1
|
Jayasinghe A, Ranaweera N, Abenayake C, Bandara N, De Silva C. Modelling vegetation land fragmentation in urban areas of Western Province, Sri Lanka using an Artificial Intelligence-based simulation technique. PLoS One 2023; 18:e0275457. [PMID: 36745645 PMCID: PMC9901792 DOI: 10.1371/journal.pone.0275457] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2021] [Accepted: 09/17/2022] [Indexed: 02/07/2023] Open
Abstract
Vegetation land fragmentation has had numerous negative repercussions on sustainable development around the world. Urban planners are currently avidly investigating vegetation land fragmentation due to its effects on sustainable development. The literature has identified a research gap in the development of Artificial Intelligence [AI]-based models to simulate vegetation land fragmentation in urban contexts with multiple affecting elements. As a result, the primary aim of this research is to create an AI-based simulation framework to simulate vegetation land fragmentation in metropolitan settings. The main objective is to use non-linear analysis to identify the factors that contribute to vegetation land fragmentation. The proposed methodology is applied for Western Province, Sri Lanka. Accessibility growth, initial vegetation large patch size, initial vegetation land fragmentation, initial built-up land fragmentation, initial vegetation shape irregularity, initial vegetation circularity, initial building density, and initial vegetation patch association are the main variables used to frame the model among the 20 variables related to patches, corridors, matrix and other. This study created a feed-forward Artificial Neural Network [ANN] using R statistical software to analyze non-linear interactions and their magnitudes. The study likewise utilized WEKA software to create a Decision Tree [DT] modeling framework to explain the effect of variables. According to the ANN olden algorithm, accessibility growth has the maximum importance level [44] between -50 and 50, while DT reveals accessibility growth as the root of the Level of Vegetation Land Fragmentation [LVLF]. Small, irregular, and dispersed vegetation patches are especially vulnerable to fragmentation. As a result, study contributes detech and managing vegetation land fragmentation patterns in urban environments, while opening up vegetation land fragmentation research topics to AI applications.
Collapse
Affiliation(s)
- Amila Jayasinghe
- Department of Town & Country Planning, Urban Simulation Laboratory, University of Moratuwa, Moratuwa, Sri Lanka
- * E-mail: (AJ); , (NR); (CA); (NB); (CDS)
| | - Nesha Ranaweera
- Department of Town & Country Planning, Urban Simulation Laboratory, University of Moratuwa, Moratuwa, Sri Lanka
- * E-mail: (AJ); , (NR); (CA); (NB); (CDS)
| | - Chethika Abenayake
- Department of Town & Country Planning, Urban Simulation Laboratory, University of Moratuwa, Moratuwa, Sri Lanka
- * E-mail: (AJ); , (NR); (CA); (NB); (CDS)
| | - Niroshan Bandara
- Department of Town & Country Planning, Urban Simulation Laboratory, University of Moratuwa, Moratuwa, Sri Lanka
- * E-mail: (AJ); , (NR); (CA); (NB); (CDS)
| | - Chathura De Silva
- Department of Town & Country Planning, Urban Simulation Laboratory, University of Moratuwa, Moratuwa, Sri Lanka
- * E-mail: (AJ); , (NR); (CA); (NB); (CDS)
| |
Collapse
|
2
|
Deng L, Han Z, Pu W, Bao R, Wang Z, Wu Q, Qiao J. Impacts of Human Activities and Climate Change on Water Storage Changes in Shandong Province, China. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2022; 29:35365-35381. [PMID: 35060057 DOI: 10.1007/s11356-022-18759-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/19/2021] [Accepted: 01/15/2022] [Indexed: 06/14/2023]
Abstract
The over-exploitation of water resources causes water resource depletion, which threatens water security, human life, and social and economic development. Only by clarifying the spatial pattern, changing trends, and influencing factors of water storage can we promote the rational development of water resources and relieve the pressure on water resources. However, there is still a lack of research on these aspects. In this study, the water-scarce area in Shandong Province, China, was selected to quantify the spatial and temporal changes in the terrestrial water storage (TWS) and groundwater storage (GWS) over the past 30 years. Nighttime light data were used to characterize the urbanization level (UL) and explore the effects of human activities (i.e., UL) and climate change (temperature and precipitation) on the TWS and GWS. The results show that 1) from 1990 to 2018, the overall TWS exhibited a significant decreasing trend (- 0.084 cm yr-1). The change trend of the GWS was consistent with that of the TWS (- 0.516 m3 yr-1). Spatially, there was significant spatial heterogeneity in the trend of the TWS and GWS. At the grid and prefectural scales, the TWS mainly exhibited a downward trend in the central and western regions, and an upward trend in the eastern region of Shandong Province. For the GWS, all cities exhibited a decreasing trend at the prefectural scale, whereas 92% of the regions exhibited a decreasing trend with less spatial heterogeneity at the grid scale. 2) Precipitation was the mean factor controlling the total amount of TWS and GWS in Shandong Province. Precipitation and temperature positively affected water storage, and the UL negatively affected it. At the prefectural scale, except for a few cities which were greatly influenced by the UL, the dominant factor of the TWS and GWS was precipitation in the other cities. At the grid scale, for the TWS, precipitation was the predominant factor in 51.82% of the entire region, followed by the UL (44.14%) and temperature (4.04%). For the GWS, precipitation was the predominant factor in 55.73% of the area, and the other 44.27% of the area was mainly influenced by the UL. Overall, precipitation and the UL were the key factors affecting the TWS and GWS. The results of this study provide a theoretical and decision-making basis for the optimal allocation and sustainable use of regional water resources.
Collapse
Affiliation(s)
- Longyun Deng
- College of Geography and Environment, Shandong Normal University, Jinan, 250358, China
| | - Zhen Han
- College of Geography and Environment, Shandong Normal University, Jinan, 250358, China
- QingDao Marine Remote Sensing Information Technology Co.,LTD, 266000, Qingdao, China
| | - Weixing Pu
- College of Geography and Environment, Shandong Normal University, Jinan, 250358, China
| | - Rong Bao
- College of Geography and Environment, Shandong Normal University, Jinan, 250358, China
| | - Zheye Wang
- Kinder Institute for Urban Research, Rice University, Houston, TX, 77005, USA
| | - Quanyuan Wu
- College of Geography and Environment, Shandong Normal University, Jinan, 250358, China.
- , Jinan, China.
| | - Jianmin Qiao
- College of Geography and Environment, Shandong Normal University, Jinan, 250358, China.
- , Jinan, China.
| |
Collapse
|
3
|
Wei H, Lu C. Farmland change and its implications in the Three River Region of Tibet during recent 20 years. PLoS One 2022; 17:e0265939. [PMID: 35404947 PMCID: PMC9000058 DOI: 10.1371/journal.pone.0265939] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2021] [Accepted: 03/11/2022] [Indexed: 11/23/2022] Open
Abstract
Farmland is a key resource for safeguarding the regional food security and social stability, particularly in Tibet where the farmland is very limited due to its high altitude. With quick economic development during recent decades, farmland changes are great in China, and thus have been extensively studied. These studies generally focused on eastern regions, and seldom for Tibet due to the lack of good quality and available data. To this end, taking the Three River Region (TRR) as the case area, this study obtained 1 m spatial resolution farmland data for 2000 and 2018 by visual interpretation of the Google Earth high resolution satellite images, and then analyzed the farmland change, its driving factors and impact on grain production between 2000 and 2018. The results showed that farmland in the TRR decreased by 8.85% from 219.29 k ha in 2000 to 199.89 k ha in 2018, averagely reduced by 0.51% per year, mainly driven by the economic development, agricultural progress, urbanization, and population growth. The farmland losses largely occurred in urban areas and their surrounding counties due to urban land occupation, and caused the grain production reduced by 9.38%. To control the quick farmland losses and to ensure the regional food security of Tibet, it should strengthen the supervision on non-agricultural occupation of farmland and increase agricultural investment to improve the land productivity in the TRR.
Collapse
Affiliation(s)
- Hui Wei
- Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
| | - Changhe Lu
- Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- * E-mail:
| |
Collapse
|
4
|
Abstract
The Huangshui River Basin (HRB) is the main grain production and key implementation region of the “Grain for Green Program” (GGP) of Qinghai Province, and has experienced a quick urbanization during the last 20 years. Therefore, identifying the farmland change and its ecological effects is significant for farmland and ecological protection in the HRB. To this end, this study analyzed the farmland change between 2000 and 2018, based on 1 m spatial resolution farmland data visually interpreted from Google Earth high-resolution images, and then estimated its ecological impact based on the Normalized Difference Vegetation Index (NDVI) data of MODIS, using an ecological impact index of farmland change. The study found that: (1) The farmland area in the HRB decreased from 320.15 k ha in 2000 to 245.01 k ha in 2018, reduced by 23.47% or 1.48% per year, as mainly caused by ecological restoration and built-up land occupation; (2) from 2000 to 2018, the natural environment showed a greening trend in the HRB, with the mean NDVI increasing by 0.74% per year; (3) the farmland changes had a positive ecological effect, contributing 6.67% to the regional increase in the NDVI, but had a negative impact on grain production; (4) it is suggested to strengthen farmland protection by strictly controlling the urban land occupation and over-conversion of farmland in the HRB.
Collapse
|