The Chah Nimeh Reservoirs (CNRs), located in Iran's Sistan region, are critical arid inland lakes that support agriculture and supply drinking water to the region. A major concern regarding water quality in these reservoirs is the concentration of Total Suspended Matter (TSM), which has significant implications for both the local communities and the aquatic ecosystem. This study demonstrates the complicated connection between wind speed and TSM values, indicating that wind speed is an essential variable influencing TSM concentrations. By combining in-situ wind measurements with satellite imagery, we mapped TSM distributions using empirically derived models. Our investigation identified the Long Short-Term Memory (LSTM) and Attention-Mechanism- Based Dynamic Inner Partial Least Squares Long Short-Term Memory (ADiPLS-LSTM) models as effective predictors of TSM levels. Specifically, two distinct machine learning models were utilized: Rrs2TSM, which relies solely on Remote Sensing Reflectance (Rrs(lambda)), and the more advanced Rrs&Wind2TSM, which incorporates both Rrs(lambda) and wind data. The ADiPLS-LSTM model generated results with minimal variance, showing exceptional consistency. The Root Mean Square Error (RMSE) remains low at 0.617, while the R2 value maintained continually elevated at 0.997. It's interesting to note that modest variations in TSM concentrations occurred when wind speed data was incorporated into the algorithm, especially during times of greater wind speeds. This study emphasizes the significant impact of wind speed on TSM dynamics in arid inland lakes, showcasing the value of satellite imagery in conducting such analyses. The findings provide essential insights for developing strategies that promote sustainable water resource management.