efficiency improvements compared to building codes reflective of 2008, then the state will face a 20% or higher increase in thermal energy consumption by 2050. Baseline annual GHG emissions associated with thermal energy consumption in the modeled building stock in 2016 is 34% below 1990 levels (110 Mt CO2eq/y). While the 2020 targets for the reduction of GHG emissions set by the California Senate Bill 350 have already been met, none of our scenarios achieve >80% reduction from 1990 levels by 2050, despite assuming an 86% reduction in electricity carbon intensity in our "Low Carbon" scenario. The results highlight the challenge California faces in meeting its new energy efficiency targets unless the State's building stock undergoes timely and strategic turnover, paired with deep retrofitting of existing buildings and natural gas equipment.

Holding the market under the stimulus plan: Local government financing vehicles' land purchasing behavior in China

China's stimulus plan in 2009–2010 brought local government financing vehicles (LGFVs) and new types of land finance into the spotlight. This paper uses national parcel-level land transaction data to examine the causes and consequences of LGFVs' land purchasing behavior in China. We found that LGFVs overbid significantly in terms of land prices. We explore channels through which LGFVs bid high prices for land. The stimulus plan induced local government to increase debt and rely more on land-based mortgages and land leasing revenue. Fiscal pressure led to an increase in LGFVs bidding for land. We found that the stimulus plan changed local governments' control over land leasing and land finance. Local governments hold more of the land market and inflate land prices following implementation of the stimulus plan.

Mapping the landscape of urban work: Home-based businesses and the built environment

Home-based businesses represent a large and growing portion of the economy, though little is known beyond limited surveys. This paper describes a novel method of identifying businesses located within residences using parcel-level land use data across 15 counties in California and analyzes their evolution from 1997 to 2014, focusing on their distribution across neighborhoods. Home-based business represented nearly one in six businesses in 2014, and employment in home-based businesses outpaced overall employment growth 37 to 24% from 1997 to 2014. While home-based businesses are associated with both middle-income and wealthy neighborhoods, only in southern California were they associated with growing shares of single-family housing, low population density, and homeownership rates. While prior research emphasizes the importance of technologically and knowledge-intensive services across a variety of home working arrangements, this study reveals that the industrial composition of home-based businesses is roughly equally comprised of knowledge-intensive services and basic economic activity.

Agricultural land‐use change and its drivers in Terceira Island, Portugal (2008–2013)

AbstractThis work aims at analysing how compensatory direct payments regimes to farmers influence land‐use patterns and changes on agricultural landscape. For this purpose a case‐study examines land‐use changes in Terceira Island (Azores, Portugal) for the period of 2008–2013. It is specifically focused on the land‐use changes associated to maize for silage annually declared on the detailed land parcels by farmers which apply for direct payments under the Common Agricultural Policy (CAP). A total increase of 28 per cent is reported on arable crops area (mostly maize silage) for the period. This process should be related not only to the agricultural coupled support policy for arable crops but also to the relative prices of farm products and raw materials for animal feed. The access facilities to the land parcels appear to be another major farm‐related factor at local context. A logistic regression analysis is performed at the land parcel level and the occurrence of the agricultural land‐use ‘maize for silage’ is explained by a set of explanatory variables. The independent variables comprise biophysical factors and socio‐economic factors. Results indicate biophysical factors (average annual temperature, annual accumulated precipitation, slope and soil agricultural use capability), accessibility, farm typology, previous land‐use, arable crops aid, milk price and bovine meat price as key factors for maize silage land‐use occupancy on Terceira Island. These conclusions seem valuable for decision‐making on the implementation of coupled support schemes under agricultural policies and their impacts on spatial arrangements in land‐use dynamics and landscape change.

SENSING URBAN LAND-USE PATTERNS BY INTEGRATING GOOGLE TENSORFLOW AND SCENE-CLASSIFICATION MODELS

Abstract. With the rapid progress of China’s urbanization, research on the automatic detection of land-use patterns in Chinese cities is of substantial importance. Deep learning is an effective method to extract image features. To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features. Using the Google Tensorflow framework, a powerful convolution neural network (CNN) library was created. First, the transferred model was previously trained on ImageNet, one of the largest object-image data sets, to fully develop the model’s ability to generate feature vectors of standard remote-sensing land-cover data sets (UC Merced and WHU-SIRI). Then, a random-forest-based classifier was constructed and trained on these generated vectors to classify the actual urban land-use pattern on the scale of traffic analysis zones (TAZs). To avoid the multi-scale effect of remote-sensing imagery, a large random patch (LRP) method was used. The proposed method could efficiently obtain acceptable accuracy (OA = 0.794, Kappa = 0.737) for the study area. In addition, the results show that the proposed method can effectively overcome the multi-scale effect that occurs in urban land-use classification at the irregular land-parcel level. The proposed method can help planners monitor dynamic urban land use and evaluate the impact of urban-planning schemes.

Educational needs and perceptions of the sustainability of precision agriculture: survey evidence from Greece

Precision agriculture (PA) constitutes a dynamic production method which is gaining attention in several parts of the world. Its environmental and economic sustainability has been examined in terms of its ability to reduce the adverse effects of agrochemical use—by regulating their application to the levels needed at the land parcel level—and of its contribution to higher incomes and profitability. At the social level, PA has been linked to collective action although little insight is available regarding the role of various actors and education. This study tackles PA through an assessment of the attitudes of farmers towards the elements of its sustainability and of their educational needs. The analysis of survey data of a sample of young farmers in Greece showed that the majority of respondents were not familiar with PA. Significant differences were found between the attitudes of knowledgeable and non-knowledgeable farmers, the former demonstrating better acknowledgement of the environmental, economic and social sustainability of PA. Important educational needs were also detected, with group and individual methods being the most preferred ones for education and information campaigns. The results of the analysis could be of use for the design of Common Agricultural Policy Pillar II measures for the promotion of PA targeting to specific audiences and actors.

Simulating urban land-use changes at a large scale by integrating dynamic land parcel subdivision and vector-based cellular automata

ABSTRACTCellular automata (CA) have been widely used to simulate complex urban development processes. Previous studies indicated that vector-based cellular automata (VCA) could be applied to simulate urban land-use changes at a realistic land parcel level. Because of the complexity of VCA, these studies were conducted at small scales or did not adequately consider the highly fragmented processes of urban development. This study aims to build an effective framework called dynamic land parcel subdivision (DLPS)-VCA to accurately simulate urban land-use change processes at the land parcel level. We introduce this model in urban land-use change simulations to reasonably divide land parcels and introduce a random forest algorithm (RFA) model to explore the transition rules of urban land-use changes. Finally, we simulate the land-use changes in Shenzhen between 2009 and 2014 via the proposed DLPS-VCA model. Compared to the advanced Patch-CA and RFA-VCA models, the DLPS-VCA model achieves the highest simulation accuracy (Figure-of-Merit = 0.232), which is 32.57% and 18.97% higher respectively, and is most similar to the actual land-use scenario (similarity = 94.73%) at the pattern level. These results indicate that the DLPS-VCA model can both accurately split the land during urban land-use changes and significantly simulate urban expansion and urban land-use changes at a fine scale. Furthermore, the land-use change rules that are based on DPLS-VCA mining and the simulation results of several future urban development scenarios can act as guides for future urban planning policy formulation.

Social sensing of urban land use based on analysis of Twitter users' mobility patterns.

A number of recent studies showed that digital footprints around built environments, such as geo-located tweets, are promising data sources for characterizing urban land use. However, challenges for achieving this purpose exist due to the volume and unstructured nature of geo-located social media. Previous studies focused on analyzing Twitter data collectively resulting in coarse resolution maps of urban land use. We argue that the complex spatial structure of a large collection of tweets, when viewed through the lens of individual-level human mobility patterns, can be simplified to a series of key locations for each user, which could be used to characterize urban land use at a higher spatial resolution. Contingent issues that could affect our approach, such as Twitter users’ biases and tendencies at locations where they tweet the most, were systematically investigated using 39 million geo-located Tweets and two independent datasets of the City of Chicago: 1) travel survey and 2) parcel-level land use map. Our results support that the majority of Twitter users show a preferential return, where their digital traces are clustered around a few key locations. However, we did not find a general relation among users between the ranks of locations for an individual—based on the density of tweets—and their land use types. On the contrary, temporal patterns of tweeting at key locations were found to be coherent among the majority of users and significantly associated with land use types of these locations. Furthermore, we used these temporal patterns to classify key locations into generic land use types with an overall classification accuracy of 0.78. The contribution of our research is twofold: a novel approach to resolving land use types at a higher resolution, and in-depth understanding of Twitter users’ location-related and temporal biases, promising to benefit human mobility and urban studies in general.

Spatial and temporal modeling of parcel-level land dynamics

Neighborhood and historical conditions are important factors in land dynamics. However, models that explicitly incorporate spatial and temporal dependencies face challenges in data availability, methodology and computation. In this research, parcel-level dynamics are investigated using the geocoded Auditor's tax database for Delaware County, Ohio, including 73,560 parcels over the period 1990–2012. A binary spatio-temporal autologistic model (STARM), incorporating space and time and their interactions, is used to investigate parcel-level dynamics. The results show that the model is able capture the impacts of contemporaneous and historical neighborhood conditions around parcels, as well as the effects of other variables such as distances to various facilities and infrastructures, agricultural and residential land-use shares within a half mile radius circle, and population density and growth expectation at the census tract level.

EFarm: A Tool for Better Observing Agricultural Land Systems.

Currently, observations of an agricultural land system (ALS) largely depend on remotely-sensed images, focusing on its biophysical features. While social surveys capture the socioeconomic features, the information was inadequately integrated with the biophysical features of an ALS and the applications are limited due to the issues of cost and efficiency to carry out such detailed and comparable social surveys at a large spatial coverage. In this paper, we introduce a smartphone-based app, called eFarm: a crowdsourcing and human sensing tool to collect the geotagged ALS information at the land parcel level, based on the high resolution remotely-sensed images. We illustrate its main functionalities, including map visualization, data management, and data sensing. Results of the trial test suggest the system works well. We believe the tool is able to acquire the human–land integrated information which is broadly-covered and timely-updated, thus presenting great potential for improving sensing, mapping, and modeling of ALS studies.

Land Use Change Dynamics in Southern California: Does Geographic Elasticity Matter?

This article examines how municipal planning contexts can shape urban land use dynamics by investigating the parcel-level land use changes in a five-county Southern California metropolitan area between 1990 and 2005. An analysis, based on a multinomial logit model, shows that land use change patterns significantly vary by municipalities that were situated in heterogeneous planning contexts. More specifically, cities with limited ability to expand their jurisdictional boundaries are found to provide more recreational areas and urban open spaces, while restricting nonconventional land uses. However, no evidence of a shift from single-family to multifamily residential development is detected for such cities.

Harbour-side land parcel land-use changes: significance in re-development planning permit appraisal in Melbourne, Australia

Results are presented of spatial query at the land parcel level of a (digital) spatial database, referring to the twentieth century Harbour-side zone of the Port of Melbourne. They refer mainly to land-use histories of individual land parcels. Such histories can be now deployed routinely in decision support during assessment of heritage potential in aid of re-development/excavation permit appraisal.Such query has long been possible in a general way: the innovation brought forward in this presentation refers to the new level of detail that is achieved by adopting digital spatial database query. The prerequisite for such query is the kind of digital spatial database that we have built from imposing spatial compatibility on archival maps and air photos.It is argued that much interest will attach to implementing the spatial database building process exemplified in this paper for decision-making in planning permit appraisal. For instance, contaminated ground might be better identified. Modern data handling tools make this feasible in a routine way if the necessary data and information flow paths and data sharing can be arranged.

Characterizing Urban Fabric Properties and Their Thermal Effect Using QuickBird Image and Landsat 8 Thermal Infrared (TIR) Data: The Case of Downtown Shanghai, China

The combined usage of high-resolution satellite images and thermal infrared (TIR) data helps understanding the thermal effect of urban fabric properties and the mechanism of urban heat island (UHI) formation. In this study, three typical urban functional zones (UFZs) of downtown Shanghai were chosen for quantifying the relationship between fine-scale urban fabric properties and their thermal effect. Nine land surfaces and 146 aggregated land parcels extracted from a QuickBird image (dated 14 April 2014) were used to characterize urban fabric properties. The thermal effect was deduced from land surface temperature (LST), intra-UHI intensity, blackbody flux density (BBFD) and blackbody flux (BBF). The net BBF was retrieved from the Landsat 8 TIR band 10 dated 13 August 2013, and 28 May 2014. The products were resampled to fine resolution using a geospatial sharpening approach and further validated. The results show that: (1) On the UFZ level, there is a significant thermal differential among land surfaces. Water, well-vegetated land, high-rises with light color and high-rises with glass curtain walls exhibited relatively low LST, UHI intensity and BBFD. In contrast, mobile homes with light steel roofs, low buildings with bituminous roofs, asphalt roads and composite material pavements showed inverse trends for LST, UHI intensity, and BBFD; (2) It was found that parcel-based per ha net BBF, which offsets the “size-effect” among parcels, is more reasonable and comparable when quantifying excess surface flux emitted by the parcels; (3) When examining the relationship between parcel-level land surfaces and per ha BBF, a partial least squares (PLS) regression model showed that buildings and asphalt roads are major contributors to parcel-based per ha BBF, followed by other impervious surfaces. In contrast, vegetated land and water contribute with a much lower per ha net BBF to parcel warming.

Supporting the risk management process with land information: a case study of Australia.

It is frequently argued that, at the parcel level, stakeholders are capable of and well supported in managing their land-related risks. Yet, evidence from the contemporary Australian context suggests otherwise: numerous large-scale disaster events have revealed that citizens are ill-prepared to respond and recover adequately. This paper begins with the premise that information, specifically land information, could better support parcel-level risk preparation, mitigation, response, and recovery. State land administration organisations in Australia primarily maintain this information and make it accessible. Land information is used regularly across all levels of government to support risk management activities; however, such application has not always occurred at the parcel and citizen level. Via a case study approach, this paper initially explores the land information available in Australia to stakeholders interested in parcel-level detail, and then goes on to propose how the utilisation of parcel-level land information could serve to enhance risk management practices.

Potential Impacts of Future Warming and Land Use Changes on Intra-Urban Heat Exposure in Houston, Texas.

Extreme heat events in the United States are projected to become more frequent and intense as a result of climate change. We investigated the individual and combined effects of land use and warming on the spatial and temporal distribution of daily minimum temperature (Tmin) and daily maximum heat index (HImax) during summer in Houston, Texas. Present-day (2010) and near-future (2040) parcel-level land use scenarios were embedded within 1-km resolution land surface model (LSM) simulations. For each land use scenario, LSM simulations were conducted for climatic scenarios representative of both the present-day and near-future periods. LSM simulations assuming present-day climate but 2040 land use patterns led to spatially heterogeneous temperature changes characterized by warmer conditions over most areas, with summer average increases of up to 1.5°C (Tmin) and 7.3°C (HImax) in some newly developed suburban areas compared to simulations using 2010 land use patterns. LSM simulations assuming present-day land use but a 1°C temperature increase above the urban canopy (consistent with warming projections for 2040) yielded more spatially homogeneous metropolitan-wide average increases of about 1°C (Tmin) and 2.5°C (HImax), respectively. LSM simulations assuming both land use and warming for 2040 led to summer average increases of up to 2.5°C (Tmin) and 8.3°C (HImax), with the largest increases in areas projected to be converted to residential, industrial and mixed-use types. Our results suggest that urbanization and climate change may significantly increase the average number of summer days that exceed current threshold temperatures for initiating a heat advisory for metropolitan Houston, potentially increasing population exposure to extreme heat.

Combining smart card data and household travel survey to analyze jobs–housing relationships in Beijing

Location Based Services (LBS) provide a new perspective for spatiotemporally analyzing dynamic urban systems. Research has investigated urban dynamics using LBS. However, less attention has been paid to the analysis of urban structure (especially commuting pattern) using smart card data (SCD), which are widely available in most large cities in China, and even in the world. This paper combines bus SCD for a one-week period with a oneday household travel survey, as well as a parcel-level land use map to identify job–housing locations and commuting trip routes in Beijing. Two data forms are proposed, one for jobs–housing identification and the other for commuting trip route identification. The results of the identification are aggregated in the bus stop and traffic analysis zone (TAZ) scales, respectively. Particularly, commuting trips from three typical residential communities to six main business zones are mapped and compared to analyze commuting patterns in Beijing. The identified commuting trips are validated by comparison with those from the survey in terms of commuting time and distance, and the positive validation results prove the applicability of our approach. Our experiment, as a first step toward enriching LBS data using conventional survey and urban GIS data, can obtain solid identification results based on rules extracted from existing surveys or censuses.