Results Of Performance Indicators Research Articles

SR Thermal GAN: 초해상화 적외선 이미지 생성 기법

Thermal infrared cameras create IR (infrared) images, thus enabling the recognition of objects regardless of weather, illuminance, or ambient color. With the recent development of deep learning, research interest in image conversion and super-resolution techniques has increased. This paper proposes an algorithm that converts electro-optical (EO) images to IR images using super-resolution techniques based on generative adversarial networks. ThermalWorld data were used as the learning data. Additionally, drones of EO and IR images were added using thermal infrared cameras. The proposed super-resolution technique adapts the loss function and neural network structure to generate a high-resolution IR image. The loss function learns the neural network by utilizing the difference between the actual image and the generated image, thereby generating an image while maintaining the shape of the object on the image. The resolution is further improved by densely connecting the generator neural network structure and removing batch normalization. Finally, the structure of the discriminator is changed, and the stability of learning improved using the spectral norm. Images are generated according to each change item and quantitatively verified through performance indicators of improved image quality. This study analyzes images made with super-resolution techniques by considering the results of performance indicators and discusses the possibility of using IR images; and presents future research directions.

Assessment of Future Climate Change Projections Using Multiple Global Climate Models

Nowadays, the hydrological cycle which alters river discharge and water availability is affected by climate change. Therefore, the understanding of climate change is curial for the security of hydrologic conditions of river basins. The main purpose of this study is to assess the projections of future climate across the Upper Ayeyarwady river basin for its sustainable development and management of water sector for this area. Global Ten climate Models available from CMIP5 represented by the IPCC for its fifth Assessment Report were bias corrected using linear scaling method to generate the model error. Among the GCMs, a suitable climate model for each station is selected based on the results of performance indicators (R2 and RMSE). Future climate data are projected based on the selected suitable climate models by using future climate scenarios: RCP2.6, RCP4.5, and RCP8.5. According to this study, future projection indicates to increase in precipitation amounts in the rainy and winter season and diminishes in summer season under all future scenarios. Based on the seasonal temperature changes analysis for all stations, the future temperature are predicted to steadily increase with higher rates during summer than the other two seasons and it can also be concluded that the monthly minimum temperature rise is a bit larger than the maximum temperature rise in all seasons.

A first integrated modelling of a river-lagoon large-scale hydrological system for forecasting purposes

Hydrological-hydrodynamic modelling of basins, rivers and large bodies of water, such as lakes and lagoons, is usually performed by external coupling of hydrological-hydraulic models and 2D or 3D hydrodynamic models. Therefore, the river discharges into the lake are calculated by using the hydrologic model. The data is used then as an input to the hydrodynamic model. This approach allows for a detailed simulation of lake or lagoon hydrodynamics and circulation. However, when the objective is solely to simulate water levels and flooded areas, this approach may become too costly, making it difficult to establish operational systems such as those for flood forecasting. Therefore, in the present study, we propose a first integrated approach using one single hydrologic-hydraulic model, the MGB-IPH model, to simulate complex systems such as wind shear influence. This model was applied to simulate the Patos Lagoon (PL) basin located in Brazil and Uruguay countries. Results showed that it was possible to use the single model to simulate hydrographs, flooded areas and water levels in the PL basin. Results of performance indicators in the lakes and lagoons were within the range of results available in the literature. Improvements of model performance metrics were verified with the inclusion of wind effect in the flow routing algorithm, thus encouraging the use of the proposed model for the establishment of flood forecasting systems or for the simulation of other similar hydrological systems.