Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning
Leaf chlorophyll content (LCC), leaf area index (LAI), and above-ground biomass (AGB) are important growth parameters for characterizing potato growth and predicting yield. While deep learning has demonstrated remarkable advancements in estimating crop growth parameters, the limited availability of...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/15/1638 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849770673007755264 |
|---|---|
| author | Sen Yang Quan Feng Faxu Guo Wenwei Zhou |
| author_facet | Sen Yang Quan Feng Faxu Guo Wenwei Zhou |
| author_sort | Sen Yang |
| collection | DOAJ |
| description | Leaf chlorophyll content (LCC), leaf area index (LAI), and above-ground biomass (AGB) are important growth parameters for characterizing potato growth and predicting yield. While deep learning has demonstrated remarkable advancements in estimating crop growth parameters, the limited availability of field data often compromises model accuracy and generalizability, impeding large-scale regional applications. This study proposes a novel deep learning model that integrates multi-task learning and few-shot learning to address the challenge of low data in growth parameter prediction. Two multi-task learning architectures, MTL-DCNN and MTL-MMOE, were designed based on deep convolutional neural networks (DCNNs) and multi-gate mixture-of-experts (MMOE) for the simultaneous estimation of LCC, LAI, and AGB from Sentinel-2 imagery. Building on this, a few-shot learning framework for growth prediction (FSLGP) was developed by integrating simulated spectral generation, model-agnostic meta-learning (MAML), and meta-transfer learning strategies, enabling accurate prediction of multiple growth parameters under limited data availability. The results demonstrated that the incorporation of calibrated simulated spectral data significantly improved the estimation accuracy of LCC, LAI, and AGB (R<sup>2</sup> = 0.62~0.73). Under scenarios with limited field measurement data, the multi-task deep learning model based on few-shot learning outperformed traditional mixed inversion methods in predicting potato growth parameters (R<sup>2</sup> = 0.69~0.73; rRMSE = 16.68%~28.13%). Among the two architectures, the MTL-MMOE model exhibited superior stability and robustness in multi-task learning. Independent spatiotemporal validation further confirmed the potential of MTL-MMOE in estimating LAI and AGB across different years and locations (R<sup>2</sup> = 0.37~0.52). These results collectively demonstrated that the proposed FSLGP framework could achieve reliable estimation of crop growth parameters using only a very limited number of in-field samples (approximately 80 samples). This study can provide a valuable technical reference for monitoring and predicting growth parameters in other crops. |
| format | Article |
| id | doaj-art-25f2b877afce4159800dcde9f5dce5b0 |
| institution | DOAJ |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-25f2b877afce4159800dcde9f5dce5b02025-08-20T03:02:55ZengMDPI AGAgriculture2077-04722025-07-011515163810.3390/agriculture15151638Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task LearningSen Yang0Quan Feng1Faxu Guo2Wenwei Zhou3College of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaCollege of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, ChinaLeaf chlorophyll content (LCC), leaf area index (LAI), and above-ground biomass (AGB) are important growth parameters for characterizing potato growth and predicting yield. While deep learning has demonstrated remarkable advancements in estimating crop growth parameters, the limited availability of field data often compromises model accuracy and generalizability, impeding large-scale regional applications. This study proposes a novel deep learning model that integrates multi-task learning and few-shot learning to address the challenge of low data in growth parameter prediction. Two multi-task learning architectures, MTL-DCNN and MTL-MMOE, were designed based on deep convolutional neural networks (DCNNs) and multi-gate mixture-of-experts (MMOE) for the simultaneous estimation of LCC, LAI, and AGB from Sentinel-2 imagery. Building on this, a few-shot learning framework for growth prediction (FSLGP) was developed by integrating simulated spectral generation, model-agnostic meta-learning (MAML), and meta-transfer learning strategies, enabling accurate prediction of multiple growth parameters under limited data availability. The results demonstrated that the incorporation of calibrated simulated spectral data significantly improved the estimation accuracy of LCC, LAI, and AGB (R<sup>2</sup> = 0.62~0.73). Under scenarios with limited field measurement data, the multi-task deep learning model based on few-shot learning outperformed traditional mixed inversion methods in predicting potato growth parameters (R<sup>2</sup> = 0.69~0.73; rRMSE = 16.68%~28.13%). Among the two architectures, the MTL-MMOE model exhibited superior stability and robustness in multi-task learning. Independent spatiotemporal validation further confirmed the potential of MTL-MMOE in estimating LAI and AGB across different years and locations (R<sup>2</sup> = 0.37~0.52). These results collectively demonstrated that the proposed FSLGP framework could achieve reliable estimation of crop growth parameters using only a very limited number of in-field samples (approximately 80 samples). This study can provide a valuable technical reference for monitoring and predicting growth parameters in other crops.https://www.mdpi.com/2077-0472/15/15/1638potatogrowth parameter predictionmulti-task learningfew-shot learning |
| spellingShingle | Sen Yang Quan Feng Faxu Guo Wenwei Zhou Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning Agriculture potato growth parameter prediction multi-task learning few-shot learning |
| title | Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning |
| title_full | Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning |
| title_fullStr | Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning |
| title_full_unstemmed | Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning |
| title_short | Estimation of Potato Growth Parameters Under Limited Field Data Availability by Integrating Few-Shot Learning and Multi-Task Learning |
| title_sort | estimation of potato growth parameters under limited field data availability by integrating few shot learning and multi task learning |
| topic | potato growth parameter prediction multi-task learning few-shot learning |
| url | https://www.mdpi.com/2077-0472/15/15/1638 |
| work_keys_str_mv | AT senyang estimationofpotatogrowthparametersunderlimitedfielddataavailabilitybyintegratingfewshotlearningandmultitasklearning AT quanfeng estimationofpotatogrowthparametersunderlimitedfielddataavailabilitybyintegratingfewshotlearningandmultitasklearning AT faxuguo estimationofpotatogrowthparametersunderlimitedfielddataavailabilitybyintegratingfewshotlearningandmultitasklearning AT wenweizhou estimationofpotatogrowthparametersunderlimitedfielddataavailabilitybyintegratingfewshotlearningandmultitasklearning |