سنجش از دور اپتيكي غلظت فيتوپلانكتون در آب هاي ساحلي خليج فارس

Advanced remote sensing technologies an‎d new satellite algorithms play a vital role in enhancing the environmental monitoring capabilities of coastal waterways. Given the increasing challenges posed by climate change an‎d human activities, the use of these technologies for accurate an‎d timely monitoring of environmental phenomena, such as algal blooms, has become a key priority in sustainable coastal resource management. The integration of high-resolution satellite data with in situ radiometric measurements is recognized as one of the effective an‎d essential methods in this field. This study presents an advanced model for analyzing the geographical an‎d temporal fluctuations of chlorophyll-a concentration in the Bushehr Bay region, located in the Persian Gulf, Iran. In this model, a combination of radiometric data an‎d high-resolution satellite images is used to obtain a comprehensive an‎d accurate analysis of chlorophyll-a concentration in this region. To achieve the best results, twenty-four bio-optical features were examined. After applying the eva‎luation an‎d selec‎tion processes, the most important an‎d influential features were determined. Finally, the top five features (A6, A3, Gil10_2, NMDI, SRT) were used to estimate chlorophyll concentration using advanced machine learning algorithms. The results of this study demonstrate the high ability of the model to investigate an‎d analyze the chlorophyll climatology in the study area. This model is not only able to identify spatial an‎d temporal changes in chlorophyll concentration with high accuracy but also acts as a powerful tool for monitoring the environmental impacts of chlorophyll-a. In addition, this method allows for rapid an‎d accurate assessment of water quality an‎d optimal management of primary production in coastal waters. This research shows that the proposed model can be used as a powerful proxy for environmental monitoring an‎d management in similar coastal areas around the world. By implementing this method in other comparable locations, it is possible to improve water quality, monitor algal blooms, an‎d enhance sustainable coastal resource management on a global scale. Furthermore, the presented approach lays the foundation for future research in the use of advanced satellite technologies an‎d machine learning in monitoring environmentally sensitive areas. Extending this model by incorporating more bio-optical features an‎d higher resolution satellite data will allow for further improvements in the accuracy an‎d efficiency of this method. Finally, this study provides new insights into environmental monitoring an‎d management that can be directly used in coastal zone protection policies an‎d programs.

5