In-season yield prediction can support crop management decisions helping farmers achieve their yield goals. The use of remote sensing to predict yield it is an alternative for non-destructive yield assessment but coupling auxiliary data such as topography features could help increase the accuracy of yield estimation. Predictive algorithms that can effectively identify, process and predict yield at field scale base on remote sensing and topography still needed. Machine learning could be an alternative algorithm for handle different sources of data in order to predict crop yield. Following this rationale, the objective of this research was to evaluate the use of ML algorithms for yield prediction. Specific objective was to evaluate remote sensing data along with topographic indices to improve prediction accuracy.  The study was conducted in a commercial cornfield in Lawrence County, Town Creek, Alabama. Here, spectral bands, topographic wetness index (TWI) and topographic position index (TPI) were integrated to predict corn yield using auto machine learning approaches, e.g. extremely randomized trees, gradient boosting machine (GBM), XGBoost algorithms, and stacked ensemble models. We tested four approaches: only spectral bands, spectral bands + TPI, spectral bands + TWI, and spectral bands + TPI + TWI as proxy for yield prediction. For this research data from seasons 2018, 2019 and pooled data (both years together) were used. Model performance were evaluated in terms of accuracy (mean absolute error) and tendency (estimated mean error). The most important outcome from the present study was that it was possible to predict corn yield using only spectral bands. However, to obtain a more accurate model, spectral bands associated with TPI and TWI should be used, which are surface-related variables. The results showed that it is possible to predict corn yield with reasonable accuracy using spectral crop information associated with TWI and TPI during the flowering growth stage. The most important features for modeling corn yield were spectral bands + TPI + TWI. From a practical standpoint, farmers can use high-quality data that have already been collected during the harvest (yield and elevation) and derive information regarding the micro-topography (TWI and TPI) associated with this information with spectral bands in high-resolution imagery to predict corn yield during the flowering period. Auto-ML using the stacked ensemble algorithm can be used to forecast corn yield before harvesting using combined data from different seasons. Future studies should focus on testing this method using fields with different topography characteristics to understand if the topography indices have the same behavior in the models developed in high and low slope areas.