FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework
Water quality prediction plays a crucial role in both enterprise management and government environmental management. However, due to the variety in water quality data, inconsistent frequency of data acquisition, inconsistency in data organization, and volatility and sparsity of data, predicting wate...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/8/1031 |
| _version_ | 1797538242032041984 |
|---|---|
| author | Jianlong Xu Kun Wang Che Lin Lianghong Xiao Xingshan Huang Yufeng Zhang |
| author_facet | Jianlong Xu Kun Wang Che Lin Lianghong Xiao Xingshan Huang Yufeng Zhang |
| author_sort | Jianlong Xu |
| collection | DOAJ |
| description | Water quality prediction plays a crucial role in both enterprise management and government environmental management. However, due to the variety in water quality data, inconsistent frequency of data acquisition, inconsistency in data organization, and volatility and sparsity of data, predicting water quality accurately and efficiently has become a key problem. This paper presents a recurrent neural network water quality prediction method based on a sequence-to-sequence (seq2seq) framework. The gate recurrent unit (GRU) model is used as an encoder and decoder, and a factorization machine (FM) is integrated into the model to solve the problem of high sparsity and high dimensional feature interaction in the data, which was not addressed by the water quality prediction models in prior research. Moreover, due to the long period and timespan of water quality data, we add a dual attention mechanism to the seq2seq framework to address memory failures in deep learning. We conducted a series of experiments, and the results show that our proposed method is more accurate than several typical water quality prediction methods. |
| first_indexed | 2024-03-10T12:27:44Z |
| format | Article |
| id | doaj.art-24717bba075d4e5baccfffa88785ab8e |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T12:27:44Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-24717bba075d4e5baccfffa88785ab8e2023-11-21T14:51:02ZengMDPI AGWater2073-44412021-04-01138103110.3390/w13081031FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq FrameworkJianlong Xu0Kun Wang1Che Lin2Lianghong Xiao3Xingshan Huang4Yufeng Zhang5College of Engineering, Shantou University, Shantou 515000, ChinaCollege of Engineering, Shantou University, Shantou 515000, ChinaCollege of Engineering, Shantou University, Shantou 515000, ChinaShantou Environmental Protection Monitoring Station, Shantou 515000, ChinaShantou Environmental Protection Monitoring Station, Shantou 515000, ChinaShantou Environmental Protection Monitoring Station, Shantou 515000, ChinaWater quality prediction plays a crucial role in both enterprise management and government environmental management. However, due to the variety in water quality data, inconsistent frequency of data acquisition, inconsistency in data organization, and volatility and sparsity of data, predicting water quality accurately and efficiently has become a key problem. This paper presents a recurrent neural network water quality prediction method based on a sequence-to-sequence (seq2seq) framework. The gate recurrent unit (GRU) model is used as an encoder and decoder, and a factorization machine (FM) is integrated into the model to solve the problem of high sparsity and high dimensional feature interaction in the data, which was not addressed by the water quality prediction models in prior research. Moreover, due to the long period and timespan of water quality data, we add a dual attention mechanism to the seq2seq framework to address memory failures in deep learning. We conducted a series of experiments, and the results show that our proposed method is more accurate than several typical water quality prediction methods.https://www.mdpi.com/2073-4441/13/8/1031water quality predictionseq2seqfactorization machineGRUattention mechanism |
| spellingShingle | Jianlong Xu Kun Wang Che Lin Lianghong Xiao Xingshan Huang Yufeng Zhang FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework Water water quality prediction seq2seq factorization machine GRU attention mechanism |
| title | FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework |
| title_full | FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework |
| title_fullStr | FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework |
| title_full_unstemmed | FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework |
| title_short | FM-GRU: A Time Series Prediction Method for Water Quality Based on seq2seq Framework |
| title_sort | fm gru a time series prediction method for water quality based on seq2seq framework |
| topic | water quality prediction seq2seq factorization machine GRU attention mechanism |
| url | https://www.mdpi.com/2073-4441/13/8/1031 |
| work_keys_str_mv | AT jianlongxu fmgruatimeseriespredictionmethodforwaterqualitybasedonseq2seqframework AT kunwang fmgruatimeseriespredictionmethodforwaterqualitybasedonseq2seqframework AT chelin fmgruatimeseriespredictionmethodforwaterqualitybasedonseq2seqframework AT lianghongxiao fmgruatimeseriespredictionmethodforwaterqualitybasedonseq2seqframework AT xingshanhuang fmgruatimeseriespredictionmethodforwaterqualitybasedonseq2seqframework AT yufengzhang fmgruatimeseriespredictionmethodforwaterqualitybasedonseq2seqframework |