Space weather predictions have become essential in this era of communication, technology and satellite advancements. In addition to intense solar flares and coronal mass ejections, high-speed solar wind streams from coronal holes are also responsible for geomagnetic disturbances. Also, studies have shown that the area of the coronal holes influences the speed of the solar wind streams. In this talk, I will discuss the extent that a Deep learning method like Convolutional Neural Network (CNN) can be used to predict the solar wind speed at L1 before 4 days of their occurrence using data from SDO's extreme ultraviolet (EUV) images.