Time Distributed Deep Learning models for Purely Exogenous Forecasting. Application to Water Table Depth Prediction using Weather Image Time Series

• URL: http://arxiv.org/abs/2409.13284v1
• Date: Fri, 20 Sep 2024 07:25:54 GMT
• Title: Time Distributed Deep Learning models for Purely Exogenous Forecasting. Application to Water Table Depth Prediction using Weather Image Time Series
• Authors: Matteo Salis, Abdourrahmane M. Atto, Stefano Ferraris, Rosa Meo,
• Abstract summary: We propose two different Deep Learning models to predict the water table depth in the Grana-Maira (Piemonte, IT) To deal with the image time series, both models are made of a first Time Distributed Convolutional Neural Network (TDC) which encodes the image available at each time step into a vectorial representation. The two models have focused on different learnable information: TDC-LSTM has focused more on lowering the bias, while the TDC-UnPWaveNet has focused more on the temporal dynamics maximising correlation and KGE.
• Score: 1.4436965372953483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Groundwater resources are one of the most relevant elements in the water cycle, therefore developing models to accurately predict them is a pivotal task in the sustainable resources management framework. Deep Learning (DL) models have been revealed very effective in hydrology, especially by feeding spatially distributed data (e.g. raster data). In many regions, hydrological measurements are difficult to obtain regularly or periodically in time, and in some cases, last available data are not up to date. Reversely, weather data, which significantly impacts water resources, are usually more available and with higher quality. More specifically, we have proposed two different DL models to predict the water table depth in the Grana-Maira catchment (Piemonte, IT) using only exogenous weather image time series. To deal with the image time series, both models are made of a first Time Distributed Convolutional Neural Network (TDC) which encodes the image available at each time step into a vectorial representation. The first model, TDC-LSTM uses then a Sequential Module based on an LSTM layer to learn temporal relations and output the predictions. The second model, TDC-UnPWaveNet uses instead a new version of the WaveNet architecture, adapted here to output a sequence shorter and completely shifted in the future with respect to the input one. To this aim, and to deal with the different sequence lengths in the UnPWaveNet, we have designed a new Channel Distributed layer, that acts like a Time Distributed one but on the channel dimension, i.e. applying the same set of operations to each channel of the input. TDC-LSTM and TDC-UnPWaveNet have shown both remarkable results. However, the two models have focused on different learnable information: TDC-LSTM has focused more on lowering the bias, while the TDC-UnPWaveNet has focused more on the temporal dynamics maximising correlation and KGE.

Related papers

• Timer: Generative Pre-trained Transformers Are Large Time Series Models [83.03091523806668]
  This paper aims at the early development of large time series models (LTSM) During pre-training, we curate large-scale datasets with up to 1 billion time points. To meet diverse application needs, we convert forecasting, imputation, and anomaly detection of time series into a unified generative task.
  arXiv  Detail & Related papers  (2024-02-04T06:55:55Z)
• Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting [10.892801642895904]
  We propose Distance-weighted Auto-regularized Neural network (DAN), a novel extreme-adaptive model for long-range forecasting of stremflow enhanced by polar representation learning. On four real-life hydrologic streamflow datasets, we demonstrate that DAN significantly outperforms both state-of-the-art hydrologic time series prediction methods and general methods designed for long-term time series prediction.
  arXiv  Detail & Related papers  (2023-12-14T09:16:01Z)
• CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting [50.23240107430597]
  We design a special Transformer, i.e., Channel Aligned Robust Blend Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting. First, CARD introduces a channel-aligned attention structure that allows it to capture both temporal correlations among signals. Second, in order to efficiently utilize the multi-scale knowledge, we design a token blend module to generate tokens with different resolutions. Third, we introduce a robust loss function for time series forecasting to alleviate the potential overfitting issue.
  arXiv  Detail & Related papers  (2023-05-20T05:16:31Z)
• Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecasting [72.89994745876086]
  This work presents the Online Neuro-Evolution-based Neural Architecture Search (ONE-NAS) algorithm. ONE-NAS is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods.
  arXiv  Detail & Related papers  (2023-02-20T22:25:47Z)
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis [80.56913334060404]
  Time series analysis is of immense importance in applications, such as weather forecasting, anomaly detection, and action recognition. Previous methods attempt to accomplish this directly from the 1D time series. We ravel out the complex temporal variations into the multiple intraperiod- and interperiod-variations.
  arXiv  Detail & Related papers  (2022-10-05T12:19:51Z)
• A data filling methodology for time series based on CNN and (Bi)LSTM neural networks [0.0]
  We develop two Deep Learning models aimed at filling data gaps in time series obtained from monitored apartments in Bolzano, Italy. Our approach manages to capture the fluctuating nature of the data and shows good accuracy in reconstructing the target time series.
  arXiv  Detail & Related papers  (2022-04-21T09:40:30Z)
• TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data [6.221375620565451]
  Prediction based on Irregularly Sampled Time Series (ISTS) is of wide concern in the real-world applications. We create a new model structure named Time Echo State Network (TE-ESN) It is the first ESNs-based model that can process ISTS data. Experiments on one chaos system and three real-world datasets show that TE-ESN performs better than all baselines.
  arXiv  Detail & Related papers  (2021-05-02T08:00:46Z)
• Semi-Supervised Video Deraining with Dynamic Rain Generator [59.71640025072209]
  This paper proposes a new semi-supervised video deraining method, in which a dynamic rain generator is employed to fit the rain layer. Specifically, such dynamic generator consists of one emission model and one transition model to simultaneously encode the spatially physical structure and temporally continuous changes of rain streaks. Various prior formats are designed for the labeled synthetic and unlabeled real data, so as to fully exploit the common knowledge underlying them.
  arXiv  Detail & Related papers  (2021-03-14T14:28:57Z)
• Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series [77.47313102926017]
  Radflow is a novel model for networks of time series that influence each other. It embodies three key ideas: a recurrent neural network to obtain node embeddings that depend on time, the aggregation of the flow of influence from neighboring nodes with multi-head attention, and the multi-layer decomposition of time series. We show that Radflow can learn different trends and seasonal patterns, that it is robust to missing nodes and edges, and that correlated temporal patterns among network neighbors reflect influence strength.
  arXiv  Detail & Related papers  (2021-02-15T00:57:28Z)
• Echo State Network for two-dimensional turbulent moist Rayleigh-B\'enard convection [0.0]
  We apply an echo state network to approximate the evolution of moist Rayleigh-B'enard convection. We conclude that our model is capable of learning complex dynamics.
  arXiv  Detail & Related papers  (2021-01-27T11:27:16Z)
• Rainfall-Runoff Prediction at Multiple Timescales with a Single Long Short-Term Memory Network [41.33870234564485]
  Long Short-Term Memory Networks (LSTMs) have been applied to daily discharge prediction with remarkable success. Many practical scenarios, however, require predictions at more granular timescales. In this study, we propose two Multi-Timescale LSTM (MTS-LSTM) architectures that jointly predict multiple timescales within one model. We test these models on 516 basins across the continental United States and benchmark against the US National Water Model.
  arXiv  Detail & Related papers  (2020-10-15T17:52:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.