scholarly journals CLASSIFICATION OF TRANSLATIONAL LANDSLIDE ACTIVITY USING VEGETATION ANOMALIES INDICATOR (VAI) IN KUNDASANG, SABAH

Author(s):  
M. R. Mohd Salleh ◽  
N. H. A. Norhairi ◽  
Z. Ismail ◽  
M. Z. Abd Rahman ◽  
M. F. Abdul Khanan ◽  
...  

Abstract. This paper introduced a novel method of landslide activity mapping using vegetation anomalies indicators (VAIs) obtained from high resolution remotely sensed data. The study area was located in a tectonically active area of Kundasang, Sabah, Malaysia. High resolution remotely sensed data were used to assist manual landslide inventory process and production on VAIs. The inventory process identified 33, 139, and 31 of active, dormant, and relict landslides, respectively. Landslide inventory map were randomly divided into two groups for training (70%) and validation (30%) datasets. Overall, 7 group of VAIs were derived including (i) tree height irregularities; (ii) tree canopy gap; (iii) density of different layer of vegetation; (iv) vegetation type distribution; (v) vegetation indices (VIs); (vi) root strength index (RSI); and (vii) distribution of water-loving trees. The VAIs were used as the feature layer input of the classification process with landslide activity as the target results. The landslide activity of the study area was classified using support vector machine (SVM) approach. SVM parameter optimization was applied by using Grid Search (GS) and Genetic Algorithm (GA) techniques. The results showed that the overall accuracy of the validation dataset is between 61.4–86%, and kappa is between 0.335–0.769 for deep-seated translational landslide. SVM RBF-GS with 0.5m spatial resolution produced highest overall accuracy and kappa values. Also, the overall accuracy of the validation dataset for shallow translational is between 49.8–71.3%, and kappa is between 0.243–0.563 where SVM RBF-GS with 0.5m resolution recorded the best result. In conclusion, this study provides a novel framework in utilizing high resolution remote sensing to support labour intensive process of landslide inventory. The nature-based vegetation anomalies indicators have been proved to be reliable for landslide activity identification in Malaysia.

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ai-Ling Jiang ◽  
Ming-Chieh Lee ◽  
Guofa Zhou ◽  
Daibin Zhong ◽  
Dawit Hawaria ◽  
...  

AbstractLarval source management has gained renewed interest as a malaria control strategy in Africa but the widespread and transient nature of larval breeding sites poses a challenge to its implementation. To address this problem, we propose combining an integrated high resolution (50 m) distributed hydrological model and remotely sensed data to simulate potential malaria vector aquatic habitats. The novelty of our approach lies in its consideration of irrigation practices and its ability to resolve complex ponding processes that contribute to potential larval habitats. The simulation was performed for the year of 2018 using ParFlow-Common Land Model (CLM) in a sugarcane plantation in the Oromia region, Ethiopia to examine the effects of rainfall and irrigation. The model was calibrated using field observations of larval habitats to successfully predict ponding at all surveyed locations from the validation dataset. Results show that without irrigation, at least half of the area inside the farms had a 40% probability of potential larval habitat occurrence. With irrigation, the probability increased to 56%. Irrigation dampened the seasonality of the potential larval habitats such that the peak larval habitat occurrence window during the rainy season was extended into the dry season. Furthermore, the stability of the habitats was prolonged, with a significant shift from semi-permanent to permanent habitats. Our study provides a hydrological perspective on the impact of environmental modification on malaria vector ecology, which can potentially inform malaria control strategies through better water management.


Author(s):  
Ned Horning ◽  
Julie A. Robinson ◽  
Eleanor J. Sterling ◽  
Woody Turner ◽  
Sacha Spector

While the savannah elephant (Loxodonta africana) is listed by the International Union for Conservation of Nature (IUCN) as “vulnerable” because of declining abundance in some regions of Africa (Blanc 2008), populations in some protected areas of South Africa are growing rapidly (van Aarde and Jackson 2007). These populations can cause extensive modification of vegetation structure when their density increases (Owen-Smith 1996; Whyte et al. 2003; Guldemond and van Aarde 2007). Management methods such as culling, translocation, and birth control have not reduced density in some cases (van Aarde et al. 1999; Pimm and van Aarde 2001). Providing more space for elephants is one alternative management strategy, yet fundamental to this strategy is a clear understanding of habitat and landscape use by elephants. Harris et al. (2008) combined remotely sensed data with Global Positioning System (GPS) and traditional ethological observations to assess elephant habitat use across three areas that span the ecological gradient of historical elephant distribution. They explored influences on habitat use across arid savannahs (Etosha National Park in Namibia) and woodlands (Tembe Elephant Park in South Africa and Maputo Elephant Reserve in Mozambique). The researchers focused on three main variables—distance to human settlements, distance to water, and vegetation type. The authors used Landsat 7 ETMþ imagery to create vegetation maps for each location, employing supervised classification and maximum likelihood estimation. Across all sites, they recorded the coordinates of patches with different vegetation and of vegetation transitions to develop signatures for the maps. Elephants do not use all vegetation types, and it can be expedient to focus on presence rather than both presence and absence. Accordingly, the researchers used GPS to record the locations of elephants with the aim of identifying important land cover types for vegetation mapping. The authors mapped water locations in the wet and dry seasons using remotely sensed data and mapped human settlements using GPS, aerial surveys, and regional maps. They tracked elephants with radiotelemetry collars that communicated with the ARGOS satellite system, sending location data for most of the elephants over 24 h, and then remaining quiescent for the next 48 h to extend battery life.


2009 ◽  
Vol 10 (6) ◽  
pp. 471-487 ◽  
Author(s):  
Xiaoyu Song ◽  
Jihua Wang ◽  
Wenjiang Huang ◽  
Liangyun Liu ◽  
Guangjian Yan ◽  
...  

Author(s):  
C. Zhang ◽  
X. Pan ◽  
S. Q. Zhang ◽  
H. P. Li ◽  
P. M. Atkinson

Recent advances in remote sensing have witnessed a great amount of very high resolution (VHR) images acquired at sub-metre spatial resolution. These VHR remotely sensed data has post enormous challenges in processing, analysing and classifying them effectively due to the high spatial complexity and heterogeneity. Although many computer-aid classification methods that based on machine learning approaches have been developed over the past decades, most of them are developed toward pixel level spectral differentiation, e.g. Multi-Layer Perceptron (MLP), which are unable to exploit abundant spatial details within VHR images. <br><br> This paper introduced a rough set model as a general framework to objectively characterize the uncertainty in CNN classification results, and further partition them into correctness and incorrectness on the map. The correct classification regions of CNN were trusted and maintained, whereas the misclassification areas were reclassified using a decision tree with both CNN and MLP. The effectiveness of the proposed rough set decision tree based MLP-CNN was tested using an urban area at Bournemouth, United Kingdom. The MLP-CNN, well capturing the complementarity between CNN and MLP through the rough set based decision tree, achieved the best classification performance both visually and numerically. Therefore, this research paves the way to achieve fully automatic and effective VHR image classification.


2020 ◽  
Vol 9 (4) ◽  
pp. 262 ◽  
Author(s):  
Maurizio Pollino ◽  
Sergio Cappucci ◽  
Ludovica Giordano ◽  
Domenico Iantosca ◽  
Luigi De Cecco ◽  
...  

Earthquake-induced rubble in urbanized areas must be mapped and characterized. Location, volume, weight and constituents are key information in order to support emergency activities and optimize rubble management. A procedure to work out the geometric characteristics of the rubble heaps has already been reported in a previous work, whereas here an original methodology for retrieving the rubble’s constituents by means of active and passive remote sensing techniques, based on airborne (LiDAR and RGB aero-photogrammetric) and satellite (WorldView-3) Very High Resolution (VHR) sensors, is presented. Due to the high spectral heterogeneity of seismic rubble, Spectral Mixture Analysis, through the Sequential Maximum Angle Convex Cone algorithm, was adopted to derive the linear mixed model distribution of remotely sensed spectral responses of pure materials (endmembers). These endmembers were then mapped on the hyperspectral signatures of various materials acquired on site, testing different machine learning classifiers in order to assess their relative abundances. The best results were provided by the C-Support Vector Machine, which allowed us to work out the characterization of the main rubble constituents with an accuracy up to 88.8% for less mixed pixels and the Random Forest, which was the only one able to detect the likely presence of asbestos.


Sign in / Sign up

Export Citation Format

Share Document