Search

The study involves an object-based segmentation method to extract feature changes in tropical rainforest cover using Landsat image and airborne LiDAR (ALS). Disturbance event that are represents the changes are examined by the classification of multisensor data; that is a highly accurate ALS with different resolutions of multispectral Landsat image. Disturbance Index (DI) derived from Tasseled Cap Transformation, Normalized Difference Vegetation Index (NDVI), and the ALS height are the variables for object-based segmentation process. The classification is categorized into two classes; disturbed and non-disturbed forest cover using Nearest Neighbor (NN), Random Forest (RF) and Support Vector Machine (SVM). The overall accuracy ranging from 88% to 96% and kappa ranging from 0.79 to 0.91. Mcnemar’s test p-value (

In oil palm plantations, Basal Stem Rot (BSR) disease has been acknowledged by many researchers worldwide to be a core and consistent danger. Given this problem, the early evaluation of the disease...

In an image classification system based on deep learning, a training dataset is a set of labelled images and is often composed of a large number of images. Image labelling tool is usually used to facilitate in creating the training dataset used by the classifier during the learning phase. This paper presents a new image labelling tool called CrackLabel that can automatically label the cracks in the asphalt pavement images. A specially designed image thresholding method called the Global and Lower Quartile Average Intensity (GLQAI) method is utilised. In this study, the training dataset is developed by using real pavement images that resized to 1024×768 resolution. First, crack images are automatically segmented into 768 small patches with 32×32 resolution (pixel). Then, a threshold-based method is applied to automatically segment these patches into two classes which are crack and non-crack patches. The image thresholding method based on the average of global average intensity (GAI) and lower quartile intensity (LQI), namely GLQAI is proposed for this task. Next, the labelling process is performed by assigning patches associated with the crack and background into the crack and non-crack folder, respectively. Finally, the performance of CrackLabel is benchmarked by comparing the results with the manual label crack images by human experts, and three commonly used thresholding methods; Otsu, Kapur and Kittler-Illingworth thresholding. Experimental results show that the proposed thresholding method achieved the best classification rate among various thresholding methods with 94.50%, 93.60% 94.00% and 94.05% for recall, precision, accuracy, and F-score respectively. In conclusion, it is observed that the proposed method using the newly threshold algorithm is very effective in label images into the crack and non-crack patches to maximize the training performance.

The Malaysian Cocoa Board (MCB) has conducted numerous research and development activities to ensure the cocoa industry's sustainability. One of the essential aspects is the management of pests and diseases of cocoa. A qualitative study to detect the relationship between presences of biological control agents, Cocoa Black Ant (CBA) against the major pest of cocoa (Cocoa pod borer, CPB) with other ants' intrusion was done with the aid of geospatial mapping and analysis approaches. Other species of ants (ant invades) will affect the availability of CBA in controlling CPB infestation. Thirty months of data collection comprised two different blocks; Blocks 10B and 18A were used as the study area. Analysis of the differences and similarities of other ant's intrusion for each block and Plots was performed to understand the behavior and distribution pattern. Four different method were introduced; Plot A was augmented with one artificial ant nest for every two cocoa trees, Plot B had one nest on every single cocoa tree, Plot C had two nests on every single cocoa tree, and Plot D without an artificial nest. The study reveals that the highest or lowest CBA populations and distribution could induce a strong, reasonable relationship against other ant types. Plots with artificial ant nests (A, B, and C) showed low intrusion rates with a ratio of 1:1 for Plot B indicated the best result, whereas, Plot without artificial ant nest (Plot D) the highest rate of intrusion during the months and years of observation. [J Bangladesh Agril Univ 2021; 19(1.000): 30-36]

Landslides have become a common disaster in Malaysia, the incident occurred according to human activity in economic development. Deforestation, urbanization, development of hill slopes and other human land use have given rise to increased risks of landslides. This paper reports the monitoring of the landslide by applying Land Cover (LC) change detection by utilizing two multispectral satellite imagery SPOT 5 for the year 2005 and 2014. ArcMap 10.2.2 software was used in the image processing using Maximum likelihood classification. This study is conducted in Ulu Kelang, Selangor which is located at hilly and sloppy terrain surround by forestry. The results show the method of LC changes and factor of the landslide can be justified via remote sensing image within 10 years’ time. The accuracy of image classification was showed an overall accuracy of 95% (2005) and 93% (2014), while kappa coefficient indicates the method of classification and the images used were excellent quality. During this study period, an urban area has shown an increase of 14.143%, while the green area had decreased by 8.432% due to an increase of interest in urbanization development. There were twelve landslides recorded during the years 2006 to 2014, about 91.66% landslide events were affected build up area which were residential area and road. This analysis showed that human influence or activity could be contributing to landslide occurrences. Therefore, the urbanization development is very important to have proper planning to reduce the susceptibility of landslide occurrences in Ulu Kelang, Selangor.

The observation of land use/land cover (LULC) is essential as it allows humans to investigate the alteration of land which occurs over a period of time. This is to allow mankind to have a proper management of the earth resources and well planned development. One way to observe LULC is by using remote sensing technology since it provides continuous data monitoring of the earth’s surface. This study is carried out at Bandar Meru Raya, Ipoh, Perak and aimed to quantify the LULC changes, especially in urban areas which occurred within two decades from 1995 to 2005 and from 2005 to 2015. Maximum likelihood supervised classification was performed on three Landsat satellite imageries using ERDAS Imagine 2014 software. The images were classified into 4 general LULC categories namely forest, development area, green area, and water bodies. The results indicated that a considerable amount of forested area was decreasing by 183.12 hectares within the last 20 years while development area gained a total of 157.12 hectares. This LULC changes showed a serious loss of trees and this sort of change tends to affect the nature’s ecosystem. Therefore, by quantifying the loss of forest area will enable authorities to oversee and plan a better management of trees for future in urban environments. Such management plan is necessary in order to maintain the importance of trees towards nature and community.

Satellite images have been used for the last 35 years to monitor the erosion rates of the coastline, which has further altered the morphology of the coastline and its biodiversity. In order to make educated judgments about the protection of our coastline biodiversity, shoreline accretion trends over time are crucial for a wide range of coastal challenges and projects. As a result, the goal of this study was to use Landsat 8 OLI to monitor the coastline mangrove forest in Tanjung Piai to distinguish changes in the coastline, as well as to generate land use land cover in 2013 and 2020, detect changes in land use land cover in 2013 until 2020, and identify changes in the coastline mangrove forest in 2013 and 2020. The results showed that the shoreline of Tanjung Piai altered by an average value of accretion per year of 296.14 ha and an average value of reduction per year of 46.87 ha using the End Point Rate (EPR) and Shoreline Change Envelope (SCE) tools from the Digital Shoreline Analyst System (DSAS). The coastal zone must be safeguarded to ensure the safety of those who live close, as well as the ecosystem and habitat’s protection from the effects of rising sea levels.

The main concern for this research is slope estimation and the beach profiling with verification sensor-based remotely data (high spatial resolution). Thus, surveying and satellite extraction data need to be accurat. It had been proven to support the relationship between coastal erosion with beach slope changes along Kuantan, Pahang. Therefore, the actual coastline can be mapped from last vegetation features and determine physical condition of beach on coastal habitable land where the baseline has been changes due to sea-level rise event. Hence, the aim of this study is to monitor beach profile using high spatial resolution remote sensing imagery and GIS techniques to distinguish slope estimation from different sources in Kuantan, Pahang Site-verification are done to identify beach slope profiling along Kuantan coastline, Pahang. The objectives of this research are i) to generate coastal slope estimation and beach profile in year 2006 and 2014, ii) to quantify the estimated and observed beach slope from IFSAR data and slope site surveying (by NAHRIM) and iii) to visualise in 3-D view of coastal slope profile derived using IFSAR data. The accuracy values provided for the measurements made in open area, undisturbed area with slopes less than 10 %. From early reconnaissance of Kuantan beach, most of the area are flat and sandy profile to which are suitable for this application. Besides, we found out this method are reliable to produce appropriate slope profile along identified areas in selected Pahang coastline. The findings may indicated a better strategy for monitoring coastline changes is needed especially for vulnerable coastal erosion areas for future sustainable coastal management.

Information on urban vegetation and land use is critical for sustainable environmental management in cities. In general, urban vegetation is important for urban planning because it helps to maintain a balance between the natural environment and the built-up region. The assessment of the composition and configuration of the vegetation is important to highlight the urban ecosystem. Thus, obtaining information about urban vegetation is critical for developing a sustainable urban development strategy. Remote sensing is increasingly being used to generate such data for mapping and monitoring changes in urban vegetation. The aim of this study is to identify and classify vegetation using the high-resolution Pleiades satellite image in urban park areas using pixel-based image analysis. Pixel based method was applied and support vector machine algorithm was used for classification of urban vegetation. Comparison of accuracy was made from the error matrices, overall accuracy and kappa coefficient for vegetation and non-vegetation classes. The overall accuracy for the classification approach was 98.98% and a kappa value of 0.97. The result demonstrates the ability of high-resolution imagery to accurately extract urban vegetation despite the complex surface of the urban area. The findings can be used to support other research and applications related to urban green space monitoring, conservation, and future urban vegetation planning.

Soil moisture is one of the contributing factors that accelerates soil erosion and landslide events due to the increase in pore pressure which eventually reduces the soil strength. For landslide prediction and monitoring purposes, large-scale measurement involves estimating the soil moisture. However, estimation of soil moisture usually involves point-based measurements at a particular site and time, which is difficult to capture the spatial and temporal soil moisture dynamics. This paper presents the estimation of the SMI using Landsat 8 images for prediction and monitoring of landslide events in Ulu Kelang, Selangor. The selected SMI map for dry, moist, and wet seasons are obtained from climatology rainfall analysis over 20-year periods (1998-2017). SMI is assessed based on remote sensing data which are land surface temperature (LST) and normalized difference vegetation index (NDVI) using GIS software. Overall results indicated that rainfall distribution is high during inter-monsoon (IM), followed by northeast monsoon (NEM) and southwest monsoon (SWM) season. High rainfall distribution is a direct contributor towards SMI condition. Results from simulation show that April 2017 is known to have the highest SMI estimation season and selected to be the best SMI mapping parameter to be applied for prediction and monitoring of landslide events.

Recently the sensing data for urban mapping used is in high demand together with the accessible of very high resolution (VHR) satellite data such as Worldview and Pleiades. This article presents the use of very high resolution (VHR) remote sensing data for urban vegetation mapping. The research objectives were to assess the use of Pleiades imagery to extricate the data of urban vegetation in urban area of Kuala Lumpur. Normalized Difference Vegetation Index (NDVI) were employs with VHR data to find Vegetation Index for classification process of vegetation and non-vegetation classes. Land use classes are easily determined by computing their Normalized Difference Vegetation Index for Land use land cover classification. Maximum likelihood was conducted for the classification phase. NDVI were extracted from the imagery to assist the process of classification. NDVI method is use by referring to its features such as vegetation at different NDVI threshold values. The result showed three classes of land cover that consist of low vegetation, high vegetation and non-vegetation area. The accuracy assessment gained was then being implemented using the visual interpretation and overall accuracy achieved was 70.740% with kappa coefficient of 0.5. This study gained the proposed threshold method using NDVI value able to identify and classify urban vegetation with the use of VHR Pleiades imagery and need further improvement when apply to different area of interest and different land use land cover characteristics. The information achieved from the result able to help planners for future planning for conservation of vegetation in urban area.

In agriculture management and cultivation, many researchers tend to introduce and implement new methods or techniques to improve the sectors in order to sustain a good production from the sectors. The oil palm plantation is one of the sectors that have received an improvement in development in many aspects. Thus, this paper reviews in detail the recent expansion of oil palm management and sustainability through the latest application technologies specifically in Remote Sensing (RS) and Geographical Information System (GIS) knowledge which covered land classification and crop changes, disease detection and pest control, age estimation for oil palm, above-ground biomass (AGB) and carbon estimation, tree counting for oil palm assessment and land suitability with soil nutrients. In the end, it concluded the most significant GIS and RS tools for oil palm management come from the implementation of Machine Learning (ML) and Deep Learning (DL) knowledge in it which can be improved over time through recent technologies and variation analysis to enhance the results.

The urban forest acts as excellent storage for carbon dioxide (CO2). Quantifying the above-ground biomass can be vital in understanding the role of urban forest in mitigating excessive carbon dioxide in the urban environment. This study aimed to quantify and compare the above-ground biomass changes that occur from 1995 to 2005 and from 2005 to 2015 in Bandar Meru Raya, Ipoh, Perak using Landsat 5 and Landsat 8 images. The estimation of above-ground biomass was carried out using two methods, the development of a model equation using correlation analysis for the oil palm plantation inside the study area and an existing model equation that uses normalized difference vegetation index (NDVI) for the urban forest. The results obtained shows that the above-ground biomass content inside the study area has decreased by 6.60% in the first 10 years and decreased by another 33.78% in the second 10 years. These above-ground biomass changes show that there is a severe loss of carbon storage in the study area. Hence, the results can enable authorities to take action in managing the urban forest in order to maintain a stable climate and achieve low carbon city status.

The social and economic development from the coastal area benefits human life. However, growing human and environmental pressures at coastal areas also bring significant impacts on coastal erosion and coastline changes. Nowadays, geospatial technology which utilized remote sensing and GIS techniques has been widely used to detect coastal erosion for controlling the development and coastal region sustainability. Thus, this study was conducted to assess the coastal erosion and accretion for the potential risk zone based on the characteristics of the landscape and land use land cover (LULC) at the Kelantan Coast using land use classification and GIS spatial interpolation techniques. In this study, the vulnerability level of the coastal profile at the Kelantan coast was determined from the beach profile survey and the Inverse Distance Weighting (IDW) interpolation method. Then, the Land Use Land Cover (LULC) along a 1 km buffer zone were classified by performing a supervised classification method on Sentinel 2 satellite images year 2020. The effect of these parameters on coastal erosion was determined from separated five management units (MU 1, MU 2, MU 3, MU 4, MU 5) along the Kelantan Coast based on the Malaysian Department of Irrigation and Drainage (DID). It is found that MU 3 (0.8%) and MU 5 (0.6%) were the area with the lowest average slope profile percentages which is located at Pantai Sabak and Pantai Kemayang respectively. Thus, the infrastructure, LULC and coastal communities in Pantai Sabak and Pantai Kemayang were potentially vulnerable to erosion. This finding supports the significant use of geospatial techniques of important decision-making to protect and mitigate steps toward sustainable coastal management along the coastline.