Analyzing Spatio-Temporal Dynamics of Dissolved Oxygen for the River Thames using Superstatistical Methods and Machine Learning
arXiv:2501.07599 · doi:10.1038/s41598-024-72084-w
Abstract
By employing superstatistical methods and machine learning, we analyze time series data of water quality indicators for the River Thames, with a specific focus on the dynamics of dissolved oxygen. After detrending, the probability density functions of dissolved oxygen fluctuations exhibit heavy tails that are effectively modeled using -Gaussian distributions. Our findings indicate that the multiplicative Empirical Mode Decomposition method stands out as the most effective detrending technique, yielding the highest log-likelihood in nearly all fittings. We also observe that the optimally fitted width parameter of the -Gaussian shows a negative correlation with the distance to the sea, highlighting the influence of geographical factors on water quality dynamics. In the context of same-time prediction of dissolved oxygen, regression analysis incorporating various water quality indicators and temporal features identify the Light Gradient Boosting Machine as the best model. SHapley Additive exPlanations reveal that temperature, pH, and time of year play crucial roles in the predictions. Furthermore, we use the Transformer to forecast dissolved oxygen concentrations. For long-term forecasting, the Informer model consistently delivers superior performance, achieving the lowest MAE and SMAPE with the 192 historical time steps that we used. This performance is attributed to the Informer's ProbSparse self-attention mechanism, which allows it to capture long-range dependencies in time-series data more effectively than other machine learning models. It effectively recognizes the half-life cycle of dissolved oxygen, with particular attention to key intervals. Our findings provide valuable insights for policymakers involved in ecological health assessments, aiding in accurate predictions of river water quality and the maintenance of healthy aquatic ecosystems.
References in corpus (21)
- Superstatistics
- Dynamical foundations of nonextensive statistical mechanics
- Brownian yet non-Gaussian diffusion: from superstatistics to subordination of diffusing diffusivities
- Topological Data Analysis of Financial Time Series: Landscapes of Crashes
- Non-Gaussian power grid frequency fluctuations characterized by Lévy-stable laws and superstatistics
- From time series to superstatistics
- Estimation of high frequency nutrient concentrations from water quality surrogates using machine learning methods
- NGBoost: Natural Gradient Boosting for Probabilistic Prediction
- Statistics of 3-dimensional Lagrangian turbulence
- Modelling train delays with q-exponential functions
- Superstatistics in hydrodynamic turbulence
- Superstatistics in high energy physics: Application to cosmic ray energy spectra and e+e- annihilation
- Stationary superstatistics distributions of trapped run-and-tumble particles
- Superstatistical energy distributions of an ion in an ultracold buffer gas
- Superstatistical approach to air pollution statistics
- Single-particle velocity distributions of collisionless, steady-state plasmas must follow Superstatistics
- Superstatistical modelling of protein diffusion dynamics in bacteria
- Two temperature Ising Model
- Fluctuating temperature and baryon chemical potential in heavy-ion collisions and the position of the critical end point in the effective QCD phase diagram
- Universal properties of primary and secondary cosmic ray energy spectra
- Superstatistics with cut-off tails for financial time series