11 research outputs found
COMPARISON OF MACHINE LEARNING ALGORITHMS FOR LAND USE AND LAND COVER ANALYSIS USING GOOGLE EARTH ENGINE (CASE STUDY: WANGGU WATERSHED)
No full textHuman population growth and land use and land cover (LULC) change have always developed side by side. Considering selection of a good Machine Learning (ML) classifier algorithm is needed considering the high estimation of LULC maps based on remote sensing. This study aims to produce a LULC classification of Landsat-8 and Sentinel-2 images by comparing the accuracy performance of three ML algorithms, namely: Classification and Regression Tree (CART), Random Forest (RF), and Support Vector Machine (SVM). Dataset comparison ratios were also explored to find the LULC classification results with the best accuracy. Sentinel-2 is better than Landsat-8 regarding Overall Accuracy (OA) and Coefficient Kappa. The comparison ratio of the training and testing datasets with a good level of accuracy is 70:30 on both images with the average OA Landsat-8 and Sentinel-2 being 92.09% and 94.21%, respectively. The RF algorithm outperforms CART and SVM in both types of satellite imagery. The mean OA of the CART, RF, and SVM classifiers was 92.03%, 94.74%, 83.54% on Landsat-8, 93.14%, 96.15%, and 93.34% on Sentinel-2, respectively
Assessing Potential Distributions of Bird Endemic Species: Case Studies of Macrocephalon maleo and Rhyticeros cassidix and Their Threats
No full textMaleo and knobbed hornbill are bird species that are endemic on the island of Sulawesi, which is highly threatened by forest fires. Fires tend to destroy any affected species; however, it is not possible to survey the entire range of the original distribution of the two endemic bird species that are affected by forest fires due to practical constraints. Species distribution modeling using maximum entropy is considered to be an alternative to understanding the potential distribution area of species against the threat of forest fires. The prediction model from MaxEnt all have AUC values of greater than 0.70, which means that the model is good enough to classify the records of the presence of M. maleo and R. cassidix along with the past forest fires. The environmental variables that affect the distribution of M. maleo are its distance from hot water, rivers, and roads, while the distribution of R. cassidix is strongly influenced by its distance from roads, settlements, and rivers. Forest fire distribution is mostly influenced by soil type, land-use land cover, and rainfall. It is predicted that around 238,690 and 677,070 ha of the potential distribution of M. maleo and R. cassidix, respectively, are potentially disturbed and affected by forest fires. However, this number much greater outside conservation areas. The results of this study can be used by the government of the Republic of Indonesia (especially the Ministry of Environment and Forestry) for determining conservation actions for both species in the future
Spatial model of industrial area suitability using spatial multi criteria evaluation: A case study in Kendari City
No full textDesigning an industrial location must be based on consideration of factors that will influence it, such as natural, environmental, and ecological conditions. One of the spatial-based location determination methods is Spatial Multi-Criteria Evaluation (SMCE). This study aims to determine suitable industrial areas and compare industrial locations that have been determined based on the Regional Spatial Plan (RTRW) for 2010-2030 in Kendari City. Industrial areas must be flood-free, located in a relatively flat area, far from settlements, have good access, and must not interfere with the river\u27s natural function. Therefore, the aspects of access, hydrology, physiography, and convenience were all taken into account in this study. The area in Scenario A was retested with Scenario B and Scenario C to get a variety of industrial areas with different perspectives. Kendari City\u27s appropriate industrial area is 2,462.36 ha and is located in Puuwatu Sub-District, which is directly connected to Mandonga Sub-District (Scenario 2.C). The RTRW map with the industrial model of the area shows the mismatch of the proposed industrial area placement. The results of this industrial area can be used as an alternative for decision-makers
Evaluation of Regional Spatial Development on Landslide and Flood Prone with Actual Site Conditions in Kendari City
No full textKendari City is an area that has a high level of vulnerability to landslides and floods. The high intensity of rainfall and the geomorphological form of the area make Kendari City almost every year landslides and floods occur. This study aims to analyze the distribution of landslide and flood susceptibility and its suitability to the actual situation and evaluate the spatial pattern plan, especially in settlement areas. The method used is survey-based scoring and weighting. Overlay technique used in this study on physical variables including geological conditions, slope, rainfall, land use, soil type and distance from the river. The results show that areas in Kendari City are prone to landslides and floods respectively 79.33% and 81.75% with variations in the level of moderate and high vulnerability. Moderate vulnerability dominates in both disasters with an area of 165.80 km2 and 165.70 km2. The suitability between the map and the actual situation reached 80.63% and 91.30%. Most of the spatial pattern plans, especially settlements that have been made and determined by the government, are appropriate for regional development in Kendari City. Evaluation of spatial patterns of landslide and flood prone zones shows that a small proportion of high vulnerability zones are in the delineation of settlement areas with suitability levels reaching 93.05% and 76.45%
Habitat Suitability Modeling of Drummer Rail (Habroptila wallacii) on Halmahera Island, Indonesia
No full textDrummer Rail (Habroptila wallacii) is a bird species of the Rallidae family with limited ecology and behavior information. The information on the distribution of H. wallacii in Halmahera Island is crucial as it is classified as a vulnerable species. Therefore, this research aims to predict the potential distribution of H. wallacii on Halmahera Island using the Maximum Entropy (MaxEnt) modeling method, which projects species distributions based on presence data and environmental variables. A total of 47 data points on H. wallacii encounters were obtained from open-access data sources and field observation. The variables used were land use land cover (LULC), normalized difference vegetation index (NDVI), elevation, slope, and proximity data (river). The results showed that 33.52% of the area was very suitable for H. wallacii habitat, 32.97% was suitable, and 33.50% was unsuitable. Approximately 29.39% of the suitable habitat was located in limited-production forest areas, while conservation areas covered only 5.19%. These results suggested the need to review spatial planning policies to increase protection of the natural habitat of the species. The results could serve as considerations and recommendations for the Ministry of Environment and Forestry regarding the future management of forest areas for these species
Rapid Flood Inundation Mapping Using Multi-Temporal Sentinel-1 SAR: An Example from Kendari City
No full textInformation regarding flood inundation presented through maps provides valuable information in preparedness and flood mitigation efforts when a disaster occurs by utilizing the potential of satellite imagery. This study aims to map flood inundation areas by integrating Sentinel-1 Synthetic Aperture Radar (SAR) data and the Otsu method. The results were validated with a confusion matrix and compared water areas that were flooded (March 2022), not flooded (February 2022), and flood seasons in previous years (April 2017 and June 2018). Historical patterns of rainfall are also analyzed to understand flood events. The overall accuracy and Kappa coefficient of the 22 March 2022 flood inundation map are 95.81% and 0.86, respectively. Areas that are submerged (region under water) classify floods well compared to areas that are not flooded (February 2022). Classification results in April 2017 and June 2018 also show the same thing. Sentinel-1 SAR which is integrated with the Otsu method in GEE can map flood inundation areas quickly and in Near-real time and increase the existing possibilities to save the grassroots and community's economic resources and protect infrastructure
Author Correction: Comprehensive analysis of chromothripsis in 2,658 human cancers using whole-genome sequencing
No full textauthor correctio
Author Correction: Pan-cancer analysis of whole genomes
No full textCell adhesion molecules are ubiquitous in multicellular organisms, specifying precise cell-cell interactions in processes as diverse as tissue development, immune cell trafficking and the wiring of the nervous system(1-4). Here we show that a wide array of synthetic cell adhesion molecules can be generated by combining orthogonal extracellular interactions with intracellular domains from native adhesion molecules, such as cadherins and integrins. The resulting molecules yield customized cell-cell interactions with adhesion properties that are similar to native interactions. The identity of the intracellular domain of the synthetic cell adhesion molecules specifies interface morphology and mechanics, whereas diverse homotypic or heterotypic extracellular interaction domains independently specify the connectivity between cells. This toolkit of orthogonal adhesion molecules enables the rationally programmed assembly of multicellular architectures, as well as systematic remodelling of native tissues. The modularity of synthetic cell adhesion molecules provides fundamental insights into how distinct classes of cell-cell interfaces may have evolved. Overall, these tools offer powerful abilities for cell and tissue engineering and for systematically studying multicellular organization. Synthetic cell adhesion molecules yield customized cell-cell interactions with adhesion properties that are similar to native interactions, and offer abilities for cell and tissue engineering and for systematically studying multicellular organization
Author Correction: Retrospective evaluation of whole exome and genome mutation calls in 746 cancer samples
No full text: Correction to this paper has been published: https://doi.org/10.1038/s41467-020-20128-w
