Viện Khoa Học Tính Toán & Trí Tuệ Nhân Tạo

Abstract:Rapid flood prediction in coastal urban areas is an important but challenging task. However, multi-driver floods in coastal areas and their non-linearity in physical processes are hard to represent in physics-based numerical models (PBNMs). In this study, we investigated the performance of surrogate machine learning (ML) models and their flood prediction capability. Initially, we utilize the MIKE+ coupled 1D–2D model to simulate coastal urban flooding in one of the severely flood-affected areas of Ho Chi Minh City (HCMC), Vietnam. Then, nine ML models, including AdaBoost (AB), Decision Tree (DT), Gaussian Process (GP), k-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Naive Bayes (NB), Neural Network (NN), Random Forest (RF), and Support Vector Machine (SVM) are employed to surrogate the PBNM flood prediction performance and engaged to predict flood depths of the study area domain. 806 simulation scenarios of MIKE+ modeling having a spatial grid of 1107 ×1513, grid size = 2 m, extracting 270,000 inundation points to generate input data for nine ML models are used to simulate surface flood depths for the study area. Results show three ML models, GP, RF, and NN, outperform the remaining models, with R2 value of 0.997, 0.996, and 0.995, respectively. Thus, applying ML models can significantly reduce the simulation time by a PBNM, improve accuracy, and potentially be adopted for real-time forecasting and emergency management.

Application of machine learning-based surrogate models for urban flood depth modeling in Ho Chi Minh City, Vietnam

Abstract:Enrofloxacin has been widely and increasingly used in veterinary medicine to treat infection on animals which could lead to antibiotic resistance for the consumer. Among the available detection techniques for Enrofloxacin, immunoassay lateral flow test strip is realised to be a rapid and accurate detection method for on-site analysis of Enrofloxacin antibiotic. The current study aims to analyse the application of inkjet printing technology on the immobilisation of biological substances at the test line and control line position of the test strip. With the printing parameters value at 35 °C, 35 °C, 7 layers and 15&nbsp;μm for cartridge temperature, substrate temperature, printing layers and drop spacing, respectively, the fabricated test strips show correlation coefficient&nbsp;R2&nbsp;at 0.993 for the test with Enrofloxacin samples in the concentration range from 0 to 100 ppb. Compared to conventional fabrication method, the immobilisation process utilising inkjet printing technology is considered to be superior in printing patterns with a simple and material-saving process, which holds a potential of innovative and financially beneficial approach for on-site detection of Enrofloxacin antibiotic.&nbsp;

Application of machine learning-based surrogate models for urban flood depth modeling in Ho Chi Minh City, Vietnam

Liên hệ để nhận thông tin tư vấn & hỗ trợ