Crop yield prediction is very important for agricultural planning, allocation of resources, and food security. So correct information regarding crop growth stages and yield estimation is crucial for effective decision-making and to ensure sustainable agricultural practices. In recent years, remote sensing data and machine learning techniques have become the valuable tools for monitoring and predicting crop phenology and yield. The target crop for this project is wheat, and it aims to develop a complete plan to map crop growth stages and forecast crop production using data from sentinel 1 and sentinel 2 and an artificial neural network algorithm. In order to identify the growth phases of the wheat crop, the Normalized Difference Vegetation Index (NDVI) time series and the backscatter time series for each cropping season from 2018 to 2023 were firstly analyzed. From sentinel 2 and sentinel 1 satellite data, the NDVI time series and backscatter time series were created in the google earth engine. The processed time series data were then used to extract phenological metrics including season duration, maximum NDVI and amplitude of NDVI curve. Insights about the duration of wheat cultivation’s growing period were derived by determining the length of the growing season. Additionally, the maximum NDVI value, a vegetation health indicator, was obtained, enabling for the characterization of crop health during the growing season. An Artificial Neural Network (ANN) model was developed to predict crop yield using data from multiple cropping seasons from 2018 to 2022. The extracted data from NDVI time series and Backscatter time series was used to train and validate the model. Along with the obtained phenological metrics and other relevant environmental and meteorological variables were also included in the ANN model. By understanding the intricate relationships between these variables, the algorithm was able to forecast wheat production with an efficiency of 72.48%