Combining autoregressive integrated moving average with Long Short-Term Memory neural network and optimisation algorithms for predicting ground water level

Khozani, Zohreh Sheikh; Banadkooki, Fatemeh Barzegari; Ehteram, Mohammad; Ahmed, Ali Najah; El‐Shafie, Ahmed

doi:10.1016/j.jclepro.2022.131224

Cited by 47 publications

(13 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Exploring the future spatiotemporal patterns of ESVs is crucial for the harmonious development of the economy, society, and nature. In this study, we introduced the autoregressive integrated moving average (ARIMA) model [63] provided of SPSS Statistics version 25.0 software to predict the future standard unit equivalent factor value. Li et al's studies [64] have found that changes in LC can affect the soil conservation function.…”

Section: Future Simulations Of Esvs Based On Lcmentioning

confidence: 99%

A Multi-Scenario Simulation and Dynamic Assessment of the Ecosystem Service Values in Key Ecological Functional Areas: A Case Study of the Sichuan Province, China

Li,

Chen,

Zheng

et al. 2024

Land

View full text Add to dashboard Cite

The ecosystem service value (ESV) is an important basis for measuring an ecological environment’s quality and the efficient management of ecosystems. It is particularly necessary to explore a proven methodology for assessing and predicting ESV dynamics coupled with policy-oriented scenarios that can provide a theoretical groundwork for macro decision, particularly in the context of implementing ecological protection and restoration projects. This study selected the land cover (LC) of Sichuan Province at five periods and the spatiotemporal dynamic equivalent factor method to assess the ESVs from 2000 to 2020. Additionally, the study coupled the Markov chain and GeoSOS-FLUS model, and predicted the future pattern of ESVs under four future development scenarios. The results show that (a) the areas of forests, shrubs, waters, wastelands, wetlands, and impervious areas showed a continuous increase from 2000 to 2020, with the most frequent interchanges occurring among croplands, forests, and grasslands. (b) The implementation of ecological protection and restoration projects led to a 13,083.32 × 108 yuan increase in ESV, and barycenter of the ESVs is located in the northeastern part of Ya’an and exhibits a tendency to move towards the northeast. (c) The ESV aggregation pattern of each city has remained unchanged, with Ganzi being the only city with a high aggregation. Overall, there are more conflict cities than coordination cities between economic development and the ecological environment. (d) The total ESV in 2025 will continue to increase under all development scenarios, reaching a maximum of 50,903.37 × 108 yuan under the EP scenario. This study can provide insights for ecological planning decisions and sustainable regional socio-economic development.

show abstract

Section: Future Simulations Of Esvs Based On Lcmentioning

confidence: 99%

A Multi-Scenario Simulation and Dynamic Assessment of the Ecosystem Service Values in Key Ecological Functional Areas: A Case Study of the Sichuan Province, China

Li,

Chen,

Zheng

et al. 2024

Land

View full text Add to dashboard Cite

show abstract

“…The main advantage of LSTM is that it can ensure long-term memory so that the problems of gradient disappearance and explosion in classical RNN can be solved. The RNN network structure is presented in Figure 1 [24]. In Figure 1, u represents the connection weight from the input layer to the hidden layer, v represents the connection weight from the hidden layer to the output layer, and w represents the connection weight from the state of the hidden layer at the current moment to the state of the hidden layer at the next moment.…”

Section: Lstm and Dbn Network 21 Lstm Networkmentioning

confidence: 99%

An efficent water quality prediction and evaluation method based on the DBN-LSTM model

Fan

Zhao

2023

Preprint

View full text Add to dashboard Cite

Currently, water environmental issues have been severe. Water quality not only affects the ecological balance of nature but is also closely related to human lives. Therefore, an accurate water quality prediction and assessment can prevent water eutrophication, thus protecting the environment and improving people's quality of life. Previous studies have shown that the Long Short-Term Memory (LSTM) neural network has a good performance in time series prediction. In view of that, this paper proposes a neural network model that integrates the Deep Belief Network (DBN) and LSTM network for water quality prediction. The real data are used to predict water quality, and the DBN network is used to extract data features, which are then fed to the LSTM network. The proposed combined model is verified by experiments, and experimental results show that the proposed DBN-LSTM model can significantly improve prediction accuracy compared to the LSTM. The results indicate that the addition of the DBN network can improve the feature extraction and denoising performances on various datasets. The proposed water quality prediction model is compared with both single- and multiple-factor evaluation methods. The comparison results show that the DBN-LSTM model outperforms the LSTM model in terms of prediction accuracy, where it can be used in water quality monitoring management and risk assessment.

show abstract

“…Due to the inherent non-linear and non-stationary nature of groundwater level time series, intelligent data-driven methodologies have showcased promising results. Across the literature, various popular forecasting approaches have been tested on specific applications of groundwater level forecasting, including Auto-Regressive Integrated Moving Average (ARIMA), Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM) as well as hybrid approaches such as ARIMA-LSTM [38][39][40][41]. Comparative studies have consistently shown that machine learning-based methods outperform traditional numerical approaches [42] with superior prediction performance and capturing complex and non-linear relationships between input and output variables [43].…”

Section: Introductionmentioning

confidence: 99%

Towards Groundwater-Level Prediction Using Prophet Forecasting Method by Exploiting a High-Resolution Hydrogeological Monitoring System

Fronzi,

Narang,

Galdelli

et al. 2023

Water

View full text Add to dashboard Cite

Forecasting of water availability has become of increasing interest in recent decades, especially due to growing human pressure and climate change, affecting groundwater resources towards a perceivable depletion. Numerous research papers developed at various spatial scales successfully investigated daily or seasonal groundwater level prediction starting from measured meteorological data (i.e., precipitation and temperature) and observed groundwater levels, by exploiting data-driven approaches. Barely a few research combine the meteorological variables and groundwater level data with unsaturated zone monitored variables (i.e., soil water content, soil temperature, and bulk electric conductivity), and—in most of these—the vadose zone is monitored only at a single depth. Our approach exploits a high spatial-temporal resolution hydrogeological monitoring system developed in the Conero Mt. Regional Park (central Italy) to predict groundwater level trends of a shallow aquifer exploited for drinking purposes. The field equipment consists of a thermo-pluviometric station, three volumetric water content, electric conductivity, and soil temperature probes in the vadose zone at 0.6 m, 0.9 m, and 1.7 m, respectively, and a piezometer instrumented with a permanent water-level probe. The monitored period started in January 2022, and the variables were recorded every fifteen minutes for more than one hydrologic year, except the groundwater level which was recorded on a daily scale. The developed model consists of three “virtual boxes” (i.e., atmosphere, unsaturated zone, and saturated zone) for which the hydrological variables characterizing each box were integrated into a time series forecasting model based on Prophet developed in the Python environment. Each measured parameter was tested for its influence on groundwater level prediction. The model was fine-tuned to an acceptable prediction (roughly 20% ahead of the monitored period). The quantitative analysis reveals that optimal results are achieved by expoiting the hydrological variables collected in the vadose zone at a depth of 1.7 m below ground level, with a Mean Absolute Error (MAE) of 0.189, a Mean Absolute Percentage Error (MAPE) of 0.062, a Root Mean Square Error (RMSE) of 0.244, and a Correlation coefficient of 0.923. This study stresses the importance of calibrating groundwater level prediction methods by exploring the hydrologic variables of the vadose zone in conjunction with those of the saturated zone and meteorological data, thus emphasizing the role of hydrologic time series forecasting as a challenging but vital aspect of optimizing groundwater management.

show abstract

Combining autoregressive integrated moving average with Long Short-Term Memory neural network and optimisation algorithms for predicting ground water level

Cited by 47 publications

References 42 publications

A Multi-Scenario Simulation and Dynamic Assessment of the Ecosystem Service Values in Key Ecological Functional Areas: A Case Study of the Sichuan Province, China

A Multi-Scenario Simulation and Dynamic Assessment of the Ecosystem Service Values in Key Ecological Functional Areas: A Case Study of the Sichuan Province, China

An efficent water quality prediction and evaluation method based on the DBN-LSTM model

Towards Groundwater-Level Prediction Using Prophet Forecasting Method by Exploiting a High-Resolution Hydrogeological Monitoring System

Contact Info

Product

Resources

About