Bangladesh is in the floodplains of the Ganges, Brahmaputra, and Meghna River delta, crisscrossed by an intricate web of rivers. Although the country is highly prone to flooding, the use of state-of-the-art deep learning models in predicting river water levels to aid flood forecasting is underexplored. Deep learning and attention-based models have shown high potential for accurately forecasting floods over space and time. The present study aims to develop a long short-term memory (LSTM) network and its attention-based architectures to predict flood water levels in the rivers of Bangladesh. The models developed in this study incorporated gauge-based water level data over 7 days for flood prediction at Dhaka and Sylhet stations. This study developed five models: artificial neural network (ANN), LSTM, spatial attention LSTM (SALSTM), temporal attention LSTM (TALSTM), and spatiotemporal attention LSTM (STALSTM). The multiple imputation by chained equations (MICE) method was applied to address missing data in the time series analysis. The results showed that the use of both spatial and temporal attention together increases the predictive performance of the LSTM model, which outperforms other attention-based LSTM models. The STALSTM-based flood forecasting system, developed in this study, could inform flood management plans to accurately predict floods in Bangladesh and elsewhere.

Brain magnetic resonance imaging (MRI) offers intricate soft tissue contrasts that are essential for diagnosing diseases and conducting neuroscience research. At 7 Tesla (7T) magnetic field intensity, MRI enables increased resolution, enhanced tissue contrast, and improved SNR, compared to MRI collected from the commonly employed 3 Tesla (3T) MRI scanners. However, the exorbitant expenses associated with 7T MRI scanners hinder their broad use in research and clinical facilities. Efforts are underway to develop algorithms that can generate 7T MRI from 3T MRI to achieve better image quality without the need for 7T MRI machines. In this study, we have adopted a cycle consistent generative adversarial network (CycleGAN)-based approach for 3T MRI to 7T MRI translation, and vice versa, using a recently published dataset of paired T1-weighted MR images collected at 3T and 7T from a total of ten subjects. Various CycleGAN architectures were experimented with and compared on this dataset. The best performing CycleGAN architecture successfully produced the reconstructed images with a high level of accuracy based on different quantitative and qualitative evaluation criteria. Utilizing a post-processing technique, the best performing model generated 7T MRI from 3T MRI with a structural similarity index measure (SSIM) of 83.80%, peak SNR (PSNR) of 26.25, normalized mean squared error (NMSE) of 0.0088 and normalized mean absolute error (NMAE) of 0.0630. Utilizing CycleGAN to convert images from 3T to 7T MRI has shown a substantial improvement in MRI resolution, setting the stage for advancements in more informative and precise diagnostic imaging.

Spatial flood susceptibility mapping (FSM) is one of the key components of flood risk assessment. Recent studies showed the efficacy of hybridized machine learning (ML)-based models in predicting flood susceptibility. The quality of this prediction depends on the presence or absence of label noise in the training data collected from real world flood inundation maps. However, no study has been conducted to explore the effects of label noise in ML based spatial FSM. In the present study, we have explored the effects of four different random class label noises on the regression performances and model complexities of both standalone and hybridized ML based FSM. We also explored the optimal hyperparameter values of different hybridized ML and reported the robustness of each model in the presence and absence of label noise. The hybridized ML models showed greater efficacy in modeling spatial flood susceptibility in both cases.

Recently COVID-19 pandemic has affected the whole world quite seriously. The number of new infectious cases and death cases are rapidly increasing over time. In this study, a theoretical linguistic fuzzy rule-based Susceptible-Exposed-Infectious-Isolated-Recovered (SEIIsR) compartmental model has been proposed to predict the dynamics of the transmission of COVID-19 over time considering population immunity and infectiousness heterogeneity based on viral load in the model. The model’s equilibrium points have been calculated and stability analysis of the model’s equilibrium points has been conducted. Consequently, the fuzzy basic reproduction number, R0f of the fuzzy model has been formulated. Finally, the temporal dynamics of different compartmental populations with immunity and infectiousness heterogeneity using the fuzzy Mamdani model are delineated and some disease control policies have been suggested to get over the infection in no time.