Predicting Water Availability in Water Bodies under the Influence of Precipitation and Water Management Actions Using VAR/VECM/LSTM

Abstract

Recently, awareness about the significance of water management has risen as population growth and global warming increase, and economic activities and land use continue to stress our water resources. In addition, global water sustenance efforts are crippled by capital-intensive water treatments and water reclamation projects. In this paper, a study of water bodies to predict the amount of water in each water body using identifiable unique features and to assess the behavior of these features on others in the event of shock was undertaken. A comparative study, using a parametric model, was conducted among Vector Autoregression (VAR), the Vector Error Correction Model (VECM), and the Long Short-Term Memory (LSTM) model for determining the change in water level and water flow of water bodies. Besides, orthogonalized impulse responses (OIR) and forecast error variance decompositions (FEVD) explaining the evolution of water levels and flow rates, the study shows the significance of VAR/VECM models over LSTM. It was found that on some water bodies, the VAR model gave reliable results. In contrast, water bodies such as water springs gave mixed results of VAR/VECM.

Temporal Variations in Chemical Proprieties of Waterbodies within Coastal Polders: Forecast Modeling for Optimizing Water Management Decisions

“…VAR, on the other hand, is a multivariate model that considers multiple time series at the same time. VAR models the relationships between multiple variables, making it more suitable for modeling non-stationary time-series data and data sets with multiple variables; in research by Kaur et al [46], a VAR model was compared to a Vector Error Correction Model (VECM) and a more complex machine-learning Long Short-Term Memory (LSTM) model for determining the changes in water levels and the water flow of different water bodies across Italy. The results showed the significance of time-series models (VAR and VECM) over LSTM, where the VAR model gave reliable results for water bodies, such as aquifers, rivers, and lakes, while the best results for springs were obtained by the VECM model.…”

Prediction of Vegetation Change by Discrete Wavelet Decomposition Based on Remote Sensing Time Series Images

“…At present, the model has active performance in the prediction research of social and economic fields such as stock price index [19], exchange rate [20], transportation [21], energy consumption [22], and agricultural product price [23]. In the field of natural sciences, LSTM is used in the prediction research of water resources [24,25], lightning [26], and air pollution [27], which has achieved excellent results. Some scholars have introduced LSTM into the research of vegetation change prediction [28,29].…”

Microwave expanded graphite felt coated with sulfonated polystyrene as light absorber and self‐floating in photothermal water desalination

“…The UN has predicted a water crisis by 2050 which will affect more than 4 billion people due to global population increase and climate change. [1][2][3] On this sense, different countries around the world have considered seawater as an important source of fresh water after its desalination, being a strategic important industry, promoting the research and the development of materials used for this technology, 4 including thermal desalination, which use heat to obtain distillate water from saline water, for example, through multi-stage flash or multiple effect distillation; and membrane technology (reverse osmosis, electrodialysis, forward osmosis and membrane distillation 5 ). Conventional desalination technologies require energy whether renewable (photovoltaic, wind, geothermal or biomass) or from fossil origin; however, the ideal process would be one that directly use the renewable energy for water desalination, which is the direct solar energy.…”

“…If the population of a country increases, water demand will also increase due to food demand which requires more water for crop irrigation. The UN has predicted a water crisis by 2050 which will affect more than 4 billion people due to global population increase and climate change 1‐3 . On this sense, different countries around the world have considered seawater as an important source of fresh water after its desalination, being a strategic important industry, promoting the research and the development of materials used for this technology, 4 including thermal desalination, which use heat to obtain distillate water from saline water, for example, through multi‐stage flash or multiple effect distillation; and membrane technology (reverse osmosis, electrodialysis, forward osmosis and membrane distillation 5 ).…”