An official website of the United States government
Predicting the transpiration stream concentration factor (TSCF) and other concentration factors is essential in understanding the plant uptake of organic contaminants. Traditional mechanistic and numerical modeling methods often fail to reliably predict the TSCF. This study developed a hybrid deep model to predict TSCF by integrating convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. This hybrid CNN-LSTM model used eight physicochemical properties of organic contaminants to predict TSCF. The training procedure for this hybrid model was successful. The results indicated the training and test losses for predicting TSCF were both in the same order and close to zero. This study showed that the hybrid CNN-LSTM model can outperform mechanistic models and have higher performances compared to classical machine learning models. Feature importance analysis using extreme gradient boosting highlighted the role and importance of lipophilicity in predicting uptake and translocation of organic contaminants.
more »
« less
This content will become publicly available on December 1, 2025
A novel hybrid deep learning model for real-time monitoring of water pollution using sensor data
This study developed a hybrid model for predicting dissolved oxygen (DO) using real-time sensor data for thirteen parameters. This novel hybrid model integrated one-dimensional convolutional neural networks (CNN) and long short-term memory (LSTM) to improve the accuracy of prediction for DO in water. The hybrid CNNLSTM model predicted DO concentration in water using soft sensor data. The primary input parameters to the model were temperature, pH, specific conductivity, salinity, density, chlorophyll, and blue-green algae. The model used 38,681 water quality data for training and testing the hybrid deep learning network. The training procedure for the model was successful. The training and test losses were both nearly zero and within a similar range. With a coefficient of determination (R2) of 0.94 and a mean squared error (MSE) of 0.12, the hybrid model indicated higher performance compared to the classical models. The normal distribution of residual errors confirmed the reliability of the DO predictions by the hybrid CNN-LSTM model. Feature importance analysis indicated pH as the most significant predictor and temperature as the second important predictor. The feature importance scores based on extreme gradient boosting (XGBoost) for the pH and temperature were 0.76 and 0.12, respectively. This study indicated that the hybrid model can outperform the classical machine learning models in the real-time prediction of DO concentration.
more »
« less
- Award ID(s):
- 2348805
- PAR ID:
- 10575301
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Journal of Water Process Engineering
- Volume:
- 68
- Issue:
- C
- ISSN:
- 2214-7144
- Page Range / eLocation ID:
- 106595
- Subject(s) / Keyword(s):
- Hybrid model CNN-LSTM Dissolved oxygen XGBoost Significant predictors
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Accurate prediction of the uptake and translocation of emerging contaminants in plants has serious implications for assessing impacts on ecosystems and human health. However, traditional modeling approaches are not reliable in the prediction of transpiration stream concentration factor (TSCF) and root concentration factor (RCF). This study applied deep neural networks (DNN), recurrent neural networks (RNN), and long short-term memory (LSTM) to enhance the accuracy of predictive models for TSCF and RCF. The predictions and feature importance analysis were based on nine chemical properties and two plant root macromolecular compositions. The results indicated that deep learning models predict TSCF and RCF with improved accuracy compared to mechanistic models. The coefficient of determination (R^2) for the DNN, RNN, and LSTM models in predicting TSCF was 0.62, 0.67, and 0.56, respectively. The corresponding mean squared error (MSE) on the test set for the models was 0.055, 0.035, and 0.06, respectively. The R^2 for the DNN, RNN, and LSTM models in predicting RCF was 0.90, 0.91, and 0.84, respectively. The corresponding MSE for the models was 0.124, 0.071, and 0.126, respectively. The results of feature extraction using extreme gradient boosting underlined the importance of lipophilicity and root lipid fraction.more » « less
-
Advancements in robotics and AI have increased the demand for interactive robots in healthcare and assistive applications. However, ensuring safe and effective physical human-robot interactions (pHRIs) remains challenging due to the complexities of human motor communication and intent recognition. Traditional physics-based models struggle to capture the dynamic nature of human force interactions, limiting robotic adaptability. To address these limitations, neural networks (NNs) have been explored for force-movement intention prediction. While multi-layer perceptron (MLP) networks show potential, they struggle with temporal dependencies and generalization. Long Short-Term Memory (LSTM) networks effectively model sequential dependencies, while Convolutional Neural Networks (CNNs) enhance spatial feature extraction from human force data. Building on these strengths, this study introduces a hybrid LSTM-CNN framework to improve force-movement intention prediction, increasing accuracy from 69% to 86% through effective denoising and advanced architectures. The combined CNN-LSTM network proved particularly effective in handling individualized force-velocity relationships and presents a generalizable model paving the way for more adaptive strategies in robot guidance. These findings highlight the importance of integrating spatial and temporal modeling to enhance robot precision, responsiveness, and human-robot collaboration. Index Terms —- Physical Human-Robot Interaction, Intention Detection, Machine Learning, Long-Short Term Memory (LSTM)more » « less
-
Abstract This study introduces a non-invasive approach to monitor operation and productivity of a legacy pipe bending machine in real-time based on a lightweight convolutional neural network (CNN) model and internal sound as input data. Various sensors were deployed to determine the optimal sensor type and placement, and labels for training and testing the CNN model were generated through the meticulous collection of sound data in conjunction with webcam videos. The CNN model, which was optimized through hyperparameter tuning via grid search and utilized feature extraction using Log-Mel spectrogram, demonstrated notable prediction accuracies in the test. However, when applied in a real-world manufacturing scenario, the model encountered a significant number of errors in predicting productivity. To navigate through this challenge and enhance the predictive accuracy of the system, a buffer algorithm using the inferences of CNN models was proposed. This algorithm employs a queuing method for continuous sound monitoring securing robust predictions, refines the interpretation of the CNN model inferences, and enhances prediction outcomes in actual implementation where accuracy of monitoring productivity information is crucial. The proposed lightweight CNN model alongside the buffer algorithm was successfully deployed on an edge computer, enabling real-time remote monitoring.more » « less
-
Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose the Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) with similar feature extraction signatures. Our experiments indicate that FedMA not only outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, but also reduces the overall communication burden.more » « less
