RESUMEN
Identifying and monitoring coastlines and shorelines play an important role in coastal erosion assessment around the world. The application of deep learning models was used in this study to detect coastlines and shorelines in Vietnam using high-resolution satellite images and different object segmentation methods. The aims are to (1) propose indicators to identify coastlines and shorelines; (2) build deep learning (DL) models to automatically interpret coastlines and shorelines from high-resolution remote sensing images; and (3) apply DL-trained models to monitor coastal erosion in Vietnam. Eight DL models were trained based on four artificial-intelligent-network structures, including U-Net, U2-Net, U-Net3+, and DexiNed. The high-resolution images collected from Google Earth Pro software were used as input data for training all models. As a result, the U-Net using an input-image size of 512 × 512 provides the highest performance of 98% with a loss function of 0.16. The interpretation results of this model were used effectively for the coastline and shoreline identification in assessing coastal erosion in Vietnam due to sea-level rise in storm events over 20 years. The outcomes proved that while the shoreline is ideal for observing seasonal tidal changes or the immediate motions of current waves, the coastline is suitable to assess coastal erosion caused by the influence of sea-level rise during storms. This paper has provided a broad scope of how the U-Net model can be used to predict the coastal changes over vietnam and the world.
Asunto(s)
Aprendizaje Profundo , VietnamAsunto(s)
Trasplante de Células Madre Hematopoyéticas , Mieloma Múltiple , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapéutico , Compuestos de Boro , Bortezomib/uso terapéutico , Dexametasona/uso terapéutico , Glicina/análogos & derivados , Humanos , Mieloma Múltiple/diagnóstico , Mieloma Múltiple/tratamiento farmacológico , Trasplante de Células Madre , Talidomida/uso terapéutico , Trasplante Autólogo , Resultado del TratamientoRESUMEN
ZSM-5/SBA-15 composite materials with different acidities and mesoporous system formations were successfully synthesized by three-step method. The catalysts were characterized by XRD, HR-TEM, BET, EDX and TPD-NH3 methods. It showed that the Si/Al molar ratio had effect on the formation and property of materials. Among synthesized catalysts with the different Si/Al molar ratios of 30 (HZSC-30), 50 (HZSC-50), 70 (HZSC-70), HZSC-50 catalyst had better mesoporous system formation and acidity. These properties helped this catalyst to have higher catalytic activity in 1,3,5-triisopropylbenzene cracking reaction than other studied catalysts in term of higher benzene product yield. In comparison to HZSM-5 microporous material that had the similar Si/Al molar ratio of 50, it showed that the formation of mesopore system of HZSC-50 catalyst had a major improvement on the cracking catalytic activity.
