Approaches for delineating landslide hazard areas using different training sites in an advanced artificial neural network model   总被引：10，自引：0，他引：10  

Biswajeet Pradhan  Ahmed M. Youssef  Renuganth Varathrajoo 《地球空间信息科学学报》2010,13(2):93-102

The current paper presents landslide hazard analysis around the Cameron area, Malaysia, using advanced artificial neural networks with the help of Geographic Information System (GIS) and remote sensing techniques. Landslide locations were determined in the study area by interpretation of aerial photographs and from field investigations. Topographical and geological data as well as satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Ten factors were selected for landslide hazard including: 1) factors related to topography as slope, aspect, and curvature; 2) factors related to geology as lithology and distance from lineament; 3) factors related to drainage as distance from drainage; and 4) factors extracted from TM satellite images as land cover and the vegetation index value. An advanced artificial neural network model has been used to analyze these factors in order to establish the landslide hazard map. The back-propagation training method has been used for the selection of the five different random training sites in order to calculate the factor’s weight and then the landslide hazard indices were computed for each of the five hazard maps. Finally, the landslide hazard maps (five cases) were prepared using GIS tools. Results of the landslides hazard maps have been verified using landslide test locations that were not used during the training phase of the neural network. Our findings of verification results show an accuracy of 69%, 75%, 70%, 83% and 86% for training sites 1, 2, 3, 4 and 5 respectively. GIS data was used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool for landslide hazard analysis. The verification results showed sufficient agreement between the presumptive hazard map and the existing data on landslide areas.  相似文献   

Tackling illegal, unregulated, and unreported trade towards Humphead wrasse (Cheilinus undulatus) recovery in Sabah, Malaysia     

Tun-Min Poh  Lucia M. Fanning 《Marine Policy》2012,36(3):696-702

The live reef food fish trade (LRFFT) has caused severe depletion of the Humphead wrasse (Cheilinus undulatus) populations globally, a species considered endangered by the International Union for the Conservation of Nature. In 2010, signatories to the Convention on International Trade in Endangered Species of Wild Fauna and Flora recognized that illegal, unregulated, and unreported (IUU) activities in the LRFFT were undermining the efforts to protect this species. Management recommendations have yet to be effectively implemented at national and local levels where the fish is harvested. This paper analyzes the threats to, and socio-economic impacts of, Humphead wrasse recovery in Sabah, Malaysia, and offers both short- and longer-term recommendations for the local recovery of the species. Key issues addressed centre around understanding the threats to recovery, specifically the role of IUU and the context-specific considerations, including the socio-economic aspects of the IUU trade in Sabah. The analysis confirms that deliberate management planning and action at multiple levels are required to prevent local-scale extinction. Lessons for other species and countries involved in the LRFFT suggest that to be effective, broad management frameworks must be tailored to local situations and must focus on gaining support and participation of fish harvesters if the recovery and long-term sustainability of both the Humphead wrasse and the LRFFT are to be achieved.  相似文献   

A tool for site prioritisation of marine protected areas under data poor conditions     

Lydia C.L. Teh  Louise S.L. TehTony J. Pitcher 《Marine Policy》2012

A challenge of managing data poor fisheries lies in overcoming uncertainties associated with a lack of information on biological and socio-economic conditions. This paper focuses on site prioritisation for marine protected areas, a process that usually imposes moderate to heavy demands on data, time, local expertise, and funds. A fuzzy logic decision support tool for zoning marine areas that is suitable for use in data poor conditions is developed. This tool, the Protected Area Suitability Index (PASI), assesses the suitability of sites for protection based on fishers’ preferences for that site and the site’s conservation value. Only eight input attributes are required to run the PASI, which operates on a series of heuristic rules to estimate a site suitability score that ranges from 0 to 10, where 10 indicates that a site is highly suitable for being protected from fishing. Sensitivity analysis reveals that the PASI is relatively robust, and produces reliable results even as the system is degraded by the loss of data. Eighteen actively fished sites and 11 sites that are closed to fishing are assessed to evaluate how well the PASI is able to distinguish differences between sites. The estimated scores are significantly different (p<0.05), whereby non-fished sites are scored as being more suitable for protection than fished sites. The PASI can be used as a decision support tool to facilitate systematic marine spatial management under data poor conditions, especially in the task of identifying suitable sites for protection.  相似文献   

Agrobiodiversity of Muda Rice Agroecosystem:A case Study in Largest Granary Area of Malaysia     

Amir Shah Ruddin Md Shah　Mashhor Mansor　Shahrul Anuar Mohd Shah　Che Salmah Mohd Rawi　Abu Hassan Ahmad　Ibrahim Jaafar 《湿地科学》2008,6(1):34-44

A survey was carried out at the largest rice cultivation area in Peninsular Malaysia,the Muda rice agroecosystem.The main objective of this study was to document the overall biodiversity associated with this unique agroecosystem by using a combination of sampling techniques in order to record different groups of fauna and flora.The total number of biota recorded and identified from the rice field ecosystem during the study period consisted of 46 species of zooplankton,81 species of aquatic insects,5 species of rodents,7 species of bats,87 species of birds,11 species of fishes and 58 species of weeds.A long-term study should be carried out as more species are expected to be recorded when more of the Muda rice agroecosystem area has been sampled to obtain sufficient information on the Muda rice agrobiodiversity.  相似文献   

A new Lower Triassic (Induan) Jerus Limestone locality in northwest Pahang,Peninsular Malaysia: Conodont fauna,depositional and tectonic settings          下载免费PDF全文

Ian Metcalfe 《Island Arc》2016,25(2):126-136

Limestones exposed north of Raub, Pahang, Malaysia, and sandwiched between the Bentong‐Raub Suture Zone and the westernmost margin of the Sukhothai Arc terrane, yield a late Dienerian (late Induan) conodont fauna. The co‐occurrence of Neospathodus dieneri Sweet (morphotypes 1, 2 and 3) and Neospathodus pakistanensis Sweet represents the Neospathodus dieneri morphotype 3 sub‐zone of the Neospathodus dieneri Zone. The sampled limestones are interpreted as the northwards extension of the Jerus Limestone which crops out near Cheroh and Jerus villages, significantly extending the known outcrop of the Jerus Limestone northwards. The Jerus Limestone is interpreted as hemipelagic and formed in a foredeep or forearc setting on top of the accretionary complex formed by eastwards subduction of the Palaeo‐Tethys during the Lower to Middle Triassic.  相似文献   

SWAT-based hydrological modelling of tropical land-use scenarios     

Hadi Memarian  Karim C. Abbaspour  Jamal B. Talib  Christopher Teh Boon Sung  Alias Mohd Sood 《水文科学杂志》2013,58(10):1808-1829

Abstract

The Hulu Langat basin, a strategic watershed in Malaysia, has in recent decades been exposed to extensive changes in land-use and consequently hydrological conditions. In this work, the impact of Land Use and Cover Change (LUCC) on hydrological conditions (water discharge and sediment load) of the basin were investigated using the Soil and Water Assessment Tool (SWAT). Four land-use scenarios were defined for land-use change impact analysis, i.e. past, present (baseline), future and water conservation planning. The land-use maps, dated 1984, 1990, 1997 and 2002, were defined as the past scenarios for LUCC impact analysis. The present scenario was defined based on the 2006 land-use map. The 2020 land-use map was simulated using a cellular automata-Markov model and defined as the future scenario. Water conservation scenarios were produced based on guidelines published by Malaysia’s Department of Town and Country Planning and Department of Environment. Model calibration and uncertainty analysis was performed using the Sequential Uncertainty Fitting (SUFI-2) algorithm. The model robustness for water discharge simulation for the period 1997–2008 was good. However, due to uncertainties, mainly resulting from intense urban development in the basin, its robustness for sediment load simulation was only acceptable for the calibration period 1997–2004. The optimized model was run using different land-use maps over the periods 1997–2008 and 1997–2004 for water discharge and sediment load estimation, respectively. In comparison to the baseline scenario, SWAT simulation using the past and conservative scenarios showed significant reduction in monthly direct runoff and monthly sediment load, while SWAT simulation based on the future scenario showed significant increase in monthly direct runoff, monthly sediment load and groundwater recharge.