Your browser has javascript turned off or blocked. This will lead to some parts of our website to not work properly or at all. Turn on javascript for best performance.

The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Application of advanced machine learning algorithms to assess groundwater potential using remote sensing-derived data

machine learning.picture

The demand for water supply is continuously rising due to population growth and development across the world. In arid and semi-arid areas, particularly the Middle East, aquifers form the central freshwater reserves, hence are being uncontrollably exploited to meet water demand for an ever-increasing population and industrialization.


To achieve sustainability in groundwater supply, the potential of the groundwater aquifer should be assessed.

We developed a technique that integrates remote sensing-derived factors and advanced machine learning algorithms to evaluate aquifers' productivity potential in arid areas of the Middle East. Our findings confirm the logistic model tree's outstanding performance and deep boosting algorithms in modeling groundwater potential.

Thus, their application can be suggested for other areas to obtain an insight into groundwater-related barriers toward sustainability. Further, the outcome based on the machine learning algorithms depicts the high impact of the remote sensing-based factors, such as NDVI, distance from the river, altitude on groundwater potential.

Using remote sensing-based data is indeed a potential alternative for areas confronted with a lack of data, such as the Middle East. 

Application of Advanced Machine Learning Algorithms to Assess Groundwater Potential Using Remote Sensing-Derived Data

(Remote Sensing, 12(17), p.2742.)

 

Photo by Markus Spiske on Unsplash