Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452775
I. Dewa Gede Arya Putra, E. Heriyanto, A. Sopaheluwakan, R. P. Pradana, D. Nuryanto
Forest fires have caused significant economic losses and environmental damage. The phenomenon of Nino variability in the Pacific region has affected the occurrence of forest fires in Indonesia. The hotspot data gridding in this study aims to change the host data format to make it more universal with other geodata, most of which are already in the grid matrix format in the NetCDF data format to facilitate the need for spatial and temporal analysis and interpretation. The method in this analysis is to add up the daily hotspots with a hotspot confidence level above 80% in a grid area with a spatial resolution of 25 km2 per month, then create a time series from 2001 to 2019 with the research domain of all parts of Indonesia. Based on gridding data, the spatial distribution of the number of dominant hotspots over 100 hotspots occurs during the JJA and SON seasons in Jambi, South Sumatra, West Kalimantan, Central Kalimantan, South Kalimantan, and East Kalimantan. Based on the spatial correlation of hotspots with Nino 1.2, Nino 3, Nino 3.4, and Nino 4, there is a positive correlation with coefficient values ranging from 0.1 to 0.4 for almost all parts of Indonesia except northern Sumatra which is negatively correlated around -0.1.
{"title":"Seasonal Analysis of the Hotspot Spatial Grid in Indonesia and the Relationship of the Hotspot Grid with the Nino SST Indices","authors":"I. Dewa Gede Arya Putra, E. Heriyanto, A. Sopaheluwakan, R. P. Pradana, D. Nuryanto","doi":"10.1109/AGERS51788.2020.9452775","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452775","url":null,"abstract":"Forest fires have caused significant economic losses and environmental damage. The phenomenon of Nino variability in the Pacific region has affected the occurrence of forest fires in Indonesia. The hotspot data gridding in this study aims to change the host data format to make it more universal with other geodata, most of which are already in the grid matrix format in the NetCDF data format to facilitate the need for spatial and temporal analysis and interpretation. The method in this analysis is to add up the daily hotspots with a hotspot confidence level above 80% in a grid area with a spatial resolution of 25 km2 per month, then create a time series from 2001 to 2019 with the research domain of all parts of Indonesia. Based on gridding data, the spatial distribution of the number of dominant hotspots over 100 hotspots occurs during the JJA and SON seasons in Jambi, South Sumatra, West Kalimantan, Central Kalimantan, South Kalimantan, and East Kalimantan. Based on the spatial correlation of hotspots with Nino 1.2, Nino 3, Nino 3.4, and Nino 4, there is a positive correlation with coefficient values ranging from 0.1 to 0.4 for almost all parts of Indonesia except northern Sumatra which is negatively correlated around -0.1.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115190814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452768
Y. Heryadi, E. Irwansyah, Eka Miranda, Haryono Soeparno, Herlawati, Kiyota Hashimoto
Semantic image segmentation is an interesting problem in Computer Vision with many potential applications. The DeepLab model is combined with two other networks: Resnet and Conditional Random Field networks, making the DeepLab model a fairly deep network structure to increase semantic segmentation performance. Many previous studies argued that there are some limits on the deep learning model's depth as the deep structure may lead to vanishing/exploding gradient, which the model's performance. This paper presents an experimental study to compare the effect of several ImageNet pre-trained Resnet variant models with different network layers used as feature extractor in DeepLab model to solve semantic image segmentation task. In this study, three Resnet34, Resnet50, and Resnet101 models as network extractor of DeepLabV3were explored. The experiment found that semantic image segmentation model performance measured by the best accuracy and average accuracies of DeepLabV3- Resnet34, DeepLabV3-Resnet50, and DeepLabV3-Resnet101 are (0.87, 0.86) (0.86, 0.84), and (0.92, 0.88) respectively. Based on the experiment, DeepLabV3-Resnet101 achieved the best semantic segmentation performance than the other models
语义图像分割是计算机视觉中一个有趣的问题，具有许多潜在的应用前景。DeepLab模型与Resnet和Conditional Random Field网络相结合，使DeepLab模型成为一个相当深度的网络结构，以提高语义分割性能。许多先前的研究认为深度学习模型的深度存在一定的限制，因为深度结构可能导致梯度消失/爆炸，从而影响模型的性能。本文通过实验研究，比较了不同网络层的ImageNet预训练Resnet变体模型在DeepLab模型中作为特征提取器解决语义图像分割任务的效果。本研究采用Resnet34、Resnet50和Resnet101三种模型作为deeplabv3的网络提取器。实验发现，DeepLabV3- Resnet34、DeepLabV3- resnet50和DeepLabV3- resnet101的最佳准确率和平均准确率分别为(0.87,0.86)、(0.86,0.84)和(0.92,0.88)。实验结果表明，DeepLabV3-Resnet101的语义分割性能优于其他模型
{"title":"The Effect of Resnet Model as Feature Extractor Network to Performance of DeepLabV3 Model for Semantic Satellite Image Segmentation","authors":"Y. Heryadi, E. Irwansyah, Eka Miranda, Haryono Soeparno, Herlawati, Kiyota Hashimoto","doi":"10.1109/AGERS51788.2020.9452768","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452768","url":null,"abstract":"Semantic image segmentation is an interesting problem in Computer Vision with many potential applications. The DeepLab model is combined with two other networks: Resnet and Conditional Random Field networks, making the DeepLab model a fairly deep network structure to increase semantic segmentation performance. Many previous studies argued that there are some limits on the deep learning model's depth as the deep structure may lead to vanishing/exploding gradient, which the model's performance. This paper presents an experimental study to compare the effect of several ImageNet pre-trained Resnet variant models with different network layers used as feature extractor in DeepLab model to solve semantic image segmentation task. In this study, three Resnet34, Resnet50, and Resnet101 models as network extractor of DeepLabV3were explored. The experiment found that semantic image segmentation model performance measured by the best accuracy and average accuracies of DeepLabV3- Resnet34, DeepLabV3-Resnet50, and DeepLabV3-Resnet101 are (0.87, 0.86) (0.86, 0.84), and (0.92, 0.88) respectively. Based on the experiment, DeepLabV3-Resnet101 achieved the best semantic segmentation performance than the other models","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123790626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452788
S. Koesuma, Riza Vina Chrismiantari
The tidal of the sea is a phenomenon of rising and falling sea levels periodically caused by the influence of gravity from celestial objects, especially the moon and sun. The purpose of this research is to determine the tidal type in West Sumatra Water, especially in Sabang, Sibolga, and Padang cities. Tidal type can be used as a reference for the port to determine when the ship can go in or out of the port. We used satellite altimetry and tide gauge data. Tidal types in the West Sumatra Waters are influenced by the characteristics of tides in the Andaman Sea and the Indian Ocean. Determining the tidal type required the Formzahl number obtained from the comparison of tidal constants using harmonic analysis. We obtained that the West Sumatra Waters has semidiurnal tidal types with a Formzahl number 0.2013 at Sabang station and has a mixed tidal type (semidiurnal dominant) at Padang and Sibolga stations with Formzahl number values of 0.4306 and 0.4893, respectively. We found 9 tidal components with different amplitudes and phase angles in each component and each station. The tidal components obtained are Z0, M2, S2, K2, K1, 01, P1, M4, and MS4.
{"title":"Determination of Tidal Components and Tidal Types Using Harmonic Analysis in the West Sumatera Waters","authors":"S. Koesuma, Riza Vina Chrismiantari","doi":"10.1109/AGERS51788.2020.9452788","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452788","url":null,"abstract":"The tidal of the sea is a phenomenon of rising and falling sea levels periodically caused by the influence of gravity from celestial objects, especially the moon and sun. The purpose of this research is to determine the tidal type in West Sumatra Water, especially in Sabang, Sibolga, and Padang cities. Tidal type can be used as a reference for the port to determine when the ship can go in or out of the port. We used satellite altimetry and tide gauge data. Tidal types in the West Sumatra Waters are influenced by the characteristics of tides in the Andaman Sea and the Indian Ocean. Determining the tidal type required the Formzahl number obtained from the comparison of tidal constants using harmonic analysis. We obtained that the West Sumatra Waters has semidiurnal tidal types with a Formzahl number 0.2013 at Sabang station and has a mixed tidal type (semidiurnal dominant) at Padang and Sibolga stations with Formzahl number values of 0.4306 and 0.4893, respectively. We found 9 tidal components with different amplitudes and phase angles in each component and each station. The tidal components obtained are Z0, M2, S2, K2, K1, 01, P1, M4, and MS4.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117128923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452758
Ilham Fajar Putra Perdana, D. Septiadi
Geostationary satellite-based heavy rain prediction algorithm called convective initiation (CI) nowcasting recently becomes a solution in providing an earlier heavy rain forecast. However, this algorithm depends on the threshold value of the interest fields to predict whether a cloud object could potentially produce heavy rain, so it is important to understand the cloud physical characteristics in a particular area if the CI nowcasting algorithm is going to be developed. This research aims to assess the cloud spectral characteristics based on twelve interest fields of Satellite Convection Analysis and Tracking (SATCAST), one of the promising CI nowcasting algorithms, in Surabaya during the June-July-August period in 2018. Six bands of Himawari-8 and Surabaya weather radar data are used to quantify the cloud object spectral characteristics and determine the CI event, respectively. Four main processes conducted in this research include CI detection, cloud masking, backward cloud object tracking, and cloud spectral evaluation. The results show that 4 of 12 interest fields depict a significant change since 30–60 minutes before the CI event with $mathbf{T}_{mathbf{b11.2}}$ as the most significant interest field. Meanwhile, five interest fields tend to be constant until a significant change has reached 10 minutes before the CI event.
{"title":"Cloud Spectral Characteristics Prior To Convective Initiation Event Based on Himawari-8 Satellite Around Surabaya","authors":"Ilham Fajar Putra Perdana, D. Septiadi","doi":"10.1109/AGERS51788.2020.9452758","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452758","url":null,"abstract":"Geostationary satellite-based heavy rain prediction algorithm called convective initiation (CI) nowcasting recently becomes a solution in providing an earlier heavy rain forecast. However, this algorithm depends on the threshold value of the interest fields to predict whether a cloud object could potentially produce heavy rain, so it is important to understand the cloud physical characteristics in a particular area if the CI nowcasting algorithm is going to be developed. This research aims to assess the cloud spectral characteristics based on twelve interest fields of Satellite Convection Analysis and Tracking (SATCAST), one of the promising CI nowcasting algorithms, in Surabaya during the June-July-August period in 2018. Six bands of Himawari-8 and Surabaya weather radar data are used to quantify the cloud object spectral characteristics and determine the CI event, respectively. Four main processes conducted in this research include CI detection, cloud masking, backward cloud object tracking, and cloud spectral evaluation. The results show that 4 of 12 interest fields depict a significant change since 30–60 minutes before the CI event with $mathbf{T}_{mathbf{b11.2}}$ as the most significant interest field. Meanwhile, five interest fields tend to be constant until a significant change has reached 10 minutes before the CI event.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131652038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452756
H. Sanjaya, Zilda Dona Okta Permata, R. Amaliyah, Ela Nurdianti
The existence of mangroves and monitoring the extent of their cover in every corner of Indonesia is very important. This is due to the importance of mangroves for ecosystems as well as disasters. Making mangrove maps nationally has classic constraints, namely the many technical constraints such as computer skills, the amount of data, and the number of operators required. Utilization of cloud computing technology using the Google Earth Engine application and carried out by crowd participation can eliminate these obstacles. A national consortium is needed to coordinate local teams that can move quickly at their respective locations. This can benefit from many aspects including location accuracy, map update speed, and a large reduction in costs.
{"title":"The Use of Cloud Computing with Crowd Participation to Have an Alternative National Mangrove Map","authors":"H. Sanjaya, Zilda Dona Okta Permata, R. Amaliyah, Ela Nurdianti","doi":"10.1109/AGERS51788.2020.9452756","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452756","url":null,"abstract":"The existence of mangroves and monitoring the extent of their cover in every corner of Indonesia is very important. This is due to the importance of mangroves for ecosystems as well as disasters. Making mangrove maps nationally has classic constraints, namely the many technical constraints such as computer skills, the amount of data, and the number of operators required. Utilization of cloud computing technology using the Google Earth Engine application and carried out by crowd participation can eliminate these obstacles. A national consortium is needed to coordinate local teams that can move quickly at their respective locations. This can benefit from many aspects including location accuracy, map update speed, and a large reduction in costs.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125390158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452778
Syam’ani
The presence of atmospheric particles in multispectral imageries such as Landsat 8 OLI can reduce the visual acuity of the imageries. The most ideal method to reduce the existence of atmospheric particles in the imagery, as well as to enhance the visual appearance of the imagery, is to employ atmospheric corrections. However, atmospheric corrections are a very complex process. Besides, sometimes the results don't have an impact visually. There are many other methods to enhance imagery radiometrically, either by stretching the pixel value, shifting the histogram, or reducing the presence of clouds. This research aims to develop practical formulations to enhance the spectral value of the Landsat 8 OLI imagery bands, by reducing the presence of aerosol particles using the C/A band. Several regression models were involved in the construction process of these formulations. The accuracy assessment was performed using the Pearson correlation coefficient and RMSE, using the USGS Landsat 8 OLI TOC imagery as a comparison. The results showed that the radiometric imagery enhancement using the C/A band gave satisfactory results. Apart from providing a significant visual sharpness increase, for the exponential model with parameters, the average Pearson correlation coefficient is 0.96, with an RMSE value of 0.04, relative to the USGS Landsat 8 OLI TOC product. For a more practical model, we can omit the parameters in the exponential model. The results that will be obtained are still quite accurate. Furthermore, we can implement this enhancement model directly on digital numbers.
在诸如Landsat 8 OLI这样的多光谱图像中，大气颗粒的存在会降低图像的视觉灵敏度。减少图像中大气颗粒的存在以及增强图像视觉外观的最理想方法是使用大气校正。然而，大气校正是一个非常复杂的过程。此外，有时结果在视觉上没有影响。还有许多其他方法可以通过扩展像素值、移动直方图或减少云的存在来增强图像的辐射。本研究旨在开发实用的配方，通过使用C/A波段减少气溶胶颗粒的存在，来提高Landsat 8 OLI图像波段的光谱值。在这些公式的构建过程中涉及了几个回归模型。使用Pearson相关系数和RMSE进行精度评估，并使用USGS Landsat 8 OLI TOC图像作为比较。结果表明，采用C/A波段进行辐射图像增强，效果满意。除了提供显著的视觉清晰度增加外，对于带参数的指数模型，相对于USGS Landsat 8 OLI TOC产品，平均Pearson相关系数为0.96,RMSE值为0.04。对于更实用的模型，我们可以省略指数模型中的参数。得到的结果仍然是相当准确的。此外，我们可以直接在数字上实现该增强模型。
{"title":"Radiometric Enhancement of Landsat 8 OLI Imagery Using Coastal/Aerosol Band","authors":"Syam’ani","doi":"10.1109/AGERS51788.2020.9452778","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452778","url":null,"abstract":"The presence of atmospheric particles in multispectral imageries such as Landsat 8 OLI can reduce the visual acuity of the imageries. The most ideal method to reduce the existence of atmospheric particles in the imagery, as well as to enhance the visual appearance of the imagery, is to employ atmospheric corrections. However, atmospheric corrections are a very complex process. Besides, sometimes the results don't have an impact visually. There are many other methods to enhance imagery radiometrically, either by stretching the pixel value, shifting the histogram, or reducing the presence of clouds. This research aims to develop practical formulations to enhance the spectral value of the Landsat 8 OLI imagery bands, by reducing the presence of aerosol particles using the C/A band. Several regression models were involved in the construction process of these formulations. The accuracy assessment was performed using the Pearson correlation coefficient and RMSE, using the USGS Landsat 8 OLI TOC imagery as a comparison. The results showed that the radiometric imagery enhancement using the C/A band gave satisfactory results. Apart from providing a significant visual sharpness increase, for the exponential model with parameters, the average Pearson correlation coefficient is 0.96, with an RMSE value of 0.04, relative to the USGS Landsat 8 OLI TOC product. For a more practical model, we can omit the parameters in the exponential model. The results that will be obtained are still quite accurate. Furthermore, we can implement this enhancement model directly on digital numbers.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115294533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452771
J. Matondang, L. Sumargana, Yudi Adityawarman, R. M. Taufik Yuniantoro
Tsunami is a prevalent issue in Indonesia ever since the 2004 Andaman Sea Tsunami. Various measurement systems are installed, such as broadband seismometers, tide gauges, and buoys are used to enhance the Indonesian Tsunami Early Warning System (InaTEWS). These data are held by their authorized organizations, to provide a quick overview of all Tsunami related data, a visualization platform is proposed showing earthquake and tidal height observed by tide gauge stations and tsunami buoys. This paper shows the development of such a platform and discusses the architecture and data flow from each data provider. The prototyped dashboard can successfully visualize the spatiotemporal data for near real-time Tsunami observation data and historical archived data to view past Tsunami events of the 2018 Tsunami in Palu.
{"title":"Development of near real-time and archival Tsunami data visualization dashboard for Indonesia","authors":"J. Matondang, L. Sumargana, Yudi Adityawarman, R. M. Taufik Yuniantoro","doi":"10.1109/AGERS51788.2020.9452771","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452771","url":null,"abstract":"Tsunami is a prevalent issue in Indonesia ever since the 2004 Andaman Sea Tsunami. Various measurement systems are installed, such as broadband seismometers, tide gauges, and buoys are used to enhance the Indonesian Tsunami Early Warning System (InaTEWS). These data are held by their authorized organizations, to provide a quick overview of all Tsunami related data, a visualization platform is proposed showing earthquake and tidal height observed by tide gauge stations and tsunami buoys. This paper shows the development of such a platform and discusses the architecture and data flow from each data provider. The prototyped dashboard can successfully visualize the spatiotemporal data for near real-time Tsunami observation data and historical archived data to view past Tsunami events of the 2018 Tsunami in Palu.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115591607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452785
R. van Beek, J. Lumban-Gaol, Syamsul Bahri Agus
Protected Areas (MPA) and No Take Zones are an effective tool for marine ecosystem preservation. Indonesia requires fishing vessels larger than 30 gross tons to use a Vessel Monitoring System (VMS). Another way to detect fisheries is through Visible Infrared Radiometer Suite (VIIRS) data. To compare VMS and VIIRS data, an R package, “LLFI” (Led Light Fisheries Identifier) was created. This package provides several R-functions that can calculate the location of VMS using vessels at the overpass time of the VIIRS satellite. An MPA near the Natuna archipelago was chosen as the research area. VMS and VIIRS data for the entire year of 2018 were obtained for this Region of Interest. The R function “vms2viirs” calculated activity for small purse seine fisheries all through the ROI and for bouke ami fisheries in the southwestern part of the ROI. The R Function “vms2viirsanalysis” created three buffers around detected fishing vessels by the VIIRS satellite and linked the closest found vessels from the VMS dataset. The amount of identified vessels for Class C was significantly higher than those for class A and B. Approximately 10% of all detected led lights could be identified with a shipping number from the VMS data set. Only around 8% of identified vessels could be found inside MPA and around 3% could be found in a No Take Zone. Paths of identified vessels that some vessels did cross MPA's and No Take Zones. It can be concluded that the LLFI package is working successfully.
{"title":"Analysis of Fishing with Led Lights in and around MPA and No Take Zones at Natuna Indonesia through VMS and VIIRS Data","authors":"R. van Beek, J. Lumban-Gaol, Syamsul Bahri Agus","doi":"10.1109/AGERS51788.2020.9452785","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452785","url":null,"abstract":"Protected Areas (MPA) and No Take Zones are an effective tool for marine ecosystem preservation. Indonesia requires fishing vessels larger than 30 gross tons to use a Vessel Monitoring System (VMS). Another way to detect fisheries is through Visible Infrared Radiometer Suite (VIIRS) data. To compare VMS and VIIRS data, an R package, “LLFI” (Led Light Fisheries Identifier) was created. This package provides several R-functions that can calculate the location of VMS using vessels at the overpass time of the VIIRS satellite. An MPA near the Natuna archipelago was chosen as the research area. VMS and VIIRS data for the entire year of 2018 were obtained for this Region of Interest. The R function “vms2viirs” calculated activity for small purse seine fisheries all through the ROI and for bouke ami fisheries in the southwestern part of the ROI. The R Function “vms2viirsanalysis” created three buffers around detected fishing vessels by the VIIRS satellite and linked the closest found vessels from the VMS dataset. The amount of identified vessels for Class C was significantly higher than those for class A and B. Approximately 10% of all detected led lights could be identified with a shipping number from the VMS data set. Only around 8% of identified vessels could be found inside MPA and around 3% could be found in a No Take Zone. Paths of identified vessels that some vessels did cross MPA's and No Take Zones. It can be concluded that the LLFI package is working successfully.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123139577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452781
G. P. Dinanta, D. Cassidy, J. Octariady, D. Fernando, M. Yusuf
The purpose of this study was to use data collected from actual landslide events between 2008 and 2018 in models to assess landslide susceptibility and to accurately forecast landslides in Sumatra, Indonesia. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modeling were compared. A digital elevation model (DEM) was used to generate data on elevation and slope. The neural network simulations were tested using a dataset from 2019, yielding a match greater than 80% with actual landslides. The accuracy and compatibility of ANN and ANFIS were compared using the 2019 landslide. Seismic activity, a parameter indirectly impacting landslides that are often ignored in probability models, was used. Precipitation, soil type and texture, and land cover were also used. The resulting landslide susceptibility map for 2008 to 2018 divides Sumatra into three zones; (1) high risk, (2) intermediate-risk, and (3) low risk.
{"title":"Assessing landslide susceptibility using ANN and ANFIS to forecast landslides in Sumatera Indonesia","authors":"G. P. Dinanta, D. Cassidy, J. Octariady, D. Fernando, M. Yusuf","doi":"10.1109/AGERS51788.2020.9452781","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452781","url":null,"abstract":"The purpose of this study was to use data collected from actual landslide events between 2008 and 2018 in models to assess landslide susceptibility and to accurately forecast landslides in Sumatra, Indonesia. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) modeling were compared. A digital elevation model (DEM) was used to generate data on elevation and slope. The neural network simulations were tested using a dataset from 2019, yielding a match greater than 80% with actual landslides. The accuracy and compatibility of ANN and ANFIS were compared using the 2019 landslide. Seismic activity, a parameter indirectly impacting landslides that are often ignored in probability models, was used. Precipitation, soil type and texture, and land cover were also used. The resulting landslide susceptibility map for 2008 to 2018 divides Sumatra into three zones; (1) high risk, (2) intermediate-risk, and (3) low risk.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128988294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-07DOI: 10.1109/AGERS51788.2020.9452755
R. M. Taufik Yuniantoro, Yudi Adityawarman, M. Frederik, A. Eugenie, Agits Agnia Fidzly Almatin, Irham Farhan Herdiardi, Fauzan Muhajir, Imas Muliatie, Sumirah Said
Large amount of oceanic data have been acquired over Indonesian waters by various institutions over the years. These collections are normally stored in the multiple institutions' archives, resulting in scattered storages. Indonesian National Oceanographic Data Center (InaNODC) aims to integrate these data collections using a portal that enables integrated access that allows data exchange between different formats for interoperability. InaNODC integrates data collections from Konsorsium Riset Samudera (KRS) - a collection of government institutions that conduct ocean research and operate research vessels. In this paper, we present the flow process of accessing data collection using CTD data from the Arafura Sea as an example of one of the data types stored in InaNODC. This shows the capability of InaNODC to do a query, extract, and display the intended data. In the future, InaNODC is designed to be a part of IODE-UNESCO as one of the oceanographic and marine data centers in compliance with international standards.
{"title":"Data Interoperability and Repository for Oceanography Research","authors":"R. M. Taufik Yuniantoro, Yudi Adityawarman, M. Frederik, A. Eugenie, Agits Agnia Fidzly Almatin, Irham Farhan Herdiardi, Fauzan Muhajir, Imas Muliatie, Sumirah Said","doi":"10.1109/AGERS51788.2020.9452755","DOIUrl":"https://doi.org/10.1109/AGERS51788.2020.9452755","url":null,"abstract":"Large amount of oceanic data have been acquired over Indonesian waters by various institutions over the years. These collections are normally stored in the multiple institutions' archives, resulting in scattered storages. Indonesian National Oceanographic Data Center (InaNODC) aims to integrate these data collections using a portal that enables integrated access that allows data exchange between different formats for interoperability. InaNODC integrates data collections from Konsorsium Riset Samudera (KRS) - a collection of government institutions that conduct ocean research and operate research vessels. In this paper, we present the flow process of accessing data collection using CTD data from the Arafura Sea as an example of one of the data types stored in InaNODC. This shows the capability of InaNODC to do a query, extract, and display the intended data. In the future, InaNODC is designed to be a part of IODE-UNESCO as one of the oceanographic and marine data centers in compliance with international standards.","PeriodicalId":125663,"journal":{"name":"2020 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116873257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：