Abstract:Change detection based on satellite images acquired from an area at different dates is of widespread interest, according to the increasing number of flood-related disasters. The images help to generate products that support emergency response and flood management at a global scale. In this paper, a novel unsupervised change detection approach based on image fusion is introduced. The approach aims to extract the reliable flood extent from very high-resolution (VHR) bi-temporal images. The method takes an advantage of the spectral distortion that occurs during image fusion process to detect the change areas by flood. To this end, a change candidate image is extracted from the fused image generated with bi-temporal images by considering a local spectral distortion. This can be done by employing a universal image quality index (UIQI), which is a measure for local evaluation of spectral distortion. The decision threshold for the determination of changed pixels is set by applying a probability mixture model to the change candidate image based on expectation maximization (EM) algorithm. We used bi-temporal KOMPSAT-2 satellite images to detect the flooded area in the city of N′djamena in Chad. The performance of the proposed method was visually and quantitatively compared with existing change detection methods. The results showed that the proposed method achieved an overall accuracy (OA = 75.04) close OPEN ACCESSRemote Sens. 2015, 7 10348 to that of the support vector machine (SVM)-based supervised change detection method. Moreover, the proposed method showed a better performance in differentiating the flooded area and the permanent water body compared to the existing change detection methods.

Although data-driven methods including deep neural network (DNN) were introduced, there was not enough assessment about spatial characteristics when using limited ground observation as reference. This work aimed to interpret the feasibility of several machine learning approaches to assess the spatial distribution of solar radiation on Earth based on the Communication, Ocean, and Meteorological Satellite (COMS) Meteorological Imager (MI) geostationary satellite. Four data-driven models were selected (artificial neural network (ANN), random forest (RF), support vector regression (SVR), and DNN), to compare their accuracy and spatial estimating performance. Moreover, we used a physical model to probe the ability of data-driven methods, implementing hold-out and k-fold cross-validation approaches based on pyranometers located in South Korea. The results of analysis showed the RF had the highest accuracy in predicting performance, although the difference between RF and the second-best technique (DNN) was insignificant. Temporal variations in root mean square error (RMSE) were dependent on the number of data samples, while the physical model showed relatively less sensitivity. Nevertheless, DNN and RF showed less variability in RMSE than the others. To examine spatial estimation performance, we mapped solar radiation over South Korea for each model. The data-driven models accurately simulated the observed cloud pattern spatially, whereas the physical model failed to do because of cloud mask errors. These exhibited different spatial retrieval performances according to their own training approaches. Overall analysis showed that deeper layers of networks approaches (RF and DNN), could best simulate the challenging spatial pattern of thin clouds when using satellite multispectral data.

No abstract

No abstract

Landslide susceptibility models are important for public safety, but often rely on inaccessible or unaffordable software and geospatial data. Thus, affordable and accessible landslide prediction systems would be especially useful in places that lack the infrastructure for acquiring and analyzing geospatial data. Current landslide susceptibility models and existing methodologies do not consider such issues; therefore, this study aimed to develop an accessible and affordable landslide susceptibility modeling application and methodology based on open-source software and geospatial data. This model used TRIGRS (asc format) and QGIS (Digital Elevation Models (DEMs) extracted from GeoTIFF format) with widely accessible environmental parameters to identify potential landslide risks. In order to verify the suitability of the proposed application and methodology, a case study was conducted on Lantau Island, Hong Kong to assess the validity of the results, a comparison with 1999 landslide locations. The application developed in this study showed a good agreement with the four previous landslide locations marked as highly susceptible, which proves the validity of the study. Therefore, the developing model and the cost-effective approach, in this study simulated the landslide performance well and suggested the new approach of the landslide prediction system.