Summary of Time Distributed Deep Learning Models For Purely Exogenous Forecasting. Application to Water Table Depth Prediction Using Weather Image Time Series, by Matteo Salis et al.
Time Distributed Deep Learning models for Purely Exogenous Forecasting. Application to Water Table Depth Prediction using Weather Image Time Series
by Matteo Salis, Abdourrahmane M. Atto, Stefano Ferraris, Rosa Meo
First submitted to arxiv on: 20 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes two Deep Learning (DL) models to predict water table depth in a catchment area using weather image time series. The models are designed to address the lack of hydrological data and rely on available weather data, which significantly impacts water resources. The first model, TDC-LSTM, combines Time Distributed Convolutional Neural Network (TDC) with Long Short-Term Memory (LSTM) layers to learn temporal relations and output predictions. The second model, TDC-UnPWaveNet, uses a modified WaveNet architecture with a new Channel Distributed layer to capture sequence relationships. Both models are tested on the Grana-Maira catchment in Piemonte, Italy, and show remarkable results. While TDC-LSTM focuses on reducing bias, TDC-UnPWaveNet maximizes correlation and KGE. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses Deep Learning to predict water table depth using weather images. It proposes two models: one that combines convolutional neural networks with long short-term memory layers, and another that uses a modified WaveNet architecture. The models are tested in Italy and show good results. This is important because it can help us manage water resources better. |
Keywords
» Artificial intelligence » Deep learning » Lstm » Neural network » Time series
