GIS-based analysis of rock salt deposits’ suitability for underground hydrogen storage

Lankof, Leszek; Tarkowski, Radosław

doi:10.1016/j.ijhydene.2023.03.415

Cited by 15 publications

(8 citation statements)

References 123 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptability of our AI framework underscores its potential application on an international scale, supporting the strategic infrastructure development for renewable energy storage. So, our research not only aligns with the objectives of Lankof and Tarkowski's work 76 but also extends it by leveraging the latest advancements in AI, thereby providing a novel and empirically validated approach to the selection of underground hydrogen storage sites.…”

Section: Resultssupporting

confidence: 56%

“…The seminal work by Lankof and Tarkowski 76 provides a robust foundation for site selection methodology using multi-criteria decision analysis and GIS. Their approach represents a significant step in identifying suitable locations for hydrogen storage within bedded salt deposits.…”

Section: Resultsmentioning

confidence: 99%

“…While Lankof and Tarkowski 76 focus on the application of a multi-criteria decision analysis in a GIS setting, the present study expands this by incorporating a suite of eight AI algorithms. This inclusion goes beyond the traditional GIS analyses by enabling a data-driven, machine-learning approach that offers increased accuracy and computational efficiency.…”

Section: Resultsmentioning

confidence: 99%

“…1 ).

Figure 1 The Na1 rock salt deposit selected for analysis 76 using ArcGIS Pro 2.8 software. The base map was developed by Esri using HERE data, DeLorme base map layers, OpenStreetMap contributors, Esri base map data, and select data from the GIS user community.…”

Section: Methodsmentioning

confidence: 99%

“…Our approach utilized the Fuzzy Analytic Hierarchy Process (FAHP) model to generate a target database for training the ML algorithms. In this paper, the input parameters of the ML algorithms included Conservation Area, Geological exploration, Water reservoir, Accessibility, Ecological Site, Energy Consumption, Land Use, Natural Gas Pipelines, Natural forest, Protected Area, Special Protection Area, Storage Capacity, and the AHP output derived from Lankof and Tarkowski 88 as the ML algorithms output parameter.…”

Section: Methodsmentioning

confidence: 99%

See 4 more Smart Citations

Artificial intelligence-driven assessment of salt caverns for underground hydrogen storage in Poland

Derakhshani,

Lankof,

GhasemiNejad

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

This study explores the feasibility of utilizing bedded salt deposits as sites for underground hydrogen storage. We introduce an innovative artificial intelligence framework that applies multi-criteria decision-making and spatial data analysis to identify the most suitable locations for storing hydrogen in salt caverns. Our approach integrates a unified platform with eight distinct machine-learning algorithms—KNN, SVM, LightGBM, XGBoost, MLP, CatBoost, GBR, and MLR—creating rock salt deposit suitability maps for hydrogen storage. The performance of these algorithms was evaluated using various metrics, including Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Correlation Coefficient (R2), compared against an actual dataset. The CatBoost model demonstrated exceptional performance, achieving an R2 of 0.88, MSE of 0.0816, MAE of 0.1994, RMSE of 0.2833, and MAPE of 0.0163. The novel methodology, leveraging advanced machine learning techniques, offers a unique perspective in assessing the potential of underground hydrogen storage. This approach is a valuable asset for various stakeholders, including government bodies, geological services, renewable energy facilities, and the chemical/petrochemical industry, aiding them in identifying optimal locations for hydrogen storage.

show abstract

Section: Resultssupporting

confidence: 56%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…1 ).

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%