I think you need to spend some time in Python to perform your tasks. Just for a review you may follow : https://github.com/meet-sapu/Crop-Yield-Prediction-Using-Satellite-Imagery
The problem of "Time series crops yield estimation using satellite images" needs to deal with satellite images carefully. Such images are mostly poor in quality and very small images that needs normalization and image enhancement during image pre-processing. Then image analysis will work better during segmentation and extraction of image features for constructing a predictive model using classification algorithms like DL, regression analysis, SVM etc.