| Link | https://www.climatechange.ai/papers/neurips2021/44 |
|---|
| Author | Search for: Hussain, Md Monwer; Search for: Durand, Guillaume1; Search for: Coffin, Michael; Search for: Valdés, Julio J1; Search for: Poirier, Luke |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | Workshop Tackling Climate Change with Machine Learning, at NeurIPS 2021 Conference on Neural Information Processing Systems, December 6-14, 2021 |
|---|
| Abstract | This paper presents a data driven study of dissolved oxygen times series collected in Atlantic Canada. The main motivation of presented work was to evaluate if machine learning techniques could help to understand and anticipate hypoxic episodes in nutrient-impacted estuaries, a phenomenon that is exacerbated by increasing temperature expected to arise due to changes in climate. A major constraint of the analysis was limiting ourselves to a single variable, the dissolved oxygen time series. Our preliminary findings show that recurring neural networks, and in particular LSTM, may be capable of predicting short horizon levels while traditional analyses are adequate for longer range hypoxia prevention. |
|---|
| Publication date | 2021-12-14 |
|---|
| Publisher | NeurIPS |
|---|
| In | |
|---|
| Language | English |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 0251a8fe-28d4-44df-95da-b03edacb5737 |
|---|
| Record created | 2022-05-10 |
|---|
| Record modified | 2022-05-10 |
|---|
