Search

Massive cyanobacterial blooms in river water causes adverse impacts on aquatic ecosystems and water quality. Complex and diverse data sources are available to investigate the cyanobacteria phenomena, including in situ data, synthetic measurements, and remote sensing images. Deep learning attention models can process these intricate sources to forecast cyanobacteria by identifying important variables in the data sources. However, deep learning attention models for predicting cyanobacteria have rarely been studied using an assemblage of various datasets. Thus, in this study, a convolutional neural network (CNN) model with a convolutional block attention module (CNN an ) was developed to predict cyanobacterial cell concentrations by using the observed cell data from field monitoring, chlorophyll-a distribution map from hyperspectral image sensing, and simulated water quality outputs from a hydrodynamic model. Then, the prediction performance of the CNN an model was compared to an environmental fluid dynamics code (EFDC) simulation and a CNN model without an attention network. The seasonal variations of the predicted cyanobacteria that was obtained from CNN an showed the best agreement with the observed variations with Nash-Sutcliffe efficiency values higher than 0.76 when compared to the EFDC and CNN predictions. The daily hydrodynamic outputs allowed the prediction of cyanobacteria cells, while the rich information of the chlorophyll-a map contributed to the improvement of the prediction performance at certain periods. Moreover, the attention network visualized the importance of the additional chlorophyll-a map and improved the CNN an model prediction performance by refining the input features. Therefore, this study demonstrated that a deep learning model with data assemblage is practically feasible for predicting the presence of harmful algae in inland water., (Copyright © 2021. Published by Elsevier Ltd.)

As semiconductor device structures become more complex and sophisticated, the formation of finer and deeper patterns is required. To achieve a higher yield for mass production as the number of process steps increases and process variables become more diverse, process optimization requires extensive engineering effort to meet the target process requirements, such as uniformity. In this study, we propose an efficient process design framework that can efficiently search for optimal process conditions by combining deep learning (DL) with plasma simulations. To establish the DL model, a dataset was created using a two-dimensional (2D) hybrid plasma equipment model code for an argon inductively coupled plasma system under a given process window. The DL model was implemented and trained using the dataset to learn the functional relationship between the process conditions and their consequential plasma states, which was characterized by 2D field data. The performance of the DL model was confirmed by comparison of the output with the ground truth, validating its high consistency. Moreover, the DL results provide a reasonable interpretation of the fundamental features of plasmas and show a good correlation with the experimental observations in terms of the measured etch rate characteristics. Using the designed DL, an extensive exploration of process variables was conducted to find the optimal processing condition using the multi-objective particle swarm optimization algorithm for the given objective functions of high etch rate and its uniform distribution. The obtained optimal candidates were evaluated and compared to other process conditions experimentally, demonstrating a fairly enhanced etch rate and uniformity at the same time. The proposed computational framework substantially reduced trial-and-error repetitions in tailoring process conditions from a practical perspective. Moreover, it will serve as an effective tool to narrow the processing window, particularly in the early stages of development for advanced equipment and processes. [ABSTRACT FROM AUTHOR]

Harmful algal blooms (HABs) caused by harmful cyanobacteria adversely impact the water quality in aquatic ecosystems and burden socioecological systems that are based on water utilization. Currently, Korea uses the Environmental Fluid Dynamics Code-National Institute of Environmental Research (EFDC-NIER) model to predict algae conditions and respond to algal blooms through the HAB alert system. This study aimed to establish an additional deep learning model to effectively respond to algal blooms. The prediction model is based on a deep neural network (DNN), which is a type of artificial neural network widely used for HAB prediction. By applying the synthetic minority over-sampling technique (SMOTE) to resolve the imbalance in the data, the DNN model showed improved performance during validation for predicting the number of cyanobacteria cells. The R-squared increased from 0.7 to 0.78, MAE decreased from 0.7 to 0.6, and RMSE decreased from 0.9 to 0.7, indicating an enhancement in the model's performance. Furthermore, regarding the HAB alert levels, the R-squared increased from 0.18 to 0.79, MAE decreased from 0.2 to 0.1, and RMSE decreased from 0.3 to 0.2, indicating improved performance as well. According to the results, the constructed data-based model reasonably predicted algae conditions in the summer when algal bloom-induced damage occurs and accurately predicted the HAB alert levels for immediate decision-making. The main objective of this study was to develop a new technology for predicting and managing HABs in river environments, aiming for a sustainable future for the aquatic ecosystem. [ABSTRACT FROM AUTHOR]

Polymer electrolyte membrane fuel cells (PEMFC) are a prevalent power source in transportation because of their ability to generate energy at low temperatures without harmful emissions. However, problems related to water management cause performance and durability degradation. The main faults are flooding, whereby the performance suffers owing to the stagnated water in gas diffusion paths and catalyst layers, and drying, which increases the ohmic loss owing to water evaporation in the electrolyte or insufficient water supply. Difficulties in recognizing these faults and normalizing operations impair the PEMFC stability. However, detecting errors in advance contributes to maintaining normal operation. Therefore, a system that diagnoses flooding and drying of the PEMFC before they occur is developed in this study using deep learning. The characteristics of flooding and drying are analyzed through preliminary experiments. Experimental data in the form of a time series are accumulated through a full-scale single-cell test. A pre-diagnosis system, developed using long short-term memory (LSTM) and a convolutional neural network (CNN), is reinforced through the bagging ensemble method. The expandability of the target future time and real-time system applicability are discussed. The detection rates achieved by the proposed system for flooding and drying that occur after 30 s are 98.52% and 95.36%, respectively. • Pre-diagnosis system that predicts the future state of PEMFC. • Flooding and drying cause performance degradation in PEMFC. • Electrical characterization of flooding and drying through PEMFC experiments. • Output voltage, relative humidity and cell temperature are selected as input features. • Bagging ensemble method based on LSTM and CNN is conducted. [ABSTRACT FROM AUTHOR]

Hyperspectral image sensing can be used to effectively detect the distribution of harmful cyanobacteria. To accomplish this, physical- and/or model-based simulations have been conducted to perform an atmospheric correction (AC) and an estimation of pigments, including phycocyanin (PC) and chlorophyll-a (Chl-a), in cyanobacteria. However, such simulations were undesirable in certain cases, due to the difficulty of representing dynamically changing aerosol and water vapor in the atmosphere and the optical complexity of inland water. Thus, this study was focused on the development of a deep neural network model for AC and cyanobacteria estimation, without considering the physical formulation. The stacked autoencoder (SAE) network was adopted for the feature extraction and dimensionality reduction of hyperspectral imagery. The artificial neural network (ANN) and support vector regression (SVR) were sequentially applied to achieve AC and estimate cyanobacteria concentrations (i.e., SAE-ANN and SAE-SVR). Further, the ANN and SVR models without SAE were compared with SAE-ANN and SAE-SVR models for the performance evaluations. In terms of AC performance, both SAE-ANN and SAE-SVR displayed reasonable accuracy with the Nash–Sutcliffe efficiency (NSE) > 0.7. For PC and Chl-a estimation, the SAE-ANN model showed the best performance, by yielding NSE values > 0.79 and > 0.77, respectively. SAE, with fine tuning operators, improved the accuracy of the original ANN and SVR estimations, in terms of both AC and cyanobacteria estimation. This is primarily attributed to the high-level feature extraction of SAE, which can represent the spatial features of cyanobacteria. Therefore, this study demonstrated that the deep neural network has a strong potential to realize an integrative remote sensing application. [ABSTRACT FROM AUTHOR]