4.7 Article

Predicting ammonia nitrogen in surface water by a new attention-based deep learning hybrid model

Related references

Note: Only part of the references are listed.
Article Geosciences, Multidisciplinary

Advanced prediction of tunnel boring machine performance based on big data

Jinhui Li et al.

Summary: A machine learning model was developed to predict the TBM performance in real-time using big data obtained from a tunnel project in China, showing superior performance compared to classical theoretical models. Filtering unnecessary parameters was proposed to enhance accuracy and computational efficiency. The study also discussed the impact of data deficiency on model accuracy and suggested supplementing highly correlated parameters to improve prediction.

GEOSCIENCE FRONTIERS (2021)

Article Construction & Building Technology

CNN-LSTM architecture for predictive indoor temperature modeling

Furkan Elmaz et al.

Summary: The study introduces a model combining Convolutional Neural Networks with Long Short Term Memory for indoor temperature modeling, showing excellent performance in long-term predictions and better robustness against errors. Experimental results demonstrate the model's ability to accurately predict room temperature within a 120-minute prediction horizon.

BUILDING AND ENVIRONMENT (2021)

Article Engineering, Civil

A novel hybrid model for water quality prediction based on synchrosqueezed wavelet transform technique and improved long short-term memory

Chenguang Song et al.

Summary: This study proposed an improved LSTM model and a hybrid model using SWT for denoising, which showed the best performance in water quality prediction by combining noise resistance and nonlinear mapping. The hybrid model performed well at two gauging stations, providing decision-making support for water quality management and pollutant control.

JOURNAL OF HYDROLOGY (2021)

Article Environmental Sciences

Predicting polycyclic aromatic hydrocarbons in surface water by a multiscale feature extraction-based deep learning approach

Liang Dong et al.

Summary: A novel hybrid surface water PAH prediction model combining two-stage decomposition and deep learning algorithm was proposed for accurate and effective prediction of PAHs in surface water. Empirical results from eight major rivers in Saxony, Germany showed that the model outperformed other benchmark data-driven methods, with good prediction performance.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Hospitality, Leisure, Sport & Tourism

Using SARIMA-CNN-LSTM approach to forecast daily tourism demand

Kaijian He et al.

Summary: This article introduces a SARIMA-CNN-LSTM model for forecasting daily tourist demand data, which combines the ability to capture both linear and nonlinear data features. The results show that this model has higher forecast accuracy than individual models and can better utilize rich information in high-frequency data.

JOURNAL OF HOSPITALITY AND TOURISM MANAGEMENT (2021)

Article Computer Science, Artificial Intelligence

A VMD-EWT-LSTM-based multi-step prediction approach for shield tunneling machine cutterhead torque

Gang Shi et al.

Summary: This study proposes a novel hybrid multi-step prediction model based on VMD-EWT-LSTM, which accurately predicts the cutterhead torque of shield tunneling machine in multiple time steps and demonstrates higher accuracy compared to other methods.

KNOWLEDGE-BASED SYSTEMS (2021)

Article Environmental Sciences

A graph-based LSTM model for PM2.5 forecasting

Xi Gao et al.

Summary: The GLSTM model combines parameterized adjacency matrix and LSTM to introduce spatiotemporal information for PM2.5 prediction. The advantage of GLSTM is synchronous operation of all stations and enhanced interpretability.

ATMOSPHERIC POLLUTION RESEARCH (2021)

Article Business

LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning

Mainak Sarkar et al.

Summary: Traditional customer response models heavily rely on feature engineering and analyst expertise, but as data complexity increases, they become exponentially complicated. This paper demonstrates that LSTM neural networks, which use raw data as input, can accurately predict customer behaviors and outperform traditional models in many cases.

JOURNAL OF INTERACTIVE MARKETING (2021)

Review Automation & Control Systems

Artificial intelligence-based single and hybrid models for prediction of water quality in rivers: A review

Taher Rajaee et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2020)

Article Engineering, Environmental

LSTM based encoder-decoder for short-term predictions of gas concentration using multi-sensor fusion

Pingyang Lyu et al.

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION (2020)

Review Chemistry, Analytical

Review of separation methods for the determination of ammonium/ammonia in natural water

Min Zhang et al.

TRENDS IN ENVIRONMENTAL ANALYTICAL CHEMISTRY (2020)

Review Environmental Sciences

Modelling eutrophication in lake ecosystems: A review

Brigitte Vincon-Leite et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2019)

Article Multidisciplinary Sciences

Deep learning and process understanding for data-driven Earth system science

Markus Reichstein et al.

NATURE (2019)

Article Environmental Sciences

An analysis of satellite-derived chlorophyll and algal bloom indices on Lake Winnipeg

C. E. Binding et al.

JOURNAL OF GREAT LAKES RESEARCH (2018)

Article Computer Science, Artificial Intelligence

Multimodal architecture for video captioning with memory networks and an attention mechanism

Wei Li et al.

PATTERN RECOGNITION LETTERS (2018)

Proceedings Paper Automation & Control Systems

Water Quality Prediction Model Combining Sparse Auto-encoder and LSTM Network

Zhenbo Li et al.

IFAC PAPERSONLINE (2018)

Article Computer Science, Hardware & Architecture

Multi-scale prediction of water temperature using empirical mode decomposition with back-propagation neural networks

Shuangyin Liu et al.

COMPUTERS & ELECTRICAL ENGINEERING (2016)

Article Computer Science, Interdisciplinary Applications

Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform

Aman Mohammad Kalteh

COMPUTERS & GEOSCIENCES (2013)

Article Computer Science, Interdisciplinary Applications

A hybrid approach of support vector regression with genetic algorithm optimization for aquaculture water quality prediction

Shuangyin Liu et al.

MATHEMATICAL AND COMPUTER MODELLING (2013)

Article Ecology

Random forests for classification in ecology

D. Richard Cutler et al.

ECOLOGY (2007)

Article Water Resources

Using support vector machines for long-term discharge prediction

Jian-Yi Lin et al.

HYDROLOGICAL SCIENCES JOURNAL (2006)

Article Computer Science, Interdisciplinary Applications

Forecasting stock market movement direction with support vector machine

W Huang et al.

COMPUTERS & OPERATIONS RESEARCH (2005)