In a groundbreaking study published in the *Egyptian Journal of Remote Sensing and Space Sciences* (translated to English as the *Egyptian Journal of Remote Sensing and Space Sciences*), researchers have demonstrated a novel approach to assessing lake water quality using a combination of drone imagery and artificial intelligence models. This research, led by Nawras Shatnawi of the Surveying and Geomatics Engineering Department at Al-Balqa Applied University in Jordan, offers promising implications for water management and decision-making, particularly in sectors reliant on water resources such as agriculture, urban planning, and recreation.
The study focused on an artificial lake at the Jordan University of Science and Technology (JUST) campus, where Shatnawi and his team captured multispectral drone images using a DJI Phantom-4 drone equipped with sensors capable of detecting various wavebands, including blue, green, red, Red Edge, and Near Infrared. Simultaneously, water samples were collected from ten different points in the lake to analyze physical and chemical quality parameters. The spectral reflection data from the drone images were used to calculate multiple water body indices, which were then correlated to the water quality parameters measured in the lab.
“By integrating drone technology with machine learning algorithms, we were able to develop a robust model that accurately predicts water quality parameters,” said Shatnawi. “This approach not only saves time and resources but also provides a non-invasive method for monitoring water bodies.”
The researchers developed several artificial intelligence models, including Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Gradient Boosted Decision Trees (GBDT), Generalized Linear Model (GLM), and Artificial Neural Network (ANN). Among these, the autoregressive with exogenous (NARX) ANN model showed the highest prediction accuracy, with a coefficient of determination (R2) of 0.95 and a relative error of 0.034.
The study also highlighted the variability of water quality parameters with seasons, with the highest inversion accuracy observed during the summer season. This seasonal variability is crucial for water management strategies, as it allows for more targeted and effective interventions.
The implications of this research are far-reaching, particularly for the energy sector, where water is a critical resource for various processes, including cooling and hydroelectric power generation. By providing a reliable and efficient method for monitoring water quality, this technology can help energy companies optimize their water usage and ensure compliance with environmental regulations.
“Our findings suggest that this approach can be a game-changer for water quality assessment,” said Shatnawi. “It offers a scalable and cost-effective solution that can be applied to various water bodies, from small lakes to large reservoirs.”
Future studies are expected to expand on this research by including more parameters and using hyperspectral sensors for investigating quality parameters of similar water bodies. This will further enhance the accuracy and applicability of the models, paving the way for more sophisticated water management strategies.
As the world grapples with increasing water scarcity and environmental challenges, innovative solutions like this one are crucial for ensuring sustainable water management. By leveraging the power of drone technology and artificial intelligence, researchers are opening new avenues for monitoring and protecting our precious water resources.