Menon, A. S., J. Aravinth, R. Sankaran, and P. Kiran. 2025. Deep learning based farm-level crop yield prediction using multi-temporal satellite data for complex engineering application. Smart Agricultural Technology 12:101562.

Feeding a growing global population requires that we must try to increase production and to reliably predict yields before a harvest. Since one anticipates farm-level yields, one enables better resource management, market planning, and sustainable agricultural decisions. The objective of this study is to develop also evaluate a deep learning regression framework because it predicts the yields of wheat, corn, as well as soybean farms using multi-temporal Landsat-5 and Landsat-7 imagery together with annual ground-truth yield records from the Kellogg Biological Station Long-Term Ecological Research (KBS LTER) site in Michigan, United States. The dataset spans across 11 cropping years (2001, 2012, with 2002 excluded) and the dataset covers 24 farms. There were two models: one had training directly on seven spectral bands, and one trained on vegetation indices (VIs) (NDVI, SAVI, EVI2, GRNDVI). A 2 × 2-pixel window data augmentation strategy was used to address the limited sample size and farm-level yields were then reconstructed via weighted aggregation of window-level predictions. The band-based model did achieve a higher accuracy of about 89.44 %. That figure is superior to the result of 87.22 % for the VI model. Wheat yields were most accurately predicted (88.3 %) when crops were assessed. Soybean (87.01 %) then corn (85.08 %) followed this result. This study provides an effective and reproducible framework for farm-level yield prediction under limited data conditions with a fully connected deep learning model, combined with systematic window-based augmentation and weighted yield reconstruction. Landsat imagery with its single-site scope and its 30 m resolution did constrain the framework yet it highlights the potential of combining deep learning with optimisation principles that are regression-based. The framework offers too a scalable basis for integration with multi-source datasets as well as decision-support systems in precision agriculture.

DOI: 10.1016/j.atech.2025.101562

Associated Treatment Areas:

• T1 Conventional Management
• T2 No-till Management
• T3 Reduced Input Management
• T4 Biologically Based Management
• MCSE Main Cropping Systems Experiment

Download citation to endnote bibtex