Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks
Real-time monitoring of key water quality parameters is essential for the scientific management and effective maintenance of aquatic ecosystems. Water quality monitoring networks equipped with multiple low-cost electrochemical and optical sensors generate abundant spatiotemporal data for water autho...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2025.1587012/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849232987231617024 |
|---|---|
| author | Xuke Wu Xuke Wu Lan Wang Lan Wang Miao Ge Miao Ge Jing Jiang Jing Jiang Yu Cai Bing Yang Bing Yang |
| author_facet | Xuke Wu Xuke Wu Lan Wang Lan Wang Miao Ge Miao Ge Jing Jiang Jing Jiang Yu Cai Bing Yang Bing Yang |
| author_sort | Xuke Wu |
| collection | DOAJ |
| description | Real-time monitoring of key water quality parameters is essential for the scientific management and effective maintenance of aquatic ecosystems. Water quality monitoring networks equipped with multiple low-cost electrochemical and optical sensors generate abundant spatiotemporal data for water authorities. However, large-scale missing data in wireless sensor networks is inevitable due to various factors, which may introduce uncertainties in downstream mathematical modeling and statistical decisions, potentially leading to misjudgments in water quality risk assessment. A high-dimensional and incomplete (HDI) tensor can specifically quantify multi-sensor data, and latent factorization of tensors (LFT) models effectively extract multivariate dependencies and spatiotemporal correlations hidden in such a tensor to achieve high-accuracy missing data imputation. Nevertheless, LFT models fail to adequately account for the inherent fluctuations in water quality data, limiting their representation learning ability. Empirical evidence suggests that incorporating bias schemes into learning models can effectively mitigate underfitting. Building on this insight, this study proposes an adaptive biases-incorporated LFT (ABL) model with four-fold ideas: basic linear biases to describe constant fluctuations in water quality data; weighted pretraining biases to capture historical prior information of data fluctuations; time-aware biases to model long-term patterns of water quality fluctuations; and hyperparameter adaptation via particle swarm optimization (PSO) to enhance practicality. Empirical studies on large-scale real-world water quality datasets demonstrate that the proposed ABL model achieves significant improvements in both prediction accuracy and computational efficiency compared with state-of-the-art models. The findings highlight that integrating multiple bias schemes into tensor factorization models can effectively address the limitations of existing LFT models in capturing inherent data fluctuations, thereby enhancing the reliability of missing data imputation for water quality monitoring. This advancement contributes to more robust downstream applications in water quality management and risk assessment. |
| format | Article |
| id | doaj-art-998fc6591c6c4a7b8ab6050ef3bdfefa |
| institution | Kabale University |
| issn | 2296-424X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj-art-998fc6591c6c4a7b8ab6050ef3bdfefa2025-08-20T13:06:54ZengFrontiers Media S.A.Frontiers in Physics2296-424X2025-08-011310.3389/fphy.2025.15870121587012Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networksXuke Wu0Xuke Wu1Lan Wang2Lan Wang3Miao Ge4Miao Ge5Jing Jiang6Jing Jiang7Yu Cai8Bing Yang9Bing Yang10Water Division, Chongqing Eco-Environment Monitoring Center, Chongqing, ChinaSchool of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Artificial Intelligence, Chongqing University of Education, Chongqing, ChinaWater Division, Chongqing Eco-Environment Monitoring Center, Chongqing, ChinaSchool of Environment and Ecology, Chongqing University, Chongqing, ChinaWater Division, Chongqing Eco-Environment Monitoring Center, Chongqing, ChinaSchool of Environment and Ecology, Chongqing University, Chongqing, ChinaWater Division, Chongqing Eco-Environment Monitoring Center, Chongqing, ChinaWater Division, Chongqing Eco-Environment Monitoring Center, Chongqing, ChinaSchool of Environment and Ecology, Chongqing University, Chongqing, ChinaReal-time monitoring of key water quality parameters is essential for the scientific management and effective maintenance of aquatic ecosystems. Water quality monitoring networks equipped with multiple low-cost electrochemical and optical sensors generate abundant spatiotemporal data for water authorities. However, large-scale missing data in wireless sensor networks is inevitable due to various factors, which may introduce uncertainties in downstream mathematical modeling and statistical decisions, potentially leading to misjudgments in water quality risk assessment. A high-dimensional and incomplete (HDI) tensor can specifically quantify multi-sensor data, and latent factorization of tensors (LFT) models effectively extract multivariate dependencies and spatiotemporal correlations hidden in such a tensor to achieve high-accuracy missing data imputation. Nevertheless, LFT models fail to adequately account for the inherent fluctuations in water quality data, limiting their representation learning ability. Empirical evidence suggests that incorporating bias schemes into learning models can effectively mitigate underfitting. Building on this insight, this study proposes an adaptive biases-incorporated LFT (ABL) model with four-fold ideas: basic linear biases to describe constant fluctuations in water quality data; weighted pretraining biases to capture historical prior information of data fluctuations; time-aware biases to model long-term patterns of water quality fluctuations; and hyperparameter adaptation via particle swarm optimization (PSO) to enhance practicality. Empirical studies on large-scale real-world water quality datasets demonstrate that the proposed ABL model achieves significant improvements in both prediction accuracy and computational efficiency compared with state-of-the-art models. The findings highlight that integrating multiple bias schemes into tensor factorization models can effectively address the limitations of existing LFT models in capturing inherent data fluctuations, thereby enhancing the reliability of missing data imputation for water quality monitoring. This advancement contributes to more robust downstream applications in water quality management and risk assessment.https://www.frontiersin.org/articles/10.3389/fphy.2025.1587012/fullmulti-sensor data processingwater quality monitoringmachine learninghighdimensional and incomplete tensorlatent factorization of tensorsbias scheme |
| spellingShingle | Xuke Wu Xuke Wu Lan Wang Lan Wang Miao Ge Miao Ge Jing Jiang Jing Jiang Yu Cai Bing Yang Bing Yang Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks Frontiers in Physics multi-sensor data processing water quality monitoring machine learning highdimensional and incomplete tensor latent factorization of tensors bias scheme |
| title | Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks |
| title_full | Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks |
| title_fullStr | Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks |
| title_full_unstemmed | Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks |
| title_short | Adaptive biases-incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks |
| title_sort | adaptive biases incorporated latent factorization of tensors for predicting missing data in water quality monitoring networks |
| topic | multi-sensor data processing water quality monitoring machine learning highdimensional and incomplete tensor latent factorization of tensors bias scheme |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2025.1587012/full |
| work_keys_str_mv | AT xukewu adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT xukewu adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT lanwang adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT lanwang adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT miaoge adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT miaoge adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT jingjiang adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT jingjiang adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT yucai adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT bingyang adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks AT bingyang adaptivebiasesincorporatedlatentfactorizationoftensorsforpredictingmissingdatainwaterqualitymonitoringnetworks |