sustainability-logo

Journal Browser

Journal Browser

Applications of Artificial Intelligence in the Study of Land Use and Land Cover Change

A special issue of Sustainability (ISSN 2071-1050). This special issue belongs to the section "Environmental Sustainability and Applications".

Deadline for manuscript submissions: closed (30 September 2019) | Viewed by 42507

Special Issue Editors

Center for Applied Geographic Information Science and Department of Geography and Earth Sciences, University of North Carolina at Charlotte, 9201 University City Blvd, Charlotte, NC 28223, USA
Interests: GIS and spatial analysis and modeling; agent-based models and spatiotemporal simulation; cyberinfrastructure and high-performance computing; complex adaptive spatial systems; land use and land cover change
Special Issues, Collections and Topics in MDPI journals
Department of Geography and Sustainability Sciences, the University of Iowa, Iowa City, IA 52242, USA
Interests: Geographic Information Science; the process and effects of environmental decision-making; human–environment interactions

Special Issue Information

Dear Colleagues,

Artificial intelligence has been increasingly used to support the study of coupled land systems, which are complex adaptive spatial systems driven by land use and land cover change. These artificial intelligence approaches comprise machine learning (e.g., artificial neural networks), evolutionary computation, and distributed artificial intelligence (e.g., agent-based models, cellular automata, and swarm intelligence). Recent developments in deep learning together with big data represent unique opportunities for using artificial intelligence to further advance spatiotemporally explicit land change modeling. However, applications of these cutting-edge artificial intelligence approaches into the study of land use and land cover change to tackle the associated spatiotemporal complexity pose grand challenges. This Special Issue aims to explore various applications of artificial intelligence approaches to the study of land use and land cover change, including but not limited to, natural resource management, agricultural land management, urban development, archaeology, public health, and transportation. The Special Issue will focus on investigating how cutting-edge artificial intelligence approaches advance the spatiotemporally explicit land change modeling and associated knowledge in these domain studies. This investigation will provide insights into the complexity of related processes and, thus, the sustainability of coupled land systems.

Prof. Dr. Wenwu Tang
Prof. Dr. David A. Bennett
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sustainability is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Land Sustainability
  • Environmental and Resource Sustainability
  • Land Use and Land Cover Change
  • Artificial Intelligence
  • Complex Adaptive Spatial Systems

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 4901 KiB  
Article
Spatial Simulation Modeling of Settlement Distribution Driven by Random Forest: Consideration of Landscape Visibility
by Minrui Zheng, Wenwu Tang, Akinwumi Ogundiran and Jianxin Yang
Sustainability 2020, 12(11), 4748; https://doi.org/10.3390/su12114748 - 10 Jun 2020
Cited by 9 | Viewed by 2464
Abstract
Settlement models help to understand the social–ecological functioning of landscape and associated land use and land cover change. One of the issues of settlement modeling is that models are typically used to explore the relationship between settlement locations and associated influential factors (e.g., [...] Read more.
Settlement models help to understand the social–ecological functioning of landscape and associated land use and land cover change. One of the issues of settlement modeling is that models are typically used to explore the relationship between settlement locations and associated influential factors (e.g., slope and aspect). However, few studies in settlement modeling adopted landscape visibility analysis. Landscape visibility provides useful information for understanding human decision-making associated with the establishment of settlements. In the past years, machine learning algorithms have demonstrated their capabilities in improving the performance of the settlement modeling and particularly capturing the nonlinear relationship between settlement locations and their drivers. However, simulation models using machine learning algorithms in settlement modeling are still not well studied. Moreover, overfitting issues and optimization of model parameters are major challenges for most machine learning algorithms. Therefore, in this study, we sought to pursue two research objectives. First, we aimed to evaluate the contribution of viewsheds and landscape visibility to the simulation modeling of - settlement locations. The second objective is to examine the performance of the machine learning algorithm-based simulation models for settlement location studies. Our study region is located in the metropolitan area of Oyo Empire, Nigeria, West Africa, ca. AD 1570–1830, and its pre-Imperial antecedents, ca. AD 1360–1570. We developed an event-driven spatial simulation model enabled by random forest algorithm to represent dynamics in settlement systems in our study region. Experimental results demonstrate that viewsheds and landscape visibility may offer more insights into unveiling the underlying mechanism that drives settlement locations. Random forest algorithm, as a machine learning algorithm, provide solid support for establishing the relationship between settlement occurrences and their drivers. Full article
Show Figures

Figure 1

23 pages, 5199 KiB  
Article
Urban Shape and Built Density Metrics through the Analysis of European Urban Fabrics Using Artificial Intelligence
by Francisco Javier Abarca-Alvarez, Francisco Sergio Campos-Sánchez and Fernando Osuna-Pérez
Sustainability 2019, 11(23), 6622; https://doi.org/10.3390/su11236622 - 23 Nov 2019
Cited by 7 | Viewed by 4509
Abstract
In recent decades, the concept of urban density has been considered key to the creation of sustainable urban fabrics. However, when it comes to measuring the built density, a difficulty has been observed in defining valid measurement indicators universally. With the intention of [...] Read more.
In recent decades, the concept of urban density has been considered key to the creation of sustainable urban fabrics. However, when it comes to measuring the built density, a difficulty has been observed in defining valid measurement indicators universally. With the intention of identifying the variables that allow the best characterization of the shape of urban fabrics and of obtaining the metrics of their density, a multi-variable analysis methodology from the field of artificial intelligence is proposed. The main objective of this paper was to evaluate the capacity and interest of such a methodology from standard indicators of the built density, measured at various urban scales, (i) to cluster differentiated urban profiles in a robust way by assessing the results statistically, and (ii) to obtain the metrics that characterize them with an identity. As a case study, this methodology was applied to the state of the art European urban fabrics (N = 117) by simultaneously integrating 13 regular parameters to qualify urban shape and density. It was verified that the profiles obtained were more robust than those based on a limited number of indicators, evidencing that the proposed methodology offers operational opportunities in urban management by allowing the comparison of a fabric with the identified profiles. Full article
Show Figures

Graphical abstract

17 pages, 8270 KiB  
Article
Classifying Street Spaces with Street View Images for a Spatial Indicator of Urban Functions
by Zhaoya Gong, Qiwei Ma, Changcheng Kan and Qianyun Qi
Sustainability 2019, 11(22), 6424; https://doi.org/10.3390/su11226424 - 15 Nov 2019
Cited by 35 | Viewed by 4848
Abstract
Streets, as one type of land use, are generally treated as developed or impervious areas in most of the land-use/land-cover studies. This coarse classification substantially understates the value of streets as a type of public space with the most complexity. Street space, being [...] Read more.
Streets, as one type of land use, are generally treated as developed or impervious areas in most of the land-use/land-cover studies. This coarse classification substantially understates the value of streets as a type of public space with the most complexity. Street space, being an important arena for urban vitality, is valued by various dimensions, such as transportation, recreation, aesthetics, public health, and social interactions. Traditional remote sensing approaches taking a sky viewpoint cannot capture these dimensions not only due to the resolution issue but also the lack of a citizen viewpoint. The proliferation of street view images provides an unprecedented opportunity to characterize street spaces from a citizen perspective at the human scale for an entire city. This paper aims to characterize and classify street spaces based on features extracted from street view images by a deep learning model of computer vision. A rule-based clustering method is devised to support the empirically generated classification of street spaces. The proposed classification scheme of street spaces can serve as an indirect indicator of place-related functions if not a direct one, once its relationship with urban functions is empirically tested and established. This approach is empirically applied to Beijing city to demonstrate its validity. Full article
Show Figures

Figure 1

27 pages, 7957 KiB  
Article
Delineation of Urban Growth Boundaries Using a Patch-Based Cellular Automata Model under Multiple Spatial and Socio-Economic Scenarios
by Jianxin Yang, Jian Gong, Wenwu Tang, Yang Shen, Chunyan Liu and Jing Gao
Sustainability 2019, 11(21), 6159; https://doi.org/10.3390/su11216159 - 04 Nov 2019
Cited by 24 | Viewed by 3435
Abstract
The urban growth boundary (UGB) plays an important role in the regulation of urban sprawl and the conservation of natural ecosystems. The delineation of UGBs is a common strategy in urban planning, especially in metropolitan areas undergoing fast expansion. However, reliable tools for [...] Read more.
The urban growth boundary (UGB) plays an important role in the regulation of urban sprawl and the conservation of natural ecosystems. The delineation of UGBs is a common strategy in urban planning, especially in metropolitan areas undergoing fast expansion. However, reliable tools for the delineation of informed UGBs are still not widely available for planners. In this study, a patch-based cellular automaton (CA) model was applied to build UGBs, in which urban expansions were represented as organic and spontaneous patch growing processes. The proposed CA model enables the modeler to build various spatial and socio-economic scenarios for UGB delineation. Parameters that control the patch size and shape, along with the spatial compactness of an urban growth pattern, were optimized using a genetic algorithm. A random forest model was employed to estimate the probability of urban development. Six scenarios in terms of the demand and the spatial pattern of urban land allocation were constructed to generate UGB alternatives based on the simulated urban land maps from the CA model. Application of the proposed model in Ezhou, China from 2004 to 2030 reveals that the model proposed in this study can help urban planners make informed decisions on the delineation of UGBs under different scenarios. Full article
Show Figures

Figure 1

23 pages, 4397 KiB  
Article
CART-RF Classification with Multifilter for Monitoring Land Use Changes Based on MODIS Time-Series Data: A Case Study from Jiangsu Province, China
by Le’an Qu, Zhenjie Chen and Manchun Li
Sustainability 2019, 11(20), 5657; https://doi.org/10.3390/su11205657 - 14 Oct 2019
Cited by 4 | Viewed by 2419
Abstract
The periodic determination of land use changes over large areas is crucial for improving our understanding of land system dynamics. Jiangsu lies at the center of China’s Yangtze Delta and has one of the fastest-developing economies in China. However, it is also a [...] Read more.
The periodic determination of land use changes over large areas is crucial for improving our understanding of land system dynamics. Jiangsu lies at the center of China’s Yangtze Delta and has one of the fastest-developing economies in China. However, it is also a region where serious conflicts exist between the available land resources and the human demand for land. To address these conflicts, it is important to analyze the patterns of land use change in Jiangsu, as they can serve as a useful reference for other rapidly urbanizing regions in China as well as other developing countries. In this study, we propose a method of classification and regression tree-random forest (CART-RF) classification with a multifilter based on time-series Moderate Resolution Imaging Spectroradiometer (MODIS) imaging data. The proposed method integrates the CART decision tree and the random forest algorithms (CART-RF) to obtain accurate yearly land use data for large areas from multivariate time-series remote sensing data and employs a spatial-temporal-logical filter to exclude any abnormal changes in the multivariate time-series pixel data. The obtained results indicated that (1) the CART-RF classifier is effective for land use classification based on the multivariate time-series MODIS data, with the overall classification accuracy being greater than 90%; (2) the use of the proposed combinatorial spatial-temporal-logical filtering method effectively eliminates most anomalous changes and minimizes the effects of “salt-and-pepper” noise; and (3) from 2000 to 2015, land use in Jiangsu province underwent significant and spatiotemporally heterogeneous changes on a province-wide scale, owing to various factors, such as those related to the economy, location, and government policies. These changes were manifested as continuous expansions in the built-up land at the expense of farmland. While this expansion of built-up land has been very rapid in southern Jiangsu, especially in the region close to Yangtze River Delta, it has been relatively slower in northern Jiangsu. Full article
Show Figures

Figure 1

18 pages, 4292 KiB  
Article
Short-Term Forecasting of Land Use Change Using Recurrent Neural Network Models
by Cong Cao, Suzana Dragićević and Songnian Li
Sustainability 2019, 11(19), 5376; https://doi.org/10.3390/su11195376 - 28 Sep 2019
Cited by 18 | Viewed by 3629
Abstract
Land use change (LUC) is a dynamic process that significantly affects the environment, and various approaches have been proposed to analyze and model LUC for sustainable land use management and decision making. Recurrent neural network (RNN) models are part of deep learning (DL) [...] Read more.
Land use change (LUC) is a dynamic process that significantly affects the environment, and various approaches have been proposed to analyze and model LUC for sustainable land use management and decision making. Recurrent neural network (RNN) models are part of deep learning (DL) approaches, which have the capability to capture spatial and temporal features from time-series data and sequential data. The main objective of this study was to examine variants of the RNN models by applying and comparing them when forecasting LUC in short time periods. Historical land use data for the City of Surrey, British Columbia, Canada were used to implement the several variants of the RNN models. The land use (LU) data for years 1996, 2001, 2006, and 2011 were used to train the DL models to enable the short-term forecast for the year 2016. For the 2011 to 2016 period, only 4.5% of the land use in the study area had changed. The results indicate that an overall accuracy of 86.9% was achieved, while actual changes in each LU type were forecasted with a relatively lower accuracy. However, only 25% of changed raster cells correctly forecasted the land use change. This research study demonstrates that RNN models provide a suite of valuable tools for short-term LUC forecast that can inform and complement the traditional long-term planning process; however, further additional geospatial data layers and considerations of driving factors of LUC need to be incorporated for model improvements. Full article
Show Figures

Figure 1

21 pages, 5992 KiB  
Article
A Self-Predictable Crop Yield Platform (SCYP) Based On Crop Diseases Using Deep Learning
by SangSik Lee, YiNa Jeong, SuRak Son and ByungKwan Lee
Sustainability 2019, 11(13), 3637; https://doi.org/10.3390/su11133637 - 02 Jul 2019
Cited by 21 | Viewed by 4158
Abstract
This paper proposes a self-predictable crop yield platform (SCYP) based on crop diseases using deep learning that collects weather information (temperature, humidity, sunshine, precipitation, etc.) and farm status information (harvest date, disease information, crop status, ground temperature, etc.), diagnoses crop diseases by using [...] Read more.
This paper proposes a self-predictable crop yield platform (SCYP) based on crop diseases using deep learning that collects weather information (temperature, humidity, sunshine, precipitation, etc.) and farm status information (harvest date, disease information, crop status, ground temperature, etc.), diagnoses crop diseases by using convolutional neural network (CNN), and predicts crop yield based on factors such as climate change, crop diseases, and others by using artificial neural network (ANN). The SCYP consists of an image preprocessing module (IPM) to determine crop diseases through the Google Vision API and image resizing, a crop disease diagnosis module (CDDM) based on CNN to diagnose the types and extent of crop diseases through photographs, and a crop yield prediction module (CYPM) based on ANN by using information of crop diseases, remaining time until harvest (based on the date), current temperature, humidity and precipitation (amount of snowfall) in the area, sunshine amount, ground temperature, atmospheric pressure, moisture evaporation in the ground, etc. Four experiments were conducted to verify the efficiency of the SCYP. In the CDMM, the accuracy and operation time of each model were measured using three neural network models: CNN, region-CNN(R-CNN), and you only look once (YOLO). In the CYPM, rectified linear unit (ReLU), Sigmoid, and Step activation functions were compared to measure ANN accuracy. The accuracy of CNN was about 3.5% higher than that of R-CNN and about 5.4% higher than that of YOLO. The operation time of CNN was about 37 s less than that of R-CNN and about 72 s less than that of YOLO. The CDDM had slightly less operation time, but in this paper, we prefer accuracy over operation time to diagnose crop diseases efficiently and accurately. When the activation function of the ANN used in the CYPM was ReLU, the accuracy of the ANN was 2% higher than that of Sigmoid and 7% higher than that of Step. The CYPM prediction was about 34% more accurate when using multiple diseases than when not using them. Therefore, the SCYP can predict farm yields more accurately than traditional methods. Full article
Show Figures

Figure 1

24 pages, 4415 KiB  
Article
Agent-Based Modeling of Sustainable Ecological Consumption for Grasslands: A Case Study of Inner Mongolia, China
by Huimin Yan, Lihu Pan, Zhichao Xue, Lin Zhen, Xuehong Bai, Yunfeng Hu and He-Qing Huang
Sustainability 2019, 11(8), 2261; https://doi.org/10.3390/su11082261 - 15 Apr 2019
Cited by 15 | Viewed by 4437
Abstract
Sustainable ecosystem services consumption is of vital importance to the survival and development of human society. How to balance the conflicts between ecosystem protection and ecosystem services consumption by local residents has been a serious challenge, especially in ecologically vulnerable areas. To explore [...] Read more.
Sustainable ecosystem services consumption is of vital importance to the survival and development of human society. How to balance the conflicts between ecosystem protection and ecosystem services consumption by local residents has been a serious challenge, especially in ecologically vulnerable areas. To explore the reasonable ecosystem services consumption approaches of grassland ecosystems for sustainable land system management, this study takes Hulun Buir of the Inner Mongolia Autonomous Region as a case study region and develops an EcoC-G (ecological consumption of grassland) model based on herders’ livelihood behaviors using the agent-based model technique to simulate the dynamics of ecosystem pressure, livestock production, and living quality of herders under different grassland management scenarios over the next 30 years. The EcoC-G model links the supply and consumption of grassland ecosystem services by calculating the ecosystem net primary productivity (NPP) supply and household NPP consumption. The model includes three sub-models, namely, the individual status transferring sub-model, the households’ grassland-use decision sub-model, and the ecosystem pressure sub-model. In accordance with multi-objective grassland management practices, the following four land management scenarios were simulated: (1) baseline scenario, (2) increasing household’s living standard, (3) ecosystem protection, and (4) balancing living standard improvement with the protection of the ecosystem. The result indicates that by focusing on the NPP supply and consumption of the grassland ecosystem, the EcoC-G is capable of simulating the impacts of herders’ livelihood behaviors on grassland ecosystems. If timely grassland management strategies are implemented, it is possible to relieve the ecosystem pressure and improve the livelihood of local herders. The specific scenario simulation results are: (1) Under the current grassland management mode, the pasture could never be overgrazed, and herders could achieve the basic living standard, but the accumulated wealth decreased due to the decline of livestock. (2) With grazing control, herders can accumulate wealth by increasing the breeding amount and reducing the marketing rate, but the ecosystem consumption pressure can reach a maximum of 2.3 times. (3) With strict restrictions on the livestock number, the pressure on the ecosystem decreases; however, herders might not achieve basic living standards. (4) Modest regulation leads to rational ecological consumption intervals, meaning the ecosystem pressure will become stable and herders can gradually accumulate wealth with the achievement of basic living standards in advance. Full article
Show Figures

Figure 1

14 pages, 2482 KiB  
Article
Combining Artificial Neural Networks and GIS Fundamentals for Coastal Erosion Prediction Modeling
by Angeliki Peponi, Paulo Morgado and Jorge Trindade
Sustainability 2019, 11(4), 975; https://doi.org/10.3390/su11040975 - 14 Feb 2019
Cited by 23 | Viewed by 5184
Abstract
The complexities of coupled environmental and human systems across the space and time of fragile systems challenge new data-driven methodologies. Combining geographic information systems (GIS) and artificial neural networks (ANN) allows us to design a model that forecasts the erosion changes in Costa [...] Read more.
The complexities of coupled environmental and human systems across the space and time of fragile systems challenge new data-driven methodologies. Combining geographic information systems (GIS) and artificial neural networks (ANN) allows us to design a model that forecasts the erosion changes in Costa da Caparica, Lisbon, Portugal, for 2021, with a high accuracy level. The GIS–ANN model proves to be a powerful tool, as it analyzes and provides the “where” and the “why” dynamics that have happened or will happen in the future. According to the literature, ANNs present noteworthy advantages compared to the other methods that are used for prediction and decision making in urban coastal areas. In order to conduct a sensitivity analysis on natural and social forces, as well as dynamic relations in the dune–beach system of the study area, two types of ANNs were tested on a GIS environment: radial basis function (RBF) and multilayer perceptron (MLP). The GIS–ANN model helps to understand the factors that impact coastal erosion changes, and the importance of having an intelligent environmental decision support system to address these risks. This quantitative knowledge of the erosion changes and the analytical map-based frame are essential for an integrated management of the area and the establishment of pro-sustainability policies. Full article
Show Figures

Figure 1

19 pages, 7457 KiB  
Article
Comparison of Approaches for Urban Functional Zones Classification Based on Multi-Source Geospatial Data: A Case Study in Yuzhong District, Chongqing, China
by Kai Cao, Hui Guo and Ye Zhang
Sustainability 2019, 11(3), 660; https://doi.org/10.3390/su11030660 - 27 Jan 2019
Cited by 27 | Viewed by 4374
Abstract
Accurate and timely classification and monitoring of urban functional zones prove to be significant in rapidly developing cities, to better understand the real and varying urban functions of cities to support urban planning and management. Many efforts have been undertaken to identify urban [...] Read more.
Accurate and timely classification and monitoring of urban functional zones prove to be significant in rapidly developing cities, to better understand the real and varying urban functions of cities to support urban planning and management. Many efforts have been undertaken to identify urban functional zones using various classification approaches and multi-source geospatial datasets. The complexity of this category of classification poses tremendous challenges to these studies especially in terms of classification accuracy, but on the opposite, the rapid development of machine learning technologies provides us with new opportunities. In this study, a set of commonly used urban functional zones classification approaches, including Multinomial Logistic Regression, K-Nearest Neighbors, Decision Tree, Support Vector Machine (SVM), and Random Forest, are examined and compared with the newly developed eXtreme Gradient Boosting (XGBoost) model, using the case study of Yuzhong District, Chongqing, China. The investigation is based on multi-variate geospatial data, including night-time imagery, geotagged Weibo data, points of interest (POI) from Gaode, and Baidu Heat Map. This study is the first endeavor of implementing the XGBoost model in the field of urban functional zones classification. The results suggest that the XGBoost classification model performed the best and was able to achieve an accuracy of 88.05%, which is significantly higher than the other commonly used approaches. In addition, the integration of night-time imagery, geotagged Weibo data, POI from Gaode, and Baidu Heat Map has also demonstrated their values for the classification of urban functional zones in this case study. Full article
Show Figures

Figure 1

Back to TopTop