A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Mining Spatiotemporal Information for Harmful Algal Bloom Forecasting and Mechanism Interpreting
https://orcid.org/0000-0002-3005-9316
A multistep spatiotemporal forecasting (MSTF) network is developed through incorporating the graph convolutional network (GCN) and the long short-term memory (LSTM) network within a sequence-to-sequence (seq2seq) framework. The MSTF method can not only extract spatial and temporal information from the input data but also make multistep-ahead and continuous predictions. An MSTF-based harmful algal bloom (HAB) forecasting model is then formulated to predict the chlorophyll-a (Chl-a) concentration of the Dianchi Lake (China). The integrated gradients (IG) method is employed to interpret the trained MSTF model and quantify the attribution of each input dimension to the Chl-a prediction. Results indicate that (i) the coefficient of determination (R 2) of the MSTF model in 24-h-ahead Chl-a prediction reaches 0.926, 28.4% higher than that of the traditional LSTM model; (ii) the ammonia nitrogen (12.3%), the total phosphorus (10.2%), the total nitrogen (9.9%), and the temperature (8.6%) are significant variables for Chl-a prediction; (iii) the spatial information from neighbor lake and river stations plays an important role in the HAB forecasting, with an average contribution of 35.0%; (iv) the proposed MSTF model is also skillful in the 72-h-ahead Chl-a prediction. Results presented highlight the importance of considering both spatial and temporal dependency of monitoring data in HAB forecasting and mechanism interpreting.
This study employs deep learning methods to harmful algal bloom forecasting and provides novel insights into the spatiotemporal mechanism of the bloom.
Mining Spatiotemporal Information for Harmful Algal Bloom Forecasting and Mechanism Interpreting
https://orcid.org/0000-0002-3005-9316
A multistep spatiotemporal forecasting (MSTF) network is developed through incorporating the graph convolutional network (GCN) and the long short-term memory (LSTM) network within a sequence-to-sequence (seq2seq) framework. The MSTF method can not only extract spatial and temporal information from the input data but also make multistep-ahead and continuous predictions. An MSTF-based harmful algal bloom (HAB) forecasting model is then formulated to predict the chlorophyll-a (Chl-a) concentration of the Dianchi Lake (China). The integrated gradients (IG) method is employed to interpret the trained MSTF model and quantify the attribution of each input dimension to the Chl-a prediction. Results indicate that (i) the coefficient of determination (R 2) of the MSTF model in 24-h-ahead Chl-a prediction reaches 0.926, 28.4% higher than that of the traditional LSTM model; (ii) the ammonia nitrogen (12.3%), the total phosphorus (10.2%), the total nitrogen (9.9%), and the temperature (8.6%) are significant variables for Chl-a prediction; (iii) the spatial information from neighbor lake and river stations plays an important role in the HAB forecasting, with an average contribution of 35.0%; (iv) the proposed MSTF model is also skillful in the 72-h-ahead Chl-a prediction. Results presented highlight the importance of considering both spatial and temporal dependency of monitoring data in HAB forecasting and mechanism interpreting.
This study employs deep learning methods to harmful algal bloom forecasting and provides novel insights into the spatiotemporal mechanism of the bloom.
Mining Spatiotemporal Information for Harmful Algal Bloom Forecasting and Mechanism Interpreting
https://orcid.org/0000-0002-3005-9316
A multistep spatiotemporal forecasting (MSTF) network is developed through incorporating the graph convolutional network (GCN) and the long short-term memory (LSTM) network within a sequence-to-sequence (seq2seq) framework. The MSTF method can not only extract spatial and temporal information from the input data but also make multistep-ahead and continuous predictions. An MSTF-based harmful algal bloom (HAB) forecasting model is then formulated to predict the chlorophyll-a (Chl-a) concentration of the Dianchi Lake (China). The integrated gradients (IG) method is employed to interpret the trained MSTF model and quantify the attribution of each input dimension to the Chl-a prediction. Results indicate that (i) the coefficient of determination (R 2) of the MSTF model in 24-h-ahead Chl-a prediction reaches 0.926, 28.4% higher than that of the traditional LSTM model; (ii) the ammonia nitrogen (12.3%), the total phosphorus (10.2%), the total nitrogen (9.9%), and the temperature (8.6%) are significant variables for Chl-a prediction; (iii) the spatial information from neighbor lake and river stations plays an important role in the HAB forecasting, with an average contribution of 35.0%; (iv) the proposed MSTF model is also skillful in the 72-h-ahead Chl-a prediction. Results presented highlight the importance of considering both spatial and temporal dependency of monitoring data in HAB forecasting and mechanism interpreting.
This study employs deep learning methods to harmful algal bloom forecasting and provides novel insights into the spatiotemporal mechanism of the bloom.
Mining Spatiotemporal Information for Harmful Algal Bloom Forecasting and Mechanism Interpreting
Jia, Qimeng (author) / Xu, Changqing (author) / Jia, Haifeng (author) / Velazquez, Carlos (author) / Leng, Linyuan (author) / Yin, Dingkun (author)
ACS ES&T Water ; 4 ; 2608-2618
2024-06-14
Article (Journal)
Electronic Resource
English
Flow Imaging Microscopy for Harmful Algal Bloom Monitoring
| Wiley | 2024
Flow Imaging Microscopy for Harmful Algal Bloom Monitoring
| Wiley | 2024
Factors affecting harmful algal bloom occurrence in a river with regulated hydrology
| Elsevier | 2021
Factors affecting harmful algal bloom occurrence in a river with regulated hydrology
| DOAJ | 2021