Spatially explicit simulation of land use/land cover changes: Current coverage and future prospects

Ren, Yanjiao; Lu, Yudong; Comber, Alexis; Fu, Bojie; Harris, Paul; Wu, Lianhai

doi:10.1016/j.earscirev.2019.01.001

Cited by 139 publications

(81 citation statements)

References 119 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, LCC studies conducted at a global scale have assessed the cumulative implications of land change processes such as urban growth and deforestation [8]. Addressing LCC from a top-down perspective, data-driven modeling tactics enable the extraction and detections of patterns that have resulted from local interactions [9]. Top-down approaches are primarily focused on overall patterns that result from processes, utilizing satellite and aggregated data sources such as Census data to obtain rates of land change over time.…”

Section: Introductionmentioning

confidence: 99%

Analyzing the Effects of Temporal Resolution and Classification Confidence for Modeling Land Cover Change with Long Short-Term Memory Networks

Duynhoven

Dragićević

2019

Remote Sensing

View full text Add to dashboard Cite

Land cover change (LCC) is typically characterized by infrequent changes over space and time. Data-driven methods such as deep learning (DL) approaches have proven effective in many domains for predictive and classification tasks. When applied to geospatial data, sequential DL methods such as long short-term memory (LSTM) have yielded promising results in remote sensing and GIScience studies. However, the characteristics of geospatial datasets selected for use with these methods have demonstrated important implications on method performance. The number of data layers available, the rate of LCC, and inherent errors resulting from classification procedures are expected to influence model performance. Yet, it is unknown how these can affect compatibility with the LSTM method. As such, the main objective of this study is to explore the capacity of LSTM to forecast patterns that have emerged from LCC dynamics given varying temporal resolutions, persistent land cover classes, and auxiliary data layers pertaining to classification confidence. Stacked LSTM modeling approaches are applied to 17-year MODIS land cover datasets focused on the province of British Columbia, Canada. This geospatial data is reclassified to four major land cover (LC) classes during pre-processing procedures. The evaluation considers the dataset at variable temporal resolutions to demonstrate the significance of geospatial data characteristics on LSTM method performance in several scenarios. Results indicate that LSTM can be utilized for forecasting LCC patterns when there are few limitations on temporal intervals of the datasets provided. Likewise, this study demonstrates improved performance measures when there are classes that do not change. Furthermore, providing classification confidence data as ancillary input also demonstrated improved results when the number of timesteps or temporal resolution is limited. This study contributes to future applications of DL and LSTM methods for forecasting LCC.

show abstract

Section: Introductionmentioning

confidence: 99%

Analyzing the Effects of Temporal Resolution and Classification Confidence for Modeling Land Cover Change with Long Short-Term Memory Networks

Duynhoven

Dragićević

2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Multivariate spatial models [4], Markov analysis [5], cellular automata (CA) [3,6-9], neural-network-based CA [2], empirical-statistical models [10,11], optimization models [12], and agent-based models [13,14] have all been used in the simulation of land use change. More details on each method can be found in [15].The CA is a common method for simulating the LULC change spatial evolution by estimating the state of a pixel according to its initial state, surrounding neighborhood effects and transition rules. A CA model can generate rich patterns and effectively represent nonlinear spatially stochastic LULC change processes [16,17].…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Prediction of Land Use and Land Cover Changes for North Sumatra, Indonesia, Using an Artificial-Neural-Network-Based Cellular Automaton

2019

View full text Add to dashboard Cite

Land use and land cover (LULC) form a baseline thematic map for monitoring, resource management, and planning activities and facilitate the development of strategies to balance conservation, conflicting uses, and development pressures. In this study, changes in LULC in North Sumatra, Indonesia, are simulated and predicted using an artificial-neural-network-based cellular automaton (ANN-CA) model. Five criteria (altitude, slope, aspect, distance from the road, and soil type) are used as exploratory data in the learning process of the ANN-CA model to determine their impacts on LULC changes between 1990 and 2000; among the criteria, altitude and distance from the road have strong impacts. Comparison between the predicted and the real LULC maps for 2010 illustrates high agreement, with a Kappa index of 0.83 and a percentage of correctness of 87.28%. Then, the ANN-CA model is applied to predict LULC changes in 2050 and 2070. The LULC predictions for 2050 and 2070 demonstrate high increases in plantation area of more than 4%. Meanwhile, forest and crop area are projected to decrease by approximately 1.2% and 1.6%, respectively, by 2050. By 2070, forest and crop areas will decrease by 1.2% and 1.7%, respectively, indicating human influences on LULC changes from forest and cropland to plantations. This study illustrates that the simulation of LULC changes using the ANN-CA model can produce reliable predictions for future LULC.Simulation of LULC changes provides the baseline scenario for use when predicting future scenarios and patterns in future development. Simulation of LULC changes can indicate anthropogenic impact, identify land use problems, such as the degradation and deforestation, and be used in land use planning [2]. Land use changes have been important aspects for regional and urban planning for centuries. Most of the research predicts land use changes using the independent variable with the highest correlation to those changes. Verburg et al. [3] illustrated that the multiscale characteristics of land use systems require new techniques to quantify neighborhood effects. Furthermore, Verburg et al.[3] also explicitly dealt with temporal dynamics and achieved a higher level of integration among disciplinary approaches and between models studying urban and rural land use changes. Multivariate spatial models [4], Markov analysis [5], cellular automata (CA) [3,6-9], neural-network-based CA [2], empirical-statistical models [10,11], optimization models [12], and agent-based models [13,14] have all been used in the simulation of land use change. More details on each method can be found in [15].The CA is a common method for simulating the LULC change spatial evolution by estimating the state of a pixel according to its initial state, surrounding neighborhood effects and transition rules. A CA model can generate rich patterns and effectively represent nonlinear spatially stochastic LULC change processes [16,17]. The applications of CA models have been growing in urban development studies, with strong capabilities for si...

show abstract

“…Predicting land use change is important for land system management, which can assist in understanding the extent of land use type transformation and enabling the scientists and policy makers to manage land use changes in plausible way [6,7]. It is important to understand the future land use change under different pathways from a management perspective [8,9].…”

Section: Introductionmentioning

confidence: 99%

Investigation of Future Land Use Change and Implications for Cropland Quality: The Case of China

et al. 2019

View full text Add to dashboard Cite

Cropland loss resulting from land use change has drawn great attention in China due to the threat to food security. However, little is known about future magnitude and quality of cropland of China. In this study, the dynamic conversion of land use and its effects model (Dyna-CLUE) together with the Markov model and the potential yield data were used to simulate the influence of land use change on cropland quality in the next two decades under three scenarios. The results indicate that, under the trend scenario, the high-yield and medium-yield cropland would decrease and the low-yield cropland would increase between 2015 and 2030. The crop yield would decrease by 1.3 × 109 kg. Under planned scenario, high-yield and medium-yield cropland would decrease and the low-yield cropland would increase, and total crop yield would stay almost unchanged. Under the cropland protection scenario, the high-yield cropland would reduce slightly, and the medium-yield and low-yield cropland would increase substantially. The crop yield would increase by 5.36 × 1010 kg. The result of this study will help decision-makers to develop reasonable land use policies to achieve the goals of harmonious development between food security, economic growth, and environmental protection.

show abstract

Spatially explicit simulation of land use/land cover changes: Current coverage and future prospects

Abstract: This is a repository copy of Spatially explicit simulation of land use/land cover changes: Current coverage and future prospects.

Cited by 139 publications

References 119 publications

Analyzing the Effects of Temporal Resolution and Classification Confidence for Modeling Land Cover Change with Long Short-Term Memory Networks

Analyzing the Effects of Temporal Resolution and Classification Confidence for Modeling Land Cover Change with Long Short-Term Memory Networks

Prediction of Land Use and Land Cover Changes for North Sumatra, Indonesia, Using an Artificial-Neural-Network-Based Cellular Automaton

Investigation of Future Land Use Change and Implications for Cropland Quality: The Case of China

Contact Info

Product

Resources

About