Yılmaz, B.Samra, R.2025-12-242025-12-2420242821-0263https://doi.org/10.22034/aeis.2024.473891.1215https://hdl.handle.net/123456789/12753Solar energy is a widely embraced renewable resource, characterized by its unpredictable, fluctuating, and stochastic nature. To mitigate risks and optimize asset utilization cost-effectively, precise analysis and forecasting of solar radiation can prove beneficial. This work aims to provide a hybrid model using machine learning to accurately predict solar Direct normal irradiance with the least amount of error. In this work, long short-term memory has been optimized using Particle swarm optimization, Grasshopper optimization algorithm, and Slime mold algorithm. SMA-LSTM, which has the best performance result compared to other developed models, is presented as the main method for this work. The data used is from June 1, 2022, to July 30, 2023. Many factors, such as the coefficient of determination, root mean square error, mean absolute percentage error, and mean absolute error have been used in presenting this work, and SMA-LSTM results with the lowest amount of R2 has illustrated acceptable performance. © 2024 by the authors.eninfo:eu-repo/semantics/closedAccessDirect Normal IrradianceDNI ForecastingLong Short-Term MemoryQinghai ProvinceSlime Mould AlgorithmArticle10.22034/aeis.2024.473891.12152-s2.0-105022830446