Abstract
Introduction High-throughput and accurate phenotyping is critical for enhancing crop breeding efficiency by enabling rapid identification of superior cultivars within large populations. For soybean [ Glycine max (L.) Merr. ], maturity group is a key determinant of geographic adaptation and influences yield potential. Consequently, accurate assessment of physiological maturity dates is essential for selecting lines suited to specific environments. This study evaluated the feasibility of three transfer learning techniques in improving the generalizability of models developed using historical data to predict the maturity dates of soybean breeding lines across new environments. Methods Our dataset included five breeding trials conducted in two sites from 2018 to 2021. Maturity dates were visually assessed at the R8 stage, and multispectral imagery from an unmanned aerial vehicle (UAV) was collected within each trial. Seven image features served as predictors in the models. Transfer learning techniques, namely pre-training and fine-tuning, single-source and multiple-source domain adaptation, were evaluated using the multiple-year datasets. Results When models were trained on data from three prior years and tested on two independent trials, the pre-training and fine-tuning technique demonstrated the best performance, with the highest agreement with visual ratings (coefficient of determination R 2 = 0.74 and 0.79) and root mean square errors of 1.70 and 1.96 days, respectively. The quantity for fine-tuning samples had minimal influence on the prediction accuracy for previously unseen data. Discussion These findings provide a reference for leveraging accumulated knowledge to generalize deep learning models for future practical utilization.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 3
Claim · model-written summary
Pre-training and fine-tuning gave the highest agreement with visual maturity ratings (R2 = 0.74 and 0.79).
- Taxon
- soybean
Glycine maxt0 - Treatment
- pre-training and fine-tuninge1
- Outcome
- agreement with visual ratingse1
- Direction
- higheste1
- Value
- R 2 = 0.74 and 0.79e1
- Qualifier
- trained on data from three prior years and tested on two independent trialse1
- Comparator
- single-source and multiple-source domain adaptatione2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“predicting soybean maturity date”
e1“When models were trained on data from three prior years and tested on two independent trials, the pre-training and fine-tuning technique demonstrated the best performance, with the highest agreement with visual ratings (coefficient of determination R 2 = 0.74 and 0.79) and root mean square errors of 1.70 and 1.96 days, respectively”
e2“Transfer learning techniques, namely pre-training and fine-tuning, single-source and multiple-source domain adaptation, were evaluated using the multiple-year datasets”
Claim · model-written summary
Pre-training and fine-tuning gave lower root mean square errors (1.70 and 1.96 days).
- Taxon
- soybeanGlycine maxt0
- Treatment
- pre-training and fine-tuninge1
- Outcome
- root mean square errorse1
- Direction
- lowerinferrede1
- Value
- 1.70 and 1.96 dayse1
- Comparator
- single-source and multiple-source domain adaptatione2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“predicting soybean maturity date”
e1“When models were trained on data from three prior years and tested on two independent trials, the pre-training and fine-tuning technique demonstrated the best performance, with the highest agreement with visual ratings (coefficient of determination R 2 = 0.74 and 0.79) and root mean square errors of 1.70 and 1.96 days, respectively”
e2“Transfer learning techniques, namely pre-training and fine-tuning, single-source and multiple-source domain adaptation, were evaluated using the multiple-year datasets”
Claim · model-written summary
The quantity of fine-tuning samples had minimal influence on prediction accuracy for previously unseen data.
- Taxon
- soybeanGlycine maxt0
- Treatment
- quantity for fine-tuning samplese3
- Outcome
- prediction accuracye3
- Direction
- no_changeinferrede3
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“predicting soybean maturity date”
e3“The quantity for fine-tuning samples had minimal influence on the prediction accuracy for previously unseen data”