What does this research mean for the field?

The Temporal Fusion Transformer (TFT) model outperforms other deep learning models in forecasting dissolved oxygen concentrations in river systems, particularly over 30-day periods. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to evaluate the effectiveness of various deep learning models in forecasting dissolved oxygen concentrations in river systems.

February 19, 2026Open Access

Advancing river water quality prediction: a comparative assessment of deep learning models for dissolved oxygen forecasting

Key Points

The study aims to evaluate the effectiveness of various deep learning models in forecasting dissolved oxygen concentrations in river systems.
Compared four deep learning models: Temporal Fusion Transformer, Informer, LSTM, and GRU.
Used a multivariate time-series dataset for predictions including temperature, turbidity, pH, conductivity, chlorophyll, and river flow.
Evaluated model performance using metrics: RMSE, MAE, R2, and SMAPE.
TFT achieved the lowest RMSE (0.06) and SMAPE (8.86%) over a 7-day period.
LSTM showed the highest R2 value (0.77) for the same duration.
At the 30-day horizon, TFT had an R2 of 0.79 and SMAPE of 8.23%, outperforming other models despite some accuracy losses.

Abstract

Accurate forecasting of dissolved oxygen (DO) is crucial for monitoring river water quality and protecting aquatic ecosystems. This study compares the performance of four deep learning models – Temporal Fusion Transformer (TFT), Informer, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) – for forecasting DO concentrations in the River Lee (London, UK) across 7- and 30-day time frames. A multivariate time-series dataset was employed, with temperature, turbidity, pH, conductivity, chlorophyll, and river flow as predictors. Model skills were evaluated using RMSE, MAE, R2, and SMAPE. Over the 7-day period, TFT had the lowest RMSE (0.06) and SMAPE (8.86%), while LSTM had the greatest R2 (0.77). TFT outperformed Informer, LSTM, and GRU at the 30-day horizon, with R2 = 0.79 and SMAPE of 8.23%, despite significant accuracy losses. According to the variable contribution study, temperature and river flow were the most significant factors, particularly for short-term projections. Overall, the results show that transformer-based structures, particularly TFT, can successfully represent nonlinear temporal dependencies and multivariate interactions, making them ideal for multi-horizon DO forecasting in river systems. These models have the ability to supplement normal monitoring by offering short-term predictions about probable oxygen conditions.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper