Deep Transfer Learning for UAV-Based Cross-Crop Yield Prediction in Root Crops
Authors:
Open Access
- 17 December 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (24) , 4054
Abstract
Limited annotated data often constrain accurate yield prediction in underrepresented crops. To address this challenge, we developed a cross-crop deep transfer learning (TL) framework that leverages potato (Solanum tuberosum L.) as the source domain to predict sweet potato (Ipomoea batatas L.) yield using multi-temporal uncrewed aerial vehicle (UAV)-based multispectral imagery. A hybrid convolutional–recurrent neural network (CNN–RNN–Attention) architecture was implemented with a robust parameter-based transfer strategy to ensure temporal alignment and feature-space consistency across crops. Cross-crop feature migration analysis showed that predictors capturing canopy vigor, structure, and soil–vegetation contrast exhibited the highest distributional similarity between potato and sweet potato. In comparison, pigment-sensitive and agronomic predictors were less transferable. These robustness patterns were reflected in model performance, as all architectures showed substantial improvement when moving from the minimal 3 predictor subset to the 5–7 predictor subsets, where the most transferable indices were introduced. The hybrid CNN–RNN–Attention model achieved peak accuracy ( and RMSE ≈ 18%) using time-series data up to the tuberization stage with only 7 predictors. In contrast, convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and bidirectional long short-term memory (BiLSTM) baseline models required 11–13 predictors to achieve comparable performance and often showed reduced or unstable accuracy at higher dimensionality due to redundancy and domain-shift amplification. Two-way ANOVA further revealed that cover crop type significantly influenced yield, whereas nitrogen rate and the interaction term were not significant. Overall, this study demonstrates that combining robustness-aware feature design with hybrid deep TL model enables accurate, data-efficient, and physiologically interpretable yield prediction in sweet potato, offering a scalable pathway for applying TL in other underrepresented root and tuber crops.
Keywords
Funding Information
- Agricultural Research Service (6066-21310-006-021-S)
- Agricultural Research Service (58-6064-3-007)
- USDA-ARS National Program 216-Sustainable Agricultural Systems (606421600-001-000-D)
This publication has 52 references indexed in Scilit:
- Transfer learning in agriculture: a reviewArtificial Intelligence Review, 2025
- Yield prediction through UAV-based multispectral imaging and deep learning in rice breeding trialsAgricultural Systems, 2024
- Sustainable sweetpotato production in the United States: Current status, challenges, and opportunitiesAgronomy Journal, 2024
- Opportunities and challenges in phenotyping row crops using drone‐based RGB imagingThe Plant Phenome Journal, 2022
- Predicting on multi-target regression for the yield of sweet potato by the market class of its roots upon vegetation indicesComputers and Electronics in Agriculture, 2021
- An adaptive adversarial domain adaptation approach for corn yield predictionComputers and Electronics in Agriculture, 2021
- Using deep transfer learning for image-based plant disease identificationComputers and Electronics in Agriculture, 2020
- Legume versus fertilizer sources of nitrogen: ecological tradeoffs and human needsAgriculture, Ecosystems & Environment, 2004
- Optimization of soil-adjusted vegetation indicesRemote Sensing of Environment, 1996
- Potentials and limits of vegetation indices for LAI and APAR assessmentRemote Sensing of Environment, 1991