Geospatial Analysis of Land Use/Cover Change and Land Surface Temperature for Landscape Risk Pattern Change Evaluation of Baghdad City, Iraq, Using CA–Markov and ANN Models

Al-Hameedi, Wafaa Majeed Mutashar; Chen, Jie; Faichia, Cheechouyang; Nath, Biswajit; Al-Shaibah, Bazel; Al-Aizari, Ali

doi:10.3390/su14148568

Cited by 13 publications

(10 citation statements)

References 47 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, XGBoost has become a de facto choice of ensemble methods [86] and has been proven to provide fast, state-of-the-art results and to act as a standard classification yardstick in many classification and regression scenarios [56,57]; it is more potent than the original Random Forest [87]. The success of the XGBoost classifier is bolstered by its ability to be scalable in all methods, resulting in systems being ten times faster than existing popular solutions [57,101,102]. It has algorithmic optimisation capabilities resulting in parallel and distributed computing power that enables quicker model exploration [57].…”

Section: Xgbrfclassifiermentioning

confidence: 99%

“…It has algorithmic optimisation capabilities resulting in parallel and distributed computing power that enables quicker model exploration [57]. It can exploit out-of-core computation that allows a hundred million data to be processed on a desktop computer [57,102]. Lastly, the ensemble provides an end-to-end system that scales extensive data with a minimum number of clusters [57].…”

Section: Xgbrfclassifiermentioning

confidence: 99%

See 1 more Smart Citation

Land Cover and Landscape Structural Changes Using Extreme Gradient Boosting Random Forest and Fragmentation Analysis

Matyukira,

Mhangara

2023

Remote Sensing

View full text Add to dashboard Cite

Land use and land cover change constitute a significant driver of land degradation worldwide, and machine-learning algorithms are providing new opportunities for effectively classifying land use and land cover changes over time. The aims of this study are threefold: Firstly, we aim to compare the accuracies of the parametric classifier Naïve Bayes with the non-parametric classifier Extreme Gradient Boosting Random Forest algorithm on the 2020 LULC dataset. Secondly, we quantify land use and land cover changes in the Cradle of Humankind from 1990 to 2020 using the Extreme Gradient Boosting Random Forest algorithm and post-classification change detection. Thirdly, the study uses landscape metrics to examine landscape structural changes occurring in the same area due to fragmentation. The classification results show that while Naïve Bayers and XGB Random Forest produce classification results of high accuracy, the XGB Random Forest Classifier produced superior results compared to the Naïve Bayers Classifier. From 1990 to 2020, bare ground/rock outcrop significantly increased by 39%, and open bush by 32%. Indigenous forests and natural grasslands lost area (26% and 12%, respectively). The results from this study indicate increasing land cover fragmentation and attest to land degradation, as shown by increases in bare ground and a reduction in indigenous forest and natural grassland. The decline in indigenous forests and natural grassland indicates the degradation of native vegetation, considered as prehistoric plant food sources. The high classification results also attest to the efficacy of the XGBRFClassifier executed in GEE. Land degradation evident in the nature reserve has long-term ecological consequences, such as loss of habitat, biodiversity decline, soil erosion, and alteration of local ecosystems, which together diminish the aesthetic value of the heritage site and negatively impact its tourism value. Consequently, it destroys crucial local economies and threatens sustainable tourism.

show abstract

Section: Xgbrfclassifiermentioning

confidence: 99%

Section: Xgbrfclassifiermentioning

confidence: 99%

Land Cover and Landscape Structural Changes Using Extreme Gradient Boosting Random Forest and Fragmentation Analysis

Matyukira,

Mhangara

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The CA model also forms the basis for many composite models, such as the CLUE-S model [16,17], ANN-CA model [18,19], and Logistic-CA model [20,21]. The CA-Markov model is a more mature simulation approach, combining the CA model's capability to simulate spatial changes in complex systems with the predictive advantages of the Markov model over time, effectively overcoming the limitations of single landscape-type dynamic simulation models [22,23].…”

Section: Introductionmentioning

confidence: 99%

Predicting Sub-Forest Type Transition Characteristics Using Canopy Density: An Analysis of the Ganjiang River Basin Case Study

Zhou,

Hu,

Liu

et al. 2024

Forests

View full text Add to dashboard Cite

In the process of societal development, forest land categories often conflict with other land use types, leading to impacts on the ecological environment. Therefore, research on changes in forest land categories has increasingly become a globally focused topic. To anticipate potential forest ecological security issues under urbanization trends, studies on regional land use simulation become more important. This paper, based on land use data from the Ganjiang River basin, analyzes the distribution characteristics and changing trends of land use types from 2000 to 2020. Using the CA-Markov model, it predicts the land use pattern of the basin in 2040 and analyzes the transfer characteristics of forest land categories. The conclusions indicate that, between 2000 and 2020, the most significant trend in land use evolution was the transfer between various subcategories of forest land, especially frequent in the high-altitude mountainous areas in the southern and western parts of the basin. The land use pattern prediction model constructed in this paper has a kappa index of 0.92, indicating high accuracy and reliability of the predictions. In 2040, the most significant land evolution phenomenon would be from forest land to arable land to construction land, particularly pronounced around large cities. Over the next 20 years, the focus of land use evolution may shift from the southern part of the basin to the central and northern parts, with urban expansion possibly becoming the main driving force of land use changes during this period. Forest land restoration work is an effective method to compensate for the loss of forest land area in the Ganjiang River basin, with key areas for such work including Longnan, Yudu, Xingguo, Ningdu, Lianhua, and Yongxin counties.

show abstract

“…The obtained results contribute to the construction of regional ecological civilizations. Studies on landscape ecological risk have mostly focused on cities (Wang D et al, 2021;Al-Hameedi et al, 2022), river basins (Tian et al, 2019;Zhang et al, 2021), mining areas (Wu et al, 2021;Xu et al, 2021) and so on. The spatiotemporal distribution of regional ecological risk is explored by constructing a relative ecological risk assessment model (Bartolo et al, 2012;Heenkenda and Bartolo, 2016) to provide a basis for landscape ecological risk management.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal evolution and driving forces of ecosystem service value and ecological risk in the Ulan Buh Desert

Liu

Wang

Sun

et al. 2023

Front. Environ. Sci.

View full text Add to dashboard Cite

A clear understanding of the spatiotemporal evolution and driving factors of ecosystem service value (ESV) and the landscape ecological risk index (ERI) can effectively link human well-being and ecosystem security, which is essential for sustainable ecosystem management. Based on multitemporal land use data (1990, 2000, 2010, and 2018), the spatiotemporal evolution of ESV and the ERI in the Ulan Buh Desert was evaluated. The driving forces of ESV and the ERI were quantitatively evaluated by the Geodetector model. The results show that 1) from 1990 to 2018, total ESV in the Ulan Buh Desert increased from 7.00×108 yuan to 11.09×108 yuan. Low-ESV areas accounted for approximately 72.28% of the study area. High-ESV and moderate-high-ESV areas were mainly distributed along the Yellow River and the northeastern region. 2) During the study period, the ecological risk of the Ulan Buh Desert generally decreased; only the ecological risk of the northeastern region improved significantly, and high-risk areas were mainly distributed across sand dunes located in the middle of the desert. 3) There was a negative correlation between ESV and the ERI in the study area, and the main relationship was low value-high risk. 4) Driving force analysis results show that natural and human impact factors jointly affected the spatiotemporal differentiation of ESV and the ERI in the Ulan Buh Desert. Among the influencing factors, the interaction between the distance to a highway and annual precipitation had the strongest impact. The implementation of relevant policies in the study area should be guided by ESV and the ERI, and the protection and restoration of various ecosystems in the study area must be strengthened.

show abstract

Geospatial Analysis of Land Use/Cover Change and Land Surface Temperature for Landscape Risk Pattern Change Evaluation of Baghdad City, Iraq, Using CA–Markov and ANN Models

Cited by 13 publications

References 47 publications

Land Cover and Landscape Structural Changes Using Extreme Gradient Boosting Random Forest and Fragmentation Analysis

Land Cover and Landscape Structural Changes Using Extreme Gradient Boosting Random Forest and Fragmentation Analysis

Predicting Sub-Forest Type Transition Characteristics Using Canopy Density: An Analysis of the Ganjiang River Basin Case Study

Spatiotemporal evolution and driving forces of ecosystem service value and ecological risk in the Ulan Buh Desert

Contact Info

Product

Resources

About