Thermal power plants pollution assessment based on deep neural networks, remote sensing, and GIS: A real case study in Iran.

To investigate the impact of the Bandar Abbas thermal power plant on the waters of the Persian Gulf coast, a combination of satellite images and ground data was utilized to determine the Sea Surface Temperature (SST) as a thermal index, Total Organic Carbon (TOC) and Chemical Oxygen Demand (COD) as biological indices. Additionally, measurements of SO 2 , O 3 , NO 2 , CO 2 , CO, and CH 4 values in the atmosphere were taken to determine the plant's impact on air pollution. Temperature values of the water for different months were predicted using Long Short-Term Memory (LSTM), Support Vector Regression (SVR), and Cascade neural networks. The results indicate that the waters near thermal power plants exhibit the highest temperatures in July and September, with temperatures reaching approximately 50 °C. Furthermore, the SST values were found to be strongly correlated with ecological indices. The Multiple Linear Regression (MLR) analysis revealed a strong correlation between the temperature and TOC, COD, and O 2 in water (R TOC 2 = 0.98), R O 2 2 = − 0.89 , R COD 2 = 0.87 and O 3 , NO 3 , CO 2 , and CO in the air (R O 3 2 = 0.99 , R NO 3 2 = 0.97 , R CO 2 2 = 0.95 , R CO 2 = 0.96). Finally, the results demonstrate that the LSTM method exhibited high accuracy in predicting the water temperature (R² = 0.98). • SST index showed high temperatures water in near thermal power plant. • LSTM method had high accurate in predicting thermal pollution near power plant. • High temperature around power plant decreased O 2 in water, posing risk to aquatic life. • There were a strong correlation between TOC, COD, O 2 values and water temperature. • Air pollution was more around the thermal power plant. [ABSTRACT FROM AUTHOR]